X-Git-Url: https://gitweb.factorcode.org/gitweb.cgi?p=factor.git;a=blobdiff_plain;f=basis%2Funicode%2FUCD%2Fauxiliary%2FWordBreakProperty.txt;h=6f868d21f352e9c39ce593ae5313df465aea03cd;hp=efb4807a2d0deb25741cb831a6ca74ec40110b0e;hb=e3f197c3bbd776e9bb83d7fa8598687a8842d0b6;hpb=44cbe83984f89ff8c53e2dd0b2ced1c268f922f0 diff --git a/basis/unicode/UCD/auxiliary/WordBreakProperty.txt b/basis/unicode/UCD/auxiliary/WordBreakProperty.txt index efb4807a2d..6f868d21f3 100644 --- a/basis/unicode/UCD/auxiliary/WordBreakProperty.txt +++ b/basis/unicode/UCD/auxiliary/WordBreakProperty.txt @@ -1,11 +1,11 @@ -# WordBreakProperty-12.1.0.txt -# Date: 2019-03-10, 10:53:28 GMT -# © 2019 Unicode®, Inc. +# WordBreakProperty-15.0.0.txt +# Date: 2022-04-27, 02:41:26 GMT +# © 2022 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. -# For terms of use, see http://www.unicode.org/terms_of_use.html +# For terms of use, see https://www.unicode.org/terms_of_use.html # # Unicode Character Database -# For documentation, see http://www.unicode.org/reports/tr44/ +# For documentation, see https://www.unicode.org/reports/tr44/ # ================================================ @@ -91,7 +91,8 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 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 -08D3..08E1 ; Extend # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +0898..089F ; Extend # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; Extend # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA 08E3..0902 ; Extend # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA 0903 ; Extend # Mc DEVANAGARI SIGN VISARGA 093A ; Extend # Mn DEVANAGARI VOWEL SIGN OE @@ -146,7 +147,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B56 ; Extend # Mn ORIYA AI LENGTH MARK +0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -160,6 +161,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0C00 ; Extend # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE 0C01..0C03 ; Extend # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA 0C04 ; Extend # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; Extend # Mn TELUGU SIGN NUKTA 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 0C46..0C48 ; Extend # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI @@ -178,6 +180,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 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 +0CF3 ; Extend # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT 0D00..0D01 ; Extend # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU 0D02..0D03 ; Extend # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA 0D3B..0D3C ; Extend # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA @@ -188,6 +191,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0D4D ; Extend # Mn MALAYALAM SIGN VIRAMA 0D57 ; Extend # Mc MALAYALAM AU LENGTH MARK 0D62..0D63 ; Extend # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; Extend # Mn SINHALA SIGN CANDRABINDU 0D82..0D83 ; Extend # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA 0DCA ; Extend # Mn SINHALA SIGN AL-LAKUNA 0DCF..0DD1 ; Extend # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA @@ -200,7 +204,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0E47..0E4E ; Extend # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN 0EB1 ; Extend # Mn LAO VOWEL SIGN MAI KAN 0EB4..0EBC ; Extend # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO -0EC8..0ECD ; Extend # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0EC8..0ECE ; Extend # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN 0F18..0F19 ; Extend # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS 0F35 ; Extend # Mn TIBETAN MARK NGAS BZUNG NYI ZLA 0F37 ; Extend # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS @@ -237,7 +241,9 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 109D ; Extend # Mn MYANMAR VOWEL SIGN AITON AI 135D..135F ; Extend # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK 1712..1714 ; Extend # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA -1732..1734 ; Extend # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1715 ; Extend # Mc TAGALOG SIGN PAMUDPOD +1732..1733 ; Extend # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1734 ; Extend # Mc HANUNOO SIGN PAMUDPOD 1752..1753 ; Extend # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U 1772..1773 ; Extend # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U 17B4..17B5 ; Extend # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -249,6 +255,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 17C9..17D3 ; Extend # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT 17DD ; Extend # Mn KHMER SIGN ATTHACAN 180B..180D ; Extend # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; Extend # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR 1885..1886 ; Extend # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 18A9 ; Extend # Mn MONGOLIAN LETTER ALI GALI DAGALGA 1920..1922 ; Extend # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U @@ -276,6 +283,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 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 +1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -315,8 +323,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1CF4 ; Extend # Mn VEDIC TONE CANDRA ABOVE 1CF7 ; Extend # Mc VEDIC SIGN ATIKRAMA 1CF8..1CF9 ; Extend # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE -1DC0..1DF9 ; Extend # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW -1DFB..1DFF ; Extend # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DC0..1DFF ; Extend # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C ; Extend # Cf ZERO WIDTH NON-JOINER 20D0..20DC ; Extend # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20DD..20E0 ; Extend # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH @@ -340,6 +347,7 @@ A80B ; Extend # Mn SYLOTI NAGRI SIGN ANUSVARA A823..A824 ; Extend # Mc [2] SYLOTI NAGRI VOWEL SIGN A..SYLOTI NAGRI VOWEL SIGN I A825..A826 ; Extend # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E A827 ; Extend # Mc SYLOTI NAGRI VOWEL SIGN OO +A82C ; Extend # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA A880..A881 ; Extend # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A8B4..A8C3 ; Extend # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU A8C4..A8C5 ; Extend # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU @@ -399,17 +407,23 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10A3F ; Extend # Mn KHAROSHTHI VIRAMA 10AE5..10AE6 ; Extend # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFD..10EFF ; Extend # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS 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 +11070 ; Extend # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; Extend # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O 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 110B7..110B8 ; Extend # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU 110B9..110BA ; Extend # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; Extend # Mn KAITHI VOWEL SIGN VOCALIC R 11100..11102 ; Extend # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA 11127..1112B ; Extend # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU 1112C ; Extend # Mc CHAKMA VOWEL SIGN E @@ -422,6 +436,8 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 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 111C9..111CC ; Extend # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CE ; Extend # Mc SHARADA VOWEL SIGN PRISHTHAMATRA E +111CF ; Extend # Mn SHARADA SIGN INVERTED CANDRABINDU 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 @@ -429,6 +445,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11235 ; Extend # Mc KHOJKI SIGN VIRAMA 11236..11237 ; Extend # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA 1123E ; Extend # Mn KHOJKI SIGN SUKUN +11241 ; Extend # Mn KHOJKI VOWEL SIGN VOCALIC R 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 @@ -488,6 +505,14 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1182F..11837 ; Extend # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA 11838 ; Extend # Mc DOGRA SIGN VISARGA 11839..1183A ; Extend # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +11930..11935 ; Extend # Mc [6] DIVES AKURU VOWEL SIGN AA..DIVES AKURU VOWEL SIGN E +11937..11938 ; Extend # Mc [2] DIVES AKURU VOWEL SIGN AI..DIVES AKURU VOWEL SIGN O +1193B..1193C ; Extend # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193D ; Extend # Mc DIVES AKURU SIGN HALANTA +1193E ; Extend # Mn DIVES AKURU VIRAMA +11940 ; Extend # Mc DIVES AKURU MEDIAL YA +11942 ; Extend # Mc DIVES AKURU MEDIAL RA +11943 ; Extend # Mn DIVES AKURU SIGN NUKTA 119D1..119D3 ; Extend # Mc [3] NANDINAGARI VOWEL SIGN AA..NANDINAGARI VOWEL SIGN II 119D4..119D7 ; Extend # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR 119DA..119DB ; Extend # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI @@ -530,12 +555,26 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 11D97 ; Extend # Mn GUNJALA GONDI VIRAMA 11EF3..11EF4 ; Extend # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U 11EF5..11EF6 ; Extend # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O +11F00..11F01 ; Extend # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F03 ; Extend # Mc KAWI SIGN VISARGA +11F34..11F35 ; Extend # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA +11F36..11F3A ; Extend # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F3E..11F3F ; Extend # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI +11F40 ; Extend # Mn KAWI VOWEL SIGN EU +11F41 ; Extend # Mc KAWI SIGN KILLER +11F42 ; Extend # Mn KAWI CONJOINER +13440 ; Extend # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; Extend # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 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 16F4F ; Extend # Mn MIAO SIGN CONSONANT MODIFIER BAR 16F51..16F87 ; Extend # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 16F8F..16F92 ; Extend # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; Extend # Mn KHITAN SMALL SCRIPT FILLER +16FF0..16FF1 ; Extend # Mc [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY 1BC9D..1BC9E ; Extend # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1CF00..1CF2D ; Extend # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; Extend # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG 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 @@ -554,15 +593,18 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E01B..1E021 ; Extend # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI 1E023..1E024 ; Extend # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS 1E026..1E02A ; Extend # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; Extend # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 1E130..1E136 ; Extend # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2372 +# Total code points: 2554 # ================================================ @@ -577,6 +619,7 @@ E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 061C ; Format # Cf ARABIC LETTER MARK 06DD ; Format # Cf ARABIC END OF AYAH 070F ; Format # Cf SYRIAC ABBREVIATION MARK +0890..0891 ; Format # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08E2 ; Format # Cf ARABIC DISPUTED END OF AYAH 180E ; Format # Cf MONGOLIAN VOWEL SEPARATOR 200E..200F ; Format # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK @@ -587,12 +630,12 @@ 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 110CD ; Format # Cf KAITHI NUMBER SIGN ABOVE -13430..13438 ; Format # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +13430..1343F ; Format # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE 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 -# Total code points: 62 +# Total code points: 71 # ================================================ @@ -608,10 +651,15 @@ E0001 ; Format # Cf LANGUAGE TAG FF66..FF6F ; Katakana # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU FF70 ; Katakana # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +1AFF0..1AFF3 ; Katakana # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 +1AFF5..1AFFB ; Katakana # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 +1AFFD..1AFFE ; Katakana # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 1B000 ; Katakana # Lo KATAKANA LETTER ARCHAIC E +1B120..1B122 ; Katakana # Lo [3] KATAKANA LETTER ARCHAIC YI..KATAKANA LETTER ARCHAIC WU +1B155 ; Katakana # Lo KATAKANA LETTER SMALL KO 1B164..1B167 ; Katakana # Lo [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N -# Total code points: 314 +# Total code points: 331 # ================================================ @@ -635,6 +683,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 02D2..02D7 ; ALetter # Sk [6] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER MINUS SIGN 02DE..02DF ; ALetter # Sk [2] MODIFIER LETTER RHOTIC HOOK..MODIFIER LETTER CROSS ACCENT 02E0..02E4 ; ALetter # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +02E5..02EB ; ALetter # Sk [7] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER YANG DEPARTING TONE MARK 02EC ; ALetter # Lm MODIFIER LETTER VOICING 02ED ; ALetter # Sk MODIFIER LETTER UNASPIRATED 02EE ; ALetter # Lm MODIFIER LETTER DOUBLE APOSTROPHE @@ -654,9 +703,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 048A..052F ; ALetter # L& [166] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EL WITH DESCENDER 0531..0556 ; ALetter # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; ALetter # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -055B..055C ; ALetter # Po [2] ARMENIAN EMPHASIS MARK..ARMENIAN EXCLAMATION MARK +055A..055C ; ALetter # Po [3] ARMENIAN APOSTROPHE..ARMENIAN EXCLAMATION MARK 055E ; ALetter # Po ARMENIAN QUESTION MARK 0560..0588 ; ALetter # L& [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE +058A ; ALetter # Pd ARMENIAN HYPHEN 05F3 ; ALetter # Po HEBREW PUNCTUATION GERESH 0620..063F ; ALetter # Lo [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE 0640 ; ALetter # Lm ARABIC TATWEEL @@ -681,8 +731,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0828 ; ALetter # Lm SAMARITAN MODIFIER LETTER I 0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ALetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA -08A0..08B4 ; ALetter # Lo [21] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER KAF WITH DOT BELOW -08B6..08BD ; ALetter # Lo [8] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER AFRICAN NOON +0870..0887 ; ALetter # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT +0889..088E ; ALetter # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +08A0..08C8 ; ALetter # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF +08C9 ; ALetter # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; ALetter # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; ALetter # Lo DEVANAGARI OM @@ -748,6 +800,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0C2A..0C39 ; ALetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ALetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA +0C5D ; ALetter # Lo TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ALetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -756,10 +809,10 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0CAA..0CB3 ; ALetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ALetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ALetter # Lo KANNADA SIGN AVAGRAHA -0CDE ; ALetter # Lo KANNADA LETTER FA +0CDD..0CDE ; ALetter # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA 0CE0..0CE1 ; ALetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ALetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA -0D05..0D0C ; ALetter # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L +0D04..0D0C ; ALetter # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L 0D0E..0D10 ; ALetter # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI 0D12..0D3A ; ALetter # Lo [41] MALAYALAM LETTER O..MALAYALAM LETTER TTTA 0D3D ; ALetter # Lo MALAYALAM SIGN AVAGRAHA @@ -807,9 +860,8 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 16A0..16EA ; ALetter # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; ALetter # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL 16F1..16F8 ; ALetter # Lo [8] RUNIC LETTER K..RUNIC LETTER FRANKS CASKET AESC -1700..170C ; ALetter # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; ALetter # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1720..1731 ; ALetter # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1700..1711 ; ALetter # Lo [18] TAGALOG LETTER A..TAGALOG LETTER HA +171F..1731 ; ALetter # Lo [19] TAGALOG LETTER ARCHAIC RA..HANUNOO LETTER HA 1740..1751 ; ALetter # Lo [18] BUHID LETTER A..BUHID LETTER HA 1760..176C ; ALetter # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA 176E..1770 ; ALetter # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA @@ -823,7 +875,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 1900..191E ; ALetter # Lo [31] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER TRA 1A00..1A16 ; ALetter # Lo [23] BUGINESE LETTER KA..BUGINESE LETTER HA 1B05..1B33 ; ALetter # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA -1B45..1B4B ; ALetter # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B45..1B4C ; ALetter # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA 1B83..1BA0 ; ALetter # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA 1BAE..1BAF ; ALetter # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA 1BBA..1BE5 ; ALetter # Lo [44] SUNDANESE AVAGRAHA..BATAK LETTER U @@ -885,9 +937,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 2183..2184 ; ALetter # L& [2] ROMAN NUMERAL REVERSED ONE HUNDRED..LATIN SMALL LETTER REVERSED C 2185..2188 ; ALetter # Nl [4] ROMAN NUMERAL SIX LATE FORM..ROMAN NUMERAL ONE HUNDRED THOUSAND 24B6..24E9 ; ALetter # So [52] CIRCLED LATIN CAPITAL LETTER A..CIRCLED LATIN SMALL LETTER Z -2C00..2C2E ; ALetter # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE -2C30..2C5E ; ALetter # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C7B ; ALetter # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E +2C00..2C7B ; ALetter # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; ALetter # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; ALetter # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CEB..2CEE ; ALetter # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA @@ -912,7 +962,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 303C ; ALetter # Lo MASU MARK 3105..312F ; ALetter # Lo [43] BOPOMOFO LETTER B..BOPOMOFO LETTER NN 3131..318E ; ALetter # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE -31A0..31BA ; ALetter # Lo [27] BOPOMOFO LETTER BU..BOPOMOFO LETTER ZY +31A0..31BF ; ALetter # Lo [32] BOPOMOFO LETTER BU..BOPOMOFO LETTER AH A000..A014 ; ALetter # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A015 ; ALetter # Lm YI SYLLABLE WU A016..A48C ; ALetter # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR @@ -929,6 +979,7 @@ A680..A69B ; ALetter # L& [28] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL L A69C..A69D ; ALetter # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A6A0..A6E5 ; ALetter # Lo [70] BAMUM LETTER A..BAMUM LETTER KI A6E6..A6EF ; ALetter # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM +A708..A716 ; ALetter # Sk [15] MODIFIER LETTER EXTRA-HIGH DOTTED TONE BAR..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR A717..A71F ; ALetter # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A720..A721 ; ALetter # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE A722..A76F ; ALetter # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN SMALL LETTER CON @@ -938,8 +989,12 @@ A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7BF ; ALetter # L& [48] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER GLOTTAL U -A7C2..A7C6 ; ALetter # L& [5] LATIN CAPITAL LETTER ANGLICANA W..LATIN CAPITAL LETTER Z WITH PALATAL HOOK +A790..A7CA ; ALetter # L& [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY +A7D0..A7D1 ; ALetter # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; ALetter # L& LATIN SMALL LETTER DOUBLE THORN +A7D5..A7D9 ; ALetter # L& [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S +A7F2..A7F4 ; ALetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F5..A7F6 ; ALetter # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; ALetter # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -971,7 +1026,8 @@ AB28..AB2E ; ALetter # Lo [7] ETHIOPIC SYLLABLE BBA..ETHIOPIC SYLLABLE BBO AB30..AB5A ; ALetter # L& [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG AB5B ; ALetter # Sk MODIFIER BREVE WITH INVERTED BREVE AB5C..AB5F ; ALetter # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK -AB60..AB67 ; ALetter # L& [8] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TS DIGRAPH WITH RETROFLEX HOOK +AB60..AB68 ; ALetter # L& [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE +AB69 ; ALetter # Lm MODIFIER LETTER SMALL TURNED W AB70..ABBF ; ALetter # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA ABC0..ABE2 ; ALetter # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM AC00..D7A3 ; ALetter # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH @@ -1019,9 +1075,20 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 104D8..104FB ; ALetter # L& [36] OSAGE SMALL LETTER A..OSAGE SMALL LETTER ZHA 10500..10527 ; ALetter # Lo [40] ELBASAN LETTER A..ELBASAN LETTER KHE 10530..10563 ; ALetter # Lo [52] CAUCASIAN ALBANIAN LETTER ALT..CAUCASIAN ALBANIAN LETTER KIW +10570..1057A ; ALetter # L& [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA +1057C..1058A ; ALetter # L& [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE +1058C..10592 ; ALetter # L& [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE +10594..10595 ; ALetter # L& [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE +10597..105A1 ; ALetter # L& [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA +105A3..105B1 ; ALetter # L& [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE +105B3..105B9 ; ALetter # L& [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE +105BB..105BC ; ALetter # L& [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 10600..10736 ; ALetter # Lo [311] LINEAR A SIGN AB001..LINEAR A SIGN A664 10740..10755 ; ALetter # Lo [22] LINEAR A SIGN A701 A..LINEAR A SIGN A732 JE 10760..10767 ; ALetter # Lo [8] LINEAR A SIGN A800..LINEAR A SIGN A807 +10780..10785 ; ALetter # Lm [6] MODIFIER LETTER SMALL CAPITAL AA..MODIFIER LETTER SMALL B WITH HOOK +10787..107B0 ; ALetter # Lm [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK +107B2..107BA ; ALetter # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10800..10805 ; ALetter # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA 10808 ; ALetter # Lo CYPRIOT SYLLABLE JO 1080A..10835 ; ALetter # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO @@ -1052,15 +1119,22 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10C80..10CB2 ; ALetter # L& [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US 