diff options
Diffstat (limited to 'lib/unicore/extracted/DLineBreak.txt')
-rw-r--r-- | lib/unicore/extracted/DLineBreak.txt | 301 |
1 files changed, 248 insertions, 53 deletions
diff --git a/lib/unicore/extracted/DLineBreak.txt b/lib/unicore/extracted/DLineBreak.txt index 72e37f3d8b..473bd87c3b 100644 --- a/lib/unicore/extracted/DLineBreak.txt +++ b/lib/unicore/extracted/DLineBreak.txt @@ -1,10 +1,10 @@ -# DerivedLineBreak-5.1.0.txt -# Date: 2008-03-20, 17:55:02 GMT [MD] +# DerivedLineBreak-5.2.0.txt +# Date: 2009-08-22, 04:58:23 GMT [MD] # # Unicode Character Database -# Copyright (c) 1991-2008 Unicode, Inc. +# Copyright (c) 1991-2009 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html -# For documentation, see UCD.html +# For documentation, see http://www.unicode.org/reports/tr44/ # ================================================ @@ -23,8 +23,8 @@ E000..F8FF ; XX # Co [6400] <private-use-E000>..<private-use-F8FF> F0000..FFFFD ; XX # Co [65534] <private-use-F0000>..<private-use-FFFFD> 100000..10FFFD; XX # Co [65534] <private-use-100000>..<private-use-10FFFD> -# The above property value applies to 873883 code points not listed here. -# Total code points: 1011351 +# The above property value applies to 783465 code points not listed here. +# Total code points: 920933 # ================================================ @@ -105,15 +105,17 @@ FF3B ; OP # Ps FULLWIDTH LEFT SQUARE BRACKET FF5B ; OP # Ps FULLWIDTH LEFT CURLY BRACKET FF5F ; OP # Ps FULLWIDTH LEFT WHITE PARENTHESIS FF62 ; OP # Ps HALFWIDTH LEFT CORNER BRACKET +13258..1325A ; OP # Lo [3] EGYPTIAN HIEROGLYPH O006A..EGYPTIAN HIEROGLYPH O006C +13286 ; OP # Lo EGYPTIAN HIEROGLYPH O036A +13288 ; OP # Lo EGYPTIAN HIEROGLYPH O036C +13379 ; OP # Lo EGYPTIAN HIEROGLYPH V011A -# Total code points: 75 +# Total code points: 81 # ================================================ # Line_Break=Close_Punctuation -0029 ; CL # Pe RIGHT PARENTHESIS -005D ; CL # Pe RIGHT SQUARE BRACKET 007D ; CL # Pe RIGHT CURLY BRACKET 0F3B ; CL # Pe TIBETAN MARK GUG RTAGS GYAS 0F3D ; CL # Pe TIBETAN MARK ANG KHANG GYAS @@ -190,8 +192,13 @@ FF60 ; CL # Pe FULLWIDTH RIGHT WHITE PARENTHESIS FF61 ; CL # Po HALFWIDTH IDEOGRAPHIC FULL STOP FF63 ; CL # Pe HALFWIDTH RIGHT CORNER BRACKET FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA +1325B..1325D ; CL # Lo [3] EGYPTIAN HIEROGLYPH O006D..EGYPTIAN HIEROGLYPH O006F +13282 ; CL # Lo EGYPTIAN HIEROGLYPH O033A +13287 ; CL # Lo EGYPTIAN HIEROGLYPH O036B +13289 ; CL # Lo EGYPTIAN HIEROGLYPH O036D +1337A..1337B ; CL # Lo [2] EGYPTIAN HIEROGLYPH V011B..EGYPTIAN HIEROGLYPH V011C -# Total code points: 81 +# Total code points: 87 # ================================================ @@ -356,13 +363,14 @@ FE13..FE14 ; IS # Po [2] PRESENTATION FORM FOR VERTICAL COLON..PRESENTATION 005C ; PR # Po REVERSE SOLIDUS 00A3..00A5 ; PR # Sc [3] POUND SIGN..YEN SIGN 00B1 ; PR # Sm PLUS-MINUS SIGN -09F2..09F3 ; PR # Sc [2] BENGALI RUPEE MARK..BENGALI RUPEE SIGN +09FB ; PR # Sc BENGALI GANDA MARK 0AF1 ; PR # Sc GUJARATI RUPEE SIGN 0BF9 ; PR # Sc TAMIL RUPEE SIGN 0E3F ; PR # Sc THAI CURRENCY SYMBOL BAHT 17DB ; PR # Sc KHMER CURRENCY SYMBOL RIEL 20A0..20A6 ; PR # Sc [7] EURO-CURRENCY SIGN..NAIRA SIGN 20A8..20B5 ; PR # Sc [14] RUPEE SIGN..CEDI SIGN +20B7..20B8 ; PR # Sc [2] SPESMILO SIGN..TENGE SIGN 2116 ; PR # So NUMERO SIGN 2212..2213 ; PR # Sm [2] MINUS SIGN..MINUS-OR-PLUS SIGN FE69 ; PR # Sc SMALL DOLLAR SIGN @@ -370,7 +378,7 @@ FF04 ; PR # Sc FULLWIDTH DOLLAR SIGN FFE1 ; PR # Sc FULLWIDTH POUND SIGN FFE5..FFE6 ; PR # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN -# Total code points: 42 +# Total code points: 43 # ================================================ @@ -382,17 +390,21 @@ FFE5..FFE6 ; PR # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN 0609..060A ; PO # Po [2] ARABIC-INDIC PER MILLE SIGN..ARABIC-INDIC PER TEN THOUSAND SIGN 060B ; PO # Sc AFGHANI SIGN 066A ; PO # Po ARABIC PERCENT SIGN +09F2..09F3 ; PO # Sc [2] BENGALI RUPEE MARK..BENGALI RUPEE SIGN +09F9 ; PO # No BENGALI CURRENCY DENOMINATOR SIXTEEN 0D79 ; PO # So MALAYALAM DATE MARK 2030..2037 ; PO # Po [8] PER MILLE SIGN..REVERSED TRIPLE PRIME 20A7 ; PO # Sc PESETA SIGN +20B6 ; PO # Sc LIVRE TOURNOIS SIGN 2103 ; PO # So DEGREE CELSIUS 2109 ; PO # So DEGREE FAHRENHEIT +A838 ; PO # Sc NORTH INDIC RUPEE MARK FDFC ; PO # Sc RIAL SIGN FE6A ; PO # Po SMALL PERCENT SIGN FF05 ; PO # Po FULLWIDTH PERCENT SIGN FFE0 ; PO # Sc FULLWIDTH CENT SIGN -# Total code points: 23 +# Total code points: 28 # ================================================ @@ -420,7 +432,9 @@ FFE0 ; PO # Sc FULLWIDTH CENT SIGN 17E0..17E9 ; NU # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE 1810..1819 ; NU # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE 1946..194F ; NU # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE -19D0..19D9 ; NU # Nd [10] NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19D0..19DA ; NU # Nd [11] NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +1A80..1A89 ; NU # Nd [10] TAI THAM HORA DIGIT ZERO..TAI THAM HORA DIGIT NINE +1A90..1A99 ; NU # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1B50..1B59 ; NU # Nd [10] BALINESE DIGIT ZERO..BALINESE DIGIT NINE 