From: Nicholas Clark Date: Wed, 31 Mar 2004 15:05:40 +0000 (+0000) Subject: Upgrade to Unicode 4.0.1 X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=7be0dac30b98062294521bd59732f1029a6de1ce;p=p5sagit%2Fp5-mst-13.2.git Upgrade to Unicode 4.0.1 p4raw-id: //depot/perl@22621 --- diff --git a/MANIFEST b/MANIFEST index 12134c8..0d22ef3 100644 --- a/MANIFEST +++ b/MANIFEST @@ -2044,6 +2044,8 @@ lib/unicore/lib/InYiRadi.pl Unicode character database lib/unicore/lib/InYiSyll.pl Unicode character database lib/unicore/lib/JoinCont.pl Unicode character database lib/unicore/lib/Kannada.pl Unicode character database +lib/unicore/lib/Katakan2.pl Unicode character database +lib/unicore/lib/Khmer.pl Unicode character database lib/unicore/lib/Katakana.pl Unicode character database lib/unicore/lib/Khmer.pl Unicode character database lib/unicore/lib/Lao.pl Unicode character database @@ -2108,6 +2110,7 @@ lib/unicore/lib/So.pl Unicode character database lib/unicore/lib/SpacePer.pl Unicode character database lib/unicore/lib/Space.pl Unicode character database lib/unicore/lib/S.pl Unicode character database +lib/unicore/lib/Sterm.pl Unicode character database lib/unicore/lib/Syriac.pl Unicode character database lib/unicore/lib/Tagalog.pl Unicode character database lib/unicore/lib/Tagbanwa.pl Unicode character database @@ -2123,6 +2126,7 @@ lib/unicore/lib/Ugaritic.pl Unicode character database lib/unicore/lib/UnifiedI.pl Unicode character database lib/unicore/lib/Uppercas.pl Unicode character database lib/unicore/lib/Upper.pl Unicode character database +lib/unicore/lib/Variatio.pl Unicode character database lib/unicore/lib/WhiteSpa.pl Unicode character database lib/unicore/lib/Word.pl Unicode character database lib/unicore/lib/XDigit.pl Unicode character database diff --git a/lib/Unicode/UCD.t b/lib/Unicode/UCD.t index 067172d..f0a29ad 100644 --- a/lib/Unicode/UCD.t +++ b/lib/Unicode/UCD.t @@ -164,7 +164,7 @@ is($charinfo->{upper}, ''); is($charinfo->{lower}, ''); is($charinfo->{title}, ''); is($charinfo->{block}, 'Mathematical Alphanumeric Symbols'); -is($charinfo->{script}, undef); +is($charinfo->{script}, 'Common'); use Unicode::UCD qw(charblock charscript); @@ -191,7 +191,7 @@ is($charinfo->{upper}, ''); is($charinfo->{lower}, ''); is($charinfo->{title}, ''); is($charinfo->{block}, 'Latin-1 Supplement'); -is($charinfo->{script}, undef); +is($charinfo->{script}, 'Common'); use Unicode::UCD qw(charblocks charscripts); @@ -221,8 +221,8 @@ is($charscript, 'Ethiopic'); my $ranges; $ranges = charscript('Ogham'); -is($ranges->[0]->[0], hex('1681'), 'Ogham charscript'); -is($ranges->[0]->[1], hex('169a')); +is($ranges->[1]->[0], hex('1681'), 'Ogham charscript'); +is($ranges->[1]->[1], hex('169a')); use Unicode::UCD qw(charinrange); @@ -232,7 +232,7 @@ ok( charinrange($ranges, "13a0")); ok( charinrange($ranges, "13f4")); ok(!charinrange($ranges, "13f5")); -is(Unicode::UCD::UnicodeVersion, '4.0.0', 'UnicodeVersion'); +is(Unicode::UCD::UnicodeVersion, '4.0.1', 'UnicodeVersion'); use Unicode::UCD qw(compexcl); diff --git a/lib/unicore/ArabLink.pl b/lib/unicore/ArabLink.pl index 649abd3..d81c906 100644 --- a/lib/unicore/ArabLink.pl +++ b/lib/unicore/ArabLink.pl @@ -36,8 +36,8 @@ return <<'END'; 06D5 R 06DD U 06EE 06EF R -06FF D 06FA 06FC D +06FF D 0710 R 0712 0714 D 0715 0719 R diff --git a/lib/unicore/ArabLnkGrp.pl b/lib/unicore/ArabLnkGrp.pl index 70bb87d..0c82268 100644 --- a/lib/unicore/ArabLnkGrp.pl +++ b/lib/unicore/ArabLnkGrp.pl @@ -70,10 +70,10 @@ return <<'END'; 06DD 06EE DAL 06EF REH -06FF KNOTTED HEH 06FA SEEN 06FB SAD 06FC AIN +06FF KNOTTED HEH 0710 ALAPH 0712 BETH 0713 0714 GAMAL diff --git a/lib/unicore/ArabicShaping.txt b/lib/unicore/ArabicShaping.txt index df1f193..84c308a 100644 --- a/lib/unicore/ArabicShaping.txt +++ b/lib/unicore/ArabicShaping.txt @@ -1,4 +1,4 @@ -# ArabicShaping-4.0.0.txt +# ArabicShaping-4.0.1.txt # # This file is a normative contributory data file in the # Unicode Character Database. @@ -192,10 +192,10 @@ 06DD; ARABIC END OF AYAH; U; 06EE; DAL WITH INVERTED V; R; DAL 06EF; REH WITH INVERTED V; R; REH -06FF; HEH WITH INVERTED V; D; KNOTTED HEH 06FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN 06FB; DAD WITH DOT BELOW; D; SAD 06FC; GHAIN WITH DOT BELOW; D; AIN +06FF; HEH WITH INVERTED V; D; KNOTTED HEH # Syriac characters diff --git a/lib/unicore/Bidirectional.pl b/lib/unicore/Bidirectional.pl index 54e7012..8a36887 100644 --- a/lib/unicore/Bidirectional.pl +++ b/lib/unicore/Bidirectional.pl @@ -16,11 +16,10 @@ return <<'END'; 0021 0022 ON 0023 0025 ET 0026 002A ON -002B ET +002B ES 002C CS -002D ET -002E CS -002F ES +002D ES +002E 002F CS 0030 0039 EN 003A CS 003B 0040 ON @@ -36,7 +35,9 @@ return <<'END'; 00A2 00A5 ET 00A6 00A9 ON 00AA L -00AB 00AF ON +00AB 00AC ON +00AD BN +00AE 00AF ON 00B0 00B1 ET 00B2 00B3 EN 00B4 ON @@ -490,7 +491,9 @@ return <<'END'; 202E RLO 202F WS 2030 2034 ET -2035 2054 ON +2035 2043 ON +2044 CS +2045 2054 ON 2057 ON 205F WS 2060 2063 BN @@ -544,10 +547,10 @@ return <<'END'; 2396 23D0 ON 2400 2426 ON 2440 244A ON -2460 249B EN +2460 2487 ON +2488 249B EN 249C 24E9 L -24EA EN -24EB 2617 ON +24EA 2617 ON 2619 267D ON 2680 2691 ON 26A0 26A1 ON @@ -563,7 +566,9 @@ return <<'END'; 2798 27AF ON 27B1 27BE ON 27D0 27EB ON -27F0 2B0D ON +27F0 27FF ON +2800 28FF L +2900 2B0D ON 2E80 2E99 ON 2E9B 2EF3 ON 2F00 2FD5 ON @@ -674,8 +679,7 @@ FFE0 FFE1 ET FFE2 FFE4 ON FFE5 FFE6 ET FFE8 FFEE ON -FFF9 FFFB BN -FFFC FFFD ON +FFF9 FFFD ON 10000 1000B L 1000D 10026 L 10028 1003A L diff --git a/lib/unicore/Blocks.pl b/lib/unicore/Blocks.pl index e6b1a4d..25e947d 100644 --- a/lib/unicore/Blocks.pl +++ b/lib/unicore/Blocks.pl @@ -12,7 +12,7 @@ return <<'END'; 0300 036F Combining Diacritical Marks 0370 03FF Greek and Coptic 0400 04FF Cyrillic -0500 052F Cyrillic Supplementary +0500 052F Cyrillic Supplement 0530 058F Armenian 0590 05FF Hebrew 0600 06FF Arabic diff --git a/lib/unicore/Blocks.txt b/lib/unicore/Blocks.txt index 6dc2bd2..aeed970 100644 --- a/lib/unicore/Blocks.txt +++ b/lib/unicore/Blocks.txt @@ -1,11 +1,25 @@ -# Blocks-4.0.0.txt -# Correlated with Unicode 4.0 -# Note: The casing of block names is not normative. -# For example, "Basic Latin" and "BASIC LATIN" are equivalent. +# Blocks-4.0.1.txt +# Date: 2004-03-01, 15:52 [KW] # -# Code points not explicitly listed in this file are given the value No_Block. +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html +# +# Note: When comparing block names, casing, whitespace, hyphens, +# and underbars are ignored. +# For example, "Latin Extended-A" and "latin extended a" are equivalent. +# For more information on the comparison of property values, +# see UCD.html. # +# Code points not explicitly listed in this file are given the value No_Block. +# Format: # Start Code..End Code; Block Name + +# ================================================ + +# Property: Block + 0000..007F; Basic Latin 0080..00FF; Latin-1 Supplement 0100..017F; Latin Extended-A @@ -15,7 +29,7 @@ 0300..036F; Combining Diacritical Marks 0370..03FF; Greek and Coptic 0400..04FF; Cyrillic -0500..052F; Cyrillic Supplementary +0500..052F; Cyrillic Supplement 0530..058F; Armenian 0590..05FF; Hebrew 0600..06FF; Arabic diff --git a/lib/unicore/Canonical.pl b/lib/unicore/Canonical.pl index 7c6dbe4..6982601 100644 --- a/lib/unicore/Canonical.pl +++ b/lib/unicore/Canonical.pl @@ -129,8 +129,8 @@ cyrillic => 'Cyrillic', - # InCyrillicSupplementary - cyrillicsupplementary => 'InCyril2', + # InCyrillicSupplement + cyrillicsupplement => 'InCyril2', dash => 'Dash', @@ -334,8 +334,8 @@ # InCyrillic incyrillic => 'InCyrill', - # InCyrillicSupplementary - incyrillicsupplementary => 'InCyril2', + # InCyrillicSupplement + incyrillicsupplement => 'InCyril2', # InDeseret indeseret => 'InDesere', @@ -630,6 +630,9 @@ kannada => 'Kannada', katakana => 'Katakana', + # KatakanaOrHiragana + katakanaorhiragana => 'Katakan2', + # InKatakanaPhoneticExtensions katakanaphoneticextensions => 'InKatak2', @@ -827,6 +830,8 @@ # InSpecials specials => 'InSpecia', + sterm => 'Sterm', + # InSuperscriptsAndSubscripts superscriptsandsubscripts => 'InSupers', @@ -887,6 +892,9 @@ # UppercaseLetter uppercaseletter => 'Lu', + # VariationSelector + variationselector => 'Variatio', + # InVariationSelectors variationselectors => 'InVariat', diff --git a/lib/unicore/CaseFolding.txt b/lib/unicore/CaseFolding.txt index 8d9b44a..65f78ff 100644 --- a/lib/unicore/CaseFolding.txt +++ b/lib/unicore/CaseFolding.txt @@ -1,6 +1,10 @@ -# CaseFolding-4.0.0.txt -# Date: 2003-03-14, 20:22:08 GMT [MD] +# CaseFolding-4.0.1.txt +# Date: 2004-03-02, 02:41:24 GMT [MD] # +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html # Case Folding Properties # # This file is a supplement to the UnicodeData file. diff --git a/lib/unicore/Category.pl b/lib/unicore/Category.pl index 5dca85e..13b9ee2 100644 --- a/lib/unicore/Category.pl +++ b/lib/unicore/Category.pl @@ -1270,8 +1270,8 @@ return <<'END'; 1FF8 1FFB Lu 1FFC Lt 1FFD 1FFE Sk -2000 200B Zs -200C 200F Cf +2000 200A Zs +200B 200F Cf 2010 2015 Pd 2016 2017 Po 2018 Pi diff --git a/lib/unicore/HangulSyllableType.txt b/lib/unicore/HangulSyllableType.txt index dfbf787..d906fb1 100644 --- a/lib/unicore/HangulSyllableType.txt +++ b/lib/unicore/HangulSyllableType.txt @@ -1,19 +1,22 @@ -# HangulSyllableType-4.0.0.txt -# Date: 2003-03-20, 20:08:09 GMT [MD] +# HangulSyllableType-4.0.1.txt +# Date: 2004-03-02, 02:42:32 GMT [MD] # -# Unicode Character Database: Extended Properties +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see UCD.html -# Note: Unassigned and Noncharacter codepoints may be omitted -# if they have default property values. + # ================================================ +# Property: Hangul_Syllable_Type + +# All code points not explicitly listed for Hangul_Syllable_Type +# have the value Not_Applicable (NA). -# ================================================ -# Hangul Syllable Type -# All code points not explicitly listed in this file have the property -# value: NA. # ================================================ +# Hangul_Syllable_Type=Leading_Jamo + 1100..1159 ; L # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH 115F ; L # Lo HANGUL CHOSEONG FILLER @@ -21,18 +24,24 @@ # ================================================ +# Hangul_Syllable_Type=Vowel_Jamo + 1160..11A2 ; V # Lo [67] HANGUL JUNGSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA # Total code points: 67 # ================================================ +# Hangul_Syllable_Type=Trailing_Jamo + 11A8..11F9 ; T # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH # Total code points: 82 # ================================================ +# Hangul_Syllable_Type=LV_Syllable + AC00 ; LV # Lo HANGUL SYLLABLE GA AC1C ; LV # Lo HANGUL SYLLABLE GAE AC38 ; LV # Lo HANGUL SYLLABLE GYA @@ -437,6 +446,8 @@ D788 ; LV # Lo HANGUL SYLLABLE HI # ================================================ +# Hangul_Syllable_Type=LVT_Syllable + AC01..AC1B ; LVT # Lo [27] HANGUL SYLLABLE GAG..HANGUL SYLLABLE GAH AC1D..AC37 ; LVT # Lo [27] HANGUL SYLLABLE GAEG..HANGUL SYLLABLE GAEH AC39..AC53 ; LVT # Lo [27] HANGUL SYLLABLE GYAG..HANGUL SYLLABLE GYAH @@ -838,4 +849,3 @@ D76D..D787 ; LVT # Lo [27] HANGUL SYLLABLE HYIG..HANGUL SYLLABLE HYIH D789..D7A3 ; LVT # Lo [27] HANGUL SYLLABLE HIG..HANGUL SYLLABLE HIH # Total code points: 10773 - diff --git a/lib/unicore/Index.txt b/lib/unicore/Index.txt index 9adb160..c55a1f8 100644 --- a/lib/unicore/Index.txt +++ b/lib/unicore/Index.txt @@ -8,6 +8,7 @@ A, COMBINING LATIN SMALL LETTER 0363 a, latin small letter script 0251 A, LATIN SMALL LETTER TURNED 0250 ABBREVIATION MARK, ARMENIAN 055F +ABBREVIATION MARK, SYRIAC 070F ABBREVIATION SIGN, DEVANAGARI 0970 Abbreviations, Squared Latin 3371 Aboriginal Syllabics, Unified Canadian 1400 @@ -84,6 +85,10 @@ ACUTE TONE MARK, COMBINING 0341 ADDRESSED TO THE SUBJECT 2101 Addu dialect, consonant for 0780 AE, LATIN SMALL LETTER 00E6 +Aegean Numbers 10100 +AEGEAN CHECK MARK 10102 +AEGEAN WORD SEPARATOR DOT 10101 +AEGEAN WORD SEPARATOR LINE 10100 Ainu, Phonetic Extensions For 31F0 AIRPLANE 2708 aldus leaf 2766 @@ -131,6 +136,8 @@ ANGLE BELOW, COMBINING LEFT 0349 ANGLE BRACKET, LEFT 3008 ANGLE BRACKET, LEFT DOUBLE 300A ANGLE BRACKET, LEFT-POINTING 2329 +ANGLE BRACKET, MATHEMATICAL LEFT 27E8 +ANGLE BRACKET, MATHEMATICAL LEFT DOUBLE 27EA ANGLE BRACKET, RIGHT-POINTING 232A ANGLE OPENING LEFT, SPHERICAL 29A0 ANGLE OPENING UP, SPHERICAL 29A1 @@ -142,13 +149,14 @@ Angle Quotation Marks, Ornamental 276E ANGLE WITH ARC, RIGHT 22BE ANGLE WITH DOWNWARDS ZIGZAG ARROW, RIGHT 237C angled dash 00AC -Angles And Measured Angles 299B +Angles and Measured Angles 299B ANGSTROM SIGN 212B ANKH 2625 Annotation, Interlinear FFF9 Annotation, Kanbun Ideographic 3190 Annotation Signs, Koranic 06D6 ANNUITY SYMBOL, COMBINING 20E7 +ano teleia 00B7 ANTICLOCKWISE INTEGRATION 2A11 ANTICLOCKWISE-ROTATED DIVISION SIGN, CIRCLED 29BC ANTIRESTRICTION, Z NOTATION DOMAIN 2A64 @@ -183,19 +191,27 @@ Arabic 0600 Arabic, Extended 0671 ARABIC COMMA 060C ARABIC DECIMAL SEPARATOR 066B +ARABIC END OF AYAH 06DD ARABIC FIVE POINTED STAR 066D +ARABIC FOOTNOTE MARKER 0602 ARABIC FORM SHAPING, ACTIVATE 206D ARABIC FORM SHAPING, INHIBIT 206C ARABIC FULL STOP 06D4 +Arabic Honorifics 0610 ARABIC LETTER DOTLESS BEH 066E ARABIC LETTER DOTLESS QAF 066F Arabic Letters 0627 +ARABIC NUMBER SIGN 0600 ARABIC PERCENT SIGN 066A Arabic Points 064B Arabic Presentation Forms-A FB50 Arabic Presentation Forms-B FE70 ARABIC QUESTION MARK 061F ARABIC SEMICOLON 061B +ARABIC SIGN SAFHA 0603 +ARABIC SIGN SANAH 0601 +Arabic Poetic Marks 0610 +Arabic Subtending Marks 0600 ARABIC TAIL FRAGMENT FE73 ARABIC THOUSANDS SEPARATOR 066C Arabic-Indic Digits 0660 @@ -242,6 +258,7 @@ ARROWHEAD, UP 2303 Arrowheads, Modifier Letter 02C2 Arrows 2190 Arrows, Long 27F5 +Arrows, Other White and Black 2B00 arrows extension 23AF Arrows-A, Supplemental 27F0 Arrows-B, Supplemental 2900 @@ -267,6 +284,7 @@ asymptotic to 2248 ASYMPTOTICALLY EQUAL TO 2243 AT, COMMERCIAL 0040 AVERAGE WITH SLASH, INTEGRAL 2A0F +AYAH, ARABIC END OF 06DD B, LATIN LETTER SMALL CAPITAL 0299 B, SCRIPT CAPITAL 212C baby gamma, latin small letter 0264 @@ -275,6 +293,7 @@ BACKSLASH, COMBINING ENCLOSING CIRCLE 20E0 backspace 0008 BACKSPACE, SYMBOL FOR 2408 backward difference 2207 +bag bracket, z notation left 27E6 BAG MEMBERSHIP, Z NOTATION 22FF bag subtraction, z notation 2A41 BAHT, THAI CURRENCY SYMBOL 0E3F @@ -352,13 +371,15 @@ BENGALI RUPEE SIGN 09F3 BENZENE RING 232C bernoulli function 212C BET SYMBOL 2136 -Betty BOOP +Betty BOOP 263A BETWEEN 226C +BEVERAGE, HOT 2615 BIDENTAL PERCUSSIVE, LATIN LETTER 02AD Bidirectional Formatting Controls 202A Big 5, Duplicates from FA0C BIG REVERSE SOLIDUS 29F9 BIG SOLIDUS 29F8 +bijection, z notation 2917 bijective mapping 2916 BILABIAL CLICK, LATIN LETTER 0298 BILABIAL PERCUSSIVE, LATIN LETTER 02AC @@ -377,6 +398,7 @@ BLACK CIRCLE WITH TWO WHITE DOTS 2689 BLACK CIRCLE WITH WHITE DOT RIGHT 2688 Black Circled Numbers, White On 24EB BLACK DIAMOND WITH DOWN ARROW 29EA +BLACK FLAG 2691 BLACK HOURGLASS 29D7 BLACK LEFT POINTING INDEX 261A BLACK LEFTWARDS BULLET 204C @@ -424,6 +446,7 @@ BOX WITH X, BALLOT 2612 bra 27E6 brace, closing 007D brace, opening 007B +bracket, z notation left bag 27E6 bracket, closing curly 007D bracket, closing square 005D BRACKET, LEFT ANGLE 3008 @@ -446,7 +469,11 @@ Bracket Pieces 239B Bracket Pieces 23B0 BRACKET WITH QUILL, LEFT SQUARE 2045 Brackets 2983 -Brackets, CJK Punctuation 3008 +Brackets, CJK Angle 3008 +Brackets, Corner 2308 +Brackets, CJK Corner 300C +Brackets, CJK 3010 +Brackets, CJK 3014 Brackets, Fullwidth FF5F Brackets, Mathematical 27E6 Brackets, Ornamental 2768 @@ -537,6 +564,7 @@ CENTRE LINE SYMBOL 2104 CENTRED LEFT HALF RING, MODIFIER LETTER 02D3 CENTRELINE LOW LINE FE4E CENTRELINE OVERLINE FE4A +cgj 034F character introducer, single 009A character tabulation set 0088 character tabulation with justification 0089 @@ -544,6 +572,7 @@ CHARACTER TIE 2040 Chart Components, Form and 2500 CHECK, BALLOT BOX WITH 2611 CHECK MARK 2713 +CHECK MARK, AEGEAN 10102 CHECK MARK, HEAVY 2714 CHECK MARK, NOT 237B Cherokee 13A0 @@ -667,6 +696,7 @@ closing square bracket 005D CLOUD 2601 cloudy weather 2601 Codes, Process Internal FDD0 +coffee 2615 COLON 003A COLON, ETHIOPIC 1365 COLON, MODIFIER LETTER HALF TRIANGULAR 02D1 @@ -839,6 +869,7 @@ COMPOSITION, Z NOTATION RELATIONAL 2A3E COMPOSITION, Z NOTATION SCHEMA 2A1F composition circle, jis 20DD COMPOSITION SYMBOL 2384 +concatenation, z notation sequence 2040 CONCAVE-SIDED DIAMOND, WHITE 27E1 CONCAVE-SIDED DIAMOND WITH LEFTWARDS TICK, WHITE 27E2 CONCAVE-SIDED DIAMOND WITH RIGHTWARDS TICK, WHITE 27E3 @@ -888,8 +919,11 @@ COPYRIGHT SIGN 00A9 CORNER, TOP LEFT 231C CORNER BRACKET, LEFT 300C CORNER BRACKET, LEFT WHITE 300E +Corner brackets 2308 +Corner brackets, CJK 300C CORNER WITH DOT, LOWER RIGHT 27D3 CORNER WITH DOT, UPPER LEFT 27D4 +corners, Quine 231C CORPORATION, SQUARE 337F CORRESPONDS TO 2258 corresponds to 2259 @@ -956,6 +990,7 @@ current, alternating 223F CURRENT SYMBOL FORM TWO, DIRECT 2393 cycle 223C CYLINDRICITY 232D +Cypriot Syllabary 10800 Cyrillic 0400 Cyrillic, Extended 048C Cyrillic Capital Letters 0401 @@ -984,7 +1019,7 @@ DASH, EN 2013 DASH, FIGURE 2012 dash, long 2015 dash, quotation 2015 -dash, swung 007E +DASH, SWUNG 2053 DASH, WAVE 301C DASH, WAVY 3030 DASHED LOW LINE FE4D @@ -996,10 +1031,12 @@ DATA LINK ESCAPE, SYMBOL FOR 2410 Database Theory Operators 27D5 DAVID, STAR OF 2721 Days, Telegraph Symbols for 33E0 +DAY SIGN, TAMIL 0BF3 decimal point 002E decimal separator 002C DECIMAL SEPARATOR, ARABIC 066B DECIMAL SEPARATOR KEY SYMBOL 2396 +deergh viram 0965 definition, equal to by 225C DEFINITION, EQUAL TO BY 225D DEGREE CELSIUS 2103 @@ -1101,6 +1138,7 @@ Digits, Malayalam 0D66 Digits, Mongolian 1810 Digits, Myanmar 1040 Digits, Oriya 0B66 +Digits, Osmanya 104A0 Digits, Subscript 2080 Digits, Superscript 2070 Digits, Tamil 0BE7 @@ -1113,6 +1151,8 @@ DIGRAPH YORI, HIRAGANA 309F Digraphs, Phonetic 02A3 Digraphs, Yiddish 05F0 Digraphs Matching Serbian Cyrillic Letters, Croatian 01C4 +Digram Symbols, Yijing Monogram and 268A +Digram Symbols, Tai Xuan Jing 1D301 dijkstra choice 2AFE dijkstra choice, n-ary 2AFF DIMENSION ORIGIN 2331 @@ -1150,10 +1190,11 @@ DIVIDED BY HORIZONTAL BAR AND TOP HALF DIVIDED BY VERTICAL BAR, CIRCLE 29BA DIVIDED BY HORIZONTAL RULE, LOZENGE 27E0 DIVIDED BY VERTICAL BAR, CIRCLE DIVIDED BY HORIZONTAL BAR AND TOP HALF 29BA DIVIDES 2223 +Divination Lore, Khmer Symbols for 17F0 DIVISION SIGN 00F7 DIVISION SIGN, CIRCLED 2A38 DIVISION SIGN, CIRCLED ANTICLOCKWISE-ROTATED 29BC -Division Sign Operators, Multiplication And 2A2F +Division Sign Operators, Multiplication and 2A2F DIVISION SLASH 2215 DIVISION SLASH, CIRCLED 2298 DIVISION TIMES 22C7 @@ -1163,6 +1204,7 @@ DOLLAR SIGN 0024 DOMAIN ANTIRESTRICTION, Z NOTATION 2A64 DONG SIGN 20AB dot 002E +DOT, AEGEAN LINE SEPARATOR 10101 dot, greek middle 00B7 DOT, KATAKANA MIDDLE 30FB DOT, MIDDLE 00B7 @@ -1292,6 +1334,7 @@ DOWN TACK BELOW, COMBINING 031E DOWN-POINTING TRIANGLE WITH LEFT HALF BLACK 29E8 DOWN-POINTING TRIANGLE WITH RIGHT HALF BLACK 29E9 DRACHMA SIGN 20AF +Drafting Symbols 232D dram 0292 drop 264F Duplicates from Big 5 FA0C @@ -1314,6 +1357,7 @@ ecu 20A0 EIGHTH NOTE 266A EIGHTH NOTES, BEAMED 266B Eighths, Fractions 215B +EJECT SYMBOL 23CF EK ONKAR, GURMUKHI 0A74 el salvadorian currency 20A1 ELECTRIC ARROW 2301 @@ -1334,6 +1378,7 @@ ELEMENT OF WITH TWO HORIZONTAL STROKES 22F9 ELEMENT OF WITH UNDERBAR 22F8 ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE 22F3 ELEMENT OF WITH VERTICAL BAR AT END OF HORIZONTAL STROKE, SMALL 22F4 +ell, mathematical symbol 2113 ELLIPSIS, HORIZONTAL 2026 ELLIPSIS, MIDLINE HORIZONTAL 22EF ELLIPSIS, UP RIGHT DIAGONAL 22F0 @@ -1551,6 +1596,7 @@ Extended-B, Latin 0180 extension, arrows 23AF EXTENSION, HORIZONTAL LINE 23AF EXTENSION, INTEGRAL 23AE +EXTENSION, VERTICAL LINE 23D0 Extension A, CJK Unified Ideographs 3400 Extensions, Cyrillic 0450 Extensions, IPA 0250 @@ -1568,6 +1614,7 @@ FACE, BLACK SMILING 263B FACE, POSTAL MARK 3020 FACE, WHITE FROWNING 2639 FACE, WHITE SMILING 263A +FACSIMILE SIGN 213B factorial 0021 FAHRENHEIT, DEGREE 2109 FALLING DIAGONAL SLASH, SQUARED 29C5 @@ -1602,12 +1649,14 @@ FISHEYE 25C9 fist 261E FIVE, LATIN SMALL LETTER TONE 01BD FIVE POINTED STAR, ARABIC 066D +FLAG, BLACK 2691 FLAT SIGN, MUSIC 266D FLOOR, LEFT 230A FLORAL HEART BULLET, REVERSED ROTATED 2619 florin currency symbol 0192 folder 0192 FOOT, SQUARE 23CD +FOONOTE MARKER, ARABIC 0602 FOR ALL 2200 FORCES 22A9 FORKING 2ADC @@ -1662,6 +1711,7 @@ function, z notation finite 21FB function, z notation partial 21F8 FUNCTION APPLICATION 2061 function symbol 0192 +fvs 180B G, LATIN LETTER SMALL CAPITAL 0262 G, LATIN SMALL LETTER SCRIPT 0261 G, SCRIPT SMALL 210A @@ -1778,6 +1828,7 @@ group separator 001D GROUP SEPARATOR, SYMBOL FOR 241D guarded area, end of 0097 guarded area, start of 0096 +gui icons 231A guillemet, left pointing 00AB guillemet, left pointing single 2039 guillemet, right pointing 00BB @@ -1785,6 +1836,7 @@ guillemet, right pointing single 203A Gujarati 0A80 Gujarati Digits 0AE6 Gujarati Letters 0A85 +GUJARATI RUPEE SIGN 0AF1 Gurmukhi 0A00 Gurmukhi Digits 0A66 Gurmukhi Letters 0A05 @@ -1842,6 +1894,7 @@ Hanunoo 1720 HANUNOO SIGN PAMUDPOD 1734 Hanunóo-specific punctuation 1734 HARPOON ABOVE, COMBINING LEFT 20D0 +hasant 09CD hash 0023 hat 0302 hat 2229 @@ -1861,8 +1914,10 @@ Hebrew Points 05B0 Hebrew Presentation Forms FB1D HELM SYMBOL 2388 HERMITIAN CONJUGATE MATRIX 22B9 +Hexagram Symbols, Yijing 4DC0 hiding, z notation schema 29F9 High Surrogates D800 +HIGH VOLTAGE SIGN 26A1 HIGH-REVERSED-9 QUOTATION MARK, DOUBLE 201F HIGH-REVERSED-9 QUOTATION MARK, SINGLE 201B higher rank than 227B @@ -1876,6 +1931,7 @@ home 21B8 home 21F1 HOMOTHETIC 223B HOMOTHETIC ABOVE, COMBINING 034B +Honorific Signs, Arabic 0610 HOOK, MODIFIER LETTER RHOTIC 02DE hook, nasal 0328 HOOK ABOVE, COMBINING 0309 @@ -1893,6 +1949,7 @@ horizontal tabulation 0009 HORIZONTAL TABULATION, SYMBOL FOR 2409 HORN, COMBINING 031B HORN, LATIN SMALL LETTER RAMS 0264 +HOT BEVERAGE 2615 HOT SPRINGS 2668 HOURGLASS 231B HOURGLASS, BLACK 29D7 @@ -1922,6 +1979,7 @@ I, SCRIPT CAPITAL 2110 I, SUPERSCRIPT LATIN SMALL LETTER 2071 I WITH DOT ABOVE, LATIN CAPITAL LETTER 0130 IBM CJK Compatibility Ideographs FA0E +icons, gui 231A identical and parallel to 2A68 IDENTICAL TO 2261 IDENTICAL TO AND SLANTED PARALLEL 29E5 @@ -1991,7 +2049,7 @@ INTEGRAL, SURFACE 222F INTEGRAL, TOP HALF 2320 INTEGRAL, TRIPLE 222D INTEGRAL, VOLUME 2230 -Integrals, Summations And 2A0A +Integrals, Summations and 2A0A INTERCALATE 22BA INTERIOR PRODUCT 2A3C INTERIOR PRODUCT, RIGHTHAND 2A3D @@ -2008,7 +2066,7 @@ intersection, proper 22D4 INTERSECTION, TRANSVERSAL 2ADB INTERSECTION OPERATOR, N-ARY SQUARE 2A05 INTERSECTION WITH DOT 2A40 -Intersections And Unions 2A40 +Intersections and Unions 2A40 introducer, control sequence 009B introducer, single character 009A Inverse Numbers, Circled 2776 @@ -2024,6 +2082,7 @@ INVERTED OHM SIGN 2127 INVERTED QUESTION MARK 00BF INVERTED R, LATIN LETTER SMALL CAPITAL 0281 INVERTED R, MODIFIER LETTER SMALL CAPITAL 02B6 +INVERTED UNDERTIE 2054 Invisible Operators 2063 IOTA, LATIN CAPITAL LETTER 0196 IOTA, LATIN SMALL LETTER 0269 @@ -2113,11 +2172,16 @@ KEY, OPTION 2325 KEY SYMBOL, ALTERNATIVE 2387 KEY SYMBOL, DECIMAL SEPARATOR 2396 KEYBOARD 2328 +Keyboard Symbols 2324 Keyboard Symbols from ISO 9995-7 2380 Keyboard Symbols from ISO 9995-7 2396 +Keyboard and UI Symbols 23CE KEYCAP, COMBINING ENCLOSING 20E3 Khmer 1780 Khmer Digits 17E0 +Khmer Lunar Date Symbols 19E0 +Khmer Symbols 19E0 +Khmer Symbols for Divination Lore 17F0 KIP SIGN 20AD kome, japanese 203B Komi Letters, Cyrillic 0500 @@ -2241,15 +2305,21 @@ level 3 lock 21EF level 3 select 21EE LEZH, LATIN SMALL LETTER 026E lf 000A +LIABILITY SIGN, LIMITED 32CF LIBRA 264E ligature ae, latin small 00E6 LIGATURE IJ, LATIN SMALL 0133 LIGATURE LEFT HALF, COMBINING FE20 LIGATURE OE, LATIN SMALL 0153 +ligature tie 0361 Ligatures, Armenian FB13 Ligatures, Latin FB00 LIGHTNING 2607 LIMIT, APPROACHES THE 2250 +Limbu 1900 +Limbu Digits 1946 +LIMITED LIABILITY SIGN 32CF +LINE, AEGEAN WORD SEPARATOR 10100 line, beginning of 2310 LINE, CENTRELINE LOW FE4E LINE, COMBINING DOUBLE LOW 0333 @@ -2282,7 +2352,10 @@ LINE SYMBOL, CENTRE 2104 line tabulation set 008A line up, partial 008C LINE WITH MIDDLE DOT, VERTICAL 237F +Linear B Ideograms 10080 +Linear B Syllabary 10000 Lines For Terminal Graphics, Scan 23BA +Lira, Italian 00A3 LIRA SIGN 20A4 liter 2113 Livonian, Additions for 022A @@ -2299,7 +2372,7 @@ LOGICAL AND, CURLY 22CF LOGICAL AND, INTERSECTION WITH 2A44 LOGICAL AND, N-ARY 22C0 LOGICAL AND OPERATOR, TWO 2A07 -Logical Ands And Ors 2A51 +Logical Ands and Ors 2A51 LOGICAL OR 2228 LOGICAL OR, CURLY 22CE LOGICAL OR, N-ARY 22C1 @@ -2364,6 +2437,7 @@ Malayalam Letters 0D05 MALE SIGN 2642 MALTESE CROSS 2720 Manchu Letters, Mongolian 1873 +Map Markers 2690 mapping, bijective 2916 maps from 27FB maps from 2906 @@ -2372,7 +2446,8 @@ maps to 2905 maps to 2907 mark, german 2133 marker, histogram 25AE -Markers, Go 2686 +Markers, Go 2686 +Markers, Map 2690 mars 2642 MASCULINE ORDINAL INDICATOR 00BA MASU MARK 303C @@ -2386,7 +2461,7 @@ Mathematical Symbols-A, Miscellaneous 27C0 Mathematical Symbols-B, Miscellaneous 2980 MATRIX, HERMITIAN CONJUGATE 22B9 MEASURED ANGLE 2221 -Measured Angles, Angles And 299B +Measured Angles, Angles and 299B MEASURED BY 225E Medieval Superscript Letter Diacritics 0363 medium, end of 0019 @@ -2435,7 +2510,7 @@ MINUS SIGN, MODIFIER LETTER 02D7 MINUS SIGN, UNION WITH 2A41 MINUS SIGN BELOW, COMBINING 0320 MINUS SIGN IN TRIANGLE 2A3A -Minus Sign Operators, Plus And 2A22 +Minus Sign Operators, Plus and 2A22 MINUS SIMILAR, SIMILAR 2A6C MINUS TILDE 2242 MINUS-OR-PLUS SIGN 2213 @@ -2444,7 +2519,10 @@ MINY 29FF Miscellaneous Mathematical Symbols-A 27C0 Miscellaneous Mathematical Symbols-B 2980 Miscellaneous Symbols 2600 +Miscellaneous Symbols and Arrows 2B00 Miscellaneous Technical 2300 +MISRA, ARABIC SIGN 060F +mmsp 205F Modal Logic Operators 27E0 MODELS 22A7 Modifier Letters, Spacing 02B0 @@ -2460,7 +2538,10 @@ MONGOLIAN FULL STOP 1803 Mongolian Manchu Letters 1873 Mongolian Sibe Letters 185D Mongolian Todo Letters 1843 +Monogram and Digram Symbols, Yijing 268C +Monogram Symbol, Tai Xuan Jing 1D300 MONOSTABLE