10CC0..10CF2 ; ALetter # L& [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US 10D00..10D23 ; ALetter # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA +10E80..10EA9 ; ALetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET +10EB0..10EB1 ; ALetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10F00..10F1C ; ALetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ALetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ALetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN +10F70..10F81 ; ALetter # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH +10FB0..10FC4 ; ALetter # Lo [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW 10FE0..10FF6 ; ALetter # Lo [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH 11003..11037 ; ALetter # Lo [53] BRAHMI SIGN JIHVAMULIYA..BRAHMI LETTER OLD TAMIL NNNA +11071..11072 ; ALetter # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O +11075 ; ALetter # Lo BRAHMI LETTER OLD TAMIL LLA 11083..110AF ; ALetter # Lo [45] KAITHI LETTER A..KAITHI LETTER HA 110D0..110E8 ; ALetter # Lo [25] SORA SOMPENG LETTER SAH..SORA SOMPENG LETTER MAE 11103..11126 ; ALetter # Lo [36] CHAKMA LETTER AA..CHAKMA LETTER HAA 11144 ; ALetter # Lo CHAKMA LETTER LHAA +11147 ; ALetter # Lo CHAKMA LETTER VAA 11150..11172 ; ALetter # Lo [35] MAHAJANI LETTER A..MAHAJANI LETTER RRA 11176 ; ALetter # Lo MAHAJANI LIGATURE SHRI 11183..111B2 ; ALetter # Lo [48] SHARADA LETTER A..SHARADA LETTER HA @@ -1069,6 +1143,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 111DC ; ALetter # Lo SHARADA HEADSTROKE 11200..11211 ; ALetter # Lo [18] KHOJKI LETTER A..KHOJKI LETTER JJA 11213..1122B ; ALetter # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA +1123F..11240 ; ALetter # Lo [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I 11280..11286 ; ALetter # Lo [7] MULTANI LETTER A..MULTANI LETTER GA 11288 ; ALetter # Lo MULTANI LETTER GHA 1128A..1128D ; ALetter # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA @@ -1086,7 +1161,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1135D..11361 ; ALetter # Lo [5] GRANTHA SIGN PLUTA..GRANTHA LETTER VOCALIC LL 11400..11434 ; ALetter # Lo [53] NEWA LETTER A..NEWA LETTER HA 11447..1144A ; ALetter # Lo [4] NEWA SIGN AVAGRAHA..NEWA SIDDHI -1145F ; ALetter # Lo NEWA LETTER VEDIC ANUSVARA +1145F..11461 ; ALetter # Lo [3] NEWA LETTER VEDIC ANUSVARA..NEWA SIGN UPADHMANIYA 11480..114AF ; ALetter # Lo [48] TIRHUTA ANJI..TIRHUTA LETTER HA 114C4..114C5 ; ALetter # Lo [2] TIRHUTA SIGN AVAGRAHA..TIRHUTA GVANG 114C7 ; ALetter # Lo TIRHUTA OM @@ -1098,7 +1173,13 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 116B8 ; ALetter # Lo TAKRI LETTER ARCHAIC KHA 11800..1182B ; ALetter # Lo [44] DOGRA LETTER A..DOGRA LETTER RRA 118A0..118DF ; ALetter # L& [64] WARANG CITI CAPITAL LETTER NGAA..WARANG CITI SMALL LETTER VIYO -118FF ; ALetter # Lo WARANG CITI OM +118FF..11906 ; ALetter # Lo [8] WARANG CITI OM..DIVES AKURU LETTER E +11909 ; ALetter # Lo DIVES AKURU LETTER O +1190C..11913 ; ALetter # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA +11915..11916 ; ALetter # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA +11918..1192F ; ALetter # Lo [24] DIVES AKURU LETTER DDA..DIVES AKURU LETTER ZA +1193F ; ALetter # Lo DIVES AKURU PREFIXED NASAL SIGN +11941 ; ALetter # Lo DIVES AKURU INITIAL RA 119A0..119A7 ; ALetter # Lo [8] NANDINAGARI LETTER A..NANDINAGARI LETTER VOCALIC RR 119AA..119D0 ; ALetter # Lo [39] NANDINAGARI LETTER E..NANDINAGARI LETTER RRA 119E1 ; ALetter # Lo NANDINAGARI SIGN AVAGRAHA @@ -1109,7 +1190,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11A50 ; ALetter # Lo SOYOMBO LETTER A 11A5C..11A89 ; ALetter # Lo [46] SOYOMBO LETTER KA..SOYOMBO CLUSTER-INITIAL LETTER SA 11A9D ; ALetter # Lo SOYOMBO MARK PLUTA -11AC0..11AF8 ; ALetter # Lo [57] PAU CIN HAU LETTER PA..PAU CIN HAU GLOTTAL STOP FINAL +11AB0..11AF8 ; ALetter # Lo [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL 11C00..11C08 ; ALetter # Lo [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L 11C0A..11C2E ; ALetter # Lo [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA 11C40 ; ALetter # Lo BHAIKSUKI SIGN AVAGRAHA @@ -1123,13 +1204,20 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 11D6A..11D89 ; ALetter # Lo [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA 11D98 ; ALetter # Lo GUNJALA GONDI OM 11EE0..11EF2 ; ALetter # Lo [19] MAKASAR LETTER KA..MAKASAR ANGKA +11F02 ; ALetter # Lo KAWI SIGN REPHA +11F04..11F10 ; ALetter # Lo [13] KAWI LETTER A..KAWI LETTER O +11F12..11F33 ; ALetter # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA +11FB0 ; ALetter # Lo LISU LETTER YHA 12000..12399 ; ALetter # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U 12400..1246E ; ALetter # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM 12480..12543 ; ALetter # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU -13000..1342E ; ALetter # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032 +12F90..12FF0 ; ALetter # Lo [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114 +13000..1342F ; ALetter # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D +13441..13446 ; ALetter # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN 14400..14646 ; ALetter # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530 16800..16A38 ; ALetter # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ 16A40..16A5E ; ALetter # Lo [31] MRO LETTER TA..MRO LETTER TEK +16A70..16ABE ; ALetter # Lo [79] TANGSA LETTER OZ..TANGSA LETTER ZA 16AD0..16AED ; ALetter # Lo [30] BASSA VAH LETTER ENNI..BASSA VAH LETTER I 16B00..16B2F ; ALetter # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 16B40..16B43 ; ALetter # Lm [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM @@ -1175,10 +1263,22 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1D78A..1D7A8 ; ALetter # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA 1D7AA..1D7C2 ; ALetter # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA 1D7C4..1D7CB ; ALetter # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA +1DF00..1DF09 ; ALetter # L& [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK +1DF0A ; ALetter # Lo LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK +1DF0B..1DF1E ; ALetter # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL +1DF25..1DF2A ; ALetter # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK +1E030..1E06D ; ALetter # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E100..1E12C ; ALetter # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1E137..1E13D ; ALetter # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1E14E ; ALetter # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ +1E290..1E2AD ; ALetter # Lo [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; ALetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH +1E4D0..1E4EA ; ALetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E4EB ; ALetter # Lm NAG MUNDARI SIGN OJOD +1E7E0..1E7E6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO +1E7E8..1E7EB ; ALetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE +1E7ED..1E7EE ; ALetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE +1E7F0..1E7FE ; ALetter # Lo [15] ETHIOPIC SYLLABLE GURAGE QWI..ETHIOPIC SYLLABLE GURAGE PWEE 1E800..1E8C4 ; ALetter # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON 1E900..1E943 ; ALetter # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA 1E94B ; ALetter # Lm ADLAM NASALIZATION MARK @@ -1219,20 +1319,21 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 28693 +# Total code points: 29489 # ================================================ 003A ; MidLetter # Po COLON 00B7 ; MidLetter # Po MIDDLE DOT 0387 ; MidLetter # Po GREEK ANO TELEIA +055F ; MidLetter # Po ARMENIAN ABBREVIATION MARK 05F4 ; MidLetter # Po HEBREW PUNCTUATION GERSHAYIM 2027 ; MidLetter # Po HYPHENATION POINT FE13 ; MidLetter # Po PRESENTATION FORM FOR VERTICAL COLON FE55 ; MidLetter # Po SMALL COLON FF1A ; MidLetter # Po FULLWIDTH COLON -# Total code points: 8 +# Total code points: 9 # ================================================ @@ -1318,17 +1419,22 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 116C0..116C9 ; Numeric # Nd [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE 11730..11739 ; Numeric # Nd [10] AHOM DIGIT ZERO..AHOM DIGIT NINE 118E0..118E9 ; Numeric # Nd [10] WARANG CITI DIGIT ZERO..WARANG CITI DIGIT NINE +11950..11959 ; Numeric # Nd [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE 11C50..11C59 ; Numeric # Nd [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE 11D50..11D59 ; Numeric # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE 11DA0..11DA9 ; Numeric # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE +11F50..11F59 ; Numeric # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE 16A60..16A69 ; Numeric # Nd [10] MRO DIGIT ZERO..MRO DIGIT NINE +16AC0..16AC9 ; Numeric # Nd [10] TANGSA DIGIT ZERO..TANGSA 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 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE +1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE +1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 631 +# Total code points: 681 # ================================================