1BB0..1BB9 ; NU # Nd [10] SUNDANESE DIGIT ZERO..SUNDANESE DIGIT NINE 1C40..1C49 ; NU # Nd [10] LEPCHA DIGIT ZERO..LEPCHA DIGIT NINE @@ -428,11 +442,13 @@ FFE0 ; PO # Sc FULLWIDTH CENT SIGN A620..A629 ; NU # Nd [10] VAI DIGIT ZERO..VAI DIGIT NINE A8D0..A8D9 ; NU # Nd [10] SAURASHTRA DIGIT ZERO..SAURASHTRA DIGIT NINE A900..A909 ; NU # Nd [10] KAYAH LI DIGIT ZERO..KAYAH LI DIGIT NINE +A9D0..A9D9 ; NU # Nd [10] JAVANESE DIGIT ZERO..JAVANESE DIGIT NINE AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE +ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 104A0..104A9 ; NU # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE 1D7CE..1D7FF ; NU # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE -# Total code points: 362 +# Total code points: 403 # ================================================ @@ -494,7 +510,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 03F6 ; AL # Sm GREEK REVERSED LUNATE EPSILON SYMBOL 03F7..0481 ; AL # L& [139] GREEK CAPITAL LETTER SHO..CYRILLIC SMALL LETTER KOPPA 0482 ; AL # So CYRILLIC THOUSANDS SIGN -048A..0523 ; AL # L& [154] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EN WITH MIDDLE HOOK +048A..0525 ; AL # L& [156] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER PE WITH DESCENDER 0531..0556 ; AL # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH 0559 ; AL # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING 055A..055F ; AL # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK @@ -532,6 +548,11 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 07F6 ; AL # So NKO SYMBOL OO DENNEN 07F7 ; AL # Po NKO SYMBOL GBAKURUNEN 07FA ; AL # Lm NKO LAJANYALAN +0800..0815 ; AL # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF +081A ; AL # Lm SAMARITAN MODIFIER LETTER EPENTHETIC YUT +0824 ; AL # Lm SAMARITAN MODIFIER LETTER SHORT A +0828 ; AL # Lm SAMARITAN MODIFIER LETTER I +0830..083E ; AL # Po [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU 0904..0939 ; AL # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; AL # Lo DEVANAGARI SIGN AVAGRAHA 0950 ; AL # Lo DEVANAGARI OM @@ -539,7 +560,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 0970 ; AL # Po DEVANAGARI ABBREVIATION SIGN 0971 ; AL # Lm DEVANAGARI SIGN HIGH SPACING DOT 0972 ; AL # Lo DEVANAGARI LETTER CANDRA A -097B..097F ; AL # Lo [5] DEVANAGARI LETTER GGA..DEVANAGARI LETTER BBA +0979..097F ; AL # Lo [7] DEVANAGARI LETTER ZHA..DEVANAGARI LETTER BBA 0985..098C ; AL # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L 098F..0990 ; AL # Lo [2] BENGALI LETTER E..BENGALI LETTER AI 0993..09A8 ; AL # Lo [22] BENGALI LETTER O..BENGALI LETTER NA @@ -551,7 +572,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 09DC..09DD ; AL # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF..09E1 ; AL # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; AL # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL -09F4..09F9 ; AL # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN +09F4..09F8 ; AL # No [5] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR 09FA ; AL # So BENGALI ISSHAR 0A05..0A0A ; AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; AL # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -646,6 +667,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 0FC7..0FCC ; AL # So [6] TIBETAN SYMBOL RDO RJE RGYA GRAM..TIBETAN SYMBOL NOR BU BZHI -KHYIL 0FCE..0FCF ; AL # So [2] TIBETAN SIGN RDEL NAG RDEL DKAR..TIBETAN SIGN RDEL NAG GSUM 0FD4 ; AL # Po TIBETAN MARK CLOSING BRDA RNYING YIG MGO SGAB MA +0FD5..0FD8 ; AL # So [4] RIGHT-FACING SVASTI SIGN..LEFT-FACING SVASTI SIGN WITH DOTS 104C..104F ; AL # Po [4] MYANMAR SYMBOL LOCATIVE..MYANMAR SYMBOL GENITIVE 10A0..10C5 ; AL # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE 10D0..10FA ; AL # Lo [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN @@ -675,7 +697,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 13A0..13F4 ; AL # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV 1401..166C ; AL # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA 166D..166E ; AL # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP -166F..1676 ; AL # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA +166F..167F ; AL # Lo [17] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS BLACKFOOT W 1681..169A ; AL # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH 16A0..16EA ; AL # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X 16EE..16F0 ; AL # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL @@ -695,6 +717,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 1844..1877 ; AL # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA 1880..18A8 ; AL # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA 18AA ; AL # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +18B0..18F5 ; AL # Lo [70] CANADIAN SYLLABICS OY..CANADIAN SYLLABICS CARRIER DENTAL S 1900..191C ; AL # Lo [29] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER HA 1940 ; AL # So LIMBU SIGN LOO 19E0..19FF ; AL # So [32] KHMER SYMBOL PATHAMASAT..KHMER SYMBOL DAP-PRAM ROC @@ -702,6 +725,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 1A1E..1A1F ; AL # Po [2] BUGINESE PALLAWA..BUGINESE END OF SECTION 1B05..1B33 ; AL # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA 1B45..1B4B ; AL # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK +1B5C ; AL # Po BALINESE WINDU 1B61..1B6A ; AL # So [10] BALINESE MUSICAL SYMBOL DONG..BALINESE MUSICAL SYMBOL DANG GEDE 1B74..1B7C ; AL # So [9] BALINESE MUSICAL SYMBOL RIGHT-HAND OPEN DUG..BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING 1B83..1BA0 ; AL # Lo [30] SUNDANESE LETTER A..SUNDANESE LETTER HA @@ -710,6 +734,9 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 1C4D..1C4F ; AL # Lo [3] LEPCHA LETTER TTA..LEPCHA LETTER DDA 1C5A..1C77 ; AL # Lo [30] OL CHIKI LETTER LA..OL CHIKI LETTER OH 1C78..1C7D ; AL # Lm [6] OL CHIKI MU TTUDDAG..OL CHIKI AHAD +1CD3 ; AL # Po VEDIC SIGN NIHSHVASA +1CE9..1CEC ; AL # Lo [4] VEDIC SIGN ANUSVARA ANTARGOMUKHA..VEDIC SIGN ANUSVARA VAMAGOMUKHA WITH TAIL +1CEE..1CF1 ; AL # Lo [4] VEDIC SIGN HEXIFORM LONG ANUSVARA..VEDIC SIGN ANUSVARA UBHAYATO MUKHA 1D00..1D2B ; AL # L& [44] LATIN LETTER SMALL CAPITAL A..CYRILLIC LETTER SMALL CAPITAL EL 1D2C..1D61 ; AL # Lm [54] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL CHI 1D62..1D77 ; AL # L& [22] LATIN SUBSCRIPT SMALL LETTER I..LATIN SMALL LETTER TURNED G @@ -756,7 +783,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 205C ; AL # Po DOTTED CROSS 2061..2064 ; AL # Cf [4] FUNCTION APPLICATION..INVISIBLE PLUS 2070 ; AL # No SUPERSCRIPT ZERO -2071 ; AL # L& SUPERSCRIPT LATIN SMALL LETTER I +2071 ; AL # Lm SUPERSCRIPT LATIN SMALL LETTER I 2075..2079 ; AL # No [5] SUPERSCRIPT FIVE..SUPERSCRIPT NINE 207A..207C ; AL # Sm [3] SUPERSCRIPT PLUS SIGN..SUPERSCRIPT EQUALS SIGN 2080 ; AL # No SUBSCRIPT ZERO @@ -797,7 +824,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 214C..214D ; AL # So [2] PER SIGN..AKTIESELSKAB 214E ; AL # L& TURNED SMALL F 214F ; AL # So SYMBOL FOR SAMARITAN SOURCE -2153 ; AL # No VULGAR FRACTION ONE THIRD +2150..2153 ; AL # No [4] VULGAR FRACTION ONE SEVENTH..VULGAR FRACTION ONE THIRD 2156..215A ; AL # No [5] VULGAR FRACTION TWO FIFTHS..VULGAR FRACTION FIVE SIXTHS 215C..215D ; AL # No [2] VULGAR FRACTION THREE EIGHTHS..VULGAR FRACTION FIVE EIGHTHS 215F ; AL # No FRACTION NUMERATOR ONE @@ -860,7 +887,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 239B..23B3 ; AL # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM 23B4..23DB ; AL # So [40] TOP SQUARE BRACKET..FUSE 23DC..23E1 ; AL # Sm [6] TOP PARENTHESIS..BOTTOM TORTOISE SHELL BRACKET -23E2..23E7 ; AL # So [6] WHITE TRAPEZIUM..ELECTRICAL INTERSECTION +23E2..23E8 ; AL # So [7] WHITE TRAPEZIUM..DECIMAL EXPONENT SYMBOL 2400..2426 ; AL # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO 2440..244A ; AL # So [11] OCR HOOK..OCR DOUBLE BACKSLASH 24FF ; AL # No NEGATIVE CIRCLED DIGIT ZERO @@ -894,7 +921,7 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 266B ; AL # So BEAMED EIGHTH NOTES 266E ; AL # So MUSIC NATURAL SIGN 2670..269D ; AL # So [46] WEST SYRIAC CROSS..OUTLINED WHITE STAR -26A0..26BC ; AL # So [29] WARNING SIGN..SESQUIQUADRATE +26A0..26BD ; AL # So [30] WARNING SIGN..SOCCER BALL 26C0..26C3 ; AL # So [4] WHITE DRAUGHTS MAN..BLACK DRAUGHTS KING 2701..2704 ; AL # So [4] UPPER BLADE SCISSORS..WHITE SCISSORS 2706..2709 ; AL # So [4] TELEPHONE LOCATION SIGN..ENVELOPE @@ -926,11 +953,11 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 2B50..2B54 ; AL # So [5] WHITE MEDIUM STAR..WHITE RIGHT-POINTING PENTAGON 2C00..2C2E ; AL # L& [47] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE 2C30..2C5E ; AL # L& [47] GLAGOLITIC SMALL LETTER AZU..GLAGOLITIC SMALL LETTER LATINATE MYSLITE -2C60..2C6F ; AL # L& [16] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN CAPITAL LETTER TURNED A -2C71..2C7C ; AL # L& [12] LATIN SMALL LETTER V WITH RIGHT HOOK..LATIN SUBSCRIPT SMALL LETTER J +2C60..2C7C ; AL # L& [29] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN SUBSCRIPT SMALL LETTER J 2C7D ; AL # Lm MODIFIER LETTER CAPITAL V -2C80..2CE4 ; AL # L& [101] COPTIC CAPITAL LETTER ALFA..COPTIC SYMBOL KAI +2C7E..2CE4 ; AL # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI 2CE5..2CEA ; AL # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA +2CEB..2CEE ; AL # L& [4] COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI..COPTIC SMALL LETTER CRYPTOGRAMMIC GANGIA 2CFD ; AL # No COPTIC FRACTION ONE HALF 2D00..2D25 ; AL # L& [38] GEORGIAN SMALL LETTER AN..GEORGIAN SMALL LETTER HOE 2D30..2D65 ; AL # Lo [54] TIFINAGH LETTER YA..TIFINAGH LETTER YAZZ @@ -950,6 +977,8 @@ AA50..AA59 ; NU # Nd [10] CHAM DIGIT ZERO..CHAM DIGIT NINE 2E1E..2E1F ; AL # Po [2] TILDE WITH DOT ABOVE..TILDE WITH DOT BELOW 2E2F ; AL # Lm VERTICAL TILDE 4DC0..4DFF ; AL # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION +A4D0..A4F7 ; AL # Lo [40] LISU LETTER BA..LISU LETTER OE +A4F8..A4FD ; AL # Lm [6] LISU LETTER TONE MYA TI..LISU LETTER TONE MYA JEU A500..A60B ; AL # Lo [268] VAI SYLLABLE EE..VAI SYLLABLE NG A60C ; AL # Lm VAI SYLLABLE LENGTHENER A610..A61F ; AL # Lo [16] VAI SYLLABLE NDOLE FA..VAI SYMBOL JONG @@ -961,6 +990,9 @@ A673 ; AL # Po SLAVONIC ASTERISK A67E ; AL # Po CYRILLIC KAVYKA A67F ; AL # Lm CYRILLIC PAYEROK A680..A697 ; AL # L& [24] CYRILLIC CAPITAL LETTER DWE..CYRILLIC SMALL LETTER SHWE +A6A0..A6E5 ; AL # Lo [70] BAMUM LETTER A..BAMUM LETTER KI +A6E6..A6EF ; AL # Nl [10] BAMUM LETTER MO..BAMUM LETTER KOGHOM +A6F2 ; AL # Po BAMUM NJAEMLI A700..A716 ; AL # Sk [23] MODIFIER LETTER CHINESE TONE YIN PING..MODIFIER LETTER EXTRA-LOW LEFT-STEM TONE BAR A717..A71F ; AL # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A720..A721 ; AL # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE @@ -975,15 +1007,27 @@ A803..A805 ; AL # Lo [3] SYLOTI NAGRI LETTER U..SYLOTI NAGRI LETTER O A807..A80A ; AL # Lo [4] SYLOTI NAGRI LETTER KO..SYLOTI NAGRI LETTER GHO A80C..A822 ; AL # Lo [23] SYLOTI NAGRI LETTER CO..SYLOTI NAGRI LETTER HO A828..A82B ; AL # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK-4 +A830..A835 ; AL # No [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTION THREE SIXTEENTHS +A836..A837 ; AL # So [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK +A839 ; AL # So NORTH INDIC QUANTITY MARK A840..A873 ; AL # Lo [52] PHAGS-PA LETTER KA..PHAGS-PA LETTER CANDRABINDU A882..A8B3 ; AL # Lo [50] SAURASHTRA LETTER A..SAURASHTRA LETTER LLA +A8F2..A8F7 ; AL # Lo [6] DEVANAGARI SIGN SPACING CANDRABINDU..DEVANAGARI SIGN CANDRABINDU AVAGRAHA +A8F8..A8FA ; AL # Po [3] DEVANAGARI SIGN PUSHPIKA..DEVANAGARI CARET +A8FB ; AL # Lo DEVANAGARI HEADSTROKE A90A..A925 ; AL # Lo [28] KAYAH LI LETTER KA..KAYAH LI LETTER OO A930..A946 ; AL # Lo [23] REJANG LETTER KA..REJANG LETTER A A95F ; AL # Po REJANG SECTION MARK +A984..A9B2 ; AL # Lo [47] JAVANESE LETTER A..JAVANESE LETTER HA +A9C1..A9C6 ; AL # Po [6] JAVANESE LEFT RERENGGAN..JAVANESE PADA WINDU +A9CA..A9CD ; AL # Po [4] JAVANESE PADA ADEG..JAVANESE TURNED PADA PISELEH +A9CF ; AL # Lm JAVANESE PANGRANGKEP +A9DE..A9DF ; AL # Po [2] JAVANESE PADA TIRTA TUMETES..JAVANESE PADA ISEN-ISEN AA00..AA28 ; AL # Lo [41] CHAM LETTER A..CHAM LETTER HA AA40..AA42 ; AL # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG AA44..AA4B ; AL # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS AA5C ; AL # Po CHAM PUNCTUATION SPIRAL +ABC0..ABE2 ; AL # Lo [35] MEETEI MAYEK LETTER KOK..MEETEI MAYEK LETTER I LONSUM FB00..FB06 ; AL # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST FB13..FB17 ; AL # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH FB1D ; AL # Lo HEBREW LETTER YOD WITH HIRIQ @@ -1046,9 +1090,10 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1080A..10835 ; AL # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO 10837..10838 ; AL # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE 1083C ; AL # Lo CYPRIOT SYLLABLE ZA -1083F ; AL # Lo CYPRIOT SYLLABLE ZO +1083F..10855 ; AL # Lo [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW +10858..1085F ; AL # No [8] IMPERIAL ARAMAIC NUMBER ONE..IMPERIAL ARAMAIC NUMBER TEN THOUSAND 10900..10915 ; AL # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU -10916..10919 ; AL # No [4] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER ONE HUNDRED +10916..1091B ; AL # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE 10920..10939 ; AL # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; AL # Po LYDIAN TRIANGULAR MARK 10A00 ; AL # Lo KHAROSHTHI LETTER A @@ -1057,8 +1102,26 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10A19..10A33 ; AL # Lo [27] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER TTTHA 10A40..10A47 ; AL # No [8] KHAROSHTHI DIGIT ONE..KHAROSHTHI NUMBER ONE THOUSAND 10A58 ; AL # Po KHAROSHTHI PUNCTUATION LINES +10A60..10A7C ; AL # Lo [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH +10A7D..10A7E ; AL # No [2] OLD SOUTH ARABIAN NUMBER ONE..OLD SOUTH ARABIAN NUMBER FIFTY +10A7F ; AL # Po OLD SOUTH ARABIAN NUMERIC INDICATOR +10B00..10B35 ; AL # Lo [54] AVESTAN LETTER A..AVESTAN LETTER HE +10B40..10B55 ; AL # Lo [22] INSCRIPTIONAL PARTHIAN LETTER ALEPH..INSCRIPTIONAL PARTHIAN LETTER TAW +10B58..10B5F ; AL # No [8] INSCRIPTIONAL PARTHIAN NUMBER ONE..INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND +10B60..10B72 ; AL # Lo [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW +10B78..10B7F ; AL # No [8] INSCRIPTIONAL PAHLAVI NUMBER ONE..INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND +10C00..10C48 ; AL # Lo [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH +10E60..10E7E ; AL # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS +11083..110AF ; AL # Lo [45] KAITHI LETTER A..KAITHI LETTER HA +110BB..110BC ; AL # Po [2] KAITHI ABBREVIATION SIGN..KAITHI ENUMERATION SIGN +110BD ; AL # Cf KAITHI NUMBER SIGN 12000..1236E ; AL # Lo [879] CUNEIFORM SIGN A..CUNEIFORM SIGN ZUM 12400..12462 ; AL # Nl [99] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN OLD ASSYRIAN ONE QUARTER +13000..13257 ; AL # Lo [600] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH O006 +1325E..13281 ; AL # Lo [36] EGYPTIAN HIEROGLYPH O007..EGYPTIAN HIEROGLYPH O033 +13283..13285 ; AL # Lo [3] EGYPTIAN HIEROGLYPH O034..EGYPTIAN HIEROGLYPH O036 +1328A..13378 ; AL # Lo [239] EGYPTIAN HIEROGLYPH O037..EGYPTIAN HIEROGLYPH V011 +1337C..1342E ; AL # Lo [179] EGYPTIAN HIEROGLYPH V012..EGYPTIAN HIEROGLYPH AA032 1D000..1D0F5 ; AL # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO 1D100..1D126 ; AL # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 1D129..1D164 ; AL # So [60] MUSICAL SYMBOL MULTIPLE MEASURE REST..