SYMBOL 238D +MONTH SIGN, TAMIL 0BF4 Months, Enclosed CJK Letters and 3200 Months, Telegraph Symbols for 32C0 MOON, FIRST QUARTER 263D @@ -2474,7 +2555,7 @@ MULTIMAP 22B8 MULTIMAP, DOUBLE-ENDED 29DF MULTIMAP, LEFT 27DC MULTIPLICATION, MULTISET 228D -Multiplication And Division Sign Operators 2A2F +Multiplication and Division Sign Operators 2A2F MULTIPLICATION SIGN 00D7 MULTIPLICATION SIGN BELOW, SUBSET WITH 2AC1 MULTIPLICATION SIGN BELOW, SUPERSET WITH 2AC2 @@ -2489,6 +2570,7 @@ MUSIC SHARP SIGN 266F Musical Symbols 2669 mutton 2003 mutton quad 2001 +mvs 180E Myanmar 1000 Myanmar Digits 1040 N, DOUBLE-STRUCK CAPITAL 2115 @@ -2514,6 +2596,7 @@ nasal hook 0328 NATIONAL DIGIT SHAPES 206E natural number 2115 NATURAL SIGN, MUSIC 266E +nbsp 0080 necessarily satisfies 2AF1 NEGATED WITH VERTICAL BAR, INFINITY 29DE negation 20D3 @@ -2533,6 +2616,7 @@ NEXT PAGE 2398 NIB, BLACK 2712 nigerian currency 20A6 nim-addition 2A27 +nnbsp 202F no break here 0083 no break space, graphic for 237D NO-BREAK SPACE 00A0 @@ -2545,6 +2629,24 @@ NON-BREAKING HYPHEN 2011 non-breaking space 00A0 NON-JOINER, ZERO WIDTH 200C non-theorem 22A3 +Noncharacters FDD0 +Noncharacters FFFE +Noncharacters 1FFFE +Noncharacters 2FFFE +Noncharacters 3FFFE +Noncharacters 4FFFE +Noncharacters 5FFFE +Noncharacters 6FFFE +Noncharacters 7FFFE +Noncharacters 8FFFE +Noncharacters 9FFFE +Noncharacters AFFFE +Noncharacters BFFFE +Noncharacters CFFFE +Noncharacters DFFFE +Noncharacters EFFFE +Noncharacters FFFFE +Noncharacters 10FFFE NONFORKING 2ADD NOR 22BD NORMAL SUBGROUP, CONTAINS AS 22B3 @@ -2587,8 +2689,11 @@ number, natural 2115 Number Forms 2150 Number Runes, Golden 16EE NUMBER SIGN 0023 +NUBMER SIGN, ARABIC 0600 +NUMBER SIGN, TAMIl 0BFA number symbol, real 210A NUMBER ZERO, IDEOGRAPHIC 3007 +Numbers, Aegean 10100 Numbers, Circled 2460 Numbers, Circled 3251 Numbers, Circled 32B1 @@ -2601,6 +2706,7 @@ numbers, the set of real 211D Numbers, White On Black Circled 24EB Numbers Period 2488 Numerals, Hangzhou-style 3021 +Numerals, Old Italic 10320 Numerals, Roman 2160 NUMERATOR ONE, FRACTION 215F numerics lock 21ED @@ -2666,9 +2772,9 @@ Operators, Database Theory 27D5 Operators, Invisible 2063 Operators, Mathematical 2200 Operators, Modal Logic 27E0 -Operators, Multiplication And Division Sign 2A2F +Operators, Multiplication and Division Sign 2A2F Operators, N-Ary 2A00 -Operators, Plus And Minus Sign 2A22 +Operators, Plus and Minus Sign 2A22 Operators, Relational 2A66 Operators, Specialized plus sign 29FA Operators, Supplemental Mathematical 2A00 @@ -2708,6 +2814,8 @@ ORNATE LEFT PARENTHESIS FD3E ors, logical ands and 2A51 ORTHODOX CROSS 2626 orthogonal to 22A5 +Osmanya 10480 +Osmanya Digits 104A0 OU, LATIN SMALL LETTER 0223 OUNCE SIGN 2125 OUTER JOIN, FULL 27D7 @@ -2796,6 +2904,7 @@ partial line up 008C partial relation, z notation 21F9 partial surjection, z notation 2900 PARTIALLY-RECYCLED PAPER SYMBOL 267D +PARTNERSHIP SIGN 3250 Parts, Summation Sign 23B2 pdf 202C PEACE SYMBOL 262E @@ -2822,8 +2931,10 @@ PHARYNGEAL VOICED FRICATIVE, LATIN LETTER 0295 PHI, LATIN SMALL LETTER 0278 Philippine Scripts, Generic Punctuation For 1735 Phonetic Alphabet, International 0250 +Phonetic Extensions 1D00 Phonetic Extensions, Katakana 31F0 -Phonetic extensions for Ainu 31F0 +Phonetic Extensions, non-IPA 1D00 +Phonetic Extensions for Ainu 31F0 Phonetic Modifiers Derived from Latin Letters 02B0 Phonetics and Symbols Area, CJK 2E00 phonorecord sign 2117 @@ -2854,7 +2965,7 @@ PLUS, DOUBLE 29FA PLUS, N-ARY UNION OPERATOR WITH 2A04 PLUS, SQUARED 229E PLUS, TRIPLE 29FB -Plus And Minus Sign Operators 2A22 +Plus and Minus Sign Operators 2A22 PLUS OPERATOR, N-ARY CIRCLED 2A01 PLUS SIGN 002B PLUS SIGN, EQUALS SIGN ABOVE 2A71 @@ -2871,6 +2982,7 @@ PLUS SIGN IN TRIANGLE 2A39 Plus Sign Operators, Specialized 29FA PLUS-MINUS SIGN 00B1 PLUTO 2647 +POETIC VERSE SIGN, ARABIC 060E POINT OPERATOR, INTEGRAL AROUND A 2A15 Pointers 25BA Points, Arabic 064B @@ -2920,9 +3032,10 @@ PRIME QUOTATION MARK, REVERSED DOUBLE 301D PRINT SCREEN SYMBOL 2399 privacy message 009E Private Use Area E000 +Private Use Area-A, Supplementary F0000 +Private Use Area-B, Supplementary 100000 private use one 0091 private use two 0092 -Process Internal Codes FDD0 PRODUCT, CLOSED UNION WITH SERIFS AND SMASH 2A50 product, direct 2299 PRODUCT, INTERIOR 2A3C @@ -2960,6 +3073,7 @@ Punctuation For Vertical Text, Double 2047 Punctuation Ornaments 275B PUNCTUATION SPACE 2008 punt, irish 00A3 +purna viram 0964 pushout 27D4 Q, DOUBLE-STRUCK CAPITAL 211A Q, ROTATED CAPITAL 213A @@ -2991,6 +3105,7 @@ QUESTION MARK ABOVE, GREATER-THAN WITH 2A7C QUESTION MARK ABOVE, LESS-THAN WITH 2A7B QUESTIONED EQUAL TO 225F QUILL, LEFT SQUARE BRACKET WITH 2045 +Quine Corners 231C quotation dash 2015 QUOTATION MARK 0022 quotation mark, double comma 201D @@ -3035,6 +3150,7 @@ Radicals, Kangxi 2F00 Radicals, Yi A490 Radicals Supplement, CJK 2E80 RADIOACTIVE SIGN 2622 +RAIN DROPS, UMBRELLA WITH 2614 rainy weather 2602 RAMS HORN, LATIN SMALL LETTER 0264 RANGE ANTIRESTRICTION, Z NOTATION 2A65 @@ -3166,6 +3282,8 @@ RUNOUT, TOTAL 2330 RUPEE MARK, BENGALI 09F2 RUPEE SIGN 20A8 RUPEE SIGN, BENGALI 09F3 +RUPEE SIGN, GUJARATI 0AF1 +RUPEE SIGN, TAMIL 0BF9 Russian Alphabet, Basic 0410 S, INVERTED LAZY 223E S, LATIN SMALL LETTER LONG 017F @@ -3174,8 +3292,11 @@ s, lazy 223D S, MODIFIER LETTER SMALL 02E2 S, PERPENDICULAR WITH 2AE1 S IN TRIANGLE 29CC +SAFHA, ARABIC SIGN 0603 SAGITTARIUS 2650 SALTIRE 2613 +sam 070F +SANAH, ARABIC SIGN 0601 SANS-SERIF CAPITAL G, TURNED 2141 SANS-SERIF CAPITAL L, REVERSED 2143 SANS-SERIF CAPITAL L, TURNED 2142 @@ -3232,6 +3353,8 @@ SEMICOLON, ETHIOPIC 1364 SEMICOLON, REVERSED 204F SEMIDIRECT PRODUCT, LEFT 22CB SEMIDIRECT PRODUCT WITH BOTTOM CLOSED 2A32 +SEPARATOR DOT, AEGEAN WORD 10101 +SEPARATOR LINE, AEGEAN WORD 10100 SEPARATOR, ARABIC DECIMAL 066B SEPARATOR, ARABIC THOUSANDS 066C separator, decimal 002C @@ -3250,6 +3373,7 @@ SEPARATOR, SYMBOL FOR UNIT 241F separator, unit 001F separator, urdu paragraph 203B SEPARATOR KEY SYMBOL, DECIMAL 2396 +sequence concatenation, z notation 2040 sequence introducer, control 009B Serbian Cyrillic Letters, Croatian Digraphs Matching 01C4 SERIFS, CLOSED INTERSECTION WITH 2A4D @@ -3277,6 +3401,7 @@ shamrock 2663 Shapes, Geometric 25A0 SHARP S, LATIN SMALL LETTER 00DF SHARP SIGN, MUSIC 266F +Shavian 10450 SHEQEL SIGN, NEW 20AA shift 21E7 shift in 000F @@ -3302,6 +3427,7 @@ SHORT UP TACK WITH UNDERBAR 2AE8 SHORT VERTICAL LINE OVERLAY, COMBINING 20D3 SHOULDERED OPEN BOX 237D SHUFFLE PRODUCT 29E2 +shy 00AD Sibe Letters, Mongolian 185D Sidelining Emphasis Marks FE45 SIMILAR, SIMILAR MINUS 2A6C @@ -3545,11 +3671,12 @@ SUBSCRIPT PLUS SIGN 208A SUBSCRIPT TWO, PLUS SIGN WITH 2A27 Subscripts 2080 SUBSET, DOUBLE 22D0 -Subset And Superset Relations 2ABD +Subset and Superset Relations 2ABD SUBSET OF 2282 substitute 001A SUBSTITUTE, SYMBOL FOR 241A SUBSTITUTE FORM TWO, SYMBOL FOR 2426 +Subtending Marks, Arabic 0600 subtraction, z notation bag 2A41 SUCCEEDS 227B SUCCEEDS, DOUBLE 2ABC @@ -3572,7 +3699,7 @@ SUMMATION, N-ARY 2211 SUMMATION BOTTOM 23B3 Summation Sign Parts 23B2 SUMMATION TOP 23B2 -Summations And Integrals 2A0A +Summations and Integrals 2A0A SUN 2609 SUN WITH RAYS, BLACK 2600 SUPERIMPOSED X, CIRCLE WITH 29BB @@ -3592,11 +3719,13 @@ Superscripts 2070 Superscripts and Subscripts 2070 SUPERSET, DOUBLE 22D1 SUPERSET OF 2283 -Superset Relations, Subset And 2ABD +Superset Relations, Subset and 2ABD Supplemental Arrows-A 27F0 Supplemental Arrows-B 2900 Supplemental Mathematical Operators 2A00 Supplementary, Cyrillic 0500 +Supplementary Private Use Area-A F0000 +Supplementary Private Use Area-B 100000 SURFACE INTEGRAL 222F surjection, z notation finite 2901 surjection, z notation partial 2900 @@ -3606,7 +3735,7 @@ Surrogates, High D800 Surrogates, Low DC00 Surrogates Area D800 swedish grave accent 02DF -swung dash 007E +SWUNG DASH 2053 Syllabics, Unified Canadian Aboriginal 1400 Syllables, Yi A000 Syllables Area, Korean Hangul AC00 @@ -3624,6 +3753,7 @@ Symbols, Miscellaneous 2600 Symbols, Recycling 2672 Symbols, Square 29C4 Symbols, Triangle 29CA +Symbols and Arrows, Miscellaneous 2B00 Symbols and Punctuation, CJK 3000 Symbols Area 2000 Symbols Area, CJK Phonetics and 2E00 @@ -3639,6 +3769,7 @@ SYMMETRY 232F synchronous idle 0016 SYNCHRONOUS IDLE, SYMBOL FOR 2416 Syriac 0700 +SYRIAC ABBREVIATION MARK 070F SYRIAC CROSS, EAST 2671 SYRIAC CROSS, WEST 2670 Syriac Format Control 070F @@ -3662,11 +3793,13 @@ TACK, RIGHT 22A2 TACK, UP 22A5 TACK BELOW, COMBINING LEFT 0318 TACK BELOW, COMBINING UP 031D -Tacks And Turnstiles 27D8 -Tacks And Turnstiles 2ADE +Tacks and Turnstiles 27D8 +Tacks and Turnstiles 2ADE Tagalog 1700 TAGALOG SIGN VIRAMA 1714 Tagbanwa 1760 +Tai Le 1950 +Tai Xuan Jing Symbols 1D300 TAIL FRAGMENT, ARABIC FE73 Tails, Fish 297C tainome (japanese, a kind of bullet) 25C9 @@ -3674,11 +3807,15 @@ TAKE, PRESCRIPTION 211E Tamil 0B80 Tamil Digits 0BE7 Tamil Letters 0B85 +TAMIL RUPEE SIGN 0BF9 +TAMIL NUMBER SIGN 0BFA +Tamil Symbols 0BF3 TAPE DRIVE 2707 TAPER, CONICAL 2332 TAURUS 2649 tautological equivalent 29E6 tautology 22A8 +tea 2615 Technical, Miscellaneous 2300 TEE TOP, PITCHFORK WITH 2ADA Telegraph Symbols for Days 33E0 @@ -3698,6 +3835,7 @@ Terminal graphic characters 23B7 Terminal Graphic Characters 2596 Terminal Graphics, Scan Lines For 23BA terminator, string 009C +Tetragram Symbols, Tai Xuan Jing 1D306 text, end of 0003 text, start of 0002 TEXT, SYMBOL FOR END OF 2403 @@ -3734,6 +3872,7 @@ TICK, WHITE CONCAVE-SIDED DIAMOND WITH RIGHTWARDS 27E3 TICK, WHITE SQUARE WITH LEFTWARDS 27E4 TICK, WHITE SQUARE WITH RIGHTWARDS 27E5 TIE, CHARACTER 2040 +tie, ligature 0361 TIE OVER INFINITY 29DD TILDE 007E tilde, apl 223C @@ -3871,8 +4010,8 @@ TURNED W, LATIN SMALL LETTER 028D TURNED Y, LATIN SMALL LETTER 028E turnstile 22A2 turnstile, reverse 22A3 -Turnstiles, Tacks And 27D8 -Turnstiles, Tacks And 2ADE +Turnstiles, Tacks and 27D8 +Turnstiles, Tacks and 2ADE TWO, SUPERSCRIPT 00B2 TWO DOT LEADER 2025 TWO-HEADED ARROW FROM BAR, RIGHTWARDS 2905 @@ -3880,7 +4019,9 @@ TWO-HEADED ARROW WITH TAIL, RIGHTWARDS 2916 TWO-HEADED ARROW WITH TAIL WITH VERTICAL STROKE, RIGHTWARDS 2917 TYPE COLON, Z NOTATION 2982 U, COMBINING LATIN SMALL LETTER 0367 +Ugaritic 10380 UMBRELLA 2602 +UMBRELLA WITH RAIN DROPS 2614 umlaut 0308 UNASPIRATED, MODIFIER LETTER 02ED UNDERDOT, COMBINING TRIPLE 20E8 @@ -3894,6 +4035,7 @@ underscore, spacing 005F underscore, spacing double 2017 Underscores, Overscores and FE49 UNDERTIE 203F +UNDERTIE, INVERTED 2054 UNDO SYMBOL 238C undoable delete 2425 UNION 222A @@ -3916,7 +4058,7 @@ UNION WITH MINUS SIGN 2A41 UNION WITH OVERBAR 2A42 UNION WITH SERIFS, CLOSED 2A4C UNION WITH SERIFS AND SMASH PRODUCT, CLOSED 2A50 -Unions, Intersections And 2A40 +Unions, Intersections and 2A40 unique element 2129 unit separator 001F UNIT SEPARATOR, SYMBOL FOR 241F @@ -3929,6 +4071,7 @@ UP RIGHT DIAGONAL ELLIPSIS 22F0 UP TACK 22A5 UP TACK, MODIFIER LETTER 02D4 UP TACK BELOW, COMBINING 031D +UPA Modifiers 02EF UPPER BLADE SCISSORS 2701 UPPER RIGHT PENCIL 2710 UPSILON, LATIN CAPITAL LETTER 01B1 @@ -3947,6 +4090,7 @@ valentine 2665 valid 22A8 varia 0300 Variation Selectors FE00 +Variation Selectors Supplement E0100 varies with (proportional to) 223C vector 20D0 vector 20D6 @@ -3985,6 +4129,7 @@ VERTICAL LINE ABOVE, COMBINING 030D VERTICAL LINE ABOVE, COMBINING DOUBLE 030E VERTICAL LINE BELOW, COMBINING 0329 VERTICAL LINE BELOW, COMBINING DOUBLE 0348 +VERTICAL LINE EXTENSION 23D0 Vertical Line Operators 2AEE VERTICAL LINE OVERLAY, COMBINING LONG 20D2 VERTICAL LINE OVERLAY, COMBINING SHORT 20D3 @@ -4006,6 +4151,8 @@ vietnamese currency 20AB Vietnamese Tone Marks 0340 VIEWDATA SQUARE 2317 vinculum 0305 +viram, deergh 0965 +viram, purna 0964 VIRAMA, BENGALI SIGN 09CD VIRAMA, DEVANAGARI SIGN 094D VIRAMA, GUJARATI SIGN 0ACD @@ -4023,10 +4170,14 @@ VOICED SOUND MARK, COMBINING KATAKANA-HIRAGANA 3099 VOICED SOUND MARK, KATAKANA-HIRAGANA 309B VOICING, MODIFIER LETTER 02EC VOLUME INTEGRAL 2230 +VOLTAGE SIGN, HIGH 26A1 vrachy 0306 +VS1 FE00 W, LATIN SMALL LETTER TURNED 028D W, MODIFIER LETTER SMALL 02B7 +WARNING SIGN 26A0 Warning Signs 2620 +Warning Signs 26A0 WATCH 231A WAVE, SINE 223F WAVE DASH 301C @@ -4050,6 +4201,7 @@ WHITE CONCAVE-SIDED DIAMOND WITH RIGHTWARDS TICK 27E3 WHITE DIAMOND WITH CENTRED DOT 27D0 WHITE DOT RIGHT, BLACK CIRCLE WITH 2688 WHITE DOTS, BLACK CIRCLE WITH TWO 2689 +WHITE FLAG 2690 white framus 29D6 WHITE HOURGLASS 29D6 WHITE MEDIUM SMALL SQUARE 25FD @@ -4066,8 +4218,11 @@ WIGGLY FENCE, LEFT 29D8 WIGGLY FENCE, LEFT DOUBLE 29DA WIGGLY FENCE, RIGHT 29D9 WIGGLY FENCE, RIGHT DOUBLE 29DB +wj 2060 WON SIGN 20A9 +WORD DIVIDER, UGARITIC 1039F WORD JOINER 2060 +Word Separators, Aegean 10100 Words, Squared Japanese Katakana 3300 WORDSPACE, ETHIOPIC 1361 WREATH PRODUCT 2240 @@ -4095,6 +4250,8 @@ Yi Radicals A490 Yi Syllables A000 Yiddish Digraphs 05F0 yields 22A2 +Yijing Monogram and Digram Symbols 268A +Yijing Hexagram Symbols 4DC0 Yijing Trigram Symbols 2630 YIN YANG 262F yogh, latin capital letter 01B7 @@ -4107,6 +4264,7 @@ Z, BLACK-LETTER CAPITAL 2128 Z, DOUBLE-STRUCK CAPITAL 2124 Z NOTATION BAG MEMBERSHIP 22FF z notation bag subtraction 2A41 +z notation bijection 2917 Z Notation Binding Brackets 2989 Z NOTATION DOMAIN ANTIRESTRICTION 2A64 z notation finite function 20E6 @@ -4116,6 +4274,7 @@ z notation finite relation 21FC z notation finite surjection 2901 z notation finite surjective injection 2918 Z Notation Image Brackets 2987 +z notation left bag bracket 27E6 z notation partial function 21F8 z notation partial injection 2914 z notation partial relation 21F9 @@ -4126,6 +4285,7 @@ Z NOTATION SCHEMA COMPOSITION 2A1F z notation schema hiding 29F9 Z NOTATION SCHEMA PIPING 2A20 Z NOTATION SCHEMA PROJECTION 2A21 +z notations sequence concatenation 2040 Z NOTATION SPOT 2981 z notation surjective injection 2917 Z NOTATION TYPE COLON 2982 @@ -4141,5 +4301,7 @@ ZIGZAG ARROW, RIGHT ANGLE WITH DOWNWARDS 237C ZIGZAG LINE, VERTICAL 299A Zodiacal Symbols 2648 zwj 200D +zwnbsp FEFF zwnj 200C +zwsp 200B diff --git a/lib/unicore/Jamo.txt b/lib/unicore/Jamo.txt index 5c0a5d0..c8bcc88 100644 --- a/lib/unicore/Jamo.txt +++ b/lib/unicore/Jamo.txt @@ -1,13 +1,14 @@ -# Jamo-3.2.0.txt +# Jamo-4.0.1.txt +# Date: 2004-03-02, 18:15 PST [KW] # -# This file is a normative contributory data file in the -# Unicode Character Database. +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html # -# This file defines the Jamo Short Name property, repeating -# in machine readable form the information printed in Table 4-4 -# of The Unicode Standard, Version 3.0. +# This file defines the Jamo Short Name property. # -# See sections 3.11 and 4.4 of The Unicode Standard, Version 3.0 +# See Section 3.12 of The Unicode Standard, Version 4.0 # for more information. # # Each line contains two fields, separated by a semicolon. diff --git a/lib/unicore/Lbrk.pl b/lib/unicore/Lbrk.pl index 70ada22..6b21977 100644 --- a/lib/unicore/Lbrk.pl +++ b/lib/unicore/Lbrk.pl @@ -62,82 +62,12 @@ return <<'END'; 00B6 00BA AI 00BB QU 00BC 00BF AI -00C0 00C5 AL -00C6 AI -00C7 00CF AL -00D0 AI -00D1 00D6 AL -00D7 00D8 AI -00D9 00DD AL -00DE 00E1 AI -00E2 00E5 AL -00E6 AI -00E7 AL -00E8 00EA AI -00EB AL -00EC 00ED AI -00EE 00EF AL -00F0 AI -00F1 AL -00F2 00F3 AI -00F4 00F6 AL -00F7 00FA AI -00FB AL -00FC AI -00FD AL -00FE AI -00FF 0100 AL -0101 AI -0102 0110 AL -0111 AI -0112 AL -0113 AI -0114 011A AL -011B AI -011C 0125 AL -0126 0127 AI -0128 012A AL -012B AI -012C 0130 AL -0131 0133 AI -0134 0137 AL -0138 AI -0139 013E AL -013F 0142 AI -0143 AL -0144 AI -0145 0147 AL -0148 014A AI -014B 014C AL -014D AI -014E 0151 AL -0152 0153 AI -0154 0165 AL -0166 0167 AI -0168 016A AL -016B AI -016C 01CD AL -01CE AI -01CF AL -01D0 AI -01D1 AL -01D2 AI -01D3 AL -01D4 AI -01D5 AL -01D6 AI -01D7 AL -01D8 AI -01D9 AL -01DA AI -01DB AL -01DC AI -01DD 0236 AL -0250 AL -0251 AI -0252 0260 AL -0261 AI -0262 02C6 AL +00C0 00D6 AL +00D7 AI +00D8 00F6 AL +00F7 AI +00F8 0236 AL +0250 02C6 AL 02C7 AI 02C8 BB 02C9 02CB AI @@ -151,28 +81,17 @@ return <<'END'; 02DD AI 02DE 02FF AL 0300 0357 CM -035D 036F CM +035D 0362 GL +0363 036F CM 0374 0375 AL 037A AL -037E AL +037E IS 0384 038A AL 038C AL -038E 0390 AL -0391 03A1 AI -03A3 03A9 AI -03AA 03B0 AL -03B1 03C1 AI -03C2 AL -03C3 03C9 AI -03CA 03CE AL +038E 03A1 AL +03A3 03CE AL 03D0 03FB AL -0400 AL -0401 AI -0402 040F AL -0410 044F AI -0450 AL -0451 AI -0452 0482 AL +0400 0482 AL 0483 0486 CM 0488 0489 CM 048A 04CE AL @@ -206,7 +125,9 @@ return <<'END'; 0640 064A AL 064B 0658 CM 0660 0669 NU -066A 066F AL +066A AL +066B 066C NU +066D 066F AL 0670 CM 0671 06D5 AL 06D6 06DC CM @@ -616,14 +537,10 @@ return <<'END'; 2116 PR 2117 2120 AL 2121 2122 AI -2123 2125 AL -2126 PO -2127 212A AL +2123 212A AL 212B AI 212C 213B AL -213D 213F AL -2140 AI -2141 214B AL +213D 214B AL 2153 AL 2154 2155 AI 2156 215A AL @@ -709,11 +626,7 @@ return <<'END'; 23B7 23D0 AL 2400 2426 AL 2440 244A AL -2460 24BF AI -24C0 24CF AL -24D0 24E9 AI -24EA AL -24EB 24FE AI +2460 24FE AI 24FF AL 2500 254B AI 254C 254F AL @@ -799,7 +712,8 @@ return <<'END'; 2773 CL 2774 OP 2775 CL -2776 2794 AL +2776 2793 AI +2794 AL 2798 27AF AL 27B1 27BE AL 27D0 27E5 AL diff --git a/lib/unicore/LineBreak.txt b/lib/unicore/LineBreak.txt index 90a116c..43faf4f 100644 --- a/lib/unicore/LineBreak.txt +++ b/lib/unicore/LineBreak.txt @@ -1,4 +1,4 @@ -# LineBreak-4.0.0.txt +# LineBreak-4.0.1.txt # # Line Break Properties # @@ -221,7 +221,7 @@ 00C3;AL # LATIN CAPITAL LETTER A WITH TILDE 00C4;AL # LATIN CAPITAL LETTER A WITH DIAERESIS 00C5;AL # LATIN CAPITAL LETTER A WITH RING ABOVE -00C6;AI # LATIN CAPITAL LETTER AE +00C6;AL # LATIN CAPITAL LETTER AE 00C7;AL # LATIN CAPITAL LETTER C WITH CEDILLA 00C8;AL # LATIN CAPITAL LETTER E WITH GRAVE 00C9;AL # LATIN CAPITAL LETTER E WITH ACUTE @@ -231,7 +231,7 @@ 00CD;AL # LATIN CAPITAL LETTER I WITH ACUTE 00CE;AL # LATIN CAPITAL LETTER I WITH CIRCUMFLEX 00CF;AL # LATIN CAPITAL LETTER I WITH DIAERESIS -00D0;AI # LATIN CAPITAL LETTER ETH +00D0;AL # LATIN CAPITAL LETTER ETH 00D1;AL # LATIN CAPITAL LETTER N WITH TILDE 00D2;AL # LATIN CAPITAL LETTER O WITH GRAVE 00D3;AL # LATIN CAPITAL LETTER O WITH ACUTE @@ -239,48 +239,48 @@ 00D5;AL # LATIN CAPITAL LETTER O WITH TILDE 00D6;AL # LATIN CAPITAL LETTER O WITH DIAERESIS 00D7;AI # MULTIPLICATION SIGN -00D8;AI # LATIN CAPITAL LETTER O WITH STROKE +00D8;AL # LATIN CAPITAL LETTER O WITH STROKE 00D9;AL # LATIN CAPITAL LETTER U WITH GRAVE 00DA;AL # LATIN CAPITAL LETTER U WITH ACUTE 00DB;AL # LATIN CAPITAL LETTER U WITH CIRCUMFLEX 00DC;AL # LATIN CAPITAL LETTER U WITH DIAERESIS 00DD;AL # LATIN CAPITAL LETTER Y WITH ACUTE -00DE;AI # LATIN CAPITAL LETTER THORN -00DF;AI # LATIN SMALL LETTER SHARP S -00E0;AI # LATIN SMALL LETTER A WITH GRAVE -00E1;AI # LATIN SMALL LETTER A WITH ACUTE +00DE;AL # LATIN CAPITAL LETTER THORN +00DF;AL # LATIN SMALL LETTER SHARP S +00E0;AL # LATIN SMALL LETTER A WITH GRAVE +00E1;AL # LATIN SMALL LETTER A WITH ACUTE 00E2;AL # LATIN SMALL LETTER A WITH CIRCUMFLEX 00E3;AL # LATIN SMALL LETTER A WITH TILDE 00E4;AL # LATIN SMALL LETTER A WITH DIAERESIS 00E5;AL # LATIN SMALL LETTER A WITH RING ABOVE -00E6;AI # LATIN SMALL LETTER AE +00E6;AL # LATIN SMALL LETTER AE 00E7;AL # LATIN SMALL LETTER C WITH CEDILLA -00E8;AI # LATIN SMALL LETTER E WITH GRAVE -00E9;AI # LATIN SMALL LETTER E WITH ACUTE -00EA;AI # LATIN SMALL LETTER E WITH CIRCUMFLEX +00E8;AL # LATIN SMALL LETTER E WITH GRAVE +00E9;AL # LATIN SMALL LETTER E WITH ACUTE +00EA;AL # LATIN SMALL LETTER E WITH CIRCUMFLEX 00EB;AL # LATIN SMALL LETTER E WITH DIAERESIS -00EC;AI # LATIN SMALL LETTER I WITH GRAVE -00ED;AI # LATIN SMALL LETTER I WITH ACUTE +00EC;AL # LATIN SMALL LETTER I WITH GRAVE +00ED;AL # LATIN SMALL LETTER I WITH ACUTE 00EE;AL # LATIN SMALL LETTER I WITH CIRCUMFLEX 00EF;AL # LATIN SMALL LETTER I WITH DIAERESIS -00F0;AI # LATIN SMALL LETTER ETH +00F0;AL # LATIN SMALL LETTER ETH 00F1;AL # LATIN SMALL LETTER N WITH TILDE -00F2;AI # LATIN SMALL LETTER O WITH GRAVE -00F3;AI # LATIN SMALL LETTER O WITH ACUTE +00F2;AL # LATIN SMALL LETTER O WITH GRAVE +00F3;AL # LATIN SMALL LETTER O WITH ACUTE 00F4;AL # LATIN SMALL LETTER O WITH CIRCUMFLEX 00F5;AL # LATIN SMALL LETTER O WITH TILDE 00F6;AL # LATIN SMALL LETTER O WITH DIAERESIS 00F7;AI # DIVISION SIGN -00F8;AI # LATIN SMALL LETTER O WITH STROKE -00F9;AI # LATIN SMALL LETTER U WITH GRAVE -00FA;AI # LATIN SMALL LETTER U WITH ACUTE +00F8;AL # LATIN SMALL LETTER O WITH STROKE +00F9;AL # LATIN SMALL LETTER U WITH GRAVE +00FA;AL # LATIN SMALL LETTER U WITH ACUTE 00FB;AL # LATIN SMALL LETTER U WITH CIRCUMFLEX -00FC;AI # LATIN SMALL LETTER U WITH DIAERESIS +00FC;AL # LATIN SMALL LETTER U WITH DIAERESIS 00FD;AL # LATIN SMALL LETTER Y WITH ACUTE -00FE;AI # LATIN SMALL LETTER THORN +00FE;AL # LATIN SMALL LETTER THORN 00FF;AL # LATIN SMALL LETTER Y WITH DIAERESIS 0100;AL # LATIN CAPITAL LETTER A WITH MACRON -0101;AI # LATIN SMALL LETTER A WITH MACRON +0101;AL # LATIN SMALL LETTER A WITH MACRON 0102;AL # LATIN CAPITAL LETTER A WITH BREVE 0103;AL # LATIN SMALL LETTER A WITH BREVE 0104;AL # LATIN CAPITAL LETTER A WITH OGONEK @@ -296,9 +296,9 @@ 010E;AL # LATIN CAPITAL LETTER D WITH CARON 010F;AL # LATIN SMALL LETTER D WITH CARON 0110;AL # LATIN CAPITAL LETTER D WITH STROKE -0111;AI # LATIN SMALL LETTER D WITH STROKE +0111;AL # LATIN SMALL LETTER D WITH STROKE 0112;AL # LATIN CAPITAL LETTER E WITH MACRON -0113;AI # LATIN SMALL LETTER E WITH MACRON +0113;AL # LATIN SMALL LETTER E WITH MACRON 0114;AL # LATIN CAPITAL LETTER E WITH BREVE 0115;AL # LATIN SMALL LETTER E WITH BREVE 0116;AL # LATIN CAPITAL LETTER E WITH DOT ABOVE @@ -306,7 +306,7 @@ 0118;AL # LATIN CAPITAL LETTER E WITH OGONEK 0119;AL # LATIN SMALL LETTER E WITH OGONEK 011A;AL # LATIN CAPITAL LETTER E WITH CARON -011B;AI # LATIN SMALL LETTER E WITH CARON +011B;AL # LATIN SMALL LETTER E WITH CARON 011C;AL # LATIN CAPITAL LETTER G WITH CIRCUMFLEX 011D;AL # LATIN SMALL LETTER G WITH CIRCUMFLEX 011E;AL # LATIN CAPITAL LETTER G WITH BREVE @@ -317,52 +317,52 @@ 0123;AL # LATIN SMALL LETTER G WITH CEDILLA 0124;AL # LATIN CAPITAL LETTER H WITH CIRCUMFLEX 0125;AL # LATIN SMALL LETTER H WITH CIRCUMFLEX -0126;AI # LATIN CAPITAL LETTER H WITH STROKE -0127;AI # LATIN SMALL LETTER H WITH STROKE +0126;AL # LATIN CAPITAL LETTER H WITH STROKE +0127;AL # LATIN SMALL LETTER H WITH STROKE 0128;AL # LATIN CAPITAL LETTER I WITH TILDE 0129;AL # LATIN SMALL LETTER I WITH TILDE 012A;AL # LATIN CAPITAL LETTER I WITH MACRON -012B;AI # LATIN SMALL LETTER I WITH MACRON +012B;AL # LATIN SMALL LETTER I WITH MACRON 012C;AL # LATIN CAPITAL LETTER I WITH BREVE 012D;AL # LATIN SMALL LETTER I WITH BREVE 012E;AL # LATIN CAPITAL LETTER I WITH OGONEK 012F;AL # LATIN SMALL LETTER I WITH OGONEK 0130;AL # LATIN CAPITAL LETTER I WITH DOT ABOVE -0131;AI # LATIN SMALL LETTER DOTLESS I -0132;AI # LATIN CAPITAL LIGATURE IJ -0133;AI # LATIN SMALL LIGATURE IJ +0131;AL # LATIN SMALL LETTER DOTLESS I +0132;AL # LATIN CAPITAL LIGATURE IJ +0133;AL # LATIN SMALL LIGATURE IJ 0134;AL # LATIN CAPITAL LETTER J WITH CIRCUMFLEX 0135;AL # LATIN SMALL LETTER J WITH CIRCUMFLEX 0136;AL # LATIN CAPITAL LETTER K WITH CEDILLA 0137;AL # LATIN SMALL LETTER K WITH CEDILLA -0138;AI # LATIN SMALL LETTER KRA +0138;AL # LATIN SMALL LETTER KRA 0139;AL # LATIN CAPITAL LETTER L WITH ACUTE 013A;AL # LATIN SMALL LETTER L WITH ACUTE 013B;AL # LATIN CAPITAL LETTER L WITH CEDILLA 013C;AL # LATIN SMALL LETTER L WITH CEDILLA 013D;AL # LATIN CAPITAL LETTER L WITH CARON 013E;AL # LATIN SMALL LETTER L WITH CARON -013F;AI # LATIN CAPITAL LETTER L WITH MIDDLE DOT -0140;AI # LATIN SMALL LETTER L WITH MIDDLE DOT -0141;AI # LATIN CAPITAL LETTER L WITH STROKE -0142;AI # LATIN SMALL LETTER L WITH STROKE +013F;AL # LATIN CAPITAL LETTER L WITH MIDDLE DOT +0140;AL # LATIN SMALL LETTER L WITH MIDDLE DOT +0141;AL # LATIN CAPITAL LETTER L WITH STROKE +0142;AL # LATIN SMALL LETTER L WITH STROKE 0143;AL # LATIN CAPITAL LETTER N WITH ACUTE -0144;AI # LATIN SMALL LETTER N WITH ACUTE +0144;AL # LATIN SMALL LETTER N WITH ACUTE 0145;AL # LATIN CAPITAL LETTER N WITH CEDILLA 0146;AL # LATIN SMALL LETTER N WITH CEDILLA 0147;AL # LATIN CAPITAL LETTER N WITH CARON -0148;AI # LATIN SMALL LETTER N WITH CARON -0149;AI # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE -014A;AI # LATIN CAPITAL LETTER ENG +0148;AL # LATIN SMALL LETTER N WITH CARON +0149;AL # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE +014A;AL # LATIN CAPITAL LETTER ENG 014B;AL # LATIN SMALL LETTER ENG 014C;AL # LATIN CAPITAL LETTER O WITH MACRON -014D;AI # LATIN SMALL LETTER O WITH MACRON +014D;AL # LATIN SMALL LETTER O WITH MACRON 014E;AL # LATIN CAPITAL LETTER O WITH BREVE 014F;AL # LATIN SMALL LETTER O WITH BREVE 0150;AL # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE 0151;AL # LATIN SMALL LETTER O WITH DOUBLE ACUTE -0152;AI # LATIN CAPITAL LIGATURE OE -0153;AI # LATIN SMALL LIGATURE OE +0152;AL # LATIN CAPITAL LIGATURE OE +0153;AL # LATIN SMALL LIGATURE OE 0154;AL # LATIN CAPITAL LETTER R WITH ACUTE 0155;AL # LATIN SMALL LETTER R WITH ACUTE 0156;AL # LATIN CAPITAL LETTER R WITH CEDILLA @@ -381,12 +381,12 @@ 0163;AL # LATIN SMALL LETTER T WITH CEDILLA 0164;AL # LATIN CAPITAL LETTER T WITH CARON 0165;AL # LATIN SMALL LETTER T WITH CARON -0166;AI # LATIN CAPITAL LETTER T WITH STROKE -0167;AI # LATIN SMALL LETTER T WITH STROKE +0166;AL # LATIN CAPITAL LETTER T WITH STROKE +0167;AL # LATIN SMALL LETTER T WITH STROKE 0168;AL # LATIN CAPITAL LETTER U WITH TILDE 0169;AL # LATIN SMALL LETTER U WITH TILDE 016A;AL # LATIN CAPITAL LETTER U WITH MACRON -016B;AI # LATIN SMALL LETTER U WITH MACRON +016B;AL # LATIN SMALL LETTER U WITH MACRON 016C;AL # LATIN CAPITAL LETTER U WITH BREVE 016D;AL # LATIN SMALL LETTER U WITH BREVE 016E;AL # LATIN CAPITAL LETTER U WITH RING ABOVE @@ -485,21 +485,21 @@ 01CB;AL # LATIN CAPITAL LETTER N WITH SMALL LETTER J 01CC;AL # LATIN SMALL LETTER NJ 01CD;AL # LATIN CAPITAL LETTER A WITH CARON -01CE;AI # LATIN SMALL LETTER A WITH CARON +01CE;AL # LATIN SMALL LETTER A WITH CARON 01CF;AL # LATIN CAPITAL LETTER I WITH CARON -01D0;AI # LATIN SMALL LETTER I WITH CARON +01D0;AL # LATIN SMALL LETTER I WITH CARON 01D1;AL # LATIN CAPITAL LETTER O WITH CARON -01D2;AI # LATIN SMALL LETTER O WITH CARON +01D2;AL # LATIN SMALL LETTER O WITH CARON 01D3;AL # LATIN CAPITAL LETTER U WITH CARON -01D4;AI # LATIN SMALL LETTER U WITH CARON +01D4;AL # LATIN