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE @@ -1112,8 +1175,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1D7C4..1D7CB ; AL # L& [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA 1F000..1F02B ; AL # So [44] MAHJONG TILE EAST WIND..MAHJONG TILE BACK 1F030..1F093 ; AL # So [100] DOMINO TILE HORIZONTAL BACK..DOMINO TILE VERTICAL-06-06 +1F12E ; AL # So CIRCLED WZ -# Total code points: 12318 +# Total code points: 14092 # ================================================ @@ -1169,7 +1233,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 31C0..31E3 ; ID # So [36] CJK STROKE T..CJK STROKE Q 3200..321E ; ID # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU 3220..3229 ; ID # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN -322A..3243 ; ID # So [26] PARENTHESIZED IDEOGRAPH MOON..PARENTHESIZED IDEOGRAPH REACH +322A..3247 ; ID # So [30] PARENTHESIZED IDEOGRAPH MOON..CIRCLED IDEOGRAPH KOTO 3250 ; ID # So PARTNERSHIP SIGN 3251..325F ; ID # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE 3260..327F ; ID # So [32] CIRCLED HANGUL KIYEOK..KOREAN STANDARD SYMBOL @@ -1179,13 +1243,18 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 32C0..32FE ; ID # So [63] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..CIRCLED KATAKANA WO 3300..33FF ; ID # So [256] SQUARE APAATO..SQUARE GAL 3400..4DB5 ; ID # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FC3 ; ID # Lo [20932] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FC3 +4DB6..4DBF ; ID # Cn [10] <reserved-4DB6>..<reserved-4DBF> +4E00..9FCB ; ID # Lo [20940] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FCB +9FCC..9FFF ; ID # Cn [52] <reserved-9FCC>..<reserved-9FFF> A000..A014 ; ID # Lo [21] YI SYLLABLE IT..YI SYLLABLE E A016..A48C ; ID # Lo [1143] YI SYLLABLE BIT..YI SYLLABLE YYR A490..A4C6 ; ID # So [55] YI RADICAL QOT..YI RADICAL KE F900..FA2D ; ID # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D -FA30..FA6A ; ID # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A +FA2E..FA2F ; ID # Cn [2] <reserved-FA2E>..<reserved-FA2F> +FA30..FA6D ; ID # Lo [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D +FA6E..FA6F ; ID # Cn [2] <reserved-FA6E>..<reserved-FA6F> FA70..FAD9 ; ID # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 +FADA..FAFF ; ID # Cn [38] <reserved-FADA>..<reserved-FAFF> 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 @@ -1220,10 +1289,18 @@ FF5E ; ID # Sm FULLWIDTH TILDE FFE2 ; ID # Sm FULLWIDTH NOT SIGN FFE3 ; ID # Sk FULLWIDTH MACRON FFE4 ; ID # So FULLWIDTH BROKEN BAR +1F200 ; ID # So SQUARE HIRAGANA HOKA +1F210..1F231 ; ID # So [34] SQUARED CJK UNIFIED IDEOGRAPH-624B..SQUARED CJK UNIFIED IDEOGRAPH-6253 +1F240..1F248 ; ID # So [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557 20000..2A6D6 ; ID # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 +2A6D7..2A6FF ; ID # Cn [41] <reserved-2A6D7>..<reserved-2A6FF> +2A700..2B734 ; ID # Lo [4149] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B734 +2B735..2F7FF ; ID # Cn [16587] <reserved-2B735>..<reserved-2F7FF> 2F800..2FA1D ; ID # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D +2FA1E..2FFFD ; ID # Cn [1504] <reserved-2FA1E>..<reserved-2FFFD> +30000..3FFFD ; ID # Cn [65534] <reserved-30000>..<reserved-3FFFD> -# Total code points: 73797 +# Total code points: 161775 # ================================================ @@ -1272,14 +1349,19 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0730..074A ; CM # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH 07A6..07B0 ; CM # Mn [11] THAANA ABAFILI..THAANA SUKUN 07EB..07F3 ; CM # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE -0901..0902 ; CM # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +0816..0819 ; CM # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; CM # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; CM # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; CM # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0900..0902 ; CM # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA 0903 ; CM # Mc DEVANAGARI SIGN VISARGA 093C ; CM # Mn DEVANAGARI SIGN NUKTA 093E..0940 ; CM # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II 0941..0948 ; CM # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI 0949..094C ; CM # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU 094D ; CM # Mn DEVANAGARI SIGN VIRAMA -0951..0954 ; CM # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +094E ; CM # Mc DEVANAGARI VOWEL SIGN PRISHTHAMATRA E +0951..0955 ; CM # Mn [5] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN CANDRA LONG E 0962..0963 ; CM # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL 0981 ; CM # Mn BENGALI SIGN CANDRABINDU 0982..0983 ; CM # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA @@ -1393,6 +1475,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1939..193B ; CM # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I 1A17..1A18 ; CM # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U 1A19..1A1B ; CM # Mc [3] BUGINESE VOWEL SIGN E..BUGINESE VOWEL SIGN AE +1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -1415,8 +1498,14 