SMALL LETTER U WITH CARON 01D5;AL # LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON -01D6;AI # LATIN SMALL LETTER U WITH DIAERESIS AND MACRON +01D6;AL # LATIN SMALL LETTER U WITH DIAERESIS AND MACRON 01D7;AL # LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE -01D8;AI # LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE +01D8;AL # LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE 01D9;AL # LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON -01DA;AI # LATIN SMALL LETTER U WITH DIAERESIS AND CARON +01DA;AL # LATIN SMALL LETTER U WITH DIAERESIS AND CARON 01DB;AL # LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE -01DC;AI # LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE +01DC;AL # LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE 01DD;AL # LATIN SMALL LETTER TURNED E 01DE;AL # LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON 01DF;AL # LATIN SMALL LETTER A WITH DIAERESIS AND MACRON @@ -591,7 +591,7 @@ 0235;AL # LATIN SMALL LETTER N WITH CURL 0236;AL # LATIN SMALL LETTER T WITH CURL 0250;AL # LATIN SMALL LETTER TURNED A -0251;AI # LATIN SMALL LETTER ALPHA +0251;AL # LATIN SMALL LETTER ALPHA 0252;AL # LATIN SMALL LETTER TURNED ALPHA 0253;AL # LATIN SMALL LETTER B WITH HOOK 0254;AL # LATIN SMALL LETTER OPEN O @@ -607,7 +607,7 @@ 025E;AL # LATIN SMALL LETTER CLOSED REVERSED OPEN E 025F;AL # LATIN SMALL LETTER DOTLESS J WITH STROKE 0260;AL # LATIN SMALL LETTER G WITH HOOK -0261;AI # LATIN SMALL LETTER SCRIPT G +0261;AL # LATIN SMALL LETTER SCRIPT G 0262;AL # LATIN LETTER SMALL CAPITAL G 0263;AL # LATIN SMALL LETTER GAMMA 0264;AL # LATIN SMALL LETTER RAMS HORN @@ -854,12 +854,12 @@ 0355;CM # COMBINING RIGHT ARROWHEAD BELOW 0356;CM # COMBINING RIGHT ARROWHEAD AND UP ARROWHEAD BELOW 0357;CM # COMBINING RIGHT HALF RING ABOVE -035D;CM # COMBINING DOUBLE BREVE -035E;CM # COMBINING DOUBLE MACRON -035F;CM # COMBINING DOUBLE MACRON BELOW -0360;CM # COMBINING DOUBLE TILDE -0361;CM # COMBINING DOUBLE INVERTED BREVE -0362;CM # COMBINING DOUBLE RIGHTWARDS ARROW BELOW +035D;GL # COMBINING DOUBLE BREVE +035E;GL # COMBINING DOUBLE MACRON +035F;GL # COMBINING DOUBLE MACRON BELOW +0360;GL # COMBINING DOUBLE TILDE +0361;GL # COMBINING DOUBLE INVERTED BREVE +0362;GL # COMBINING DOUBLE RIGHTWARDS ARROW BELOW 0363;CM # COMBINING LATIN SMALL LETTER A 0364;CM # COMBINING LATIN SMALL LETTER E 0365;CM # COMBINING LATIN SMALL LETTER I @@ -876,7 +876,7 @@ 0374;AL # GREEK NUMERAL SIGN 0375;AL # GREEK LOWER NUMERAL SIGN 037A;AL # GREEK YPOGEGRAMMENI -037E;AL # GREEK QUESTION MARK +037E;IS # GREEK QUESTION MARK 0384;AL # GREEK TONOS 0385;AL # GREEK DIALYTIKA TONOS 0386;AL # GREEK CAPITAL LETTER ALPHA WITH TONOS @@ -888,30 +888,30 @@ 038E;AL # GREEK CAPITAL LETTER UPSILON WITH TONOS 038F;AL # GREEK CAPITAL LETTER OMEGA WITH TONOS 0390;AL # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS -0391;AI # GREEK CAPITAL LETTER ALPHA -0392;AI # GREEK CAPITAL LETTER BETA -0393;AI # GREEK CAPITAL LETTER GAMMA -0394;AI # GREEK CAPITAL LETTER DELTA -0395;AI # GREEK CAPITAL LETTER EPSILON -0396;AI # GREEK CAPITAL LETTER ZETA -0397;AI # GREEK CAPITAL LETTER ETA -0398;AI # GREEK CAPITAL LETTER THETA -0399;AI # GREEK CAPITAL LETTER IOTA -039A;AI # GREEK CAPITAL LETTER KAPPA -039B;AI # GREEK CAPITAL LETTER LAMDA -039C;AI # GREEK CAPITAL LETTER MU -039D;AI # GREEK CAPITAL LETTER NU -039E;AI # GREEK CAPITAL LETTER XI -039F;AI # GREEK CAPITAL LETTER OMICRON -03A0;AI # GREEK CAPITAL LETTER PI -03A1;AI # GREEK CAPITAL LETTER RHO -03A3;AI # GREEK CAPITAL LETTER SIGMA -03A4;AI # GREEK CAPITAL LETTER TAU -03A5;AI # GREEK CAPITAL LETTER UPSILON -03A6;AI # GREEK CAPITAL LETTER PHI -03A7;AI # GREEK CAPITAL LETTER CHI -03A8;AI # GREEK CAPITAL LETTER PSI -03A9;AI # GREEK CAPITAL LETTER OMEGA +0391;AL # GREEK CAPITAL LETTER ALPHA +0392;AL # GREEK CAPITAL LETTER BETA +0393;AL # GREEK CAPITAL LETTER GAMMA +0394;AL # GREEK CAPITAL LETTER DELTA +0395;AL # GREEK CAPITAL LETTER EPSILON +0396;AL # GREEK CAPITAL LETTER ZETA +0397;AL # GREEK CAPITAL LETTER ETA +0398;AL # GREEK CAPITAL LETTER THETA +0399;AL # GREEK CAPITAL LETTER IOTA +039A;AL # GREEK CAPITAL LETTER KAPPA +039B;AL # GREEK CAPITAL LETTER LAMDA +039C;AL # GREEK CAPITAL LETTER MU +039D;AL # GREEK CAPITAL LETTER NU +039E;AL # GREEK CAPITAL LETTER XI +039F;AL # GREEK CAPITAL LETTER OMICRON +03A0;AL # GREEK CAPITAL LETTER PI +03A1;AL # GREEK CAPITAL LETTER RHO +03A3;AL # GREEK CAPITAL LETTER SIGMA +03A4;AL # GREEK CAPITAL LETTER TAU +03A5;AL # GREEK CAPITAL LETTER UPSILON +03A6;AL # GREEK CAPITAL LETTER PHI +03A7;AL # GREEK CAPITAL LETTER CHI +03A8;AL # GREEK CAPITAL LETTER PSI +03A9;AL # GREEK CAPITAL LETTER OMEGA 03AA;AL # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA 03AB;AL # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA 03AC;AL # GREEK SMALL LETTER ALPHA WITH TONOS @@ -919,31 +919,31 @@ 03AE;AL # GREEK SMALL LETTER ETA WITH TONOS 03AF;AL # GREEK SMALL LETTER IOTA WITH TONOS 03B0;AL # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS -03B1;AI # GREEK SMALL LETTER ALPHA -03B2;AI # GREEK SMALL LETTER BETA -03B3;AI # GREEK SMALL LETTER GAMMA -03B4;AI # GREEK SMALL LETTER DELTA -03B5;AI # GREEK SMALL LETTER EPSILON -03B6;AI # GREEK SMALL LETTER ZETA -03B7;AI # GREEK SMALL LETTER ETA -03B8;AI # GREEK SMALL LETTER THETA -03B9;AI # GREEK SMALL LETTER IOTA -03BA;AI # GREEK SMALL LETTER KAPPA -03BB;AI # GREEK SMALL LETTER LAMDA -03BC;AI # GREEK SMALL LETTER MU -03BD;AI # GREEK SMALL LETTER NU -03BE;AI # GREEK SMALL LETTER XI -03BF;AI # GREEK SMALL LETTER OMICRON -03C0;AI # GREEK SMALL LETTER PI -03C1;AI # GREEK SMALL LETTER RHO +03B1;AL # GREEK SMALL LETTER ALPHA +03B2;AL # GREEK SMALL LETTER BETA +03B3;AL # GREEK SMALL LETTER GAMMA +03B4;AL # GREEK SMALL LETTER DELTA +03B5;AL # GREEK SMALL LETTER EPSILON +03B6;AL # GREEK SMALL LETTER ZETA +03B7;AL # GREEK SMALL LETTER ETA +03B8;AL # GREEK SMALL LETTER THETA +03B9;AL # GREEK SMALL LETTER IOTA +03BA;AL # GREEK SMALL LETTER KAPPA +03BB;AL # GREEK SMALL LETTER LAMDA +03BC;AL # GREEK SMALL LETTER MU +03BD;AL # GREEK SMALL LETTER NU +03BE;AL # GREEK SMALL LETTER XI +03BF;AL # GREEK SMALL LETTER OMICRON +03C0;AL # GREEK SMALL LETTER PI +03C1;AL # GREEK SMALL LETTER RHO 03C2;AL # GREEK SMALL LETTER FINAL SIGMA -03C3;AI # GREEK SMALL LETTER SIGMA -03C4;AI # GREEK SMALL LETTER TAU -03C5;AI # GREEK SMALL LETTER UPSILON -03C6;AI # GREEK SMALL LETTER PHI -03C7;AI # GREEK SMALL LETTER CHI -03C8;AI # GREEK SMALL LETTER PSI -03C9;AI # GREEK SMALL LETTER OMEGA +03C3;AL # GREEK SMALL LETTER SIGMA +03C4;AL # GREEK SMALL LETTER TAU +03C5;AL # GREEK SMALL LETTER UPSILON +03C6;AL # GREEK SMALL LETTER PHI +03C7;AL # GREEK SMALL LETTER CHI +03C8;AL # GREEK SMALL LETTER PSI +03C9;AL # GREEK SMALL LETTER OMEGA 03CA;AL # GREEK SMALL LETTER IOTA WITH DIALYTIKA 03CB;AL # GREEK SMALL LETTER UPSILON WITH DIALYTIKA 03CC;AL # GREEK SMALL LETTER OMICRON WITH TONOS @@ -994,7 +994,7 @@ 03FA;AL # GREEK CAPITAL LETTER SAN 03FB;AL # GREEK SMALL LETTER SAN 0400;AL # CYRILLIC CAPITAL LETTER IE WITH GRAVE -0401;AI # CYRILLIC CAPITAL LETTER IO +0401;AL # CYRILLIC CAPITAL LETTER IO 0402;AL # CYRILLIC CAPITAL LETTER DJE 0403;AL # CYRILLIC CAPITAL LETTER GJE 0404;AL # CYRILLIC CAPITAL LETTER UKRAINIAN IE @@ -1009,72 +1009,72 @@ 040D;AL # CYRILLIC CAPITAL LETTER I WITH GRAVE 040E;AL # CYRILLIC CAPITAL LETTER SHORT U 040F;AL # CYRILLIC CAPITAL LETTER DZHE -0410;AI # CYRILLIC CAPITAL LETTER A -0411;AI # CYRILLIC CAPITAL LETTER BE -0412;AI # CYRILLIC CAPITAL LETTER VE -0413;AI # CYRILLIC CAPITAL LETTER GHE -0414;AI # CYRILLIC CAPITAL LETTER DE -0415;AI # CYRILLIC CAPITAL LETTER IE -0416;AI # CYRILLIC CAPITAL LETTER ZHE -0417;AI # CYRILLIC CAPITAL LETTER ZE -0418;AI # CYRILLIC CAPITAL LETTER I -0419;AI # CYRILLIC CAPITAL LETTER SHORT I -041A;AI # CYRILLIC CAPITAL LETTER KA -041B;AI # CYRILLIC CAPITAL LETTER EL -041C;AI # CYRILLIC CAPITAL LETTER EM -041D;AI # CYRILLIC CAPITAL LETTER EN -041E;AI # CYRILLIC CAPITAL LETTER O -041F;AI # CYRILLIC CAPITAL LETTER PE -0420;AI # CYRILLIC CAPITAL LETTER ER -0421;AI # CYRILLIC CAPITAL LETTER ES -0422;AI # CYRILLIC CAPITAL LETTER TE -0423;AI # CYRILLIC CAPITAL LETTER U -0424;AI # CYRILLIC CAPITAL LETTER EF -0425;AI # CYRILLIC CAPITAL LETTER HA -0426;AI # CYRILLIC CAPITAL LETTER TSE -0427;AI # CYRILLIC CAPITAL LETTER CHE -0428;AI # CYRILLIC CAPITAL LETTER SHA -0429;AI # CYRILLIC CAPITAL LETTER SHCHA -042A;AI # CYRILLIC CAPITAL LETTER HARD SIGN -042B;AI # CYRILLIC CAPITAL LETTER YERU -042C;AI # CYRILLIC CAPITAL LETTER SOFT SIGN -042D;AI # CYRILLIC CAPITAL LETTER E -042E;AI # CYRILLIC CAPITAL LETTER YU -042F;AI # CYRILLIC CAPITAL LETTER YA -0430;AI # CYRILLIC SMALL LETTER A -0431;AI # CYRILLIC SMALL LETTER BE -0432;AI # CYRILLIC SMALL LETTER VE -0433;AI # CYRILLIC SMALL LETTER GHE -0434;AI # CYRILLIC SMALL LETTER DE -0435;AI # CYRILLIC SMALL LETTER IE -0436;AI # CYRILLIC SMALL LETTER ZHE -0437;AI # CYRILLIC SMALL LETTER ZE -0438;AI # CYRILLIC SMALL LETTER I -0439;AI # CYRILLIC SMALL LETTER SHORT I -043A;AI # CYRILLIC SMALL LETTER KA -043B;AI # CYRILLIC SMALL LETTER EL -043C;AI # CYRILLIC SMALL LETTER EM -043D;AI # CYRILLIC SMALL LETTER EN -043E;AI # CYRILLIC SMALL LETTER O -043F;AI # CYRILLIC SMALL LETTER PE -0440;AI # CYRILLIC SMALL LETTER ER -0441;AI # CYRILLIC SMALL LETTER ES -0442;AI # CYRILLIC SMALL LETTER TE -0443;AI # CYRILLIC SMALL LETTER U -0444;AI # CYRILLIC SMALL LETTER EF -0445;AI # CYRILLIC SMALL LETTER HA -0446;AI # CYRILLIC SMALL LETTER TSE -0447;AI # CYRILLIC SMALL LETTER CHE -0448;AI # CYRILLIC SMALL LETTER SHA -0449;AI # CYRILLIC SMALL LETTER SHCHA -044A;AI # CYRILLIC SMALL LETTER HARD SIGN -044B;AI # CYRILLIC SMALL LETTER YERU -044C;AI # CYRILLIC SMALL LETTER SOFT SIGN -044D;AI # CYRILLIC SMALL LETTER E -044E;AI # CYRILLIC SMALL LETTER YU -044F;AI # CYRILLIC SMALL LETTER YA +0410;AL # CYRILLIC CAPITAL LETTER A +0411;AL # CYRILLIC CAPITAL LETTER BE +0412;AL # CYRILLIC CAPITAL LETTER VE +0413;AL # CYRILLIC CAPITAL LETTER GHE +0414;AL # CYRILLIC CAPITAL LETTER DE +0415;AL # CYRILLIC CAPITAL LETTER IE +0416;AL # CYRILLIC CAPITAL LETTER ZHE +0417;AL # CYRILLIC CAPITAL LETTER ZE +0418;AL # CYRILLIC CAPITAL LETTER I +0419;AL # CYRILLIC CAPITAL LETTER SHORT I +041A;AL # CYRILLIC CAPITAL LETTER KA +041B;AL # CYRILLIC CAPITAL LETTER EL +041C;AL # CYRILLIC CAPITAL LETTER EM +041D;AL # CYRILLIC CAPITAL LETTER EN +041E;AL # CYRILLIC CAPITAL LETTER O +041F;AL # CYRILLIC CAPITAL LETTER PE +0420;AL # CYRILLIC CAPITAL LETTER ER +0421;AL # CYRILLIC CAPITAL LETTER ES +0422;AL # CYRILLIC CAPITAL LETTER TE +0423;AL # CYRILLIC CAPITAL LETTER U +0424;AL # CYRILLIC CAPITAL LETTER EF +0425;AL # CYRILLIC CAPITAL LETTER HA +0426;AL # CYRILLIC CAPITAL LETTER TSE +0427;AL # CYRILLIC CAPITAL LETTER CHE +0428;AL # CYRILLIC CAPITAL LETTER SHA +0429;AL # CYRILLIC CAPITAL LETTER SHCHA +042A;AL # CYRILLIC CAPITAL LETTER HARD SIGN +042B;AL # CYRILLIC CAPITAL LETTER YERU +042C;AL # CYRILLIC CAPITAL LETTER SOFT SIGN +042D;AL # CYRILLIC CAPITAL LETTER E +042E;AL # CYRILLIC CAPITAL LETTER YU +042F;AL # CYRILLIC CAPITAL LETTER YA +0430;AL # CYRILLIC SMALL LETTER A +0431;AL # CYRILLIC SMALL LETTER BE +0432;AL # CYRILLIC SMALL LETTER VE +0433;AL # CYRILLIC SMALL LETTER GHE +0434;AL # CYRILLIC SMALL LETTER DE +0435;AL # CYRILLIC SMALL LETTER IE +0436;AL # CYRILLIC SMALL LETTER ZHE +0437;AL # CYRILLIC SMALL LETTER ZE +0438;AL # CYRILLIC SMALL LETTER I +0439;AL # CYRILLIC SMALL LETTER SHORT I +043A;AL # CYRILLIC SMALL LETTER KA +043B;AL # CYRILLIC SMALL LETTER EL +043C;AL # CYRILLIC SMALL LETTER EM +043D;AL # CYRILLIC SMALL LETTER EN +043E;AL # CYRILLIC SMALL LETTER O +043F;AL # CYRILLIC SMALL LETTER PE +0440;AL # CYRILLIC SMALL LETTER ER +0441;AL # CYRILLIC SMALL LETTER ES +0442;AL # CYRILLIC SMALL LETTER TE +0443;AL # CYRILLIC SMALL LETTER U +0444;AL # CYRILLIC SMALL LETTER EF +0445;AL # CYRILLIC SMALL LETTER HA +0446;AL # CYRILLIC SMALL LETTER TSE +0447;AL # CYRILLIC SMALL LETTER CHE +0448;AL # CYRILLIC SMALL LETTER SHA +0449;AL # CYRILLIC SMALL LETTER SHCHA +044A;AL # CYRILLIC SMALL LETTER HARD SIGN +044B;AL # CYRILLIC SMALL LETTER YERU +044C;AL # CYRILLIC SMALL LETTER SOFT SIGN +044D;AL # CYRILLIC SMALL LETTER E +044E;AL # CYRILLIC SMALL LETTER YU +044F;AL # CYRILLIC SMALL LETTER YA 0450;AL # CYRILLIC SMALL LETTER IE WITH GRAVE -0451;AI # CYRILLIC SMALL LETTER IO +0451;AL # CYRILLIC SMALL LETTER IO 0452;AL # CYRILLIC SMALL LETTER DJE 0453;AL # CYRILLIC SMALL LETTER GJE 0454;AL # CYRILLIC SMALL LETTER UKRAINIAN IE @@ -1501,8 +1501,8 @@ 0668;NU # ARABIC-INDIC DIGIT EIGHT 0669;NU # ARABIC-INDIC DIGIT NINE 066A;AL # ARABIC PERCENT SIGN -066B;AL # ARABIC DECIMAL SEPARATOR -066C;AL # ARABIC THOUSANDS SEPARATOR +066B;NU # ARABIC DECIMAL SEPARATOR +066C;NU # ARABIC THOUSANDS SEPARATOR 066D;AL # ARABIC FIVE POINTED STAR 066E;AL # ARABIC LETTER DOTLESS BEH 066F;AL # ARABIC LETTER DOTLESS QAF @@ -5794,7 +5794,7 @@ 2123;AL # VERSICLE 2124;AL # DOUBLE-STRUCK CAPITAL Z 2125;AL # OUNCE SIGN -2126;PO # OHM SIGN +2126;AL # OHM SIGN 2127;AL # INVERTED OHM SIGN 2128;AL # BLACK-LETTER CAPITAL Z 2129;AL # TURNED GREEK SMALL LETTER IOTA @@ -5819,7 +5819,7 @@ 213D;AL # DOUBLE-STRUCK SMALL GAMMA 213E;AL # DOUBLE-STRUCK CAPITAL GAMMA 213F;AL # DOUBLE-STRUCK CAPITAL PI -2140;AI # DOUBLE-STRUCK N-ARY SUMMATION +2140;AL # DOUBLE-STRUCK N-ARY SUMMATION 2141;AL # TURNED SANS-SERIF CAPITAL G 2142;AL # TURNED SANS-SERIF CAPITAL L 2143;AL # REVERSED SANS-SERIF CAPITAL L @@ -6603,22 +6603,22 @@ 24BD;AI # CIRCLED LATIN CAPITAL LETTER H 24BE;AI # CIRCLED LATIN CAPITAL LETTER I 24BF;AI # CIRCLED LATIN CAPITAL LETTER J -24C0;AL # CIRCLED LATIN CAPITAL LETTER K -24C1;AL # CIRCLED LATIN CAPITAL LETTER L -24C2;AL # CIRCLED LATIN CAPITAL LETTER M -24C3;AL # CIRCLED LATIN CAPITAL LETTER N -24C4;AL # CIRCLED LATIN CAPITAL LETTER O -24C5;AL # CIRCLED LATIN CAPITAL LETTER P -24C6;AL # CIRCLED LATIN CAPITAL LETTER Q -24C7;AL # CIRCLED LATIN CAPITAL LETTER R -24C8;AL # CIRCLED LATIN CAPITAL LETTER S -24C9;AL # CIRCLED LATIN CAPITAL LETTER T -24CA;AL # CIRCLED LATIN CAPITAL LETTER U -24CB;AL # CIRCLED LATIN CAPITAL LETTER V -24CC;AL # CIRCLED LATIN CAPITAL LETTER W -24CD;AL # CIRCLED LATIN CAPITAL LETTER X -24CE;AL # CIRCLED LATIN CAPITAL LETTER Y -24CF;AL # CIRCLED LATIN CAPITAL LETTER Z +24C0;AI # CIRCLED LATIN CAPITAL LETTER K +24C1;AI # CIRCLED LATIN CAPITAL LETTER L +24C2;AI # CIRCLED LATIN CAPITAL LETTER M +24C3;AI # CIRCLED LATIN CAPITAL LETTER N +24C4;AI # CIRCLED LATIN CAPITAL LETTER O +24C5;AI # CIRCLED LATIN CAPITAL LETTER P +24C6;AI # CIRCLED LATIN CAPITAL LETTER Q +24C7;AI # CIRCLED LATIN CAPITAL LETTER R +24C8;AI # CIRCLED LATIN CAPITAL LETTER S +24C9;AI # CIRCLED LATIN CAPITAL LETTER T +24CA;AI # CIRCLED LATIN CAPITAL LETTER U +24CB;AI # CIRCLED LATIN CAPITAL LETTER V +24CC;AI # CIRCLED LATIN CAPITAL LETTER W +24CD;AI # CIRCLED LATIN CAPITAL LETTER X +24CE;AI # CIRCLED LATIN CAPITAL LETTER Y +24CF;AI # CIRCLED LATIN CAPITAL LETTER Z 24D0;AI # CIRCLED LATIN SMALL LETTER A 24D1;AI # CIRCLED LATIN SMALL LETTER B 24D2;AI # CIRCLED LATIN SMALL LETTER C @@ -6645,7 +6645,7 @@ 24E7;AI # CIRCLED LATIN SMALL LETTER X 24E8;AI # CIRCLED LATIN SMALL LETTER Y 24E9;AI # CIRCLED LATIN SMALL LETTER Z -24EA;AL # CIRCLED DIGIT ZERO +24EA;AI # CIRCLED DIGIT ZERO 24EB;AI # NEGATIVE CIRCLED NUMBER ELEVEN 24EC;AI # NEGATIVE CIRCLED NUMBER TWELVE 24ED;AI # NEGATIVE CIRCLED NUMBER THIRTEEN @@ -7173,36 +7173,36 @@ 2773;CL # LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT 2774;OP # MEDIUM LEFT CURLY BRACKET ORNAMENT 2775;CL # MEDIUM RIGHT CURLY BRACKET ORNAMENT -2776;AL # DINGBAT NEGATIVE CIRCLED DIGIT ONE -2777;AL # DINGBAT NEGATIVE CIRCLED DIGIT TWO -2778;AL # DINGBAT NEGATIVE CIRCLED DIGIT THREE -2779;AL # DINGBAT NEGATIVE CIRCLED DIGIT FOUR -277A;AL # DINGBAT NEGATIVE CIRCLED DIGIT FIVE -277B;AL # DINGBAT NEGATIVE CIRCLED DIGIT SIX -277C;AL # DINGBAT NEGATIVE CIRCLED DIGIT SEVEN -277D;AL # DINGBAT NEGATIVE CIRCLED DIGIT EIGHT -277E;AL # DINGBAT NEGATIVE CIRCLED DIGIT NINE -277F;AL # DINGBAT NEGATIVE CIRCLED NUMBER TEN -2780;AL # DINGBAT CIRCLED SANS-SERIF DIGIT ONE -2781;AL # DINGBAT CIRCLED SANS-SERIF DIGIT TWO -2782;AL # DINGBAT CIRCLED SANS-SERIF DIGIT THREE -2783;AL # DINGBAT CIRCLED SANS-SERIF DIGIT FOUR -2784;AL # DINGBAT CIRCLED SANS-SERIF DIGIT FIVE -2785;AL # DINGBAT CIRCLED SANS-SERIF DIGIT SIX -2786;AL # DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN -2787;AL # DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT -2788;AL # DINGBAT CIRCLED SANS-SERIF DIGIT NINE -2789;AL # DINGBAT CIRCLED SANS-SERIF NUMBER TEN -278A;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE -278B;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO -278C;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE -278D;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR -278E;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE -278F;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX -2790;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN -2791;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT -2792;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE -2793;AL # DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN +2776;AI # DINGBAT NEGATIVE CIRCLED DIGIT ONE +2777;AI # DINGBAT NEGATIVE CIRCLED DIGIT TWO +2778;AI # DINGBAT NEGATIVE CIRCLED DIGIT THREE +2779;AI # DINGBAT NEGATIVE CIRCLED DIGIT FOUR +277A;AI # DINGBAT NEGATIVE CIRCLED DIGIT FIVE +277B;AI # DINGBAT NEGATIVE CIRCLED DIGIT SIX +277C;AI # DINGBAT NEGATIVE CIRCLED DIGIT SEVEN +277D;AI # DINGBAT NEGATIVE CIRCLED DIGIT EIGHT +277E;AI # DINGBAT NEGATIVE CIRCLED DIGIT NINE +277F;AI # DINGBAT NEGATIVE CIRCLED NUMBER TEN +2780;AI # DINGBAT CIRCLED SANS-SERIF DIGIT ONE +2781;AI # DINGBAT CIRCLED SANS-SERIF DIGIT TWO +2782;AI # DINGBAT CIRCLED SANS-SERIF DIGIT THREE +2783;AI # DINGBAT CIRCLED SANS-SERIF DIGIT FOUR +2784;AI # DINGBAT CIRCLED SANS-SERIF DIGIT FIVE +2785;AI # DINGBAT CIRCLED SANS-SERIF DIGIT SIX +2786;AI # DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN +2787;AI # DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT +2788;AI # DINGBAT CIRCLED SANS-SERIF DIGIT NINE +2789;AI # DINGBAT CIRCLED SANS-SERIF NUMBER TEN +278A;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE +278B;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO +278C;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE +278D;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR +278E;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE +278F;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX +2790;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN +2791;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT +2792;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE +2793;AI # DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN 2794;AL # HEAVY WIDE-HEADED RIGHTWARDS ARROW 2798;AL # HEAVY SOUTH EAST ARROW 2799;AL # HEAVY RIGHTWARDS ARROW diff --git a/lib/unicore/PropList.txt b/lib/unicore/PropList.txt index 90176ad..964c40a 100644 --- a/lib/unicore/PropList.txt +++ b/lib/unicore/PropList.txt @@ -1,17 +1,16 @@ -# PropList-4.0.0.txt -# Date: 2003-03-20, 20:07:40 GMT [MD] +# PropList-4.0.1.txt +# Date: 2004-03-02, 02:42:40 GMT [MD] # -# Unicode Character Database: Extended Properties +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see UCD.html -# Note: Unassigned and Noncharacter codepoints may be omitted -# if they have default property values. -# ================================================ # ================================================ -0009..000D ; White_Space # Cc [5] .. +0009..000D ; White_Space # Cc [5] .. 0020 ; White_Space # Zs SPACE -0085 ; White_Space # Cc +0085 ; White_Space # Cc 00A0 ; White_Space # Zs NO-BREAK SPACE 1680 ; White_Space # Zs OGHAM SPACE MARK 180E ; White_Space # Zs MONGOLIAN VOWEL SEPARATOR @@ -112,6 +111,7 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET 037E ; Terminal_Punctuation # Po GREEK QUESTION MARK 0387 ; Terminal_Punctuation # Po GREEK ANO TELEIA 0589 ; Terminal_Punctuation # Po ARMENIAN FULL STOP +05C3 ; Terminal_Punctuation # Po HEBREW PUNCTUATION SOF PASUQ 060C ; Terminal_Punctuation # Po ARABIC COMMA 061B ; Terminal_Punctuation # Po ARABIC SEMICOLON 061F ; Terminal_Punctuation # Po ARABIC QUESTION MARK @@ -120,6 +120,8 @@ FF63 ; Quotation_Mark # Pe HALFWIDTH RIGHT CORNER BRACKET 070C ; Terminal_Punctuation # Po SYRIAC HARKLEAN METOBELUS 0964..0965 ; Terminal_Punctuation # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA 0E5A..0E5B ; Terminal_Punctuation # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT +0F08 ; Terminal_Punctuation # Po TIBETAN MARK SBRUL SHAD +0F0D..0F12 ; Terminal_Punctuation # Po [6] TIBETAN MARK SHAD..TIBETAN MARK RGYA GRAM SHAD 104A..104B ; Terminal_Punctuation # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION 1361..1368 ; Terminal_Punctuation # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR 166D..166E ; Terminal_Punctuation # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP @@ -142,63 +144,80 @@ FF1F ; Terminal_Punctuation # Po FULLWIDTH QUESTION MARK FF61 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC FULL STOP FF64 ; Terminal_Punctuation # Po HALFWIDTH IDEOGRAPHIC COMMA -# Total code points: 78 +# Total code points: 86 # ================================================ -0028 ; Other_Math # Ps LEFT PARENTHESIS -0029 ; Other_Math # Pe RIGHT PARENTHESIS -002A ; Other_Math # Po ASTERISK -002D ; Other_Math # Pd HYPHEN-MINUS -002F ; Other_Math # Po SOLIDUS -005B ; Other_Math # Ps LEFT SQUARE BRACKET -005C ; Other_Math # Po REVERSE SOLIDUS -005D ; Other_Math # Pe RIGHT SQUARE BRACKET 005E ; Other_Math # Sk CIRCUMFLEX ACCENT -007B ; Other_Math # Ps LEFT CURLY BRACKET -007D ; Other_Math # Pe RIGHT CURLY BRACKET +03D0..03D2 ; Other_Math # L& [3] GREEK BETA SYMBOL..GREEK UPSILON WITH HOOK SYMBOL +03D5 ; Other_Math # L& GREEK PHI SYMBOL +03F0..03F1 ; Other_Math # L& [2] GREEK KAPPA SYMBOL..GREEK RHO SYMBOL +03F4..03F5 ; Other_Math # L& [2] GREEK CAPITAL THETA SYMBOL..GREEK LUNATE EPSILON SYMBOL 2016 ; Other_Math # Po DOUBLE VERTICAL LINE 2032..2034 ; Other_Math # Po [3] PRIME..TRIPLE PRIME +2040 ; Other_Math # Pc CHARACTER TIE +2061..2063 ; Other_Math # Cf [3] FUNCTION APPLICATION..INVISIBLE SEPARATOR 207D ; Other_Math # Ps SUPERSCRIPT LEFT PARENTHESIS 207E ; Other_Math # Pe SUPERSCRIPT RIGHT PARENTHESIS 208D ; Other_Math # Ps SUBSCRIPT LEFT PARENTHESIS 208E ; Other_Math # Pe SUBSCRIPT RIGHT PARENTHESIS 20D0..20DC ; Other_Math # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE 20E1 ; Other_Math # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E5..20E6 ; Other_Math # Mn [2] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING DOUBLE VERTICAL STROKE OVERLAY 2102 ; Other_Math # L& DOUBLE-STRUCK CAPITAL C 210A..2113 ; Other_Math # L& [10] SCRIPT SMALL G..SCRIPT SMALL L 2115 ; Other_Math # L& DOUBLE-STRUCK CAPITAL N 2119..211D ; Other_Math # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R 2124 ; Other_Math # L& DOUBLE-STRUCK CAPITAL Z 2128 ; Other_Math # L& BLACK-LETTER CAPITAL Z +2129 ; Other_Math # So TURNED GREEK SMALL LETTER IOTA 212C..212D ; Other_Math # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C 212F..2131 ; Other_Math # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F 2133..2134 ; Other_Math # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O 2135..2138 ; Other_Math # Lo [4] ALEF SYMBOL..DALET SYMBOL -FE35 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS -FE36 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS -FE37 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET -FE38 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET -FE47 ; Other_Math # Ps PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET -FE48 ; Other_Math # Pe PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET -FE59 ; Other_Math # Ps SMALL LEFT PARENTHESIS -FE5A ; Other_Math # Pe SMALL RIGHT PARENTHESIS -FE5B ; Other_Math # Ps SMALL LEFT CURLY BRACKET -FE5C ; Other_Math # Pe SMALL RIGHT CURLY BRACKET +213D..213F ; Other_Math # L& [3] DOUBLE-STRUCK SMALL GAMMA..DOUBLE-STRUCK CAPITAL PI +2145..2149 ; Other_Math # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J +23B7 ; Other_Math # So RADICAL SYMBOL BOTTOM +23D0 ; Other_Math # So VERTICAL LINE EXTENSION +27E6 ; Other_Math # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET +27E7 ; Other_Math # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET +27E8 ; Other_Math # Ps MATHEMATICAL LEFT ANGLE BRACKET +27E9 ; Other_Math # Pe MATHEMATICAL RIGHT ANGLE BRACKET +27EA ; Other_Math # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET +27EB ; Other_Math # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET +2983 ; Other_Math # Ps LEFT WHITE CURLY BRACKET +2984 ; Other_Math # Pe RIGHT WHITE CURLY BRACKET +2985 ; Other_Math # Ps LEFT WHITE PARENTHESIS +2986 ; Other_Math # Pe RIGHT WHITE PARENTHESIS +2987 ; Other_Math # Ps Z NOTATION LEFT IMAGE BRACKET +2988 ; Other_Math # Pe Z NOTATION RIGHT IMAGE BRACKET +2989 ; Other_Math # Ps Z NOTATION LEFT BINDING BRACKET +298A ; Other_Math # Pe Z NOTATION RIGHT BINDING BRACKET +298B ; Other_Math # Ps LEFT SQUARE BRACKET WITH UNDERBAR +298C ; Other_Math # Pe RIGHT SQUARE BRACKET WITH UNDERBAR +298D ; Other_Math # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +298E ; Other_Math # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +298F ; Other_Math # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +2990 ; Other_Math # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +2991 ; Other_Math # Ps LEFT ANGLE BRACKET WITH DOT +2992 ; Other_Math # Pe RIGHT ANGLE BRACKET WITH DOT +2993 ; Other_Math # Ps LEFT ARC LESS-THAN BRACKET +2994 ; Other_Math # Pe RIGHT ARC GREATER-THAN BRACKET +2995 ; Other_Math # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET +2996 ; Other_Math # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET +2997 ; Other_Math # Ps LEFT BLACK TORTOISE SHELL BRACKET +2998 ; Other_Math # Pe RIGHT BLACK TORTOISE SHELL BRACKET +29D8 ; Other_Math # Ps LEFT WIGGLY FENCE +29D9 ; Other_Math # Pe RIGHT WIGGLY FENCE +29DA ; Other_Math # Ps LEFT DOUBLE WIGGLY FENCE +29DB ; Other_Math # Pe RIGHT DOUBLE WIGGLY FENCE +29FC ; Other_Math # Ps LEFT-POINTING CURVED ANGLE BRACKET +29FD ; Other_Math # Pe RIGHT-POINTING CURVED ANGLE BRACKET FE61 ; Other_Math # Po SMALL ASTERISK FE63 ; Other_Math # Pd SMALL HYPHEN-MINUS FE68 ; Other_Math # Po SMALL REVERSE SOLIDUS -FF08 ; Other_Math # Ps FULLWIDTH LEFT PARENTHESIS -FF09 ; Other_Math # Pe FULLWIDTH RIGHT PARENTHESIS -FF0A ; Other_Math # Po FULLWIDTH ASTERISK -FF0D ; Other_Math # Pd FULLWIDTH HYPHEN-MINUS -FF0F ; Other_Math # Po FULLWIDTH SOLIDUS -FF3B ; Other_Math # Ps FULLWIDTH LEFT SQUARE BRACKET FF3C ; Other_Math # Po FULLWIDTH REVERSE SOLIDUS -FF3D ; Other_Math # Pe FULLWIDTH RIGHT SQUARE BRACKET FF3E ; Other_Math # Sk FULLWIDTH CIRCUMFLEX ACCENT -FF5B ; Other_Math # Ps FULLWIDTH LEFT CURLY BRACKET -FF5D ; Other_Math # Pe FULLWIDTH RIGHT CURLY BRACKET 1D400..1D454 ; Other_Math # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G 1D456..1D49C ; Other_Math # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A 1D49E..1D49F ; Other_Math # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D @@ -231,7 +250,7 @@ FF5D ; Other_Math # Pe FULLWIDTH RIGHT CURLY BRACKET 1D7C4..1D7C9 ; Other_Math # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL 1D7CE..1D7FF ; Other_Math # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE -# Total code points: 1069 +# Total code points: 1099 # ================================================ @@ -537,24 +556,24 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND # ================================================ -FDD0..FDEF ; Noncharacter_Code_Point # Cn [32] -FFFE..FFFF ; Noncharacter_Code_Point # Cn [2] -1FFFE..1FFFF ; Noncharacter_Code_Point # Cn [2] -2FFFE..2FFFF ; Noncharacter_Code_Point # Cn [2] -3FFFE..3FFFF ; Noncharacter_Code_Point # Cn [2] -4FFFE..4FFFF ; Noncharacter_Code_Point # Cn [2] -5FFFE..5FFFF ; Noncharacter_Code_Point # Cn [2] -6FFFE..6FFFF ; Noncharacter_Code_Point # Cn [2] -7FFFE..7FFFF ; Noncharacter_Code_Point # Cn [2] -8FFFE..8FFFF ; Noncharacter_Code_Point # Cn [2] -9FFFE..9FFFF ; Noncharacter_Code_Point # Cn [2] -AFFFE..AFFFF ; Noncharacter_Code_Point # Cn [2] -BFFFE..BFFFF ; Noncharacter_Code_Point # Cn [2] -CFFFE..CFFFF ; Noncharacter_Code_Point # Cn [2] -DFFFE..DFFFF ; Noncharacter_Code_Point # Cn [2] -EFFFE..EFFFF ; Noncharacter_Code_Point # Cn [2] -FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] -10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2] +FDD0..FDEF ; Noncharacter_Code_Point # Cn [32] .. +FFFE..FFFF ; Noncharacter_Code_Point # Cn [2] .. +1FFFE..1FFFF ; Noncharacter_Code_Point # Cn [2] .. +2FFFE..2FFFF ; Noncharacter_Code_Point # Cn [2] .. +3FFFE..3FFFF ; Noncharacter_Code_Point # Cn [2] .. +4FFFE..4FFFF ; Noncharacter_Code_Point # Cn [2] .. +5FFFE..5FFFF ; Noncharacter_Code_Point # Cn [2] .. +6FFFE..6FFFF ; Noncharacter_Code_Point # Cn [2] .. +7FFFE..7FFFF ; Noncharacter_Code_Point # Cn [2] .. +8FFFE..8FFFF ; Noncharacter_Code_Point # Cn [2] .. +9FFFE..9FFFF ; Noncharacter_Code_Point # Cn [2] .. +AFFFE..AFFFF ; Noncharacter_Code_Point # Cn [2] .. +BFFFE..BFFFF ; Noncharacter_Code_Point # Cn [2] .. +CFFFE..CFFFF ; Noncharacter_Code_Point # Cn [2] .. +DFFFE..DFFFF ; Noncharacter_Code_Point # Cn [2] .. +EFFFE..EFFFF ; Noncharacter_Code_Point # Cn [2] .. +FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] .. +10FFFE..10FFFF; Noncharacter_Code_Point # Cn [2] .. # Total code points: 66 @@ -572,10 +591,11 @@ FFFFE..FFFFF ; Noncharacter_Code_Point # Cn [2] 0D57 ; Other_Grapheme_Extend # Mc MALAYALAM AU LENGTH MARK 0DCF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN AELA-PILLA 0DDF ; Other_Grapheme_Extend # Mc SINHALA VOWEL SIGN GAYANUKITTA +200C..200D ; Other_Grapheme_Extend # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER 1D165 ; Other_Grapheme_Extend # Mc MUSICAL SYMBOL COMBINING STEM 1D16E..1D16F ; Other_Grapheme_Extend # Mc [2] MUSICAL SYMBOL COMBINING FLAG-1..MUSICAL SYMBOL COMBINING FLAG-2 -# Total code points: 16 +# Total code points: 18 # ================================================ @@ -636,20 +656,17 @@ FA27..FA29 ; Unified_Ideograph # Lo [3] CJK COMPATIBILITY IDEOGRAPH-FA27..C 034F ; Other_Default_Ignorable_Code_Point # Mn COMBINING GRAPHEME JOINER 115F..1160 ; Other_Default_Ignorable_Code_Point # Lo [2] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG FILLER -180B..180D ; Other_Default_Ignorable_Code_Point # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE -200B ; Other_Default_Ignorable_Code_Point # Zs ZERO WIDTH SPACE -2064..2069 ; Other_Default_Ignorable_Code_Point # Cn [6] +200B ; Other_Default_Ignorable_Code_Point # Cf ZERO WIDTH SPACE +2064..2069 ; Other_Default_Ignorable_Code_Point # Cn [6] .. 3164 ; Other_Default_Ignorable_Code_Point # Lo HANGUL FILLER -FE00..FE0F ; Other_Default_Ignorable_Code_Point # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 FFA0 ; Other_Default_Ignorable_Code_Point # Lo HALFWIDTH HANGUL FILLER -FFF0..FFF8 ; Other_Default_Ignorable_Code_Point # Cn [9] -E0000 ; Other_Default_Ignorable_Code_Point # Cn -E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] -E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] -E0100..E01EF ; Other_Default_Ignorable_Code_Point # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] +FFF0..FFF8 ; Other_Default_Ignorable_Code_Point # Cn [9] .. +E0000 ; Other_Default_Ignorable_Code_Point # Cn +E0002..E001F ; Other_Default_Ignorable_Code_Point # Cn [30] .. +E0080..E00FF ; Other_Default_Ignorable_Code_Point # Cn [128] .. +E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] .. -# Total code points: 4039 +# Total code points: 3780 # ================================================ @@ -665,14 +682,31 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] 0069..006A ; Soft_Dotted # L& [2] LATIN SMALL LETTER I..LATIN SMALL LETTER J 012F ; Soft_Dotted # L& LATIN SMALL LETTER I WITH OGONEK 0268 ; Soft_Dotted # L& LATIN SMALL LETTER I WITH STROKE +029D ; Soft_Dotted # L& LATIN SMALL LETTER J WITH CROSSED-TAIL +02B2 ; Soft_Dotted # Lm MODIFIER LETTER SMALL J +03F3 ; Soft_Dotted # L& GREEK LETTER YOT 0456 ; Soft_Dotted # L& CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I 0458 ; Soft_Dotted # L& CYRILLIC SMALL LETTER JE 1D62 ; Soft_Dotted # L& LATIN SUBSCRIPT SMALL LETTER I 1E2D ; Soft_Dotted # L& LATIN SMALL LETTER I WITH TILDE BELOW 1ECB ; Soft_Dotted # L& LATIN SMALL LETTER I WITH DOT BELOW 2071 ; Soft_Dotted # L& SUPERSCRIPT LATIN SMALL LETTER I - -# Total code points: 10 +2148..2149 ; Soft_Dotted # L& [2] DOUBLE-STRUCK ITALIC SMALL I..DOUBLE-STRUCK ITALIC SMALL J +1D422..1D423 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SMALL I..MATHEMATICAL BOLD SMALL J +1D456..1D457 ; Soft_Dotted # L& [2] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL ITALIC SMALL J +1D48A..1D48B ; Soft_Dotted # L& [2] MATHEMATICAL BOLD ITALIC SMALL I..MATHEMATICAL BOLD ITALIC SMALL J +1D4BE..1D4BF ; Soft_Dotted # L& [2] MATHEMATICAL SCRIPT SMALL I..MATHEMATICAL SCRIPT SMALL J +1D4F2..1D4F3 ; Soft_Dotted # L& [2] MATHEMATICAL BOLD SCRIPT SMALL I..MATHEMATICAL BOLD SCRIPT SMALL J +1D526..1D527 ; Soft_Dotted # L& [2] MATHEMATICAL FRAKTUR SMALL I..MATHEMATICAL FRAKTUR SMALL J +1D55A..1D55B ; Soft_Dotted # L& [2] MATHEMATICAL DOUBLE-STRUCK SMALL I..MATHEMATICAL DOUBLE-STRUCK SMALL J +1D58E..1D58F ; Soft_Dotted # L& [2] MATHEMATICAL BOLD FRAKTUR SMALL I..MATHEMATICAL BOLD FRAKTUR SMALL J +1D5C2..1D5C3 ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF SMALL I..MATHEMATICAL SANS-SERIF SMALL J +1D5F6..1D5F7 ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD SMALL I..MATHEMATICAL SANS-SERIF BOLD SMALL J +1D62A..1D62B ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF ITALIC SMALL I..MATHEMATICAL SANS-SERIF ITALIC SMALL J +1D65E..1D65F ; Soft_Dotted # L& [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J +1D692..1D693 ; Soft_Dotted # L& [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J + +# Total code points: 41 # ================================================ @@ -689,3 +723,41 @@ E01F0..E0FFF ; Other_Default_Ignorable_Code_Point # Cn [3600] # Total code points: 4 +# ================================================ + +0021 ; STerm # Po EXCLAMATION MARK +002E ; STerm # Po FULL STOP +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 +0700..0702 ; STerm # Po [3] SYRIAC END OF PARAGRAPH..SYRIAC SUBLINEAR FULL STOP +0964..0965 ; STerm # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA +104A..104B ; STerm # Po [2] MYANMAR SIGN LITTLE SECTION..MYANMAR SIGN SECTION +1362 ; STerm # Po ETHIOPIC FULL STOP +1367..1368 ; STerm # Po [2] ETHIOPIC QUESTION MARK..ETHIOPIC PARAGRAPH SEPARATOR +166E ; STerm # Po CANADIAN SYLLABICS FULL STOP +1803 ; STerm # Po MONGOLIAN FULL STOP +1809 ; STerm # Po MONGOLIAN MANCHU FULL STOP +1944..1945 ; STerm # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK +203C..203D ; STerm # Po [2] DOUBLE EXCLAMATION MARK..INTERROBANG +2047..2049 ; STerm # Po [3] DOUBLE QUESTION MARK..EXCLAMATION QUESTION MARK +3002 ; STerm # Po IDEOGRAPHIC FULL STOP +FE52 ; STerm # Po SMALL FULL STOP +FE56..FE57 ; STerm # Po [2] SMALL QUESTION MARK..SMALL EXCLAMATION MARK +FF01 ; STerm # Po FULLWIDTH EXCLAMATION MARK +FF0E ; STerm # Po FULLWIDTH FULL STOP +FF1F ; STerm # Po FULLWIDTH QUESTION MARK +FF61 ; STerm # Po HALFWIDTH IDEOGRAPHIC FULL STOP + +# Total code points: 36 + +# ================================================ + +180B..180D ; Variation_Selector # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +FE00..FE0F ; Variation_Selector # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 259 diff --git a/lib/unicore/PropValueAliases.txt b/lib/unicore/PropValueAliases.txt index fe82f23..74460d5 100644 --- a/lib/unicore/PropValueAliases.txt +++ b/lib/unicore/PropValueAliases.txt @@ -1,6 +1,10 @@ -# PropertyValueAliases-4.0.0.txt -# Date: 2003-03-12, 23:46:08 GMT [MD] +# PropertyValueAliases-4.0.1.txt +# Date: 2004-03-02, 19:46:47 GMT [MD] # +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html # This file contains aliases for property values used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression # property tests, and other programmatic textual descriptions of Unicode data. @@ -12,11 +16,10 @@ # FORMAT # # Each line describes a property value name. -# This consists of three fields, separated by semicolons. +# This consists of three or more fields, separated by semicolons. # # First Field: The first field describes the property for which that # property value name is used. -# There is one special pseudo-property: "qc" stands for any quick-check property # # Second Field: The second field is an abbreviated name. # If there is no abbreviated name available, the field is marked with "n/a". @@ -26,32 +29,44 @@ # In the case of ccc, there are 4 fields. The second field is numeric, third # is abbreviated, and fourth is long. # -# With loose matching of property names, the case distinctions, whitespace, -# and '_' are ignored. +# The above are the preferred aliases. Other aliases may be listed in additional fields. # -# NOTE: Currently there is at most one abbreviated name and one long name for -# property value. However, in the future additional aliases may be added. -# In such a case, the first line for the property value would have -# the preferred alias for output. +# Loose matching should be applied to all property names and property values, with +# the exception of String Property values. With loose matching of property names and +# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property +# values, numeric equivalencies are applied: thus "01.00" is equivalent to "1". # -# NOTE: The property value names are NOT unique across properties, especially -# with loose matches. For example: +# NOTE: Property value names are NOT unique across properties. For example: # -# AL means Arabic Letter for the Bidi_Class property, and -# AL means Alpha_Left for the Combining_Class property, and -# AL means Alphabetic for the Line_Break property. +# AL means Arabic Letter for the Bidi_Class property, and +# AL means Alpha_Left for the Combining_Class property, and +# AL means Alphabetic for the Line_Break property. # # In addition, some property names may be the same as some property value names. # For example: # -# cc means Combining_Class property, and -# cc means the General_Category property value Control (cc) +# sc means the Script property, and +# Sc means the General_Category property value Currency_Symbol (Sc) # # The combination of property value and property name is, however, unique. -# For more information, see UTR #18: Regular Expression Guidelines +# +# For more information, see UTS #18: Regular Expression Guidelines # ================================================ +# Age (age) + +age; n/a ; 1.1 +age; n/a ; 2.0 +age; n/a ; 2.1 +age; n/a ; 3.0 +age; n/a ; 3.1 +age; n/a ; 3.2 +age; n/a ; 4.0 +age; n/a ; unassigned + +# Bidi_Class (bc) + bc ; AL ; Arabic_Letter bc ; AN ; Arabic_Number bc ; B ; Paragraph_Separator @@ -72,6 +87,8 @@ bc ; RLO ; Right_To_Left_Override bc ; S ; Segment_Separator bc ; WS ; White_Space +# Block (blk) + blk; n/a ; Aegean_Numbers blk; n/a ; Alphabetic_Presentation_Forms blk; n/a ; Arabic @@ -105,7 +122,7 @@ blk; n/a ; Control_Pictures blk; n/a ; Currency_Symbols blk; n/a ; Cypriot_Syllabary blk; n/a ; Cyrillic -blk; n/a ; Cyrillic_Supplementary +blk; n/a ; Cyrillic_Supplement ; Cyrillic_Supplementary blk; n/a ; Deseret blk; n/a ; Devanagari blk; n/a ; Dingbats @@ -139,10 +156,10 @@ blk; n/a ; Katakana_Phonetic_Extensions blk; n/a ; Khmer blk; n/a ; Khmer_Symbols blk; n/a ; Lao -blk; n/a ; Latin_Extended_Additional +blk; n/a ; Latin-1_Supplement blk; n/a ; Latin_Extended-A blk; n/a ; Latin_Extended-B -blk; n/a ; Latin-1_Supplement +blk; n/a ; Latin_Extended_Additional blk; n/a ; Letterlike_Symbols blk; n/a ; Limbu blk; n/a ; Linear_B_Ideograms @@ -199,8 +216,14 @@ blk; n/a ; Yi_Radicals blk; n/a ; Yi_Syllables blk; n/a ; Yijing_Hexagram_Symbols +# Canonical_Combining_Class (ccc) + ccc; 0; NR ; Not_Reordered ccc; 1; OV ; Overlay +ccc; 7; NK ; Nukta +ccc; 8; KV ; Kana_Voicing +ccc; 9; VR ; Virama +ccc; 200; ATBL ; Attached_Below_Left ccc; 202; ATB ; Attached_Below ccc; 216; ATAR ; Attached_Above_Right ccc; 218; BL ; Below_Left @@ -214,28 +237,29 @@ ccc; 232; AR ; Above_Right ccc; 233; DB ; Double_Below ccc; 234; DA ; Double_Above ccc; 240; IS ; Iota_Subscript -ccc; 7; NK ; Nukta -ccc; 8; KV ; Kana_Voicing -ccc; 9; VR ; Virama -dt ; can ; canonical -dt ; com ; compat -dt ; enc ; circle -dt ; fin ; final -dt ; font ; font -dt ; fra ; fraction -dt ; init ; initial -dt ; iso ; isolated -dt ; med ; medial -dt ; n/a ; none -dt ; nar ; narrow -dt ; nb ; noBreak -dt ; sml ; small -dt ; sqr ; square -dt ; sub ; sub -dt ; sup ; super -dt ; vert ; vertical -dt ; wide ; wide +# Decomposition_Type (dt) + +dt ; can ; Canonical +dt ; com ; Compat +dt ; enc ; Circle +dt ; fin ; Final +dt ; font ; Font +dt ; fra ; Fraction +dt ; init ; Initial +dt ; iso ; Isolated +dt ; med ; Medial +dt ; nar ; Narrow +dt ; nb ; Nobreak +dt ; none ; None +dt ; sml ; Small +dt ; sqr ; Square +dt ; sub ; Sub +dt ; sup ; Super +dt ; vert ; Vertical +dt ; wide ; Wide + +# East_Asian_Width (ea) ea ; A ; Ambiguous ea ; F ; Fullwidth @@ -244,6 +268,8 @@ ea ; N ; Neutral ea ; Na ; Narrow ea ; W ; Wide +# General_Category (gc) + gc ; C ; Other # Cc | Cf | Cn | Co | Cs gc ; Cc ; Control gc ; Cf ; Format @@ -283,6 +309,8 @@ gc ; Zl ; Line_Separator gc ; Zp ; Paragraph_Separator gc ; Zs ; Space_Separator +# Hangul_Syllable_Type (hst) + hst; L ; Leading_Jamo hst; LV ; LV_Syllable hst; LVT ; LVT_Syllable @@ -290,60 +318,64 @@ hst; NA ; Not_Applicable hst; T ; Trailing_Jamo hst; V ; Vowel_Jamo -jg ; n/a ; AIN -jg ; n/a ; ALAPH -jg ; n/a ; ALEF -jg ; n/a ; BEH -jg ; n/a ; BETH -jg ; n/a ; DAL -jg ; n/a ; DALATH_RISH +# Joining_Group (jg) + +jg ; n/a ; Ain +jg ; n/a ; Alaph +jg ; n/a ; Alef +jg ; n/a ; Beh +jg ; n/a ; Beth +jg ; n/a ; Dal +jg ; n/a ; Dalath_Rish jg ; n/a ; E -jg ; n/a ; FE -jg ; n/a ; FEH -jg ; n/a ; FINAL_SEMKATH -jg ; n/a ; GAF -jg ; n/a ; GAMAL -jg ; n/a ; HAH -jg ; n/a ; HAMZA_ON_HEH_GOAL -jg ; n/a ; HE -jg ; n/a ; HEH -jg ; n/a ; HEH_GOAL -jg ; n/a ; HETH -jg ; n/a ; KAF -jg ; n/a ; KAPH -jg ; n/a ; KHAPH -jg ; n/a ; KNOTTED_HEH -jg ; n/a ; LAM -jg ; n/a ; LAMADH -jg ; n/a ; MEEM -jg ; n/a ; MIM -jg ; n/a ; NO_JOINING_GROUP -jg ; n/a ; NOON -jg ; n/a ; NUN -jg ; n/a ; PE -jg ; n/a ; QAF -jg ; n/a ; QAPH -jg ; n/a ; REH -jg ; n/a ; REVERSED_PE -jg ; n/a ; SAD -jg ; n/a ; SADHE -jg ; n/a ; SEEN -jg ; n/a ; SEMKATH -jg ; n/a ; SHIN -jg ; n/a ; SWASH_KAF -jg ; n/a ; SYRIAC_WAW -jg ; n/a ; TAH -jg ; n/a ; TAW -jg ; n/a ; TEH_MARBUTA -jg ; n/a ; TETH -jg ; n/a ; WAW -jg ; n/a ; YEH -jg ; n/a ; YEH_BARREE -jg ; n/a ; YEH_WITH_TAIL -jg ; n/a ; YUDH -jg ; n/a ; YUDH_HE -jg ; n/a ; ZAIN -jg ; n/a ; ZHAIN +jg ; n/a ; Fe +jg ; n/a ; Feh +jg ; n/a ; Final_Semkath +jg ; n/a ; Gaf +jg ; n/a ; Gamal +jg ; n/a ; Hah +jg ; n/a ; Hamza_On_Heh_Goal +jg ; n/a ; He +jg ; n/a ; Heh +jg ; n/a ; Heh_Goal +jg ; n/a ; Heth +jg ; n/a ; Kaf +jg ; n/a ; Kaph +jg ; n/a ; Khaph +jg ; n/a ; Knotted_Heh +jg ; n/a ; Lam +jg ; n/a ; Lamadh +jg ; n/a ; Meem +jg ; n/a ; Mim +jg ; n/a ; No_Joining_Group +jg ; n/a ; Noon +jg ; n/a ; Nun +jg ; n/a ; Pe +jg ; n/a ; Qaf +jg ; n/a ; Qaph +jg ; n/a ; Reh +jg ; n/a ; Reversed_Pe +jg ; n/a ; Sad +jg ; n/a ; Sadhe +jg ; n/a ; Seen +jg ; n/a ; Semkath +jg ; n/a ; Shin +jg ; n/a ; Swash_Kaf +jg ; n/a ; Syriac_Waw +jg ; n/a ; Tah +jg ; n/a ; Taw +jg ; n/a ; Teh_Marbuta +jg ; n/a ; Teth +jg ; n/a ; Waw +jg ; n/a ; Yeh +jg ; n/a ; Yeh_Barree +jg ; n/a ; Yeh_With_Tail +jg ; n/a ; Yudh +jg ; n/a ; Yudh_He +jg ; n/a ; Zain +jg ; n/a ; Zhain + +# Joining_Type (jt) jt ; C ; Join_Causing jt ; D ; Dual_Joining @@ -352,6 +384,8 @@ jt ; R ; Right_Joining jt ; T ; Transparent jt ; U ; Non_Joining +# Line_Break (lb) + lb ; AI ; Ambiguous lb ; AL ; Alphabetic lb ; B2 ; Break_Both @@ -366,7 +400,7 @@ lb ; EX ; Exclamation lb ; GL ; Glue lb ; HY ; Hyphen lb ; ID ; Ideographic -lb ; IN ; Inseperable +lb ; IN ; Inseparable ; Inseperable lb ; IS ; Infix_Numeric lb ; LF ; Line_Feed lb ; NL ; Next_Line @@ -384,14 +418,36 @@ lb ; WJ ; Word_Joiner lb ; XX ; Unknown lb ; ZW ; ZWSpace -nt ; de ; Decimal -nt ; di ; Digit -nt ; n/a ; None -nt ; nu ; Numeric +# NFC_Quick_Check (NFC_QC) + +NFC_QC; M ; Maybe +NFC_QC; N ; No +NFC_QC; Y ; Yes + +# NFD_Quick_Check (NFD_QC) + +NFD_QC; N ; No +NFD_QC; Y ; Yes + +# NFKC_Quick_Check (NFKC_QC) + +NFKC_QC; M ; Maybe +NFKC_QC; N ; No +NFKC_QC; Y ; Yes + +# NFKD_Quick_Check (NFKD_QC) + +NFKD_QC; N ; No +NFKD_QC; Y ; Yes + +# Numeric_Type (nt) + +nt ; De ; Decimal +nt ; Di ; Digit +nt ; None ; None +nt ; Nu ; Numeric -qc ; M ; Maybe -qc ; N ; No -qc ; Y ; Yes +# Script (sc) sc ; Arab ; Arabic sc ; Armn ; Armenian @@ -416,6 +472,7 @@ sc ; Hani ; Han sc ; Hano ; Hanunoo sc ; Hebr ; Hebrew sc ; Hira ; Hiragana +sc ; Hrkt ; Katakana_Or_Hiragana sc ; Ital ; Old_Italic sc ; Kana ; Katakana sc ; Khmr ; Khmer diff --git a/lib/unicore/Properties b/lib/unicore/Properties index 963c625..50789db 100644 --- a/lib/unicore/Properties +++ b/lib/unicore/Properties @@ -11,11 +11,11 @@ \p{Alpha} [[:Alpha:]] \p{Any} Alias for \p{Any} ([\x{0000}-\x{10FFFF}]) \p{Any} [\x{0000}-\x{10FFFF}] -* \p{Arabic} Script 'ARABIC' -* \p{Armenian} Script 'ARMENIAN' +* \p{Arabic} Script 'Arabic' +* \p{Armenian} Script 'Armenian' * \p{AsciiHexDigit} Extended property 'ASCII_Hex_Digit' \p{Assigned} All assigned code points -* \p{Bengali} Script 'BENGALI' +* \p{Bengali} Script 'Bengali' \p{BidiAL} Bi-directional category 'AL' \p{BidiAN} Bi-directional category 'AN' \p{BidiBN} Bi-directional category 'BN' @@ -37,27 +37,27 @@ \p{BidiS} Bi-directional category 'S' \p{BidiWS} Bi-directional category 'WS' \p{Blank} [[:Blank:]] -* \p{Bopomofo} Script 'BOPOMOFO' -* \p{Braille} Script 'BRAILLE' -* \p{Buhid} Script 'BUHID' -* \p{CanadianAboriginal} Script 'CANADIAN_ABORIGINAL' +* \p{Bopomofo} Script 'Bopomofo' +* \p{Braille} Script 'Braille' +* \p{Buhid} Script 'Buhid' +* \p{CanadianAboriginal} Script 'Canadian_Aboriginal' \p{Canon} Decomposes to multiple characters * \p{Cc} Alias for \p{Cc} (General Category 'Cc') \p{Cc} General Category 'Cc' * \p{Cf} Alias for \p{Cf} (General Category 'Cf') \p{Cf} General Category 'Cf' -* \p{Cherokee} Script 'CHEROKEE' +* \p{Cherokee} Script 'Cherokee' \p{Cntrl} [[:Cntrl:]] * \p{Cn} Alias for \p{Cn} (General Category 'Cn' [not functional in Perl]) \p{Cn} General Category 'Cn' [not functional in Perl] -* \p{Common} Pseudo-Script of codepoints not in other Unicode scripts +* \p{Common} Script 'Common' \p{Compat} Compatible with a more-basic character * \p{Co} Alias for \p{Co} (General Category 'Co') \p{Co} General Category 'Co' * \p{Cs} Alias for \p{Cs} (General Category 'Cs') \p{Cs} General Category 'Cs' -* \p{Cypriot} Script 'CYPRIOT' -* \p{Cyrillic} Script 'CYRILLIC' +* \p{Cypriot} Script 'Cypriot' +* \p{Cyrillic} Script 'Cyrillic' * \p{C} Alias for \p{C} (Major Category 'C') \p{C} Major Category 'C' \p{DCcircle} Compatible with 'circle' @@ -78,25 +78,25 @@ \p{DCwide} Compatible with 'wide' * \p{Dash} Extended property 'Dash' * \p{Deprecated} Extended property 'Deprecated' -* \p{Deseret} Script 'DESERET' -* \p{Devanagari} Script 'DEVANAGARI' +* \p{Deseret} Script 'Deseret' +* \p{Devanagari} Script 'Devanagari' * \p{Diacritic} Extended property 'Diacritic' \p{Digit} [[:Digit:]] -* \p{Ethiopic} Script 'ETHIOPIC' +* \p{Ethiopic} Script 'Ethiopic' * \p{Extender} Extended property 'Extender' -* \p{Georgian} Script 'GEORGIAN' -* \p{Gothic} Script 'GOTHIC' +* \p{Georgian} Script 'Georgian' +* \p{Gothic} Script 'Gothic' * \p{GraphemeLink} Extended property 'Grapheme_Link' \p{Graph} [[:Graph:]] -* \p{Greek} Script 'GREEK' -* \p{Gujarati} Script 'GUJARATI' -* \p{Gurmukhi} Script 'GURMUKHI' -* \p{Hangul} Script 'HANGUL' -* \p{Hanunoo} Script 'HANUNOO' -* \p{Han} Script 'HAN' -* \p{Hebrew} Script 'HEBREW' +* \p{Greek} Script 'Greek' +* \p{Gujarati} Script 'Gujarati' +* \p{Gurmukhi} Script 'Gurmukhi' +* \p{Hangul} Script 'Hangul' +* \p{Hanunoo} Script 'Hanunoo' +* \p{Han} Script 'Han' +* \p{Hebrew} Script 'Hebrew' * \p{HexDigit} Extended property 'Hex_Digit' -* \p{Hiragana} Script 'HIRAGANA' +* \p{Hiragana} Script 'Hiragana' * \p{Hyphen} Extended property 'Hyphen' * \p{IdContinue} [\p{ID_Start}\p{Mn}\p{Mc}\p{Nd}\p{Pc}] * \p{IdStart} [\p{Ll}\p{Lu}\p{Lt}\p{Lm}\p{Lo}\p{Nl}] @@ -135,7 +135,7 @@ * \p{InControlPictures} Block 'Control Pictures' * \p{InCurrencySymbols} Block 'Currency Symbols' * \p{InCypriotSyllabary} Block 'Cypriot Syllabary' -* \p{InCyrillicSupplementary} Block 'Cyrillic Supplementary' +* \p{InCyrillicSupplement} Block 'Cyrillic Supplement' * \p{InCyrillic} Block 'Cyrillic' * \p{InDeseret} Block 'Deseret' * \p{InDevanagari} Block 'Devanagari' @@ -228,16 +228,17 @@ * \p{InYiRadicals} Block 'Yi Radicals' * \p{InYiSyllables} Block 'Yi Syllables' * \p{InYijingHexagramSymbols} Block 'Yijing Hexagram Symbols' -* \p{Inherited} Script 'INHERITED' +* \p{Inherited} Script 'Inherited' * \p{JoinControl} Extended property 'Join_Control' -* \p{Kannada} Script 'KANNADA' -* \p{Katakana} Script 'KATAKANA' -* \p{Khmer} Script 'KHMER' +* \p{Kannada} Script 'Kannada' +* \p{KatakanaOrHiragana} Script 'Katakana_Or_Hiragana' +* \p{Katakana} Script 'Katakana' +* \p{Khmer} Script 'Khmer' \p{L&} [\p{Ll}\p{Lu}\p{Lt}] -* \p{Lao} Script 'LAO' -* \p{Latin} Script 'LATIN' -* \p{Limbu} Script 'LIMBU' -* \p{LinearB} Script 'LINEAR_B' +* \p{Lao} Script 'Lao' +* \p{Latin} Script 'Latin' +* \p{Limbu} Script 'Limbu' +* \p{LinearB} Script 'Linear_B' * \p{Ll} Alias for \p{Ll} (General Category 'Ll') \p{Ll} General Category 'Ll' * \p{Lm} Alias for \p{Lm} (General Category 'Lm') @@ -253,7 +254,7 @@ \p{Lu} General Category 'Lu' * \p{L} Alias for \p{L} (Major Category 'L') \p{L} Major Category 'L' -* \p{Malayalam} Script 'MALAYALAM' +* \p{Malayalam} Script 'Malayalam' * \p{Math} [\p{Sm}\p{OtherMath}] * \p{Mc} Alias for \p{Mc} (General Category 'Mc') \p{Mc} General Category 'Mc' @@ -262,8 +263,8 @@ \p{Mirrored} Mirrored in bidirectional text * \p{Mn} Alias for \p{Mn} (General Category 'Mn') \p{Mn} General Category 'Mn' -* \p{Mongolian} Script 'MONGOLIAN' -* \p{Myanmar} Script 'MYANMAR' +* \p{Mongolian} Script 'Mongolian' +* \p{Myanmar} Script 'Myanmar' * \p{M} Alias for \p{M} (Major Category 'M') \p{M} Major Category 'M' * \p{Nd} Alias for \p{Nd} (General Category 'Nd') @@ -275,10 +276,10 @@ \p{No} General Category 'No' * \p{N} Alias for \p{N} (Major Category 'N') \p{N} Major Category 'N' -* \p{Ogham} Script 'OGHAM' -* \p{OldItalic} Script 'OLD_ITALIC' -* \p{Oriya} Script 'ORIYA' -* \p{Osmanya} Script 'OSMANYA' +* \p{Ogham} Script 'Ogham' +* \p{OldItalic} Script 'Old_Italic' +* \p{Oriya} Script 'Oriya' +* \p{Osmanya} Script 'Osmanya' * \p{OtherAlphabetic} Extended property 'Other_Alphabetic' * \p{OtherDefaultIgnorableCodePoint} Extended property 'Other_Default_Ignorable_Code_Point' * \p{OtherGraphemeExtend} Extended property 'Other_Grapheme_Extend' @@ -306,11 +307,11 @@ \p{P} Major Category 'P' * \p{QuotationMark} Extended property 'Quotation_Mark' * \p{Radical} Extended property 'Radical' -* \p{Runic} Script 'RUNIC' +* \p{Runic} Script 'Runic' * \p{Sc} Alias for \p{Sc} (General Category 'Sc') \p{Sc} General Category 'Sc' -* \p{Shavian} Script 'SHAVIAN' -* \p{Sinhala} Script 'SINHALA' +* \p{Shavian} Script 'Shavian' +* \p{Sinhala} Script 'Sinhala' * \p{Sk} Alias for \p{Sk} (General Category 'Sk') \p{Sk} General Category 'Sk' * \p{Sm} Alias for \p{Sm} (General Category 'Sm') @@ -320,27 +321,29 @@ \p{So} General Category 'So' \p{SpacePerl} \s \p{Space} [[:Space:]] -* \p{Syriac} Script 'SYRIAC' +* \p{Sterm} Extended property 'STerm' +* \p{Syriac} Script 'Syriac' * \p{S} Alias for \p{S} (Major Category 'S') \p{S} Major Category 'S' -* \p{Tagalog} Script 'TAGALOG' -* \p{Tagbanwa} Script 'TAGBANWA' -* \p{TaiLe} Script 'TAI_LE' -* \p{Tamil} Script 'TAMIL' -* \p{Telugu} Script 'TELUGU' +* \p{Tagalog} Script 'Tagalog' +* \p{Tagbanwa} Script 'Tagbanwa' +* \p{TaiLe} Script 'Tai_Le' +* \p{Tamil} Script 'Tamil' +* \p{Telugu} Script 'Telugu' * \p{TerminalPunctuation} Extended property 'Terminal_Punctuation' -* \p{Thaana} Script 'THAANA' -* \p{Thai} Script 'THAI' -* \p{Tibetan} Script 'TIBETAN' +* \p{Thaana} Script 'Thaana' +* \p{Thai} Script 'Thai' +* \p{Tibetan} Script 'Tibetan' \p{Title} [[:Title:]] -* \p{Ugaritic} Script 'UGARITIC' +* \p{Ugaritic} Script 'Ugaritic' * \p{UnifiedIdeograph} Extended property 'Unified_Ideograph' * \p{Uppercase} [\p{Lu}\p{Other_Uppercase}] \p{Upper} [[:Upper:]] +* \p{VariationSelector} Extended property 'Variation_Selector' * \p{WhiteSpace} Extended property 'White_Space' \p{Word} [[:Word:]] \p{XDigit} [[:XDigit:]] -* \p{Yi} Script 