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1C2C..1C33 ; CM # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T 1C34..1C35 ; CM # Mc [2] LEPCHA CONSONANT SIGN NYIN-DO..LEPCHA CONSONANT SIGN KANG 1C36..1C37 ; CM # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; CM # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; CM # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE1 ; CM # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA +1CE2..1CE8 ; CM # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; CM # Mn VEDIC SIGN TIRYAK +1CF2 ; CM # Mc VEDIC SIGN ARDHAVISARGA 1DC0..1DE6 ; CM # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z -1DFE..1DFF ; CM # Mn [2] COMBINING LEFT ARROWHEAD ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +1DFD..1DFF ; CM # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW 200C..200F ; CM # Cf [4] ZERO WIDTH NON-JOINER..RIGHT-TO-LEFT MARK 202A..202E ; CM # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE 206A..206F ; CM # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES @@ -1425,12 +1514,14 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 20E1 ; CM # Mn COMBINING LEFT RIGHT ARROW ABOVE 20E2..20E4 ; CM # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE 20E5..20F0 ; CM # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; CM # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS 2DE0..2DFF ; CM # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS 302A..302F ; CM # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK 3099..309A ; CM # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK A66F ; CM # Mn COMBINING CYRILLIC VZMET A670..A672 ; CM # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN A67C..A67D ; CM # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK +A6F0..A6F1 ; CM # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS A802 ; CM # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; CM # Mn SYLOTI NAGRI SIGN HASANTA A80B ; CM # Mn SYLOTI NAGRI SIGN ANUSVARA @@ -1440,9 +1531,18 @@ A827 ; CM # Mc SYLOTI NAGRI VOWEL SIGN OO A880..A881 ; CM # Mc [2] SAURASHTRA SIGN ANUSVARA..SAURASHTRA SIGN VISARGA A8B4..A8C3 ; CM # Mc [16] SAURASHTRA CONSONANT SIGN HAARU..SAURASHTRA VOWEL SIGN AU A8C4 ; CM # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; CM # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA A926..A92D ; CM # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU A947..A951 ; CM # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R A952..A953 ; CM # Mc [2] REJANG CONSONANT SIGN H..REJANG VIRAMA +A980..A982 ; CM # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A983 ; CM # Mc JAVANESE SIGN WIGNYAN +A9B3 ; CM # Mn JAVANESE SIGN CECAK TELU +A9B4..A9B5 ; CM # Mc [2] JAVANESE VOWEL SIGN TARUNG..JAVANESE VOWEL SIGN TOLONG +A9B6..A9B9 ; CM # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BA..A9BB ; CM # Mc [2] JAVANESE VOWEL SIGN TALING..JAVANESE VOWEL SIGN DIRGA MURE +A9BC ; CM # Mn JAVANESE VOWEL SIGN PEPET +A9BD..A9C0 ; CM # Mc [4] JAVANESE CONSONANT SIGN KERET..JAVANESE PANGKON AA29..AA2E ; CM # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE AA2F..AA30 ; CM # Mc [2] CHAM VOWEL SIGN O..CHAM VOWEL SIGN AI AA31..AA32 ; CM # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE @@ -1451,6 +1551,13 @@ AA35..AA36 ; CM # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA AA43 ; CM # Mn CHAM CONSONANT SIGN FINAL NG AA4C ; CM # Mn CHAM CONSONANT SIGN FINAL M AA4D ; CM # Mc CHAM CONSONANT SIGN FINAL H +ABE3..ABE4 ; CM # Mc [2] MEETEI MAYEK VOWEL SIGN ONAP..MEETEI MAYEK VOWEL SIGN INAP +ABE5 ; CM # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE6..ABE7 ; CM # Mc [2] MEETEI MAYEK VOWEL SIGN YENAP..MEETEI MAYEK VOWEL SIGN SOUNAP +ABE8 ; CM # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABE9..ABEA ; CM # Mc [2] MEETEI MAYEK VOWEL SIGN CHEINAP..MEETEI MAYEK VOWEL SIGN NUNG +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..FE26 ; CM # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON @@ -1461,6 +1568,12 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 10A0C..10A0F ; CM # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA 10A38..10A3A ; CM # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW 10A3F ; CM # Mn KHAROSHTHI VIRAMA +11080..11081 ; CM # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +11082 ; CM # Mc KAITHI SIGN VISARGA +110B0..110B2 ; CM # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II +110B3..110B6 ; CM # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B7..110B8 ; CM # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU +110B9..110BA ; CM # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA 1D165..1D166 ; CM # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM 1D167..1D169 ; CM # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 1D16D..1D172 ; CM # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 @@ -1473,7 +1586,7 @@ 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: 1319 +# Total code points: 1436 # ================================================ @@ -1514,6 +1627,7 @@ A874..A875 ; BB # Po [2] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA DOUBLE HEAD MA 0FD2 ; BA # Po TIBETAN MARK NYIS TSHEG 104A..104B ; BA # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION 1361 ; BA # Po ETHIOPIC WORDSPACE +1400 ; BA # Pd CANADIAN SYLLABICS HYPHEN 1680 ; BA # Zs OGHAM SPACE MARK 16EB..16ED ; BA # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION 1735..1736 ; BA # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION @@ -1521,7 +1635,8 @@ A874..A875 ; BB # Po [2] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA DOUBLE HEAD MA 17D8 ; BA # Po KHMER SIGN BEYYAL 17DA ; BA # Po KHMER SIGN KOOMUUT 1804..1805 ; BA # Po [2] MONGOLIAN COLON..MONGOLIAN FOUR DOTS -1B5A..1B60 ; BA # Po [7] BALINESE PANTI..BALINESE PAMENENG +1B5A..1B5B ; BA # Po [2] BALINESE PANTI..BALINESE PAMADA +1B5D..1B60 ; BA # Po [4] BALINESE CARIK PAMUNGKAH..BALINESE PAMENENG 1C3B..1C3F ; BA # Po [5] LEPCHA PUNCTUATION TA-ROL..LEPCHA PUNCTUATION TSHOOK 1C7E..1C7F ; BA # Po [2] OL CHIKI PUNCTUATION MUCAAD..OL CHIKI PUNCTUATION DOUBLE MUCAAD 2000..2006 ; BA # Zs [7] EN QUAD..SIX-PER-EM SPACE @@ -1539,21 +1654,28 @@ A874..A875 ; BB # Po [2] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA DOUBLE HEAD MA 2E17 ; BA # Pd DOUBLE OBLIQUE HYPHEN 2E19 ; BA # Po PALM BRANCH 2E2A..2E2D ; BA # Po [4] TWO DOTS OVER ONE DOT PUNCTUATION..FIVE DOT MARK -2E30 ; BA # Po RING POINT +2E30..2E31 ; BA # Po [2] RING POINT..WORD SEPARATOR MIDDLE DOT +A4FE..A4FF ; BA # Po [2] LISU PUNCTUATION COMMA..LISU PUNCTUATION FULL STOP A60D ; BA # Po VAI COMMA A60F ; BA # Po VAI QUESTION MARK +A6F3..A6F7 ; BA # Po [5] BAMUM FULL STOP..BAMUM QUESTION MARK A8CE..A8CF ; BA # Po [2] SAURASHTRA DANDA..SAURASHTRA DOUBLE DANDA A92E..A92F ; BA # Po [2] KAYAH LI SIGN CWI..KAYAH LI SIGN SHYA +A9C7..A9C9 ; BA # Po [3] JAVANESE PADA PANGKAT..JAVANESE PADA LUNGSI AA5D..AA5F ; BA # Po [3] CHAM PUNCTUATION DANDA..CHAM PUNCTUATION TRIPLE DANDA +ABEB ; BA # Po MEETEI MAYEK CHEIKHEI 10100..10101 ; BA # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT 10102 ; BA # So AEGEAN CHECK MARK 1039F ; BA # Po UGARITIC WORD DIVIDER 103D0 ; BA # Po OLD PERSIAN WORD DIVIDER +10857 ; BA # Po IMPERIAL ARAMAIC SECTION SIGN 1091F ; BA # Po PHOENICIAN WORD SEPARATOR 10A50..10A57 ; BA # Po [8] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION DOUBLE DANDA +10B39..10B3F ; BA # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION +110BE..110C1 ; BA # Po [4] KAITHI SECTION MARK..KAITHI DOUBLE DANDA 12470..12473 ; BA # Po [4] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL TRICOLON -# Total code points: 113 +# Total code points: 137 # ================================================ @@ -1658,6 +1780,8 @@ FFFC ; CB # So OBJECT REPLACEMENT CHARACTER 108D ; SA # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE 108E ; SA # Lo MYANMAR LETTER RUMAI PALAUNG FA 108F ; SA # Mc MYANMAR SIGN RUMAI PALAUNG TONE-5 +109A..109C ; SA # Mc [3] MYANMAR SIGN KHAMTI TONE-1..MYANMAR VOWEL SIGN AITON A +109D ; SA # Mn MYANMAR VOWEL SIGN AITON AI 109E..109F ; SA # So [2] MYANMAR SYMBOL SHAN ONE..MYANMAR SYMBOL SHAN EXCLAMATION 1780..17B3 ; SA # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU 17B4..17B5 ; SA # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA @@ -1672,13 +1796,48 @@ FFFC ; CB # So OBJECT REPLACEMENT CHARACTER 17DD ; SA # Mn KHMER SIGN ATTHACAN 1950..196D ; SA # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI 1970..1974 ; SA # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 -1980..19A9 ; SA # Lo [42] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW XVA +1980..19AB ; SA # Lo [44] NEW TAI LUE LETTER HIGH QA..NEW TAI LUE LETTER LOW SUA 19B0..19C0 ; SA # Mc [17] NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE VOWEL SIGN IY 19C1..19C7 ; SA # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B 19C8..19C9 ; SA # Mc [2] NEW TAI LUE TONE MARK-1..NEW TAI LUE TONE MARK-2 19DE..19DF ; SA # Po [2] NEW TAI LUE SIGN LAE..NEW TAI LUE SIGN LAEV - -# Total code points: 450 +1A20..1A54 ; SA # Lo [53] TAI THAM LETTER HIGH KA..TAI THAM LETTER GREAT SA +1A55 ; SA # Mc TAI THAM CONSONANT SIGN MEDIAL RA +1A56 ; SA # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A57 ; SA # Mc TAI THAM CONSONANT SIGN LA TANG LAI +1A58..1A5E ; SA # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; SA # Mn TAI THAM SIGN SAKOT +1A61 ; SA # Mc TAI THAM VOWEL SIGN A +1A62 ; SA # Mn TAI THAM VOWEL SIGN MAI SAT +1A63..1A64 ; SA # Mc [2] TAI THAM VOWEL SIGN AA..TAI THAM VOWEL SIGN TALL AA +1A65..1A6C ; SA # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A6D..1A72 ; SA # Mc [6] TAI THAM VOWEL SIGN OY..TAI THAM VOWEL SIGN THAM AI +1A73..1A7C ; SA # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1AA0..1AA6 ; SA # Po [7] TAI THAM SIGN WIANG..TAI THAM SIGN REVERSED ROTATED RANA +1AA7 ; SA # Lm TAI THAM SIGN MAI YAMOK +1AA8..1AAD ; SA # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG +AA60..AA6F ; SA # Lo [16] MYANMAR LETTER KHAMTI GA..MYANMAR LETTER KHAMTI FA +AA70 ; SA # Lm MYANMAR MODIFIER LETTER KHAMTI REDUPLICATION +AA71..AA76 ; SA # Lo [6] MYANMAR LETTER KHAMTI XA..MYANMAR LOGOGRAM KHAMTI HM +AA77..AA79 ; SA # So [3] MYANMAR SYMBOL AITON EXCLAMATION..MYANMAR SYMBOL AITON TWO +AA7A ; SA # Lo MYANMAR LETTER AITON RA +AA7B ; SA # Mc MYANMAR SIGN PAO KAREN TONE +AA80..AAAF ; SA # Lo [48] TAI VIET