'YI' +* \p{Yi} Script 'Yi' * \p{Zl} Alias for \p{Zl} (General Category 'Zl') \p{Zl} General Category 'Zl' * \p{Zp} Alias for \p{Zp} (General Category 'Zp') diff --git a/lib/unicore/PropertyAliases.txt b/lib/unicore/PropertyAliases.txt index 1195e8f..cf9950f 100644 --- a/lib/unicore/PropertyAliases.txt +++ b/lib/unicore/PropertyAliases.txt @@ -1,6 +1,10 @@ -# PropertyAliases-4.0.0.txt -# Date: 2003-03-12, 23:46:08 GMT [MD] +# PropertyAliases-4.0.1.txt +# Date: 2004-03-02, 19:47:55 GMT [MD] # +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html # This file contains aliases for properties used in the UCD. # These names can be used for XML formats of UCD data, for regular-expression # property tests, and other programmatic textual descriptions of Unicode data. @@ -11,46 +15,50 @@ # # FORMAT # -# Each line has two fields, separated by semicolons. +# Each line has two or more fields, separated by semicolons. # # First Field: The first field is an abbreviated name for the property. # # Second Field: The second field is a long name # -# With loose matching of property names, the case distinctions, whitespace, -# and '_' are ignored. +# The above are the preferred aliases. Other aliases may be listed in additional fields. # -# NOTE: Currently there is at most one abbreviated name and one long name for -# each property. However, in the future additional aliases may be added. +# Loose matching should be applied to all property names and property values, with +# the exception of String Property values. With loose matching of property names and +# values, the case distinctions, whitespace, and '_' are ignored. For Numeric Property +# values, numeric equivalencies are applied: thus "01.00" is equivalent to "1". # -# NOTE: The property value names are NOT unique across properties, especially -# with loose matches. For example: +# NOTE: Property value names are NOT unique across properties. For example: # # AL means Arabic Letter for the Bidi_Class property, and # AL means Alpha_Left for the Combining_Class property, and # AL means Alphabetic for the Line_Break property. # # In addition, some property names may be the same as some property value names. +# For example: +# +# sc means the Script property, and +# Sc means the General_Category property value Currency_Symbol (Sc) # # The combination of property value and property name is, however, unique. -# For more information, see UTR #18: Regular Expression Guidelines +# +# For more information, see UTS #18: Regular Expression Guidelines # ================================================ # ================================================ -# Non-enumerated Properties +# Numeric Properties +# ================================================ +nv ; Numeric_Value + +# ================================================ +# String Properties # ================================================ -age ; Age -blk ; Block bmg ; Bidi_Mirroring_Glyph cf ; Case_Folding dm ; Decomposition_Mapping FC_NFKC ; FC_NFKC_Closure -isc ; ISO_Comment lc ; Lowercase_Mapping -na ; Name -na1 ; Unicode_1_Name -nv ; Numeric_Value scc ; Special_Case_Condition sfc ; Simple_Case_Folding slc ; Simple_Lowercase_Mapping @@ -58,10 +66,24 @@ stc ; Simple_Titlecase_Mapping suc ; Simple_Uppercase_Mapping tc ; Titlecase_Mapping uc ; Uppercase_Mapping + +# ================================================ +# Miscellaneous Properties +# ================================================ +isc ; ISO_Comment +na ; Name +na1 ; Unicode_1_Name URS ; Unicode_Radical_Stroke # ================================================ -# Enumerated Non-Binary Properties +# Catalog Properties +# ================================================ +age ; Age +blk ; Block +sc ; Script + +# ================================================ +# Enumerated Properties # ================================================ bc ; Bidi_Class ccc ; Canonical_Combining_Class @@ -77,7 +99,6 @@ NFD_QC ; NFD_Quick_Check NFKC_QC ; NFKC_Quick_Check NFKD_QC ; NFKD_Quick_Check nt ; Numeric_Type -sc ; Script # ================================================ # Binary Properties @@ -118,9 +139,11 @@ OUpper ; Other_Uppercase QMark ; Quotation_Mark Radical ; Radical SD ; Soft_Dotted +STerm ; STerm Term ; Terminal_Punctuation UIdeo ; Unified_Ideograph Upper ; Uppercase +VS ; Variation_Selector WSpace ; White_Space XIDC ; XID_Continue XIDS ; XID_Start @@ -128,3 +151,7 @@ XO_NFC ; Expands_On_NFC XO_NFD ; Expands_On_NFD XO_NFKC ; Expands_On_NFKC XO_NFKD ; Expands_On_NFKD + +# ================================================ +# Total: 82 + diff --git a/lib/unicore/ReadMe.txt b/lib/unicore/ReadMe.txt index b8869c0..212bbdc 100644 --- a/lib/unicore/ReadMe.txt +++ b/lib/unicore/ReadMe.txt @@ -1,41 +1,19 @@ -2003 April 16 +2004 March 30 -This directory contains the Unicode Character Database -data files. - -Currently, the Unicode Character Database files are at -the version level: - - Unicode Standard, Version 4.0.0 - -For information about the standard itself, see: - -http://www.unicode.org/versions/Unicode4.0.0/ +This directory contains the updated data +files for Version 4.0.1 of the Unicode Standard. Detailed documentation of the files constituting the Unicode Character Database (contributory data files for the standard itself) can be found in UCD.html. -Unihan.txt is a very large file and is unchanged from -its Unicode 3.2.0 version. A zipped version is -also provided for downloading convenience: Unihan.zip. - -The current Unicode 3.2.0 version of Unihan.txt is also available in -two compressed formats in the Unicode 3.2.0 update directory. See: -http://www.unicode.org/Public/3.2-Update/ -or -ftp://ftp.unicode.org/Public/3.2-Update/ - -Unihan-3.2.0.zip for Windows. (Use winzip) -Unihan-3.2.0.txt.gz for Unix. (Use gzip or gunzip) - -Note that the files are zipped in -exactly the same format they have on the server (with Unix -line endings). From a browser, right-clicking on -Unihan-3.2.0.zip will allow automatic download and unzip on a -Windows system with winzip installed. - +See: +http://www.unicode.org/versions/enumeratedversions.html +for exact details of the definition of Version 4.0.1 +of the Unicode Standard. That listing details which +contributory files are new in this version and which +are retained unchanged from prior versions of the standard. diff --git a/lib/unicore/Scripts.pl b/lib/unicore/Scripts.pl index 68c0e8d..92c0179 100644 --- a/lib/unicore/Scripts.pl +++ b/lib/unicore/Scripts.pl @@ -3,395 +3,507 @@ # Any changes made here will be lost! return <<'END'; -0041 005A LATIN -0061 007A LATIN -00AA LATIN -00B5 GREEK -00BA LATIN -00C0 00D6 LATIN -00D8 00F6 LATIN -00F8 0236 LATIN -0250 02B8 LATIN -02E0 02E4 LATIN -0300 034F INHERITED -0360 036F INHERITED -037A GREEK -0386 GREEK -0388 038A GREEK -038C GREEK -038E 03A1 GREEK -03A3 03CE GREEK -03D0 03F5 GREEK -03F7 03FB GREEK -0400 0481 CYRILLIC -0483 0486 CYRILLIC -0488 0489 INHERITED -048A 04CE CYRILLIC -04D0 04F5 CYRILLIC -04F8 04F9 CYRILLIC -0500 050F CYRILLIC -0531 0556 ARMENIAN -0559 ARMENIAN -0561 0587 ARMENIAN -0591 05A1 INHERITED -05A3 05B9 INHERITED -05BB 05BD INHERITED -05BF INHERITED -05C1 05C2 INHERITED -05C4 INHERITED -05D0 05EA HEBREW -05F0 05F2 HEBREW -0621 063A ARABIC -0641 064A ARABIC -064B 0655 INHERITED -066E 066F ARABIC -0670 INHERITED -0671 06D3 ARABIC -06D5 ARABIC -06D6 06E4 INHERITED -06E5 06E6 ARABIC -06E7 06E8 INHERITED -06EA 06ED INHERITED -06EE 06EF ARABIC -06FA 06FC ARABIC -06FF ARABIC -0710 074A SYRIAC -074D 074F SYRIAC -0780 07B1 THAANA -0901 0939 DEVANAGARI -093C 094D DEVANAGARI -0950 0954 DEVANAGARI -0958 0963 DEVANAGARI -0966 096F DEVANAGARI -0981 0983 BENGALI -0985 098C BENGALI -098F 0990 BENGALI -0993 09A8 BENGALI -09AA 09B0 BENGALI -09B2 BENGALI -09B6 09B9 BENGALI -09BC 09C4 BENGALI -09C7 09C8 BENGALI -09CB 09CD BENGALI -09D7 BENGALI -09DC 09DD BENGALI -09DF 09E3 BENGALI -09E6 09F1 BENGALI -0A02 0A03 GURMUKHI -0A05 0A0A GURMUKHI -0A0F 0A10 GURMUKHI -0A13 0A28 GURMUKHI -0A2A 0A30 GURMUKHI -0A32 0A33 GURMUKHI -0A35 0A36 GURMUKHI -0A38 0A39 GURMUKHI -0A3C GURMUKHI -0A3E 0A42 GURMUKHI -0A47 0A48 GURMUKHI -0A4B 0A4D GURMUKHI -0A59 0A5C GURMUKHI -0A5E GURMUKHI -0A66 0A74 GURMUKHI -0A81 0A83 GUJARATI -0A85 0A8D GUJARATI -0A8F 0A91 GUJARATI -0A93 0AA8 GUJARATI -0AAA 0AB0 GUJARATI -0AB2 0AB3 GUJARATI -0AB5 0AB9 GUJARATI -0ABC 0AC5 GUJARATI -0AC7 0AC9 GUJARATI -0ACB 0ACD GUJARATI -0AD0 GUJARATI -0AE0 0AE3 GUJARATI -0AE6 0AEF GUJARATI -0B01 0B03 ORIYA -0B05 0B0C ORIYA -0B0F 0B10 ORIYA -0B13 0B28 ORIYA -0B2A 0B30 ORIYA -0B32 0B33 ORIYA -0B35 0B39 ORIYA -0B3C 0B43 ORIYA -0B47 0B48 ORIYA -0B4B 0B4D ORIYA -0B56 0B57 ORIYA -0B5C 0B5D ORIYA -0B5F 0B61 ORIYA -0B66 0B6F ORIYA -0B71 ORIYA -0B82 0B83 TAMIL -0B85 0B8A TAMIL -0B8E 0B90 TAMIL -0B92 0B95 TAMIL -0B99 0B9A TAMIL -0B9C TAMIL -0B9E 0B9F TAMIL -0BA3 0BA4 TAMIL -0BA8 0BAA TAMIL -0BAE 0BB5 TAMIL -0BB7 0BB9 TAMIL -0BBE 0BC2 TAMIL -0BC6 0BC8 TAMIL -0BCA 0BCD TAMIL -0BD7 TAMIL -0BE7 0BF2 TAMIL -0C01 0C03 TELUGU -0C05 0C0C TELUGU -0C0E 0C10 TELUGU -0C12 0C28 TELUGU -0C2A 0C33 TELUGU -0C35 0C39 TELUGU -0C3E 0C44 TELUGU -0C46 0C48 TELUGU -0C4A 0C4D TELUGU -0C55 0C56 TELUGU -0C60 0C61 TELUGU -0C66 0C6F TELUGU -0C82 0C83 KANNADA -0C85 0C8C KANNADA -0C8E 0C90 KANNADA -0C92 0CA8 KANNADA -0CAA 0CB3 KANNADA -0CB5 0CB9 KANNADA -0CBD 0CC4 KANNADA -0CC6 0CC8 KANNADA -0CCA 0CCD KANNADA -0CD5 0CD6 KANNADA -0CDE KANNADA -0CE0 0CE1 KANNADA -0CE6 0CEF KANNADA -0D02 0D03 MALAYALAM -0D05 0D0C MALAYALAM -0D0E 0D10 MALAYALAM -0D12 0D28 MALAYALAM -0D2A 0D39 MALAYALAM -0D3E 0D43 MALAYALAM -0D46 0D48 MALAYALAM -0D4A 0D4D MALAYALAM -0D57 MALAYALAM -0D60 0D61 MALAYALAM -0D66 0D6F MALAYALAM -0D82 0D83 SINHALA -0D85 0D96 SINHALA -0D9A 0DB1 SINHALA -0DB3 0DBB SINHALA -0DBD SINHALA -0DC0 0DC6 SINHALA -0DCA SINHALA -0DCF 0DD4 SINHALA -0DD6 SINHALA -0DD8 0DDF SINHALA -0DF2 0DF3 SINHALA -0E01 0E3A THAI -0E40 0E4E THAI -0E50 0E59 THAI -0E81 0E82 LAO -0E84 LAO -0E87 0E88 LAO -0E8A LAO -0E8D LAO -0E94 0E97 LAO -0E99 0E9F LAO -0EA1 0EA3 LAO -0EA5 LAO -0EA7 LAO -0EAA 0EAB LAO -0EAD 0EB9 LAO -0EBB 0EBD LAO -0EC0 0EC4 LAO -0EC6 LAO -0EC8 0ECD LAO -0ED0 0ED9 LAO -0EDC 0EDD LAO -0F00 TIBETAN -0F18 0F19 TIBETAN -0F20 0F33 TIBETAN -0F35 TIBETAN -0F37 TIBETAN -0F39 TIBETAN -0F40 0F47 TIBETAN -0F49 0F6A TIBETAN -0F71 0F84 TIBETAN -0F86 0F8B TIBETAN -0F90 0F97 TIBETAN -0F99 0FBC TIBETAN -0FC6 TIBETAN -1000 1021 MYANMAR -1023 1027 MYANMAR -1029 102A MYANMAR -102C 1032 MYANMAR -1036 1039 MYANMAR -1040 1049 MYANMAR -1050 1059 MYANMAR -10A0 10C5 GEORGIAN -10D0 10F8 GEORGIAN -1100 1159 HANGUL -115F 11A2 HANGUL -11A8 11F9 HANGUL -1200 1206 ETHIOPIC -1208 1246 ETHIOPIC -1248 ETHIOPIC -124A 124D ETHIOPIC -1250 1256 ETHIOPIC -1258 ETHIOPIC -125A 125D ETHIOPIC -1260 1286 ETHIOPIC -1288 ETHIOPIC -128A 128D ETHIOPIC -1290 12AE ETHIOPIC -12B0 ETHIOPIC -12B2 12B5 ETHIOPIC -12B8 12BE ETHIOPIC -12C0 ETHIOPIC -12C2 12C5 ETHIOPIC -12C8 12CE ETHIOPIC -12D0 12D6 ETHIOPIC -12D8 12EE ETHIOPIC -12F0 130E ETHIOPIC -1310 ETHIOPIC -1312 1315 ETHIOPIC -1318 131E ETHIOPIC -1320 1346 ETHIOPIC -1348 135A ETHIOPIC -1369 137C ETHIOPIC -13A0 13F4 CHEROKEE -1401 166C CANADIAN_ABORIGINAL -166F 1676 CANADIAN_ABORIGINAL -1681 169A OGHAM -16A0 16EA RUNIC -16EE 16F0 RUNIC -1700 170C TAGALOG -170E 1714 TAGALOG -1720 1734 HANUNOO -1740 1753 BUHID -1760 176C TAGBANWA -176E 1770 TAGBANWA -1772 1773 TAGBANWA -1780 17D3 KHMER -17E0 17E9 KHMER -180B 180D INHERITED -1810 1819 MONGOLIAN -1820 1877 MONGOLIAN -1880 18A9 MONGOLIAN -1900 191C LIMBU -1920 192B LIMBU -1930 193B LIMBU -1946 194F LIMBU -1950 196D TAI_LE -1970 1974 TAI_LE -1D00 1D25 LATIN -1D26 1D2A GREEK -1D2B CYRILLIC -1D2C 1D5C LATIN -1D5D 1D61 GREEK -1D62 1D65 LATIN -1D66 1D6A GREEK -1D6B LATIN -1E00 1E9B LATIN -1EA0 1EF9 LATIN -1F00 1F15 GREEK -1F18 1F1D GREEK -1F20 1F45 GREEK -1F48 1F4D GREEK -1F50 1F57 GREEK -1F59 GREEK -1F5B GREEK -1F5D GREEK -1F5F 1F7D GREEK -1F80 1FB4 GREEK -1FB6 1FBC GREEK -1FBE GREEK -1FC2 1FC4 GREEK -1FC6 1FCC GREEK -1FD0 1FD3 GREEK -1FD6 1FDB GREEK -1FE0 1FEC GREEK -1FF2 1FF4 GREEK -1FF6 1FFC GREEK -2071 LATIN -207F LATIN -20D0 20EA INHERITED -2126 GREEK -212A 212B LATIN -2800 28FF BRAILLE -2E80 2E99 HAN -2E9B 2EF3 HAN -2F00 2FD5 HAN -3005 HAN -3007 HAN -3021 3029 HAN -302A 302F INHERITED -3038 303B HAN -3041 3096 HIRAGANA -3099 309A INHERITED -309D 309F HIRAGANA -30A1 30FA KATAKANA -30FD 30FF KATAKANA -3105 312C BOPOMOFO -3131 318E HANGUL -31A0 31B7 BOPOMOFO -31F0 31FF KATAKANA -3400 4DB5 HAN -4E00 9FA5 HAN -A000 A48C YI -A490 A4C6 YI -AC00 D7A3 HANGUL -F900 FA2D HAN -FA30 FA6A HAN -FB00 FB06 LATIN -FB13 FB17 ARMENIAN -FB1D HEBREW -FB1E INHERITED -FB1F FB28 HEBREW -FB2A FB36 HEBREW -FB38 FB3C HEBREW -FB3E HEBREW -FB40 FB41 HEBREW -FB43 FB44 HEBREW -FB46 FB4F HEBREW -FB50 FBB1 ARABIC -FBD3 FD3D ARABIC -FD50 FD8F ARABIC -FD92 FDC7 ARABIC -FDF0 FDFB ARABIC -FE00 FE0F INHERITED -FE20 FE23 INHERITED -FE70 FE74 ARABIC -FE76 FEFC ARABIC -FF21 FF3A LATIN -FF41 FF5A LATIN -FF66 FF6F KATAKANA -FF71 FF9D KATAKANA -FFA0 FFBE HANGUL -FFC2 FFC7 HANGUL -FFCA FFCF HANGUL -FFD2 FFD7 HANGUL -FFDA FFDC HANGUL -10000 1000B LINEAR_B -1000D 10026 LINEAR_B -10028 1003A LINEAR_B -1003C 1003D LINEAR_B -1003F 1004D LINEAR_B -10050 1005D LINEAR_B -10080 100FA LINEAR_B -10300 1031E OLD_ITALIC -10330 1034A GOTHIC -10380 1039D UGARITIC -10400 1044F DESERET -10450 1047F SHAVIAN -10480 1049D OSMANYA -104A0 104A9 OSMANYA -10800 10805 CYPRIOT -10808 CYPRIOT -1080A 10835 CYPRIOT -10837 10838 CYPRIOT -1083C CYPRIOT -1083F CYPRIOT -1D167 1D169 INHERITED -1D17B 1D182 INHERITED -1D185 1D18B INHERITED -1D1AA 1D1AD INHERITED -20000 2A6D6 HAN -2F800 2FA1D HAN +0000 0040 Common +0041 005A Latin +005B 0060 Common +0061 007A Latin +007B 00A9 Common +00AA Latin +00AB 00B9 Common +00BA Latin +00BB 00BF Common +00C0 00D6 Latin +00D7 Common +00D8 00F6 Latin +00F7 Common +00F8 0236 Latin +0250 02B8 Latin +02B9 02DF Common +02E0 02E4 Latin +02E5 02FF Common +0300 0357 Inherited +035D 036F Inherited +0374 0375 Greek +037A Greek +037E Common +0384 0386 Greek +0387 Common +0388 038A Greek +038C Greek +038E 03A1 Greek +03A3 03CE Greek +03D0 03FB Greek +0400 0486 Cyrillic +0488 04CE Cyrillic +04D0 04F5 Cyrillic +04F8 04F9 Cyrillic +0500 050F Cyrillic +0531 0556 Armenian +0559 055F Armenian +0561 0587 Armenian +0589 Common +058A Armenian +0591 05A1 Hebrew +05A3 05B9 Hebrew +05BB 05C4 Hebrew +05D0 05EA Hebrew +05F0 05F4 Hebrew +0600 0603 Common +060C Common +060D 0615 Arabic +061B Common +061F Common +0621 063A Arabic +0640 Common +0641 064A Arabic +064B 0655 Inherited +0656 0658 Arabic +0660 0669 Common +066A 066F Arabic +0670 Inherited +0671 06DC Arabic +06DD Common +06DE 06FF Arabic +0700 070D Syriac +070F 074A Syriac +074D 074F Syriac +0780 07B1 Thaana +0901 0939 Devanagari +093C 094D Devanagari +0950 0954 Devanagari +0958 0963 Devanagari +0964 0965 Common +0966 096F Devanagari +0970 Common +0981 0983 Bengali +0985 098C Bengali +098F 0990 Bengali +0993 09A8 Bengali +09AA 09B0 Bengali +09B2 Bengali +09B6 09B9 Bengali +09BC 09C4 Bengali +09C7 09C8 Bengali +09CB 09CD Bengali +09D7 Bengali +09DC 09DD Bengali +09DF 09E3 Bengali +09E6 09FA Bengali +0A01 0A03 Gurmukhi +0A05 0A0A Gurmukhi +0A0F 0A10 Gurmukhi +0A13 0A28 Gurmukhi +0A2A 0A30 Gurmukhi +0A32 0A33 Gurmukhi +0A35 0A36 Gurmukhi +0A38 0A39 Gurmukhi +0A3C Gurmukhi +0A3E 0A42 Gurmukhi +0A47 0A48 Gurmukhi +0A4B 0A4D Gurmukhi +0A59 0A5C Gurmukhi +0A5E Gurmukhi +0A66 0A74 Gurmukhi +0A81 0A83 Gujarati +0A85 0A8D Gujarati +0A8F 0A91 Gujarati +0A93 0AA8 Gujarati +0AAA 0AB0 Gujarati +0AB2 0AB3 Gujarati +0AB5 0AB9 Gujarati +0ABC 0AC5 Gujarati +0AC7 0AC9 Gujarati +0ACB 0ACD Gujarati +0AD0 Gujarati +0AE0 0AE3 Gujarati +0AE6 0AEF Gujarati +0AF1 Gujarati +0B01 0B03 Oriya +0B05 0B0C Oriya +0B0F 0B10 Oriya +0B13 0B28 Oriya +0B2A 0B30 Oriya +0B32 0B33 Oriya +0B35 0B39 Oriya +0B3C 0B43 Oriya +0B47 0B48 Oriya +0B4B 0B4D Oriya +0B56 0B57 Oriya +0B5C 0B5D Oriya +0B5F 0B61 Oriya +0B66 0B71 Oriya +0B82 0B83 Tamil +0B85 0B8A Tamil +0B8E 0B90 Tamil +0B92 0B95 Tamil +0B99 0B9A Tamil +0B9C Tamil +0B9E 0B9F Tamil +0BA3 0BA4 Tamil +0BA8 0BAA Tamil +0BAE 0BB5 Tamil +0BB7 0BB9 Tamil +0BBE 0BC2 Tamil +0BC6 0BC8 Tamil +0BCA 0BCD Tamil +0BD7 Tamil +0BE7 0BFA Tamil +0C01 0C03 Telugu +0C05 0C0C Telugu +0C0E 0C10 Telugu +0C12 0C28 Telugu +0C2A 0C33 Telugu +0C35 0C39 Telugu +0C3E 0C44 Telugu +0C46 0C48 Telugu +0C4A 0C4D Telugu +0C55 0C56 Telugu +0C60 0C61 Telugu +0C66 0C6F Telugu +0C82 0C83 Kannada +0C85 0C8C Kannada +0C8E 0C90 Kannada +0C92 0CA8 Kannada +0CAA 0CB3 Kannada +0CB5 0CB9 Kannada +0CBC 0CC4 Kannada +0CC6 0CC8 Kannada +0CCA 0CCD Kannada +0CD5 0CD6 Kannada +0CDE Kannada +0CE0 0CE1 Kannada +0CE6 0CEF Kannada +0D02 0D03 Malayalam +0D05 0D0C Malayalam +0D0E 0D10 Malayalam +0D12 0D28 Malayalam +0D2A 0D39 Malayalam +0D3E 0D43 Malayalam +0D46 0D48 Malayalam +0D4A 0D4D Malayalam +0D57 Malayalam +0D60 0D61 Malayalam +0D66 0D6F Malayalam +0D82 0D83 Sinhala +0D85 0D96 Sinhala +0D9A 0DB1 Sinhala +0DB3 0DBB Sinhala +0DBD Sinhala +0DC0 0DC6 Sinhala +0DCA Sinhala +0DCF 0DD4 Sinhala +0DD6 Sinhala +0DD8 0DDF Sinhala +0DF2 0DF4 Sinhala +0E01 0E3A Thai +0E3F Common +0E40 0E5B Thai +0E81 0E82 Lao +0E84 Lao +0E87 0E88 Lao +0E8A Lao +0E8D Lao +0E94 0E97 Lao +0E99 0E9F Lao +0EA1 0EA3 Lao +0EA5 Lao +0EA7 Lao +0EAA 0EAB Lao +0EAD 0EB9 Lao +0EBB 0EBD Lao +0EC0 0EC4 Lao +0EC6 Lao +0EC8 0ECD Lao +0ED0 0ED9 Lao +0EDC 0EDD Lao +0F00 0F47 Tibetan +0F49 0F6A Tibetan +0F71 0F8B Tibetan +0F90 0F97 Tibetan +0F99 0FBC Tibetan +0FBE 0FCC Tibetan +0FCF Tibetan +1000 1021 Myanmar +1023 1027 Myanmar +1029 102A Myanmar +102C 1032 Myanmar +1036 1039 Myanmar +1040 1059 Myanmar +10A0 10C5 Georgian +10D0 10F8 Georgian +10FB Common +1100 1159 Hangul +115F 11A2 Hangul +11A8 11F9 Hangul +1200 1206 Ethiopic +1208 1246 Ethiopic +1248 Ethiopic +124A 124D Ethiopic +1250 1256 Ethiopic +1258 Ethiopic +125A 125D Ethiopic +1260 1286 Ethiopic +1288 Ethiopic +128A 128D Ethiopic +1290 12AE Ethiopic +12B0 Ethiopic +12B2 12B5 Ethiopic +12B8 12BE Ethiopic +12C0 Ethiopic +12C2 12C5 Ethiopic +12C8 12CE Ethiopic +12D0 12D6 Ethiopic +12D8 12EE Ethiopic +12F0 130E Ethiopic +1310 Ethiopic +1312 1315 Ethiopic +1318 131E Ethiopic +1320 1346 Ethiopic +1348 135A Ethiopic +1361 137C Ethiopic +13A0 13F4 Cherokee +1401 1676 Canadian_Aboriginal +1680 169C Ogham +16A0 16EA Runic +16EB 16ED Common +16EE 16F0 Runic +1700 170C Tagalog +170E 1714 Tagalog +1720 1734 Hanunoo +1735 1736 Common +1740 1753 Buhid +1760 176C Tagbanwa +176E 1770 Tagbanwa +1772 1773 Tagbanwa +1780 17DD Khmer +17E0 17E9 Khmer +17F0 17F9 Khmer +1800 180E Mongolian +1810 1819 Mongolian +1820 1877 Mongolian +1880 18A9 Mongolian +1900 191C Limbu +1920 192B Limbu +1930 193B Limbu +1940 Limbu +1944 194F Limbu +1950 196D Tai_Le +1970 1974 Tai_Le +19E0 19FF Khmer +1D00 1D25 Latin +1D26 1D2A Greek +1D2B Cyrillic +1D2C 1D5C Latin +1D5D 1D61 Greek +1D62 1D65 Latin +1D66 1D6A Greek +1D6B Latin +1E00 1E9B Latin +1EA0 1EF9 Latin +1F00 1F15 Greek +1F18 1F1D Greek +1F20 1F45 Greek +1F48 1F4D Greek +1F50 1F57 Greek +1F59 Greek +1F5B Greek +1F5D Greek +1F5F 1F7D Greek +1F80 1FB4 Greek +1FB6 1FC4 Greek +1FC6 1FD3 Greek +1FD6 1FDB Greek +1FDD 1FEF Greek +1FF2 1FF4 Greek +1FF6 1FFE Greek +2000 200B Common +200C 200D Inherited +200E 2054 Common +2057 Common +205F 2063 Common +206A 2070 Common +2071 Latin +2074 207E Common +207F Latin +2080 208E Common +20A0 20B1 Common +20D0 20EA Inherited +2100 2125 Common +2126 Greek +2127 2129 Common +212A 212B Latin +212C 213B Common +213D 214B Common +2153 2183 Common +2190 23D0 Common +2400 2426 Common +2440 244A Common +2460 2617 Common +2619 267D Common +2680 2691 Common +26A0 26A1 Common +2701 2704 Common +2706 2709 Common +270C 2727 Common +2729 274B Common +274D Common +274F 2752 Common +2756 Common +2758 275E Common +2761 2794 Common +2798 27AF Common +27B1 27BE Common +27D0 27EB Common +27F0 27FF Common +2800 28FF Braille +2900 2B0D Common +2E80 2E99 Han +2E9B 2EF3 Han +2F00 2FD5 Han +2FF0 2FFB Common +3000 3004 Common +3005 Han +3006 Common +3007 Han +3008 3020 Common +3021 3029 Han +302A 302F Inherited +3030 Common +3031 3035 Katakana_Or_Hiragana +3036 3037 Common +3038 303B Han +303C 303F Common +3041 3096 Hiragana +3099 309A Inherited +309B 309C Katakana_Or_Hiragana +309D 309F Hiragana +30A0 Common +30A1 30FA Katakana +30FB 30FC Common +30FD 30FF Katakana +3105 312C Bopomofo +3131 318E Hangul +3190 319F Common +31A0 31B7 Bopomofo +31F0 31FF Katakana +3200 321E Hangul +3220 3243 Common +3250 325F Common +3260 327D Hangul +327F 32FE Common +3300 33FF Common +3400 4DB5 Han +4DC0 4DFF Common +4E00 9FA5 Han +A000 A48C Yi +A490 A4C6 Yi +AC00 D7A3 Hangul +E000 F8FF Common +F900 FA2D Han +FA30 FA6A Han +FB00 FB06 Latin +FB13 FB17 Armenian +FB1D FB36 Hebrew +FB38 FB3C Hebrew +FB3E Hebrew +FB40 FB41 Hebrew +FB43 FB44 Hebrew +FB46 FB4F Hebrew +FB50 FBB1 Arabic +FBD3 FD3D Arabic +FD3E FD3F Common +FD50 FD8F Arabic +FD92 FDC7 Arabic +FDF0 FDFC Arabic +FDFD Common +FE00 FE0F Inherited +FE20 FE23 Inherited +FE30 FE52 Common +FE54 FE66 Common +FE68 FE6B Common +FE70 FE74 Arabic +FE76 FEFC Arabic +FEFF Common +FF01 FF20 Common +FF21 FF3A Latin +FF3B FF40 Common +FF41 FF5A Latin +FF5B FF65 Common +FF66 FF6F Katakana +FF70 Katakana_Or_Hiragana +FF71 FF9D Katakana +FF9E FF9F Katakana_Or_Hiragana +FFA0 FFBE Hangul +FFC2 FFC7 Hangul +FFCA FFCF Hangul +FFD2 FFD7 Hangul +FFDA FFDC Hangul +FFE0 FFE6 Common +FFE8 FFEE Common +FFF9 FFFD Common +10000 1000B Linear_B +1000D 10026 Linear_B +10028 1003A Linear_B +1003C 1003D Linear_B +1003F 1004D Linear_B +10050 1005D Linear_B +10080 100FA Linear_B +10100 10102 Common +10107 10133 Common +10137 1013F Common +10300 1031E Old_Italic +10320 10323 Old_Italic +10330 1034A Gothic +10380 1039D Ugaritic +1039F Ugaritic +10400 1044F Deseret +10450 1047F Shavian +10480 1049D Osmanya +104A0 104A9 Osmanya +10800 10805 Cypriot +10808 Cypriot +1080A 10835 Cypriot +10837 10838 Cypriot +1083C Cypriot +1083F Cypriot +1D000 1D0F5 Common +1D100 1D126 Common +1D12A 1D166 Common +1D167 1D169 Inherited +1D16A 1D17A Common +1D17B 1D182 Inherited +1D183 1D184 Common +1D185 1D18B Inherited +1D18C 1D1A9 Common +1D1AA 1D1AD Inherited +1D1AE 1D1DD Common +1D300 1D356 Common +1D400 1D454 Common +1D456 1D49C Common +1D49E 1D49F Common +1D4A2 Common +1D4A5 1D4A6 Common +1D4A9 1D4AC Common +1D4AE 1D4B9 Common +1D4BB Common +1D4BD 1D4C3 Common +1D4C5 1D505 Common +1D507 1D50A Common +1D50D 1D514 Common +1D516 1D51C Common +1D51E 1D539 Common +1D53B 1D53E Common +1D540 1D544 Common +1D546 Common +1D54A 1D550 Common +1D552 1D6A3 Common +1D6A8 1D7C9 Common +1D7CE 1D7FF Common +20000 2A6D6 Han +2F800 2FA1D Han +E0001 Common +E0020 E007F Common +E0100 E01EF Inherited +F0000 FFFFD Common +100000 10FFFD Common END diff --git a/lib/unicore/Scripts.txt b/lib/unicore/Scripts.txt index 696720a..2aa0630 100644 --- a/lib/unicore/Scripts.txt +++ b/lib/unicore/Scripts.txt @@ -1,774 +1,1336 @@ -# Scripts-4.0.0.txt -# Date: 2003-03-20, 20:07:48 GMT [MD] +# Scripts-4.0.1.txt +# Date: 2004-03-11, 18:47:37 GMT [MD] # +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html # For documentation, see UCD.html -# Note: Unassigned and Noncharacter codepoints may be omitted -# if they have default property values. -# ================================================ - - -# ================================================ -# Script -# All code points not explicitly listed in this file have the property -# value: COMMON. -# ================================================ - -0041..005A ; LATIN # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z -0061..007A ; LATIN # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z -00AA ; LATIN # L& FEMININE ORDINAL INDICATOR -00BA ; LATIN # L& MASCULINE ORDINAL INDICATOR -00C0..00D6 ; LATIN # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS -00D8..00F6 ; LATIN # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS -00F8..01BA ; LATIN # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL -01BB ; LATIN # Lo LATIN LETTER TWO WITH STROKE -01BC..01BF ; LATIN # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN -01C0..01C3 ; LATIN # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK -01C4..0236 ; LATIN # L& [115] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER T WITH CURL -0250..02AF ; LATIN # L& [96] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL -02B0..02B8 ; LATIN # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y -02E0..02E4 ; LATIN # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP -1D00..1D25 ; LATIN # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN -1D2C..1D5C ; LATIN # Lm [49] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL AIN -1D62..1D65 ; LATIN # L& [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V -1D6B ; LATIN # L& LATIN SMALL LETTER UE -1E00..1E9B ; LATIN # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE -1EA0..1EF9 ; LATIN # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE -2071 ; LATIN # L& SUPERSCRIPT LATIN SMALL LETTER I -207F ; LATIN # L& SUPERSCRIPT LATIN SMALL LETTER N -212A..212B ; LATIN # L& [2] KELVIN SIGN..ANGSTROM SIGN -FB00..FB06 ; LATIN # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST -FF21..FF3A ; LATIN # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z -FF41..FF5A ; LATIN # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z + +# ================================================ + +# Property: Script + +# All code points not explicitly listed for Script +# have the value Common (Zyyy). + +# ================================================ + +0000..001F ; Common # Cc [32] .. +0020 ; Common # Zs SPACE +0021..0023 ; Common # Po [3] EXCLAMATION MARK..NUMBER SIGN +0024 ; Common # Sc DOLLAR SIGN +0025..0027 ; Common # Po [3] PERCENT SIGN..APOSTROPHE +0028 ; Common # Ps LEFT PARENTHESIS +0029 ; Common # Pe RIGHT PARENTHESIS +002A ; Common # Po ASTERISK +002B ; Common # Sm PLUS SIGN +002C ; Common # Po COMMA +002D ; Common # Pd HYPHEN-MINUS +002E..002F ; Common # Po [2] FULL STOP..SOLIDUS +0030..0039 ; Common # Nd [10] DIGIT ZERO..DIGIT NINE +003A..003B ; Common # Po [2] COLON..SEMICOLON +003C..003E ; Common # Sm [3] LESS-THAN SIGN..GREATER-THAN SIGN +003F..0040 ; Common # Po [2] QUESTION MARK..COMMERCIAL AT +005B ; Common # Ps LEFT SQUARE BRACKET +005C ; Common # Po REVERSE SOLIDUS +005D ; Common # Pe RIGHT SQUARE BRACKET +005E ; Common # Sk CIRCUMFLEX ACCENT +005F ; Common # Pc LOW LINE +0060 ; Common # Sk GRAVE ACCENT +007B ; Common # Ps LEFT CURLY BRACKET +007C ; Common # Sm VERTICAL LINE +007D ; Common # Pe RIGHT CURLY BRACKET +007E ; Common # Sm TILDE +007F..009F ; Common # Cc [33] .. +00A0 ; Common # Zs NO-BREAK SPACE +00A1 ; Common # Po INVERTED EXCLAMATION MARK +00A2..00A5 ; Common # Sc [4] CENT SIGN..YEN SIGN +00A6..00A7 ; Common # So [2] BROKEN BAR..SECTION SIGN +00A8 ; Common # Sk DIAERESIS +00A9 ; Common # So COPYRIGHT SIGN +00AB ; Common # Pi LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +00AC ; Common # Sm NOT SIGN +00AD ; Common # Cf SOFT HYPHEN +00AE ; Common # So REGISTERED SIGN +00AF ; Common # Sk MACRON +00B0 ; Common # So DEGREE SIGN +00B1 ; Common # Sm PLUS-MINUS SIGN +00B2..00B3 ; Common # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE +00B4 ; Common # Sk ACUTE ACCENT +00B5 ; Common # L& MICRO SIGN +00B6 ; Common # So PILCROW SIGN +00B7 ; Common # Po MIDDLE DOT +00B8 ; Common # Sk CEDILLA +00B9 ; Common # No SUPERSCRIPT ONE +00BB ; Common # Pf RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +00BC..00BE ; Common # No [3] VULGAR FRACTION ONE QUARTER..VULGAR FRACTION THREE QUARTERS +00BF ; Common # Po INVERTED QUESTION MARK +00D7 ; Common # Sm MULTIPLICATION SIGN +00F7 ; Common # Sm DIVISION SIGN +02B9..02C1 ; Common # Lm [9] MODIFIER LETTER PRIME..MODIFIER LETTER REVERSED GLOTTAL STOP +02C2..02C5 ; Common # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD +02C6..02D1 ; Common # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON +02D2..02DF ; Common # Sk [14] MODIFIER LETTER CENTRED RIGHT HALF RING..MODIFIER LETTER CROSS ACCENT +02E5..02ED ; Common # Sk [9] MODIFIER LETTER EXTRA-HIGH TONE BAR..MODIFIER LETTER UNASPIRATED +02EE ; Common # Lm MODIFIER LETTER DOUBLE APOSTROPHE +02EF..02FF ; Common # Sk [17] MODIFIER LETTER LOW DOWN ARROWHEAD..MODIFIER LETTER LOW LEFT ARROW +037E ; Common # Po GREEK QUESTION MARK +0387 ; Common # Po GREEK ANO TELEIA +0589 ; Common # Po ARMENIAN FULL STOP +0600..0603 ; Common # Cf [4] ARABIC NUMBER SIGN..ARABIC SIGN SAFHA +060C ; Common # Po ARABIC COMMA +061B ; Common # Po ARABIC SEMICOLON +061F ; Common # Po ARABIC QUESTION MARK +0640 ; Common # Lm ARABIC TATWEEL +0660..0669 ; Common # Nd [10] ARABIC-INDIC DIGIT ZERO..ARABIC-INDIC DIGIT NINE +06DD ; Common # Cf ARABIC END OF AYAH +0964..0965 ; Common # Po [2] DEVANAGARI DANDA..DEVANAGARI DOUBLE DANDA +0970 ; Common # Po DEVANAGARI ABBREVIATION SIGN +0E3F ; Common # Sc THAI CURRENCY SYMBOL BAHT +10FB ; Common # Po GEORGIAN PARAGRAPH SEPARATOR +16EB..16ED ; Common # Po [3] RUNIC SINGLE PUNCTUATION..RUNIC CROSS PUNCTUATION +1735..1736 ; Common # Po [2] PHILIPPINE SINGLE PUNCTUATION..PHILIPPINE DOUBLE PUNCTUATION +2000..200A ; Common # Zs [11] EN QUAD..HAIR SPACE +200B ; Common # Cf ZERO WIDTH SPACE +200E..200F ; Common # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +2010..2015 ; Common # Pd [6] HYPHEN..HORIZONTAL BAR +2016..2017 ; Common # Po [2] DOUBLE VERTICAL LINE..DOUBLE LOW LINE +2018 ; Common # Pi LEFT SINGLE QUOTATION MARK +2019 ; Common # Pf RIGHT SINGLE QUOTATION MARK +201A ; Common # Ps SINGLE LOW-9 QUOTATION MARK +201B..201C ; Common # Pi [2] SINGLE HIGH-REVERSED-9 QUOTATION MARK..LEFT DOUBLE QUOTATION MARK +201D ; Common # Pf RIGHT DOUBLE QUOTATION MARK +201E ; Common # Ps DOUBLE LOW-9 QUOTATION MARK +201F ; Common # Pi DOUBLE HIGH-REVERSED-9 QUOTATION MARK +2020..2027 ; Common # Po [8] DAGGER..HYPHENATION POINT +2028 ; Common # Zl LINE SEPARATOR +2029 ; Common # Zp PARAGRAPH SEPARATOR +202A..202E ; Common # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +202F ; Common # Zs NARROW NO-BREAK SPACE +2030..2038 ; Common # Po [9] PER MILLE SIGN..CARET +2039 ; Common # Pi SINGLE LEFT-POINTING ANGLE QUOTATION MARK +203A ; Common # Pf SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +203B..203E ; Common # Po [4] REFERENCE MARK..OVERLINE +203F..2040 ; Common # Pc [2] UNDERTIE..CHARACTER TIE +2041..2043 ; Common # Po [3] CARET INSERTION POINT..HYPHEN BULLET +2044 ; Common # Sm FRACTION SLASH +2045 ; Common # Ps LEFT SQUARE BRACKET WITH QUILL +2046 ; Common # Pe RIGHT SQUARE BRACKET WITH QUILL +2047..2051 ; Common # Po [11] DOUBLE QUESTION MARK..TWO ASTERISKS ALIGNED VERTICALLY +2052 ; Common # Sm COMMERCIAL MINUS SIGN +2053 ; Common # Po SWUNG DASH +2054 ; Common # Pc INVERTED UNDERTIE +2057 ; Common # Po QUADRUPLE PRIME +205F ; Common # Zs MEDIUM MATHEMATICAL SPACE +2060..2063 ; Common # Cf [4] WORD JOINER..INVISIBLE SEPARATOR +206A..206F ; Common # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +2070 ; Common # No SUPERSCRIPT ZERO +2074..2079 ; Common # No [6] SUPERSCRIPT FOUR..SUPERSCRIPT NINE +207A..207C ; Common # Sm [3] SUPERSCRIPT PLUS SIGN..SUPERSCRIPT EQUALS SIGN +207D ; Common # Ps SUPERSCRIPT LEFT PARENTHESIS +207E ; Common # Pe SUPERSCRIPT RIGHT PARENTHESIS +2080..2089 ; Common # No [10] SUBSCRIPT ZERO..SUBSCRIPT NINE +208A..208C ; Common # Sm [3] SUBSCRIPT PLUS SIGN..SUBSCRIPT EQUALS SIGN +208D ; Common # Ps SUBSCRIPT LEFT PARENTHESIS +208E ; Common # Pe SUBSCRIPT RIGHT PARENTHESIS +20A0..20B1 ; Common # Sc [18] EURO-CURRENCY SIGN..PESO SIGN +2100..2101 ; Common # So [2] ACCOUNT OF..ADDRESSED TO THE SUBJECT +2102 ; Common # L& DOUBLE-STRUCK CAPITAL C +2103..2106 ; Common # So [4] DEGREE CELSIUS..CADA UNA +2107 ; Common # L& EULER CONSTANT +2108..2109 ; Common # So [2] SCRUPLE..DEGREE FAHRENHEIT +210A..2113 ; Common # L& [10] SCRIPT SMALL G..SCRIPT SMALL L +2114 ; Common # So L B BAR SYMBOL +2115 ; Common # L& DOUBLE-STRUCK CAPITAL N +2116..2118 ; Common # So [3] NUMERO SIGN..SCRIPT CAPITAL P +2119..211D ; Common # L& [5] DOUBLE-STRUCK CAPITAL P..DOUBLE-STRUCK CAPITAL R +211E..2123 ; Common # So [6] PRESCRIPTION TAKE..VERSICLE +2124 ; Common # L& DOUBLE-STRUCK CAPITAL Z +2125 ; Common # So OUNCE SIGN +2127 ; Common # So INVERTED OHM SIGN +2128 ; Common # L& BLACK-LETTER CAPITAL Z +2129 ; Common # So TURNED GREEK SMALL LETTER IOTA +212C..212D ; Common # L& [2] SCRIPT CAPITAL B..BLACK-LETTER CAPITAL C +212E ; Common # So ESTIMATED SYMBOL +212F..2131 ; Common # L& [3] SCRIPT SMALL E..SCRIPT CAPITAL F +2132 ; Common # So TURNED CAPITAL F +2133..2134 ; Common # L& [2] SCRIPT CAPITAL M..SCRIPT SMALL O +2135..2138 ; Common # Lo [4] ALEF SYMBOL..DALET SYMBOL +2139 ; Common # L& INFORMATION SOURCE +213A..213B ; Common # So [2] ROTATED CAPITAL Q..FACSIMILE SIGN +213D..213F ; Common # L& [3] DOUBLE-STRUCK SMALL GAMMA..DOUBLE-STRUCK CAPITAL PI +2140..2144 ; Common # Sm [5] DOUBLE-STRUCK N-ARY SUMMATION..TURNED SANS-SERIF CAPITAL Y +2145..2149 ; Common # L& [5] DOUBLE-STRUCK ITALIC CAPITAL D..DOUBLE-STRUCK ITALIC SMALL J +214A ; Common # So PROPERTY LINE +214B ; Common # Sm TURNED AMPERSAND +2153..215F ; Common # No [13] VULGAR FRACTION ONE THIRD..FRACTION NUMERATOR ONE +2160..2183 ; Common # Nl [36] ROMAN NUMERAL ONE..ROMAN NUMERAL REVERSED ONE HUNDRED +2190..2194 ; Common # Sm [5] LEFTWARDS ARROW..LEFT RIGHT ARROW +2195..2199 ; Common # So [5] UP DOWN ARROW..SOUTH WEST ARROW +219A..219B ; Common # Sm [2] LEFTWARDS ARROW WITH STROKE..RIGHTWARDS ARROW WITH STROKE +219C..219F ; Common # So [4] LEFTWARDS WAVE ARROW..UPWARDS TWO HEADED ARROW +21A0 ; Common # Sm RIGHTWARDS TWO HEADED ARROW +21A1..21A2 ; Common # So [2] DOWNWARDS TWO HEADED ARROW..LEFTWARDS ARROW WITH TAIL +21A3 ; Common # Sm RIGHTWARDS ARROW WITH TAIL +21A4..21A5 ; Common # So [2] LEFTWARDS ARROW FROM BAR..UPWARDS ARROW FROM BAR +21A6 ; Common # Sm RIGHTWARDS ARROW FROM BAR +21A7..21AD ; Common # So [7] DOWNWARDS ARROW FROM BAR..LEFT RIGHT WAVE ARROW +21AE ; Common # Sm LEFT RIGHT ARROW WITH STROKE +21AF..21CD ; Common # So [31] DOWNWARDS ZIGZAG ARROW..LEFTWARDS DOUBLE ARROW WITH STROKE +21CE..21CF ; Common # Sm [2] LEFT RIGHT DOUBLE ARROW WITH STROKE..RIGHTWARDS DOUBLE ARROW WITH STROKE +21D0..21D1 ; Common # So [2] LEFTWARDS DOUBLE ARROW..UPWARDS DOUBLE ARROW +21D2 ; Common # Sm RIGHTWARDS DOUBLE ARROW +21D3 ; Common # So DOWNWARDS DOUBLE ARROW +21D4 ; Common # Sm LEFT RIGHT DOUBLE ARROW +21D5..21F3 ; Common # So [31] UP DOWN DOUBLE ARROW..UP DOWN WHITE ARROW +21F4..22FF ; Common # Sm [268] RIGHT ARROW WITH SMALL CIRCLE..Z NOTATION BAG MEMBERSHIP +2300..2307 ; Common # So [8] DIAMETER SIGN..WAVY LINE +2308..230B ; Common # Sm [4] LEFT CEILING..RIGHT FLOOR +230C..231F ; Common # So [20] BOTTOM RIGHT CROP..BOTTOM RIGHT CORNER +2320..2321 ; Common # Sm [2] TOP HALF INTEGRAL..BOTTOM HALF INTEGRAL +2322..2328 ; Common # So [7] FROWN..KEYBOARD +2329 ; Common # Ps LEFT-POINTING ANGLE BRACKET +232A ; Common # Pe RIGHT-POINTING ANGLE BRACKET +232B..237B ; Common # So [81] ERASE TO THE LEFT..NOT CHECK MARK +237C ; Common # Sm RIGHT ANGLE WITH DOWNWARDS ZIGZAG ARROW +237D..239A ; Common # So [30] SHOULDERED OPEN BOX..CLEAR SCREEN SYMBOL +239B..23B3 ; Common # Sm [25] LEFT PARENTHESIS UPPER HOOK..SUMMATION BOTTOM +23B4 ; Common # Ps TOP SQUARE BRACKET +23B5 ; Common # Pe BOTTOM SQUARE BRACKET +23B6 ; Common # Po BOTTOM SQUARE BRACKET OVER TOP SQUARE BRACKET +23B7..23D0 ; Common # So [26] RADICAL SYMBOL BOTTOM..VERTICAL LINE EXTENSION +2400..2426 ; Common # So [39] SYMBOL FOR NULL..SYMBOL FOR SUBSTITUTE FORM TWO +2440..244A ; Common # So [11] OCR HOOK..OCR DOUBLE BACKSLASH +2460..249B ; Common # No [60] CIRCLED DIGIT ONE..NUMBER TWENTY FULL STOP +249C..24E9 ; Common # So [78] PARENTHESIZED LATIN SMALL LETTER A..CIRCLED LATIN SMALL LETTER Z +24EA..24FF ; Common # No [22] CIRCLED DIGIT ZERO..NEGATIVE CIRCLED DIGIT ZERO +2500..25B6 ; Common # So [183] BOX DRAWINGS LIGHT HORIZONTAL..BLACK RIGHT-POINTING TRIANGLE +25B7 ; Common # Sm WHITE RIGHT-POINTING TRIANGLE +25B8..25C0 ; Common # So [9] BLACK RIGHT-POINTING SMALL TRIANGLE..BLACK LEFT-POINTING TRIANGLE +25C1 ; Common # Sm WHITE LEFT-POINTING TRIANGLE +25C2..25F7 ; Common # So [54] BLACK LEFT-POINTING SMALL TRIANGLE..WHITE CIRCLE WITH UPPER RIGHT QUADRANT +25F8..25FF ; Common # Sm [8] UPPER LEFT TRIANGLE..LOWER RIGHT TRIANGLE +2600..2617 ; Common # So [24] BLACK SUN WITH RAYS..BLACK SHOGI PIECE +2619..266E ; Common # So [86] REVERSED ROTATED FLORAL HEART BULLET..MUSIC NATURAL SIGN +266F ; Common # Sm MUSIC SHARP SIGN +2670..267D ; Common # So [14] WEST SYRIAC CROSS..PARTIALLY-RECYCLED PAPER SYMBOL +2680..2691 ; Common # So [18] DIE FACE-1..BLACK FLAG +26A0..26A1 ; Common # So [2] WARNING SIGN..HIGH VOLTAGE SIGN +2701..2704 ; Common # So [4] UPPER BLADE SCISSORS..WHITE SCISSORS +2706..2709 ; Common # So [4] TELEPHONE LOCATION SIGN..ENVELOPE +270C..2727 ; Common # So [28] VICTORY HAND..WHITE FOUR POINTED STAR +2729..274B ; Common # So [35] STRESS OUTLINED WHITE STAR..HEAVY EIGHT TEARDROP-SPOKED PROPELLER ASTERISK +274D ; Common # So SHADOWED WHITE CIRCLE +274F..2752 ; Common # So [4] LOWER RIGHT DROP-SHADOWED WHITE SQUARE..UPPER RIGHT SHADOWED WHITE SQUARE +2756 ; Common # So BLACK DIAMOND MINUS WHITE X +2758..275E ; Common # So [7] LIGHT VERTICAL BAR..HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT +2761..2767 ; Common # So [7] CURVED STEM PARAGRAPH SIGN ORNAMENT..ROTATED FLORAL HEART BULLET +2768 ; Common # Ps MEDIUM LEFT PARENTHESIS ORNAMENT +2769 ; Common # Pe MEDIUM RIGHT PARENTHESIS ORNAMENT +276A ; Common # Ps MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT +276B ; Common # Pe MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT +276C ; Common # Ps MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT +276D ; Common # Pe MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT +276E ; Common # Ps HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT +276F ; Common # Pe HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT +2770 ; Common # Ps HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT +2771 ; Common # Pe HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT +2772 ; Common # Ps LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT +2773 ; Common # Pe LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT +2774 ; Common # Ps MEDIUM LEFT CURLY BRACKET ORNAMENT +2775 ; Common # Pe MEDIUM RIGHT CURLY BRACKET ORNAMENT +2776..2793 ; Common # No [30] DINGBAT NEGATIVE CIRCLED DIGIT ONE..DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN +2794 ; Common # So HEAVY WIDE-HEADED RIGHTWARDS ARROW +2798..27AF ; Common # So [24] HEAVY SOUTH EAST ARROW..NOTCHED LOWER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW +27B1..27BE ; Common # So [14] NOTCHED UPPER RIGHT-SHADOWED WHITE RIGHTWARDS ARROW..OPEN-OUTLINED RIGHTWARDS ARROW +27D0..27E5 ; Common # Sm [22] WHITE DIAMOND WITH CENTRED DOT..WHITE SQUARE WITH RIGHTWARDS TICK +27E6 ; Common # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET +27E7 ; Common # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET +27E8 ; Common # Ps MATHEMATICAL LEFT ANGLE BRACKET +27E9 ; Common # Pe MATHEMATICAL RIGHT ANGLE BRACKET +27EA ; Common # Ps MATHEMATICAL LEFT DOUBLE ANGLE BRACKET +27EB ; Common # Pe MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET +27F0..27FF ; Common # Sm [16] UPWARDS QUADRUPLE ARROW..LONG RIGHTWARDS SQUIGGLE ARROW +2900..2982 ; Common # Sm [131] RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE..Z NOTATION TYPE COLON +2983 ; Common # Ps LEFT WHITE CURLY BRACKET +2984 ; Common # Pe RIGHT WHITE CURLY BRACKET +2985 ; Common # Ps LEFT WHITE PARENTHESIS +2986 ; Common # Pe RIGHT WHITE PARENTHESIS +2987 ; Common # Ps Z NOTATION LEFT IMAGE BRACKET +2988 ; Common # Pe Z NOTATION RIGHT IMAGE BRACKET +2989 ; Common # Ps Z NOTATION LEFT BINDING BRACKET +298A ; Common # Pe Z NOTATION RIGHT BINDING BRACKET +298B ; Common # Ps LEFT SQUARE BRACKET WITH UNDERBAR +298C ; Common # Pe RIGHT SQUARE BRACKET WITH UNDERBAR +298D ; Common # Ps LEFT SQUARE BRACKET WITH TICK IN TOP CORNER +298E ; Common # Pe RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +298F ; Common # Ps LEFT SQUARE BRACKET WITH TICK IN BOTTOM CORNER +2990 ; Common # Pe RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER +2991 ; Common # Ps LEFT ANGLE BRACKET WITH DOT +2992 ; Common # Pe RIGHT ANGLE BRACKET WITH DOT +2993 ; Common # Ps LEFT ARC LESS-THAN BRACKET +2994 ; Common # Pe RIGHT ARC GREATER-THAN BRACKET +2995 ; Common # Ps DOUBLE LEFT ARC GREATER-THAN BRACKET +2996 ; Common # Pe DOUBLE RIGHT ARC LESS-THAN BRACKET +2997 ; Common # Ps LEFT BLACK TORTOISE SHELL BRACKET +2998 ; Common # Pe RIGHT BLACK TORTOISE SHELL BRACKET +2999..29D7 ; Common # Sm [63] DOTTED FENCE..BLACK HOURGLASS +29D8 ; Common # Ps LEFT WIGGLY FENCE +29D9 ; Common # Pe RIGHT WIGGLY FENCE +29DA ; Common # Ps LEFT DOUBLE WIGGLY FENCE +29DB ; Common # Pe RIGHT DOUBLE WIGGLY FENCE +29DC..29FB ; Common # Sm [32] INCOMPLETE INFINITY..TRIPLE PLUS +29FC ; Common # Ps LEFT-POINTING CURVED ANGLE BRACKET +29FD ; Common # Pe RIGHT-POINTING CURVED ANGLE BRACKET +29FE..2AFF ; Common # Sm [258] TINY..N-ARY WHITE VERTICAL BAR +2B00..2B0D ; Common # So [14] NORTH EAST WHITE ARROW..UP DOWN BLACK ARROW +2FF0..2FFB ; Common # So [12] IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID +3000 ; Common # Zs IDEOGRAPHIC SPACE +3001..3003 ; Common # Po [3] IDEOGRAPHIC COMMA..DITTO MARK +3004 ; Common # So JAPANESE INDUSTRIAL STANDARD SYMBOL +3006 ; Common # Lo IDEOGRAPHIC CLOSING MARK +3008 ; Common # Ps LEFT ANGLE BRACKET +3009 ; Common # Pe RIGHT ANGLE BRACKET +300A ; Common # Ps LEFT DOUBLE ANGLE BRACKET +300B ; Common # Pe RIGHT DOUBLE ANGLE BRACKET +300C ; Common # Ps LEFT CORNER BRACKET +300D ; Common # Pe RIGHT CORNER BRACKET +300E ; Common # Ps LEFT WHITE CORNER BRACKET +300F ; Common # Pe RIGHT WHITE CORNER BRACKET +3010 ; Common # Ps LEFT BLACK LENTICULAR BRACKET +3011 ; Common # Pe RIGHT BLACK LENTICULAR BRACKET +3012..3013 ; Common # So [2] POSTAL MARK..GETA MARK +3014 ; Common # Ps LEFT TORTOISE SHELL BRACKET +3015 ; Common # Pe RIGHT TORTOISE SHELL BRACKET +3016 ; Common # Ps LEFT WHITE LENTICULAR BRACKET +3017 ; Common # Pe RIGHT WHITE LENTICULAR BRACKET +3018 ; Common # Ps LEFT WHITE TORTOISE SHELL BRACKET +3019 ; Common # Pe RIGHT WHITE TORTOISE SHELL BRACKET +301A ; Common # Ps LEFT WHITE SQUARE BRACKET +301B ; Common # Pe RIGHT WHITE SQUARE BRACKET +301C ; Common # Pd WAVE DASH +301D ; Common # Ps REVERSED DOUBLE PRIME QUOTATION MARK +301E..301F ; Common # Pe [2] DOUBLE PRIME QUOTATION MARK..LOW DOUBLE PRIME QUOTATION MARK +3020 ; Common # So POSTAL MARK FACE +3030 ; Common # Pd WAVY DASH +3036..3037 ; Common # So [2] CIRCLED POSTAL MARK..IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL +303C ; Common # Lo MASU MARK +303D ; Common # Po PART ALTERNATION MARK +303E..303F ; Common # So [2] IDEOGRAPHIC VARIATION INDICATOR..IDEOGRAPHIC HALF FILL SPACE +30A0 ; Common # Pd KATAKANA-HIRAGANA DOUBLE HYPHEN +30FB ; Common # Pc KATAKANA MIDDLE DOT +30FC ; Common # Lm KATAKANA-HIRAGANA PROLONGED SOUND MARK +3190..3191 ; Common # So [2] IDEOGRAPHIC ANNOTATION LINKING MARK..IDEOGRAPHIC ANNOTATION REVERSE MARK +3192..3195 ; Common # No [4] IDEOGRAPHIC ANNOTATION ONE MARK..IDEOGRAPHIC ANNOTATION FOUR MARK +3196..319F ; Common # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK +3220..3229 ; Common # No [10] PARENTHESIZED IDEOGRAPH ONE..PARENTHESIZED IDEOGRAPH TEN +322A..3243 ; Common # So [26] PARENTHESIZED IDEOGRAPH MOON..PARENTHESIZED IDEOGRAPH REACH +3250 ; Common # So PARTNERSHIP SIGN +3251..325F ; Common # No [15] CIRCLED NUMBER TWENTY ONE..CIRCLED NUMBER THIRTY FIVE +327F ; Common # So KOREAN STANDARD SYMBOL +3280..3289 ; Common # No [10] CIRCLED IDEOGRAPH ONE..CIRCLED IDEOGRAPH TEN +328A..32B0 ; Common # So [39] CIRCLED IDEOGRAPH MOON..CIRCLED IDEOGRAPH NIGHT +32B1..32BF ; Common # No [15] CIRCLED NUMBER THIRTY SIX..CIRCLED NUMBER FIFTY +32C0..32FE ; Common # So [63] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..CIRCLED KATAKANA WO +3300..33FF ; Common # So [256] SQUARE APAATO..SQUARE GAL +4DC0..4DFF ; Common # So [64] HEXAGRAM FOR THE CREATIVE HEAVEN..HEXAGRAM FOR BEFORE COMPLETION +E000..F8FF ; Common # Co [6400] .. +FD3E ; Common # Ps ORNATE LEFT PARENTHESIS +FD3F ; Common # Pe ORNATE RIGHT PARENTHESIS +FDFD ; Common # So ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM +FE30 ; Common # Po PRESENTATION FORM FOR VERTICAL TWO DOT LEADER +FE31..FE32 ; Common # Pd [2] PRESENTATION FORM FOR VERTICAL EM DASH..PRESENTATION FORM FOR VERTICAL EN DASH +FE33..FE34 ; Common # Pc [2] PRESENTATION FORM FOR VERTICAL LOW LINE..PRESENTATION FORM FOR VERTICAL WAVY LOW LINE +FE35 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS +FE36 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT PARENTHESIS +FE37 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT CURLY BRACKET +FE38 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT CURLY BRACKET +FE39 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT TORTOISE SHELL BRACKET +FE3A ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT TORTOISE SHELL BRACKET +FE3B ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT BLACK LENTICULAR BRACKET +FE3C ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT BLACK LENTICULAR BRACKET +FE3D ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT DOUBLE ANGLE BRACKET +FE3E ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT DOUBLE ANGLE BRACKET +FE3F ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT ANGLE BRACKET +FE40 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT ANGLE BRACKET +FE41 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT CORNER BRACKET +FE42 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT CORNER BRACKET +FE43 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE CORNER BRACKET +FE44 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT WHITE CORNER BRACKET +FE45..FE46 ; Common # Po [2] SESAME DOT..WHITE SESAME DOT +FE47 ; Common # Ps PRESENTATION FORM FOR VERTICAL LEFT SQUARE BRACKET +FE48 ; Common # Pe PRESENTATION FORM FOR VERTICAL RIGHT SQUARE BRACKET +FE49..FE4C ; Common # Po [4] DASHED OVERLINE..DOUBLE WAVY OVERLINE +FE4D..FE4F ; Common # Pc [3] DASHED LOW LINE..WAVY LOW LINE +FE50..FE52 ; Common # Po [3] SMALL COMMA..SMALL FULL STOP +FE54..FE57 ; Common # Po [4] SMALL SEMICOLON..SMALL EXCLAMATION MARK +FE58 ; Common # Pd SMALL EM DASH +FE59 ; Common # Ps SMALL LEFT PARENTHESIS +FE5A ; Common # Pe SMALL RIGHT PARENTHESIS +FE5B ; Common # Ps SMALL LEFT CURLY BRACKET +FE5C ; Common # Pe SMALL RIGHT CURLY BRACKET +FE5D ; Common # Ps SMALL LEFT TORTOISE SHELL BRACKET +FE5E ; Common # Pe SMALL RIGHT TORTOISE SHELL BRACKET +FE5F..FE61 ; Common # Po [3] SMALL NUMBER SIGN..SMALL ASTERISK +FE62 ; Common # Sm SMALL PLUS SIGN +FE63 ; Common # Pd SMALL HYPHEN-MINUS +FE64..FE66 ; Common # Sm [3] SMALL LESS-THAN SIGN..SMALL EQUALS SIGN +FE68 ; Common # Po SMALL REVERSE SOLIDUS +FE69 ; Common # Sc SMALL DOLLAR SIGN +FE6A..FE6B ; Common # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT +FEFF ; Common # Cf ZERO WIDTH NO-BREAK SPACE +FF01..FF03 ; Common # Po [3] FULLWIDTH EXCLAMATION MARK..FULLWIDTH NUMBER SIGN +FF04 ; Common # Sc FULLWIDTH DOLLAR SIGN +FF05..FF07 ; Common # Po [3] FULLWIDTH PERCENT SIGN..FULLWIDTH APOSTROPHE +FF08 ; Common # Ps FULLWIDTH LEFT PARENTHESIS +FF09 ; Common # Pe FULLWIDTH RIGHT PARENTHESIS +FF0A ; Common # Po FULLWIDTH ASTERISK +FF0B ; Common # Sm FULLWIDTH PLUS SIGN +FF0C ; Common # Po FULLWIDTH COMMA +FF0D ; Common # Pd FULLWIDTH HYPHEN-MINUS +FF0E..FF0F ; Common # Po [2] FULLWIDTH FULL STOP..FULLWIDTH SOLIDUS +FF10..FF19 ; Common # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE +FF1A..FF1B ; Common # Po [2] FULLWIDTH COLON..FULLWIDTH SEMICOLON +FF1C..FF1E ; Common # Sm [3] FULLWIDTH LESS-THAN SIGN..FULLWIDTH GREATER-THAN SIGN +FF1F..FF20 ; Common # Po [2] FULLWIDTH QUESTION MARK..FULLWIDTH COMMERCIAL AT +FF3B ; Common # Ps FULLWIDTH LEFT SQUARE BRACKET +FF3C ; Common # Po FULLWIDTH REVERSE SOLIDUS +FF3D ; Common # Pe FULLWIDTH RIGHT SQUARE BRACKET +FF3E ; Common # Sk FULLWIDTH CIRCUMFLEX ACCENT +FF3F ; Common # Pc FULLWIDTH LOW LINE +FF40 ; Common # Sk FULLWIDTH GRAVE ACCENT +FF5B ; Common # Ps FULLWIDTH LEFT CURLY BRACKET +FF5C ; Common # Sm FULLWIDTH VERTICAL LINE +FF5D ; Common # Pe FULLWIDTH RIGHT CURLY BRACKET +FF5E ; Common # Sm FULLWIDTH TILDE +FF5F ; Common # Ps FULLWIDTH LEFT WHITE PARENTHESIS +FF60 ; Common # Pe FULLWIDTH RIGHT WHITE PARENTHESIS +FF61 ; Common # Po HALFWIDTH IDEOGRAPHIC FULL STOP +FF62 ; Common # Ps HALFWIDTH LEFT CORNER BRACKET +FF63 ; Common # Pe HALFWIDTH RIGHT CORNER BRACKET +FF64 ; Common # Po HALFWIDTH IDEOGRAPHIC COMMA +FF65 ; Common # Pc HALFWIDTH KATAKANA MIDDLE DOT +FFE0..FFE1 ; Common # Sc [2] FULLWIDTH CENT SIGN..FULLWIDTH POUND SIGN +FFE2 ; Common # Sm FULLWIDTH NOT SIGN +FFE3 ; Common # Sk FULLWIDTH MACRON +FFE4 ; Common # So FULLWIDTH BROKEN BAR +FFE5..FFE6 ; Common # Sc [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN +FFE8 ; Common # So HALFWIDTH FORMS LIGHT VERTICAL +FFE9..FFEC ; Common # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS ARROW +FFED..FFEE ; Common # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE +FFF9..FFFB ; Common # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER +10100..10101 ; Common # Po [2] AEGEAN WORD SEPARATOR LINE..AEGEAN WORD SEPARATOR DOT +10102 ; Common # So AEGEAN CHECK MARK +10107..10133 ; Common # No [45] AEGEAN NUMBER ONE..AEGEAN NUMBER NINETY THOUSAND +10137..1013F ; Common # So [9] AEGEAN WEIGHT BASE UNIT..AEGEAN MEASURE THIRD SUBUNIT +1D000..1D0F5 ; Common # So [246] BYZANTINE MUSICAL SYMBOL PSILI..BYZANTINE MUSICAL SYMBOL GORGON NEO KATO +1D100..1D126 ; Common # So [39] MUSICAL SYMBOL SINGLE BARLINE..MUSICAL SYMBOL DRUM CLEF-2 +1D12A..1D164 ; Common # So [59] MUSICAL SYMBOL DOUBLE SHARP..MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE +1D165..1D166 ; Common # Mc [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM +1D16A..1D16C ; Common # So [3] MUSICAL SYMBOL FINGERED TREMOLO-1..MUSICAL SYMBOL FINGERED TREMOLO-3 +1D16D..1D172 ; Common # Mc [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5 +1D173..1D17A ; Common # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D183..1D184 ; Common # So [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN +1D18C..1D1A9 ; Common # So [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH +1D1AE..1D1DD ; Common # So [48] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL PES SUBPUNCTIS +1D300..1D356 ; Common # So [87] MONOGRAM FOR EARTH..TETRAGRAM FOR FOSTERING +1D400..1D454 ; Common # L& [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G +1D456..1D49C ; Common # L& [71] MATHEMATICAL ITALIC SMALL I..MATHEMATICAL SCRIPT CAPITAL A +1D49E..1D49F ; Common # L& [2] MATHEMATICAL SCRIPT CAPITAL C..MATHEMATICAL SCRIPT CAPITAL D +1D4A2 ; Common # L& MATHEMATICAL SCRIPT CAPITAL G +1D4A5..1D4A6 ; Common # L& [2] MATHEMATICAL SCRIPT CAPITAL J..MATHEMATICAL SCRIPT CAPITAL K +1D4A9..1D4AC ; Common # L& [4] MATHEMATICAL SCRIPT CAPITAL N..MATHEMATICAL SCRIPT CAPITAL Q +1D4AE..1D4B9 ; Common # L& [12] MATHEMATICAL SCRIPT CAPITAL S..MATHEMATICAL SCRIPT SMALL D +1D4BB ; Common # L& MATHEMATICAL SCRIPT SMALL F +1D4BD..1D4C3 ; Common # L& [7] MATHEMATICAL SCRIPT SMALL H..MATHEMATICAL SCRIPT SMALL N +1D4C5..1D505 ; Common # L& [65] MATHEMATICAL SCRIPT SMALL P..MATHEMATICAL FRAKTUR CAPITAL B +1D507..1D50A ; Common # L& [4] MATHEMATICAL FRAKTUR CAPITAL D..MATHEMATICAL FRAKTUR CAPITAL G +1D50D..1D514 ; Common # L& [8] MATHEMATICAL FRAKTUR CAPITAL J..MATHEMATICAL FRAKTUR CAPITAL Q +1D516..1D51C ; Common # L& [7] MATHEMATICAL FRAKTUR CAPITAL S..MATHEMATICAL FRAKTUR CAPITAL Y +1D51E..1D539 ; Common # L& [28] MATHEMATICAL FRAKTUR SMALL A..MATHEMATICAL DOUBLE-STRUCK CAPITAL B +1D53B..1D53E ; Common # L& [4] MATHEMATICAL DOUBLE-STRUCK CAPITAL D..MATHEMATICAL DOUBLE-STRUCK CAPITAL G +1D540..1D544 ; Common # L& [5] MATHEMATICAL DOUBLE-STRUCK CAPITAL I..MATHEMATICAL DOUBLE-STRUCK CAPITAL M +1D546 ; Common # L& MATHEMATICAL DOUBLE-STRUCK CAPITAL O +1D54A..1D550 ; Common # L& [7] MATHEMATICAL DOUBLE-STRUCK CAPITAL S..MATHEMATICAL DOUBLE-STRUCK CAPITAL Y +1D552..1D6A3 ; Common # L& [338] MATHEMATICAL DOUBLE-STRUCK SMALL A..MATHEMATICAL MONOSPACE SMALL Z +1D6A8..1D6C0 ; Common # L& [25] MATHEMATICAL BOLD CAPITAL ALPHA..MATHEMATICAL BOLD CAPITAL OMEGA +1D6C1 ; Common # Sm MATHEMATICAL BOLD NABLA +1D6C2..1D6DA ; Common # L& [25] MATHEMATICAL BOLD SMALL ALPHA..MATHEMATICAL BOLD SMALL OMEGA +1D6DB ; Common # Sm MATHEMATICAL BOLD PARTIAL DIFFERENTIAL +1D6DC..1D6FA ; Common # L& [31] MATHEMATICAL BOLD EPSILON SYMBOL..MATHEMATICAL ITALIC CAPITAL OMEGA +1D6FB ; Common # Sm MATHEMATICAL ITALIC NABLA +1D6FC..1D714 ; Common # L& [25] MATHEMATICAL ITALIC SMALL ALPHA..MATHEMATICAL ITALIC SMALL OMEGA +1D715 ; Common # Sm MATHEMATICAL ITALIC PARTIAL DIFFERENTIAL +1D716..1D734 ; Common # L& [31] MATHEMATICAL ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD ITALIC CAPITAL OMEGA +1D735 ; Common # Sm MATHEMATICAL BOLD ITALIC NABLA +1D736..1D74E ; Common # L& [25] MATHEMATICAL BOLD ITALIC SMALL ALPHA..MATHEMATICAL BOLD ITALIC SMALL OMEGA +1D74F ; Common # Sm MATHEMATICAL BOLD ITALIC PARTIAL DIFFERENTIAL +1D750..1D76E ; Common # L& [31] MATHEMATICAL BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD CAPITAL OMEGA +1D76F ; Common # Sm MATHEMATICAL SANS-SERIF BOLD NABLA +1D770..1D788 ; Common # L& [25] MATHEMATICAL SANS-SERIF BOLD SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD SMALL OMEGA +1D789 ; Common # Sm MATHEMATICAL SANS-SERIF BOLD PARTIAL DIFFERENTIAL +1D78A..1D7A8 ; Common # L& [31] MATHEMATICAL SANS-SERIF BOLD EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL OMEGA +1D7A9 ; Common # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC NABLA +1D7AA..1D7C2 ; Common # L& [25] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL ALPHA..