LETTER LOW KO..TAI VIET LETTER HIGH O +AAB0 ; SA # Mn TAI VIET MAI KANG +AAB1 ; SA # Lo TAI VIET VOWEL AA +AAB2..AAB4 ; SA # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB5..AAB6 ; SA # Lo [2] TAI VIET VOWEL E..TAI VIET VOWEL O +AAB7..AAB8 ; SA # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AAB9..AABD ; SA # Lo [5] TAI VIET VOWEL UEA..TAI VIET VOWEL AN +AABE..AABF ; SA # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC0 ; SA # Lo TAI VIET TONE MAI NUENG +AAC1 ; SA # Mn TAI VIET TONE MAI THO +AAC2 ; SA # Lo TAI VIET TONE MAI SONG +AADB..AADC ; SA # Lo [2] TAI VIET SYMBOL KON..TAI VIET SYMBOL NUENG +AADD ; SA # Lm TAI VIET SYMBOL SAM +AADE..AADF ; SA # Po [2] TAI VIET SYMBOL HO HOI..TAI VIET SYMBOL KOI KOI + +# Total code points: 662 # ================================================ @@ -1707,7 +1866,7 @@ FFFC ; CB # So OBJECT REPLACEMENT CHARACTER 2020..2021 ; AI # Po [2] DAGGER..DOUBLE DAGGER 203B ; AI # Po REFERENCE MARK 2074 ; AI # No SUPERSCRIPT FOUR -207F ; AI # L& SUPERSCRIPT LATIN SMALL LETTER N +207F ; AI # Lm SUPERSCRIPT LATIN SMALL LETTER N 2081..2084 ; AI # No [4] SUBSCRIPT ONE..SUBSCRIPT FOUR 2105 ; AI # So CARE OF 2113 ; AI # L& SCRIPT SMALL L @@ -1718,6 +1877,7 @@ FFFC ; CB # So OBJECT REPLACEMENT CHARACTER 215E ; AI # No VULGAR FRACTION SEVEN EIGHTHS 2160..216B ; AI # Nl [12] ROMAN NUMERAL ONE..ROMAN NUMERAL TWELVE 2170..2179 ; AI # Nl [10] SMALL ROMAN NUMERAL ONE..SMALL ROMAN NUMERAL TEN +2189 ; AI # No VULGAR FRACTION ZERO THIRDS 2190..2194 ; AI # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW 2195..2199 ; AI # So [5] UP DOWN ARROW..SOUTH WEST ARROW 21D2 ; AI # Sm RIGHTWARDS DOUBLE ARROW @@ -1784,10 +1944,34 @@ FFFC ; CB # So OBJECT REPLACEMENT CHARACTER 2667..266A ; AI # So [4] WHITE CLUB SUIT..EIGHTH NOTE 266C..266D ; AI # So [2] BEAMED SIXTEENTH NOTES..MUSIC FLAT SIGN 266F ; AI # Sm MUSIC SHARP SIGN +269E..269F ; AI # So [2] THREE LINES CONVERGING RIGHT..THREE LINES CONVERGING LEFT +26BE..26BF ; AI # So [2] BASEBALL..SQUARED KEY +26C4..26CD ; AI # So [10] SNOWMAN WITHOUT SNOW..DISABLED CAR +26CF..26E1 ; AI # So [19] PICK..RESTRICTED LEFT ENTRY-2 +26E3 ; AI # So HEAVY CIRCLE WITH STROKE AND TWO DOTS ABOVE +26E8..26FF ; AI # So [24] BLACK CROSS ON SHIELD..WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE +2757 ; AI # So HEAVY EXCLAMATION MARK SYMBOL 2776..2793 ; AI # No [30] DINGBAT NEGATIVE CIRCLED DIGIT ONE..DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN +2B55..2B59 ; AI # So [5] HEAVY LARGE CIRCLE..HEAVY CIRCLED SALTIRE +3248..324F ; AI # So [8] CIRCLED NUMBER TEN ON BLACK SQUARE..CIRCLED NUMBER EIGHTY ON BLACK SQUARE FFFD ; AI # So REPLACEMENT CHARACTER - -# Total code points: 509 +1F100..1F10A ; AI # No [11] DIGIT ZERO FULL STOP..DIGIT NINE COMMA +1F110..1F12D ; AI # So [30] PARENTHESIZED LATIN CAPITAL LETTER A..CIRCLED CD +1F131 ; AI # So SQUARED LATIN CAPITAL LETTER B +1F13D ; AI # So SQUARED LATIN CAPITAL LETTER N +1F13F ; AI # So SQUARED LATIN CAPITAL LETTER P +1F142 ; AI # So SQUARED LATIN CAPITAL LETTER S +1F146 ; AI # So SQUARED LATIN CAPITAL LETTER W +1F14A..1F14E ; AI # So [5] SQUARED HV..SQUARED PPV +1F157 ; AI # So NEGATIVE CIRCLED LATIN CAPITAL LETTER H +1F15F ; AI # So NEGATIVE CIRCLED LATIN CAPITAL LETTER P +1F179 ; AI # So NEGATIVE SQUARED LATIN CAPITAL LETTER J +1F17B..1F17C ; AI # So [2] NEGATIVE SQUARED LATIN CAPITAL LETTER L..NEGATIVE SQUARED LATIN CAPITAL LETTER M +1F17F ; AI # So NEGATIVE SQUARED LATIN CAPITAL LETTER P +1F18A..1F18D ; AI # So [4] CROSSED NEGATIVE SQUARED LATIN CAPITAL LETTER P..NEGATIVE SQUARED SA +1F190 ; AI # So SQUARE DJ + +# Total code points: 644 # ================================================ @@ -1834,26 +2018,28 @@ FEFF ; WJ # Cf ZERO WIDTH NO-BREAK SPACE # Line_Break=JL -1100..1159 ; JL # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH -115F ; JL # Lo HANGUL CHOSEONG FILLER +1100..115F ; JL # Lo [96] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG FILLER +A960..A97C ; JL # Lo [29] HANGUL CHOSEONG TIKEUT-MIEUM..HANGUL CHOSEONG SSANGYEORINHIEUH -# Total code points: 91 +# Total code points: 125 # ================================================ # Line_Break=JV -1160..11A2 ; JV # Lo [67] HANGUL JUNGSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA +1160..11A7 ; JV # Lo [72] HANGUL JUNGSEONG FILLER..HANGUL JUNGSEONG O-YAE +D7B0..D7C6 ; JV # Lo [23] HANGUL JUNGSEONG O-YEO..HANGUL JUNGSEONG ARAEA-E -# Total code points: 67 +# Total code points: 95 # ================================================ # Line_Break=JT -11A8..11F9 ; JT # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH +11A8..11FF ; JT # Lo [88] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG SSANGNIEUN +D7CB..D7FB ; JT # Lo [49] HANGUL JONGSEONG NIEUN-RIEUL..HANGUL JONGSEONG PHIEUPH-THIEUTH -# Total code points: 82 +# Total code points: 137 # ================================================ @@ -2667,4 +2853,13 @@ D789..D7A3 ; H3 # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH # Total code points: 10773 +# ================================================ + +# Line_Break=Close_Parenthesis + +0029 ; CP # Pe RIGHT PARENTHESIS +005D ; CP # Pe RIGHT SQUARE BRACKET + +# Total code points: 2 + # EOF |