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL OMEGA +1D7C3 ; Common # Sm MATHEMATICAL SANS-SERIF BOLD ITALIC PARTIAL DIFFERENTIAL +1D7C4..1D7C9 ; Common # L& [6] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL SANS-SERIF BOLD ITALIC PI SYMBOL +1D7CE..1D7FF ; Common # Nd [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE +E0001 ; Common # Cf LANGUAGE TAG +E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG +F0000..FFFFD ; Common # Co [65534] .. +100000..10FFFD; Common # Co [65534] .. + +# The above property value applies to 880197 code points not listed here. +# Total code points: 1022471 + +# ================================================ + +0041..005A ; Latin # L& [26] LATIN CAPITAL LETTER A..LATIN CAPITAL LETTER Z +0061..007A ; Latin # L& [26] LATIN SMALL LETTER A..LATIN SMALL LETTER Z +00AA ; Latin # L& FEMININE ORDINAL INDICATOR +00BA ; Latin # L& MASCULINE ORDINAL INDICATOR +00C0..00D6 ; Latin # L& [23] LATIN CAPITAL LETTER A WITH GRAVE..LATIN CAPITAL LETTER O WITH DIAERESIS +00D8..00F6 ; Latin # L& [31] LATIN CAPITAL LETTER O WITH STROKE..LATIN SMALL LETTER O WITH DIAERESIS +00F8..01BA ; Latin # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL +01BB ; Latin # Lo LATIN LETTER TWO WITH STROKE +01BC..01BF ; Latin # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN +01C0..01C3 ; Latin # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK +01C4..0236 ; Latin # L& [115] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER T WITH CURL +0250..02AF ; Latin # L& [96] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +02B0..02B8 ; Latin # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y +02E0..02E4 ; Latin # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP +1D00..1D25 ; Latin # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN +1D2C..1D5C ; Latin # Lm [49] MODIFIER LETTER CAPITAL A..MODIFIER LETTER SMALL AIN +1D62..1D65 ; Latin # L& [4] LATIN SUBSCRIPT SMALL LETTER I..LATIN SUBSCRIPT SMALL LETTER V +1D6B ; Latin # L& LATIN SMALL LETTER UE +1E00..1E9B ; Latin # L& [156] LATIN CAPITAL LETTER A WITH RING BELOW..LATIN SMALL LETTER LONG S WITH DOT ABOVE +1EA0..1EF9 ; Latin # L& [90] LATIN CAPITAL LETTER A WITH DOT BELOW..LATIN SMALL LETTER Y WITH TILDE +2071 ; Latin # L& SUPERSCRIPT LATIN SMALL LETTER I +207F ; Latin # L& SUPERSCRIPT LATIN SMALL LETTER N +212A..212B ; Latin # L& [2] KELVIN SIGN..ANGSTROM SIGN +FB00..FB06 ; Latin # L& [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST +FF21..FF3A ; Latin # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAPITAL LETTER Z +FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL LETTER Z # Total code points: 938 # ================================================ -00B5 ; GREEK # L& MICRO SIGN -037A ; GREEK # Lm GREEK YPOGEGRAMMENI -0386 ; GREEK # L& GREEK CAPITAL LETTER ALPHA WITH TONOS -0388..038A ; GREEK # L& [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS -038C ; GREEK # L& GREEK CAPITAL LETTER OMICRON WITH TONOS -038E..03A1 ; GREEK # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO -03A3..03CE ; GREEK # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS -03D0..03F5 ; GREEK # L& [38] GREEK BETA SYMBOL..GREEK LUNATE EPSILON SYMBOL -03F7..03FB ; GREEK # L& [5] GREEK CAPITAL LETTER SHO..GREEK SMALL LETTER SAN -1D26..1D2A ; GREEK # L& [5] GREEK LETTER SMALL CAPITAL GAMMA..GREEK LETTER SMALL CAPITAL PSI -1D5D..1D61 ; GREEK # Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI -1D66..1D6A ; GREEK # L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI -1F00..1F15 ; GREEK # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA -1F18..1F1D ; GREEK # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA -1F20..1F45 ; GREEK # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA -1F48..1F4D ; GREEK # L& [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA -1F50..1F57 ; GREEK # L& [8] GREEK SMALL LETTER UPSILON WITH PSILI..GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI -1F59 ; GREEK # L& GREEK CAPITAL LETTER UPSILON WITH DASIA -1F5B ; GREEK # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA -1F5D ; GREEK # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA -1F5F..1F7D ; GREEK # L& [31] GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI..GREEK SMALL LETTER OMEGA WITH OXIA -1F80..1FB4 ; GREEK # L& [53] GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI -1FB6..1FBC ; GREEK # L& [7] GREEK SMALL LETTER ALPHA WITH PERISPOMENI..GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI -1FBE ; GREEK # L& GREEK PROSGEGRAMMENI -1FC2..1FC4 ; GREEK # L& [3] GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI -1FC6..1FCC ; GREEK # L& [7] GREEK SMALL LETTER ETA WITH PERISPOMENI..GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI -1FD0..1FD3 ; GREEK # L& [4] GREEK SMALL LETTER IOTA WITH VRACHY..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA -1FD6..1FDB ; GREEK # L& [6] GREEK SMALL LETTER IOTA WITH PERISPOMENI..GREEK CAPITAL LETTER IOTA WITH OXIA -1FE0..1FEC ; GREEK # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA -1FF2..1FF4 ; GREEK # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI -1FF6..1FFC ; GREEK # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI -2126 ; GREEK # L& OHM SIGN - -# Total code points: 348 - -# ================================================ - -0400..0481 ; CYRILLIC # L& [130] CYRILLIC CAPITAL LETTER IE WITH GRAVE..CYRILLIC SMALL LETTER KOPPA -0483..0486 ; CYRILLIC # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA -048A..04CE ; CYRILLIC # L& [69] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EM WITH TAIL -04D0..04F5 ; CYRILLIC # L& [38] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER CHE WITH DIAERESIS -04F8..04F9 ; CYRILLIC # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS -0500..050F ; CYRILLIC # L& [16] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER KOMI TJE -1D2B ; CYRILLIC # L& CYRILLIC LETTER SMALL CAPITAL EL - -# Total code points: 260 - -# ================================================ - -0531..0556 ; ARMENIAN # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH -0559 ; ARMENIAN # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING -0561..0587 ; ARMENIAN # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN -FB13..FB17 ; ARMENIAN # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH +0374..0375 ; Greek # Sk [2] GREEK NUMERAL SIGN..GREEK LOWER NUMERAL SIGN +037A ; Greek # Lm GREEK YPOGEGRAMMENI +0384..0385 ; Greek # Sk [2] GREEK TONOS..GREEK DIALYTIKA TONOS +0386 ; Greek # L& GREEK CAPITAL LETTER ALPHA WITH TONOS +0388..038A ; Greek # L& [3] GREEK CAPITAL LETTER EPSILON WITH TONOS..GREEK CAPITAL LETTER IOTA WITH TONOS +038C ; Greek # L& GREEK CAPITAL LETTER OMICRON WITH TONOS +038E..03A1 ; Greek # L& [20] GREEK CAPITAL LETTER UPSILON WITH TONOS..GREEK CAPITAL LETTER RHO +03A3..03CE ; Greek # L& [44] GREEK CAPITAL LETTER SIGMA..GREEK SMALL LETTER OMEGA WITH TONOS +03D0..03F5 ; Greek # L& [38] GREEK BETA SYMBOL..GREEK LUNATE EPSILON SYMBOL +03F6 ; Greek # Sm GREEK REVERSED LUNATE EPSILON SYMBOL +03F7..03FB ; Greek # L& [5] GREEK CAPITAL LETTER SHO..GREEK SMALL LETTER SAN +1D26..1D2A ; Greek # L& [5] GREEK LETTER SMALL CAPITAL GAMMA..GREEK LETTER SMALL CAPITAL PSI +1D5D..1D61 ; Greek # Lm [5] MODIFIER LETTER SMALL BETA..MODIFIER LETTER SMALL CHI +1D66..1D6A ; Greek # L& [5] GREEK SUBSCRIPT SMALL LETTER BETA..GREEK SUBSCRIPT SMALL LETTER CHI +1F00..1F15 ; Greek # L& [22] GREEK SMALL LETTER ALPHA WITH PSILI..GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA +1F18..1F1D ; Greek # L& [6] GREEK CAPITAL LETTER EPSILON WITH PSILI..GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F20..1F45 ; Greek # L& [38] GREEK SMALL LETTER ETA WITH PSILI..GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA +1F48..1F4D ; Greek # L& [6] GREEK CAPITAL LETTER OMICRON WITH PSILI..GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F50..1F57 ; Greek # L& [8] GREEK SMALL LETTER UPSILON WITH PSILI..GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F59 ; Greek # L& GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B ; Greek # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D ; Greek # L& GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F..1F7D ; Greek # L& [31] GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI..GREEK SMALL LETTER OMEGA WITH OXIA +1F80..1FB4 ; Greek # L& [53] GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI..GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6..1FBC ; Greek # L& [7] GREEK SMALL LETTER ALPHA WITH PERISPOMENI..GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBD ; Greek # Sk GREEK KORONIS +1FBE ; Greek # L& GREEK PROSGEGRAMMENI +1FBF..1FC1 ; Greek # Sk [3] GREEK PSILI..GREEK DIALYTIKA AND PERISPOMENI +1FC2..1FC4 ; Greek # L& [3] GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6..1FCC ; Greek # L& [7] GREEK SMALL LETTER ETA WITH PERISPOMENI..GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FCD..1FCF ; Greek # Sk [3] GREEK PSILI AND VARIA..GREEK PSILI AND PERISPOMENI +1FD0..1FD3 ; Greek # L& [4] GREEK SMALL LETTER IOTA WITH VRACHY..GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6..1FDB ; Greek # L& [6] GREEK SMALL LETTER IOTA WITH PERISPOMENI..GREEK CAPITAL LETTER IOTA WITH OXIA +1FDD..1FDF ; Greek # Sk [3] GREEK DASIA AND VARIA..GREEK DASIA AND PERISPOMENI +1FE0..1FEC ; Greek # L& [13] GREEK SMALL LETTER UPSILON WITH VRACHY..GREEK CAPITAL LETTER RHO WITH DASIA +1FED..1FEF ; Greek # Sk [3] GREEK DIALYTIKA AND VARIA..GREEK VARIA +1FF2..1FF4 ; Greek # L& [3] GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI..GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6..1FFC ; Greek # L& [7] GREEK SMALL LETTER OMEGA WITH PERISPOMENI..GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +1FFD..1FFE ; Greek # Sk [2] GREEK OXIA..GREEK DASIA +2126 ; Greek # L& OHM SIGN + +# Total code points: 367 -# Total code points: 83 +# ================================================ + +0400..0481 ; Cyrillic # L& [130] CYRILLIC CAPITAL LETTER IE WITH GRAVE..CYRILLIC SMALL LETTER KOPPA +0482 ; Cyrillic # So CYRILLIC THOUSANDS SIGN +0483..0486 ; Cyrillic # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA +0488..0489 ; Cyrillic # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +048A..04CE ; Cyrillic # L& [69] CYRILLIC CAPITAL LETTER SHORT I WITH TAIL..CYRILLIC SMALL LETTER EM WITH TAIL +04D0..04F5 ; Cyrillic # L& [38] CYRILLIC CAPITAL LETTER A WITH BREVE..CYRILLIC SMALL LETTER CHE WITH DIAERESIS +04F8..04F9 ; Cyrillic # L& [2] CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS..CYRILLIC SMALL LETTER YERU WITH DIAERESIS +0500..050F ; Cyrillic # L& [16] CYRILLIC CAPITAL LETTER KOMI DE..CYRILLIC SMALL LETTER KOMI TJE +1D2B ; Cyrillic # L& CYRILLIC LETTER SMALL CAPITAL EL + +# Total code points: 263 # ================================================ -05D0..05EA ; HEBREW # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV -05F0..05F2 ; HEBREW # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD -FB1D ; HEBREW # Lo HEBREW LETTER YOD WITH HIRIQ -FB1F..FB28 ; HEBREW # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV -FB2A..FB36 ; HEBREW # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH -FB38..FB3C ; HEBREW # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH -FB3E ; HEBREW # Lo HEBREW LETTER MEM WITH DAGESH -FB40..FB41 ; HEBREW # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH -FB43..FB44 ; HEBREW # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH -FB46..FB4F ; HEBREW # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED +0531..0556 ; Armenian # L& [38] ARMENIAN CAPITAL LETTER AYB..ARMENIAN CAPITAL LETTER FEH +0559 ; Armenian # Lm ARMENIAN MODIFIER LETTER LEFT HALF RING +055A..055F ; Armenian # Po [6] ARMENIAN APOSTROPHE..ARMENIAN ABBREVIATION MARK +0561..0587 ; Armenian # L& [39] ARMENIAN SMALL LETTER AYB..ARMENIAN SMALL LIGATURE ECH YIWN +058A ; Armenian # Pd ARMENIAN HYPHEN +FB13..FB17 ; Armenian # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH -# Total code points: 74 +# Total code points: 90 # ================================================ -0621..063A ; ARABIC # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN -0641..064A ; ARABIC # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH -066E..066F ; ARABIC # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF -0671..06D3 ; ARABIC # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE -06D5 ; ARABIC # Lo ARABIC LETTER AE -06E5..06E6 ; ARABIC # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH -06EE..06EF ; ARABIC # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V -06FA..06FC ; ARABIC # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW -06FF ; ARABIC # Lo ARABIC LETTER HEH WITH INVERTED V -FB50..FBB1 ; ARABIC # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM -FBD3..FD3D ; ARABIC # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM -FD50..FD8F ; ARABIC # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD92..FDC7 ; ARABIC # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDF0..FDFB ; ARABIC # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU -FE70..FE74 ; ARABIC # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM -FE76..FEFC ; ARABIC # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM +0591..05A1 ; Hebrew # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER +05A3..05B9 ; Hebrew # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM +05BB..05BD ; Hebrew # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG +05BE ; Hebrew # Po HEBREW PUNCTUATION MAQAF +05BF ; Hebrew # Mn HEBREW POINT RAFE +05C0 ; Hebrew # Po HEBREW PUNCTUATION PASEQ +05C1..05C2 ; Hebrew # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C3 ; Hebrew # Po HEBREW PUNCTUATION SOF PASUQ +05C4 ; Hebrew # Mn HEBREW MARK UPPER DOT +05D0..05EA ; Hebrew # Lo [27] HEBREW LETTER ALEF..HEBREW LETTER TAV +05F0..05F2 ; Hebrew # Lo [3] HEBREW LIGATURE YIDDISH DOUBLE VAV..HEBREW LIGATURE YIDDISH DOUBLE YOD +05F3..05F4 ; Hebrew # Po [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM +FB1D ; Hebrew # Lo HEBREW LETTER YOD WITH HIRIQ +FB1E ; Hebrew # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FB1F..FB28 ; Hebrew # Lo [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV +FB29 ; Hebrew # Sm HEBREW LETTER ALTERNATIVE PLUS SIGN +FB2A..FB36 ; Hebrew # Lo [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH +FB38..FB3C ; Hebrew # Lo [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH +FB3E ; Hebrew # Lo HEBREW LETTER MEM WITH DAGESH +FB40..FB41 ; Hebrew # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH +FB43..FB44 ; Hebrew # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH +FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED + +# Total code points: 128 + +# ================================================ -# Total code points: 877 +060D ; Arabic # Po ARABIC DATE SEPARATOR +060E..060F ; Arabic # So [2] ARABIC POETIC VERSE SIGN..ARABIC SIGN MISRA +0610..0615 ; Arabic # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH +0621..063A ; Arabic # Lo [26] ARABIC LETTER HAMZA..ARABIC LETTER GHAIN +0641..064A ; Arabic # Lo [10] ARABIC LETTER FEH..ARABIC LETTER YEH +0656..0658 ; Arabic # Mn [3] ARABIC SUBSCRIPT ALEF..ARABIC MARK NOON GHUNNA +066A..066D ; Arabic # Po [4] ARABIC PERCENT SIGN..ARABIC FIVE POINTED STAR +066E..066F ; Arabic # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0671..06D3 ; Arabic # Lo [99] ARABIC LETTER ALEF WASLA..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D4 ; Arabic # Po ARABIC FULL STOP +06D5 ; Arabic # Lo ARABIC LETTER AE +06D6..06DC ; Arabic # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DE ; Arabic # Me ARABIC START OF RUB EL HIZB +06DF..06E4 ; Arabic # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E5..06E6 ; Arabic # Lm [2] ARABIC SMALL WAW..ARABIC SMALL YEH +06E7..06E8 ; Arabic # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06E9 ; Arabic # So ARABIC PLACE OF SAJDAH +06EA..06ED ; Arabic # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +06EE..06EF ; Arabic # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +06F0..06F9 ; Arabic # Nd [10] EXTENDED ARABIC-INDIC DIGIT ZERO..EXTENDED ARABIC-INDIC DIGIT NINE +06FA..06FC ; Arabic # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FD..06FE ; Arabic # So [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN +06FF ; Arabic # Lo ARABIC LETTER HEH WITH INVERTED V +FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM +FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM +FD50..FD8F ; Arabic # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD92..FDC7 ; Arabic # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDF0..FDFB ; Arabic # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU +FDFC ; Arabic # Sc RIAL SIGN +FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM +FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM + +# Total code points: 928 # ================================================ -0710 ; SYRIAC # Lo SYRIAC LETTER ALAPH -0711 ; SYRIAC # Mn SYRIAC LETTER SUPERSCRIPT ALAPH -0712..072F ; SYRIAC # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH -0730..074A ; SYRIAC # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH -074D..074F ; SYRIAC # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE +0700..070D ; Syriac # Po [14] SYRIAC END OF PARAGRAPH..SYRIAC HARKLEAN ASTERISCUS +070F ; Syriac # Cf SYRIAC ABBREVIATION MARK +0710 ; Syriac # Lo SYRIAC LETTER ALAPH +0711 ; Syriac # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0712..072F ; Syriac # Lo [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH +0730..074A ; Syriac # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +074D..074F ; Syriac # Lo [3] SYRIAC LETTER SOGDIAN ZHAIN..SYRIAC LETTER SOGDIAN FE -# Total code points: 62 +# Total code points: 77 # ================================================ -0780..07A5 ; THAANA # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU -07A6..07B0 ; THAANA # Mn [11] THAANA ABAFILI..THAANA SUKUN -07B1 ; THAANA # Lo THAANA LETTER NAA +0780..07A5 ; Thaana # Lo [38] THAANA LETTER HAA..THAANA LETTER WAAVU +07A6..07B0 ; Thaana # Mn [11] THAANA ABAFILI..THAANA SUKUN +07B1 ; Thaana # Lo THAANA LETTER NAA # Total code points: 50 # ================================================ -0901..0902 ; DEVANAGARI # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA -0903 ; DEVANAGARI # Mc DEVANAGARI SIGN VISARGA -0904..0939 ; DEVANAGARI # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA -093C ; DEVANAGARI # Mn DEVANAGARI SIGN NUKTA -093D ; DEVANAGARI # Lo DEVANAGARI SIGN AVAGRAHA -093E..0940 ; DEVANAGARI # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II -0941..0948 ; DEVANAGARI # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI -0949..094C ; DEVANAGARI # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU -094D ; DEVANAGARI # Mn DEVANAGARI SIGN VIRAMA -0950 ; DEVANAGARI # Lo DEVANAGARI OM -0951..0954 ; DEVANAGARI # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT -0958..0961 ; DEVANAGARI # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL -0962..0963 ; DEVANAGARI # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL -0966..096F ; DEVANAGARI # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE +0901..0902 ; Devanagari # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +0903 ; Devanagari # Mc DEVANAGARI SIGN VISARGA +0904..0939 ; Devanagari # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA +093C ; Devanagari # Mn DEVANAGARI SIGN NUKTA +093D ; Devanagari # Lo DEVANAGARI SIGN AVAGRAHA +093E..0940 ; Devanagari # Mc [3] DEVANAGARI VOWEL SIGN AA..DEVANAGARI VOWEL SIGN II +0941..0948 ; Devanagari # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +0949..094C ; Devanagari # Mc [4] DEVANAGARI VOWEL SIGN CANDRA O..DEVANAGARI VOWEL SIGN AU +094D ; Devanagari # Mn DEVANAGARI SIGN VIRAMA +0950 ; Devanagari # Lo DEVANAGARI OM +0951..0954 ; Devanagari # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +0958..0961 ; Devanagari # Lo [10] DEVANAGARI LETTER QA..DEVANAGARI LETTER VOCALIC LL +0962..0963 ; Devanagari # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0966..096F ; Devanagari # Nd [10] DEVANAGARI DIGIT ZERO..DEVANAGARI DIGIT NINE # Total code points: 102 # ================================================ -0981 ; BENGALI # Mn BENGALI SIGN CANDRABINDU -0982..0983 ; BENGALI # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA -0985..098C ; BENGALI # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L -098F..0990 ; BENGALI # Lo [2] BENGALI LETTER E..BENGALI LETTER AI -0993..09A8 ; BENGALI # Lo [22] BENGALI LETTER O..BENGALI LETTER NA -09AA..09B0 ; BENGALI # Lo [7] BENGALI LETTER PA..BENGALI LETTER RA -09B2 ; BENGALI # Lo BENGALI LETTER LA -09B6..09B9 ; BENGALI # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA -09BC ; BENGALI # Mn BENGALI SIGN NUKTA -09BD ; BENGALI # Lo BENGALI SIGN AVAGRAHA -09BE..09C0 ; BENGALI # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II -09C1..09C4 ; BENGALI # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR -09C7..09C8 ; BENGALI # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI -09CB..09CC ; BENGALI # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU -09CD ; BENGALI # Mn BENGALI SIGN VIRAMA -09D7 ; BENGALI # Mc BENGALI AU LENGTH MARK -09DC..09DD ; BENGALI # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA -09DF..09E1 ; BENGALI # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL -09E2..09E3 ; BENGALI # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL -09E6..09EF ; BENGALI # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE -09F0..09F1 ; BENGALI # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +0981 ; Bengali # Mn BENGALI SIGN CANDRABINDU +0982..0983 ; Bengali # Mc [2] BENGALI SIGN ANUSVARA..BENGALI SIGN VISARGA +0985..098C ; Bengali # Lo [8] BENGALI LETTER A..BENGALI LETTER VOCALIC L +098F..0990 ; Bengali # Lo [2] BENGALI LETTER E..BENGALI LETTER AI +0993..09A8 ; Bengali # Lo [22] BENGALI LETTER O..BENGALI LETTER NA +09AA..09B0 ; Bengali # Lo [7] BENGALI LETTER PA..BENGALI LETTER RA +09B2 ; Bengali # Lo BENGALI LETTER LA +09B6..09B9 ; Bengali # Lo [4] BENGALI LETTER SHA..BENGALI LETTER HA +09BC ; Bengali # Mn BENGALI SIGN NUKTA +09BD ; Bengali # Lo BENGALI SIGN AVAGRAHA +09BE..09C0 ; Bengali # Mc [3] BENGALI VOWEL SIGN AA..BENGALI VOWEL SIGN II +09C1..09C4 ; Bengali # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09C7..09C8 ; Bengali # Mc [2] BENGALI VOWEL SIGN E..BENGALI VOWEL SIGN AI +09CB..09CC ; Bengali # Mc [2] BENGALI VOWEL SIGN O..BENGALI VOWEL SIGN AU +09CD ; Bengali # Mn BENGALI SIGN VIRAMA +09D7 ; Bengali # Mc BENGALI AU LENGTH MARK +09DC..09DD ; Bengali # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA +09DF..09E1 ; Bengali # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL +09E2..09E3 ; Bengali # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09E6..09EF ; Bengali # Nd [10] BENGALI DIGIT ZERO..BENGALI DIGIT NINE +09F0..09F1 ; Bengali # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09F2..09F3 ; Bengali # Sc [2] BENGALI RUPEE MARK..BENGALI RUPEE SIGN +09F4..09F9 ; Bengali # No [6] BENGALI CURRENCY NUMERATOR ONE..BENGALI CURRENCY DENOMINATOR SIXTEEN +09FA ; Bengali # So BENGALI ISSHAR + +# Total code points: 90 -# Total code points: 81 +# ================================================ + +0A01..0A02 ; Gurmukhi # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A03 ; Gurmukhi # Mc GURMUKHI SIGN VISARGA +0A05..0A0A ; Gurmukhi # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU +0A0F..0A10 ; Gurmukhi # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI +0A13..0A28 ; Gurmukhi # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA +0A2A..0A30 ; Gurmukhi # Lo [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA +0A32..0A33 ; Gurmukhi # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA +0A35..0A36 ; Gurmukhi # Lo [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA +0A38..0A39 ; Gurmukhi # Lo [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA +0A3C ; Gurmukhi # Mn GURMUKHI SIGN NUKTA +0A3E..0A40 ; Gurmukhi # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II +0A41..0A42 ; Gurmukhi # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; Gurmukhi # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; Gurmukhi # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A59..0A5C ; Gurmukhi # Lo [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA +0A5E ; Gurmukhi # Lo GURMUKHI LETTER FA +0A66..0A6F ; Gurmukhi # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE +0A70..0A71 ; Gurmukhi # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A72..0A74 ; Gurmukhi # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR + +# Total code points: 77 # ================================================ -0A02 ; GURMUKHI # Mn GURMUKHI SIGN BINDI -0A03 ; GURMUKHI # Mc GURMUKHI SIGN VISARGA -0A05..0A0A ; GURMUKHI # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU -0A0F..0A10 ; GURMUKHI # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI -0A13..0A28 ; GURMUKHI # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA -0A2A..0A30 ; GURMUKHI # Lo [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA -0A32..0A33 ; GURMUKHI # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA -0A35..0A36 ; GURMUKHI # Lo [2] GURMUKHI LETTER VA..GURMUKHI LETTER SHA -0A38..0A39 ; GURMUKHI # Lo [2] GURMUKHI LETTER SA..GURMUKHI LETTER HA -0A3C ; GURMUKHI # Mn GURMUKHI SIGN NUKTA -0A3E..0A40 ; GURMUKHI # Mc [3] GURMUKHI VOWEL SIGN AA..GURMUKHI VOWEL SIGN II -0A41..0A42 ; GURMUKHI # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU -0A47..0A48 ; GURMUKHI # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI -0A4B..0A4D ; GURMUKHI # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA -0A59..0A5C ; GURMUKHI # Lo [4] GURMUKHI LETTER KHHA..GURMUKHI LETTER RRA -0A5E ; GURMUKHI # Lo GURMUKHI LETTER FA -0A66..0A6F ; GURMUKHI # Nd [10] GURMUKHI DIGIT ZERO..GURMUKHI DIGIT NINE -0A70..0A71 ; GURMUKHI # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK -0A72..0A74 ; GURMUKHI # Lo [3] GURMUKHI IRI..GURMUKHI EK ONKAR - -# Total code points: 76 - -# ================================================ - -0A81..0A82 ; GUJARATI # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA -0A83 ; GUJARATI # Mc GUJARATI SIGN VISARGA -0A85..0A8D ; GUJARATI # Lo [9] GUJARATI LETTER A..GUJARATI VOWEL CANDRA E -0A8F..0A91 ; GUJARATI # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O -0A93..0AA8 ; GUJARATI # Lo [22] GUJARATI LETTER O..GUJARATI LETTER NA -0AAA..0AB0 ; GUJARATI # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA -0AB2..0AB3 ; GUJARATI # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA -0AB5..0AB9 ; GUJARATI # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA -0ABC ; GUJARATI # Mn GUJARATI SIGN NUKTA -0ABD ; GUJARATI # Lo GUJARATI SIGN AVAGRAHA -0ABE..0AC0 ; GUJARATI # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II -0AC1..0AC5 ; GUJARATI # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E -0AC7..0AC8 ; GUJARATI # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI -0AC9 ; GUJARATI # Mc GUJARATI VOWEL SIGN CANDRA O -0ACB..0ACC ; GUJARATI # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU -0ACD ; GUJARATI # Mn GUJARATI SIGN VIRAMA -0AD0 ; GUJARATI # Lo GUJARATI OM -0AE0..0AE1 ; GUJARATI # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL -0AE2..0AE3 ; GUJARATI # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL -0AE6..0AEF ; GUJARATI # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE +0A81..0A82 ; Gujarati # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0A83 ; Gujarati # Mc GUJARATI SIGN VISARGA +0A85..0A8D ; Gujarati # Lo [9] GUJARATI LETTER A..GUJARATI VOWEL CANDRA E +0A8F..0A91 ; Gujarati # Lo [3] GUJARATI LETTER E..GUJARATI VOWEL CANDRA O +0A93..0AA8 ; Gujarati # Lo [22] GUJARATI LETTER O..GUJARATI LETTER NA +0AAA..0AB0 ; Gujarati # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA +0AB2..0AB3 ; Gujarati # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA +0AB5..0AB9 ; Gujarati # Lo [5] GUJARATI LETTER VA..GUJARATI LETTER HA +0ABC ; Gujarati # Mn GUJARATI SIGN NUKTA +0ABD ; Gujarati # Lo GUJARATI SIGN AVAGRAHA +0ABE..0AC0 ; Gujarati # Mc [3] GUJARATI VOWEL SIGN AA..GUJARATI VOWEL SIGN II +0AC1..0AC5 ; Gujarati # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; Gujarati # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0AC9 ; Gujarati # Mc GUJARATI VOWEL SIGN CANDRA O +0ACB..0ACC ; Gujarati # Mc [2] GUJARATI VOWEL SIGN O..GUJARATI VOWEL SIGN AU +0ACD ; Gujarati # Mn GUJARATI SIGN VIRAMA +0AD0 ; Gujarati # Lo GUJARATI OM +0AE0..0AE1 ; Gujarati # Lo [2] GUJARATI LETTER VOCALIC RR..GUJARATI LETTER VOCALIC LL +0AE2..0AE3 ; Gujarati # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AE6..0AEF ; Gujarati # Nd [10] GUJARATI DIGIT ZERO..GUJARATI DIGIT NINE +0AF1 ; Gujarati # Sc GUJARATI RUPEE SIGN -# Total code points: 82 +# Total code points: 83 # ================================================ -0B01 ; ORIYA # Mn ORIYA SIGN CANDRABINDU -0B02..0B03 ; ORIYA # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA -0B05..0B0C ; ORIYA # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L -0B0F..0B10 ; ORIYA # Lo [2] ORIYA LETTER E..ORIYA LETTER AI -0B13..0B28 ; ORIYA # Lo [22] ORIYA LETTER O..ORIYA LETTER NA -0B2A..0B30 ; ORIYA # Lo [7] ORIYA LETTER PA..ORIYA LETTER RA -0B32..0B33 ; ORIYA # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA -0B35..0B39 ; ORIYA # Lo [5] ORIYA LETTER VA..ORIYA LETTER HA -0B3C ; ORIYA # Mn ORIYA SIGN NUKTA -0B3D ; ORIYA # Lo ORIYA SIGN AVAGRAHA -0B3E ; ORIYA # Mc ORIYA VOWEL SIGN AA -0B3F ; ORIYA # Mn ORIYA VOWEL SIGN I -0B40 ; ORIYA # Mc ORIYA VOWEL SIGN II -0B41..0B43 ; ORIYA # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R -0B47..0B48 ; ORIYA # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI -0B4B..0B4C ; ORIYA # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU -0B4D ; ORIYA # Mn ORIYA SIGN VIRAMA -0B56 ; ORIYA # Mn ORIYA AI LENGTH MARK -0B57 ; ORIYA # Mc ORIYA AU LENGTH MARK -0B5C..0B5D ; ORIYA # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA -0B5F..0B61 ; ORIYA # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL -0B66..0B6F ; ORIYA # Nd [10] ORIYA DIGIT ZERO..ORIYA DIGIT NINE -0B71 ; ORIYA # Lo ORIYA LETTER WA +0B01 ; Oriya # Mn ORIYA SIGN CANDRABINDU +0B02..0B03 ; Oriya # Mc [2] ORIYA SIGN ANUSVARA..ORIYA SIGN VISARGA +0B05..0B0C ; Oriya # Lo [8] ORIYA LETTER A..ORIYA LETTER VOCALIC L +0B0F..0B10 ; Oriya # Lo [2] ORIYA LETTER E..ORIYA LETTER AI +0B13..0B28 ; Oriya # Lo [22] ORIYA LETTER O..ORIYA LETTER NA +0B2A..0B30 ; Oriya # Lo [7] ORIYA LETTER PA..ORIYA LETTER RA +0B32..0B33 ; Oriya # Lo [2] ORIYA LETTER LA..ORIYA LETTER LLA +0B35..0B39 ; Oriya # Lo [5] ORIYA LETTER VA..ORIYA LETTER HA +0B3C ; Oriya # Mn ORIYA SIGN NUKTA +0B3D ; Oriya # Lo ORIYA SIGN AVAGRAHA +0B3E ; Oriya # Mc ORIYA VOWEL SIGN AA +0B3F ; Oriya # Mn ORIYA VOWEL SIGN I +0B40 ; Oriya # Mc ORIYA VOWEL SIGN II +0B41..0B43 ; Oriya # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R +0B47..0B48 ; Oriya # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI +0B4B..0B4C ; Oriya # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU +0B4D ; Oriya # Mn ORIYA SIGN VIRAMA +0B56 ; Oriya # Mn ORIYA AI LENGTH MARK +0B57 ; Oriya # Mc ORIYA AU LENGTH MARK +0B5C..0B5D ; Oriya # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA +0B5F..0B61 ; Oriya # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL +0B66..0B6F ; Oriya # Nd [10] ORIYA DIGIT ZERO..ORIYA DIGIT NINE +0B70 ; Oriya # So ORIYA ISSHAR +0B71 ; Oriya # Lo ORIYA LETTER WA -# Total code points: 80 +# Total code points: 81 + +# ================================================ + +0B82 ; Tamil # Mn TAMIL SIGN ANUSVARA +0B83 ; Tamil # Lo TAMIL SIGN VISARGA +0B85..0B8A ; Tamil # Lo [6] TAMIL LETTER A..TAMIL LETTER UU +0B8E..0B90 ; Tamil # Lo [3] TAMIL LETTER E..TAMIL LETTER AI +0B92..0B95 ; Tamil # Lo [4] TAMIL LETTER O..TAMIL LETTER KA +0B99..0B9A ; Tamil # Lo [2] TAMIL LETTER NGA..TAMIL LETTER CA +0B9C ; Tamil # Lo TAMIL LETTER JA +0B9E..0B9F ; Tamil # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA +0BA3..0BA4 ; Tamil # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA +0BA8..0BAA ; Tamil # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA +0BAE..0BB5 ; Tamil # Lo [8] TAMIL LETTER MA..TAMIL LETTER VA +0BB7..0BB9 ; Tamil # Lo [3] TAMIL LETTER SSA..TAMIL LETTER HA +0BBE..0BBF ; Tamil # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I +0BC0 ; Tamil # Mn TAMIL VOWEL SIGN II +0BC1..0BC2 ; Tamil # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU +0BC6..0BC8 ; Tamil # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI +0BCA..0BCC ; Tamil # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU +0BCD ; Tamil # Mn TAMIL SIGN VIRAMA +0BD7 ; Tamil # Mc TAMIL AU LENGTH MARK +0BE7..0BEF ; Tamil # Nd [9] TAMIL DIGIT ONE..TAMIL DIGIT NINE +0BF0..0BF2 ; Tamil # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND +0BF3..0BF8 ; Tamil # So [6] TAMIL DAY SIGN..TAMIL AS ABOVE SIGN +0BF9 ; Tamil # Sc TAMIL RUPEE SIGN +0BFA ; Tamil # So TAMIL NUMBER SIGN + +# Total code points: 69 # ================================================ -0B82 ; TAMIL # Mn TAMIL SIGN ANUSVARA -0B83 ; TAMIL # Lo TAMIL SIGN VISARGA -0B85..0B8A ; TAMIL # Lo [6] TAMIL LETTER A..TAMIL LETTER UU -0B8E..0B90 ; TAMIL # Lo [3] TAMIL LETTER E..TAMIL LETTER AI -0B92..0B95 ; TAMIL # Lo [4] TAMIL LETTER O..TAMIL LETTER KA -0B99..0B9A ; TAMIL # Lo [2] TAMIL LETTER NGA..TAMIL LETTER CA -0B9C ; TAMIL # Lo TAMIL LETTER JA -0B9E..0B9F ; TAMIL # Lo [2] TAMIL LETTER NYA..TAMIL LETTER TTA -0BA3..0BA4 ; TAMIL # Lo [2] TAMIL LETTER NNA..TAMIL LETTER TA -0BA8..0BAA ; TAMIL # Lo [3] TAMIL LETTER NA..TAMIL LETTER PA -0BAE..0BB5 ; TAMIL # Lo [8] TAMIL LETTER MA..TAMIL LETTER VA -0BB7..0BB9 ; TAMIL # Lo [3] TAMIL LETTER SSA..TAMIL LETTER HA -0BBE..0BBF ; TAMIL # Mc [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I -0BC0 ; TAMIL # Mn TAMIL VOWEL SIGN II -0BC1..0BC2 ; TAMIL # Mc [2] TAMIL VOWEL SIGN U..TAMIL VOWEL SIGN UU -0BC6..0BC8 ; TAMIL # Mc [3] TAMIL VOWEL SIGN E..TAMIL VOWEL SIGN AI -0BCA..0BCC ; TAMIL # Mc [3] TAMIL VOWEL SIGN O..TAMIL VOWEL SIGN AU -0BCD ; TAMIL # Mn TAMIL SIGN VIRAMA -0BD7 ; TAMIL # Mc TAMIL AU LENGTH MARK -0BE7..0BEF ; TAMIL # Nd [9] TAMIL DIGIT ONE..TAMIL DIGIT NINE -0BF0..0BF2 ; TAMIL # No [3] TAMIL NUMBER TEN..TAMIL NUMBER ONE THOUSAND - -# Total code points: 61 - -# ================================================ - -0C01..0C03 ; TELUGU # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA -0C05..0C0C ; TELUGU # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L -0C0E..0C10 ; TELUGU # Lo [3] TELUGU LETTER E..TELUGU LETTER AI -0C12..0C28 ; TELUGU # Lo [23] TELUGU LETTER O..TELUGU LETTER NA -0C2A..0C33 ; TELUGU # Lo [10] TELUGU LETTER PA..TELUGU LETTER LLA -0C35..0C39 ; TELUGU # Lo [5] TELUGU LETTER VA..TELUGU LETTER HA -0C3E..0C40 ; TELUGU # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II -0C41..0C44 ; TELUGU # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR -0C46..0C48 ; TELUGU # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI -0C4A..0C4D ; TELUGU # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA -0C55..0C56 ; TELUGU # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK -0C60..0C61 ; TELUGU # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL -0C66..0C6F ; TELUGU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE +0C01..0C03 ; Telugu # Mc [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA +0C05..0C0C ; Telugu # Lo [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L +0C0E..0C10 ; Telugu # Lo [3] TELUGU LETTER E..TELUGU LETTER AI +0C12..0C28 ; Telugu # Lo [23] TELUGU LETTER O..TELUGU LETTER NA +0C2A..0C33 ; Telugu # Lo [10] TELUGU LETTER PA..TELUGU LETTER LLA +0C35..0C39 ; Telugu # Lo [5] TELUGU LETTER VA..TELUGU LETTER HA +0C3E..0C40 ; Telugu # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C41..0C44 ; Telugu # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR +0C46..0C48 ; Telugu # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; Telugu # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; Telugu # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C60..0C61 ; Telugu # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL +0C66..0C6F ; Telugu # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE # Total code points: 80 # ================================================ -0C82..0C83 ; KANNADA # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA -0C85..0C8C ; KANNADA # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L -0C8E..0C90 ; KANNADA # Lo [3] KANNADA LETTER E..KANNADA LETTER AI -0C92..0CA8 ; KANNADA # Lo [23] KANNADA LETTER O..KANNADA LETTER NA -0CAA..0CB3 ; KANNADA # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA -0CB5..0CB9 ; KANNADA # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA -0CBD ; KANNADA # Lo KANNADA SIGN AVAGRAHA -0CBE ; KANNADA # Mc KANNADA VOWEL SIGN AA -0CBF ; KANNADA # Mn KANNADA VOWEL SIGN I -0CC0..0CC4 ; KANNADA # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR -0CC6 ; KANNADA # Mn KANNADA VOWEL SIGN E -0CC7..0CC8 ; KANNADA # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI -0CCA..0CCB ; KANNADA # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO -0CCC..0CCD ; KANNADA # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA -0CD5..0CD6 ; KANNADA # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDE ; KANNADA # Lo KANNADA LETTER FA -0CE0..0CE1 ; KANNADA # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL -0CE6..0CEF ; KANNADA # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE +0C82..0C83 ; Kannada # Mc [2] KANNADA SIGN ANUSVARA..KANNADA SIGN VISARGA +0C85..0C8C ; Kannada # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L +0C8E..0C90 ; Kannada # Lo [3] KANNADA LETTER E..KANNADA LETTER AI +0C92..0CA8 ; Kannada # Lo [23] KANNADA LETTER O..KANNADA LETTER NA +0CAA..0CB3 ; Kannada # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA +0CB5..0CB9 ; Kannada # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA +0CBC ; Kannada # Mn KANNADA SIGN NUKTA +0CBD ; Kannada # Lo KANNADA SIGN AVAGRAHA +0CBE ; Kannada # Mc KANNADA VOWEL SIGN AA +0CBF ; Kannada # Mn KANNADA VOWEL SIGN I +0CC0..0CC4 ; Kannada # Mc [5] KANNADA VOWEL SIGN II..KANNADA VOWEL SIGN VOCALIC RR +0CC6 ; Kannada # Mn KANNADA VOWEL SIGN E +0CC7..0CC8 ; Kannada # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI +0CCA..0CCB ; Kannada # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO +0CCC..0CCD ; Kannada # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CD5..0CD6 ; Kannada # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK +0CDE ; Kannada # Lo KANNADA LETTER FA +0CE0..0CE1 ; Kannada # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL +0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE -# Total code points: 81 +# Total code points: 82 # ================================================ -0D02..0D03 ; MALAYALAM # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA -0D05..0D0C ; MALAYALAM # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L -0D0E..0D10 ; MALAYALAM # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI -0D12..0D28 ; MALAYALAM # Lo [23] MALAYALAM LETTER O..MALAYALAM LETTER NA -0D2A..0D39 ; MALAYALAM # Lo [16] MALAYALAM LETTER PA..MALAYALAM LETTER HA -0D3E..0D40 ; MALAYALAM # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II -0D41..0D43 ; MALAYALAM # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R -0D46..0D48 ; MALAYALAM # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI -0D4A..0D4C ; MALAYALAM # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU -0D4D ; MALAYALAM # Mn MALAYALAM SIGN VIRAMA -0D57 ; MALAYALAM # Mc MALAYALAM AU LENGTH MARK -0D60..0D61 ; MALAYALAM # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL -0D66..0D6F ; MALAYALAM # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE +0D02..0D03 ; Malayalam # Mc [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA +0D05..0D0C ; Malayalam # Lo [8] MALAYALAM LETTER A..MALAYALAM LETTER VOCALIC L +0D0E..0D10 ; Malayalam # Lo [3] MALAYALAM LETTER E..MALAYALAM LETTER AI +0D12..0D28 ; Malayalam # Lo [23] MALAYALAM LETTER O..MALAYALAM LETTER NA +0D2A..0D39 ; Malayalam # Lo [16] MALAYALAM LETTER PA..MALAYALAM LETTER HA +0D3E..0D40 ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II +0D41..0D43 ; Malayalam # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R +0D46..0D48 ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI +0D4A..0D4C ; Malayalam # Mc [3] MALAYALAM VOWEL SIGN O..MALAYALAM VOWEL SIGN AU +0D4D ; Malayalam # Mn MALAYALAM SIGN VIRAMA +0D57 ; Malayalam # Mc MALAYALAM AU LENGTH MARK +0D60..0D61 ; Malayalam # Lo [2] MALAYALAM LETTER VOCALIC RR..MALAYALAM LETTER VOCALIC LL +0D66..0D6F ; Malayalam # Nd [10] MALAYALAM DIGIT ZERO..MALAYALAM DIGIT NINE # Total code points: 78 # ================================================ -0D82..0D83 ; SINHALA # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA -0D85..0D96 ; SINHALA # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA -0D9A..0DB1 ; SINHALA # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA -0DB3..0DBB ; SINHALA # Lo [9] SINHALA LETTER SANYAKA DAYANNA..SINHALA LETTER RAYANNA -0DBD ; SINHALA # Lo SINHALA LETTER DANTAJA LAYANNA -0DC0..0DC6 ; SINHALA # Lo [7] SINHALA LETTER VAYANNA..SINHALA LETTER FAYANNA -0DCA ; SINHALA # Mn SINHALA SIGN AL-LAKUNA -0DCF..0DD1 ; SINHALA # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA -0DD2..0DD4 ; SINHALA # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA -0DD6 ; SINHALA # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA -0DD8..0DDF ; SINHALA # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA -0DF2..0DF3 ; SINHALA # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA +0D82..0D83 ; Sinhala # Mc [2] SINHALA SIGN ANUSVARAYA..SINHALA SIGN VISARGAYA +0D85..0D96 ; Sinhala # Lo [18] SINHALA LETTER AYANNA..SINHALA LETTER AUYANNA +0D9A..0DB1 ; Sinhala # Lo [24] SINHALA LETTER ALPAPRAANA KAYANNA..SINHALA LETTER DANTAJA NAYANNA +0DB3..0DBB ; Sinhala # Lo [9] SINHALA LETTER SANYAKA DAYANNA..SINHALA LETTER RAYANNA +0DBD ; Sinhala # Lo SINHALA LETTER DANTAJA LAYANNA +0DC0..0DC6 ; Sinhala # Lo [7] SINHALA LETTER VAYANNA..SINHALA LETTER FAYANNA +0DCA ; Sinhala # Mn SINHALA SIGN AL-LAKUNA +0DCF..0DD1 ; Sinhala # Mc [3] SINHALA VOWEL SIGN AELA-PILLA..SINHALA VOWEL SIGN DIGA AEDA-PILLA +0DD2..0DD4 ; Sinhala # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; Sinhala # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0DD8..0DDF ; Sinhala # Mc [8] SINHALA VOWEL SIGN GAETTA-PILLA..SINHALA VOWEL SIGN GAYANUKITTA +0DF2..0DF3 ; Sinhala # Mc [2] SINHALA VOWEL SIGN DIGA GAETTA-PILLA..SINHALA VOWEL SIGN DIGA GAYANUKITTA +0DF4 ; Sinhala # Po SINHALA PUNCTUATION KUNDDALIYA -# Total code points: 79 +# Total code points: 80 # ================================================ -0E01..0E30 ; THAI # Lo [48] THAI CHARACTER KO KAI..THAI CHARACTER SARA A -0E31 ; THAI # Mn THAI CHARACTER MAI HAN-AKAT -0E32..0E33 ; THAI # Lo [2] THAI CHARACTER SARA AA..THAI CHARACTER SARA AM -0E34..0E3A ; THAI # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU -0E40..0E45 ; THAI # Lo [6] THAI CHARACTER SARA E..THAI CHARACTER LAKKHANGYAO -0E46 ; THAI # Lm THAI CHARACTER MAIYAMOK -0E47..0E4E ; THAI # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN -0E50..0E59 ; THAI # Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE +0E01..0E30 ; Thai # Lo [48] THAI CHARACTER KO KAI..THAI CHARACTER SARA A +0E31 ; Thai # Mn THAI CHARACTER MAI HAN-AKAT +0E32..0E33 ; Thai # Lo [2] THAI CHARACTER SARA AA..THAI CHARACTER SARA AM +0E34..0E3A ; Thai # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E40..0E45 ; Thai # Lo [6] THAI CHARACTER SARA E..THAI CHARACTER LAKKHANGYAO +0E46 ; Thai # Lm THAI CHARACTER MAIYAMOK +0E47..0E4E ; Thai # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0E4F ; Thai # Po THAI CHARACTER FONGMAN +0E50..0E59 ; Thai # Nd [10] THAI DIGIT ZERO..THAI DIGIT NINE +0E5A..0E5B ; Thai # Po [2] THAI CHARACTER ANGKHANKHU..THAI CHARACTER KHOMUT -# Total code points: 83 +# Total code points: 86 # ================================================ -0E81..0E82 ; LAO # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG -0E84 ; LAO # Lo LAO LETTER KHO TAM -0E87..0E88 ; LAO # Lo [2] LAO LETTER NGO..LAO LETTER CO -0E8A ; LAO # Lo LAO LETTER SO TAM -0E8D ; LAO # Lo LAO LETTER NYO -0E94..0E97 ; LAO # Lo [4] LAO LETTER DO..LAO LETTER THO TAM -0E99..0E9F ; LAO # Lo [7] LAO LETTER NO..LAO LETTER FO SUNG -0EA1..0EA3 ; LAO # Lo [3] LAO LETTER MO..LAO LETTER LO LING -0EA5 ; LAO # Lo LAO LETTER LO LOOT -0EA7 ; LAO # Lo LAO LETTER WO -0EAA..0EAB ; LAO # Lo [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG -0EAD..0EB0 ; LAO # Lo [4] LAO LETTER O..LAO VOWEL SIGN A -0EB1 ; LAO # Mn LAO VOWEL SIGN MAI KAN -0EB2..0EB3 ; LAO # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM -0EB4..0EB9 ; LAO # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU -0EBB..0EBC ; LAO # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO -0EBD ; LAO # Lo LAO SEMIVOWEL SIGN NYO -0EC0..0EC4 ; LAO # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI -0EC6 ; LAO # Lm LAO KO LA -0EC8..0ECD ; LAO # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA -0ED0..0ED9 ; LAO # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE -0EDC..0EDD ; LAO # Lo [2] LAO HO NO..LAO HO MO +0E81..0E82 ; Lao # Lo [2] LAO LETTER KO..LAO LETTER KHO SUNG +0E84 ; Lao # Lo LAO LETTER KHO TAM +0E87..0E88 ; Lao # Lo [2] LAO LETTER NGO..LAO LETTER CO +0E8A ; Lao # Lo LAO LETTER SO TAM +0E8D ; Lao # Lo LAO LETTER NYO +0E94..0E97 ; Lao # Lo [4] LAO LETTER DO..LAO LETTER THO TAM +0E99..0E9F ; Lao # Lo [7] LAO LETTER NO..LAO LETTER FO SUNG +0EA1..0EA3 ; Lao # Lo [3] LAO LETTER MO..LAO LETTER LO LING +0EA5 ; Lao # Lo LAO LETTER LO LOOT +0EA7 ; Lao # Lo LAO LETTER WO +0EAA..0EAB ; Lao # Lo [2] LAO LETTER SO SUNG..LAO LETTER HO SUNG +0EAD..0EB0 ; Lao # Lo [4] LAO LETTER O..LAO VOWEL SIGN A +0EB1 ; Lao # Mn LAO VOWEL SIGN MAI KAN +0EB2..0EB3 ; Lao # Lo [2] LAO VOWEL SIGN AA..LAO VOWEL SIGN AM +0EB4..0EB9 ; Lao # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; Lao # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EBD ; Lao # Lo LAO SEMIVOWEL SIGN NYO +0EC0..0EC4 ; Lao # Lo [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI +0EC6 ; Lao # Lm LAO KO LA +0EC8..0ECD ; Lao # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0ED0..0ED9 ; Lao # Nd [10] LAO DIGIT ZERO..LAO DIGIT NINE +0EDC..0EDD ; Lao # Lo [2] LAO HO NO..LAO HO MO # Total code points: 65 # ================================================ -0F00 ; TIBETAN # Lo TIBETAN SYLLABLE OM -0F18..0F19 ; TIBETAN # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS -0F20..0F29 ; TIBETAN # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE -0F2A..0F33 ; TIBETAN # No [10] TIBETAN DIGIT HALF ONE..TIBETAN DIGIT HALF ZERO -0F35 ; TIBETAN # Mn TIBETAN MARK NGAS BZUNG NYI ZLA -0F37 ; TIBETAN # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS -0F39 ; TIBETAN # Mn TIBETAN MARK TSA -PHRU -0F40..0F47 ; TIBETAN # Lo [8] TIBETAN LETTER KA..TIBETAN LETTER JA -0F49..0F6A ; TIBETAN # Lo [34] TIBETAN LETTER NYA..TIBETAN LETTER FIXED-FORM RA -0F71..0F7E ; TIBETAN # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO -0F7F ; TIBETAN # Mc TIBETAN SIGN RNAM BCAD -0F80..0F84 ; TIBETAN # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA -0F86..0F87 ; TIBETAN # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS -0F88..0F8B ; TIBETAN # Lo [4] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN GRU MED RGYINGS -0F90..0F97 ; TIBETAN # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA -0F99..0FBC ; TIBETAN # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA -0FC6 ; TIBETAN # Mn TIBETAN SYMBOL PADMA GDAN - -# Total code points: 139 +0F00 ; Tibetan # Lo TIBETAN SYLLABLE OM +0F01..0F03 ; Tibetan # So [3] TIBETAN MARK GTER YIG MGO TRUNCATED A..TIBETAN MARK GTER YIG MGO -UM GTER TSHEG MA +0F04..0F12 ; Tibetan # Po [15] TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK RGYA GRAM SHAD +0F13..0F17 ; Tibetan # So [5] TIBETAN MARK CARET -DZUD RTAGS ME LONG CAN..TIBETAN ASTROLOGICAL SIGN SGRA GCAN -CHAR RTAGS +0F18..0F19 ; Tibetan # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F1A..0F1F ; Tibetan # So [6] TIBETAN SIGN RDEL DKAR GCIG..TIBETAN SIGN RDEL DKAR RDEL NAG +0F20..0F29 ; Tibetan # Nd [10] TIBETAN DIGIT ZERO..TIBETAN DIGIT NINE +0F2A..0F33 ; Tibetan # No [10] TIBETAN DIGIT HALF ONE..TIBETAN DIGIT HALF ZERO +0F34 ; Tibetan # So TIBETAN MARK BSDUS RTAGS +0F35 ; Tibetan # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F36 ; Tibetan # So TIBETAN MARK CARET -DZUD RTAGS BZHI MIG CAN +0F37 ; Tibetan # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F38 ; Tibetan # So TIBETAN MARK CHE MGO +0F39 ; Tibetan # Mn TIBETAN MARK TSA -PHRU +0F3A ; Tibetan # Ps TIBETAN MARK GUG RTAGS GYON +0F3B ; Tibetan # Pe TIBETAN MARK GUG RTAGS GYAS +0F3C ; Tibetan # Ps TIBETAN MARK ANG KHANG GYON +0F3D ; Tibetan # Pe TIBETAN MARK ANG KHANG GYAS +0F3E..0F3F ; Tibetan # Mc [2] TIBETAN SIGN YAR TSHES..TIBETAN SIGN MAR TSHES +0F40..0F47 ; Tibetan # Lo [8] TIBETAN LETTER KA..TIBETAN LETTER JA +0F49..0F6A ; Tibetan # Lo [34] TIBETAN LETTER NYA..TIBETAN LETTER FIXED-FORM RA +0F71..0F7E ; Tibetan # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F7F ; Tibetan # Mc TIBETAN SIGN RNAM BCAD +0F80..0F84 ; Tibetan # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F85 ; Tibetan # Po TIBETAN MARK PALUTA +0F86..0F87 ; Tibetan # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F88..0F8B ; Tibetan # Lo [4] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN GRU MED RGYINGS +0F90..0F97 ; Tibetan # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; Tibetan # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FBE..0FC5 ; Tibetan # So [8] TIBETAN KU RU KHA..TIBETAN SYMBOL RDO RJE +0FC6 ; Tibetan # Mn TIBETAN SYMBOL PADMA GDAN +0FC7..0FCC ; Tibetan # So [6] TIBETAN SYMBOL RDO RJE RGYA GRAM..TIBETAN SYMBOL NOR BU BZHI -KHYIL +0FCF ; Tibetan # So TIBETAN SIGN RDEL NAG GSUM + +# Total code points: 193 # ================================================ -1000..1021 ; MYANMAR # Lo [34] MYANMAR LETTER KA..MYANMAR LETTER A -1023..1027 ; MYANMAR # Lo [5] MYANMAR LETTER I..MYANMAR LETTER E -1029..102A ; MYANMAR # Lo [2] MYANMAR LETTER O..MYANMAR LETTER AU -102C ; MYANMAR # Mc MYANMAR VOWEL SIGN AA -102D..1030 ; MYANMAR # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU -1031 ; MYANMAR # Mc MYANMAR VOWEL SIGN E -1032 ; MYANMAR # Mn MYANMAR VOWEL SIGN AI -1036..1037 ; MYANMAR # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW -1038 ; MYANMAR # Mc MYANMAR SIGN VISARGA -1039 ; MYANMAR # Mn MYANMAR SIGN VIRAMA -1040..1049 ; MYANMAR # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE -1050..1055 ; MYANMAR # Lo [6] MYANMAR LETTER SHA..MYANMAR LETTER VOCALIC LL -1056..1057 ; MYANMAR # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR -1058..1059 ; MYANMAR # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +1000..1021 ; Myanmar # Lo [34] MYANMAR LETTER KA..MYANMAR LETTER A +1023..1027 ; Myanmar # Lo [5] MYANMAR LETTER I..MYANMAR LETTER E +1029..102A ; Myanmar # Lo [2] MYANMAR LETTER O..MYANMAR LETTER AU +102C ; Myanmar # Mc MYANMAR VOWEL SIGN AA +102D..1030 ; Myanmar # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1031 ; Myanmar # Mc MYANMAR VOWEL SIGN E +1032 ; Myanmar # Mn MYANMAR VOWEL SIGN AI +1036..1037 ; Myanmar # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW +1038 ; Myanmar # Mc MYANMAR SIGN VISARGA +1039 ; Myanmar # Mn MYANMAR SIGN VIRAMA +1040..1049 ; Myanmar # Nd [10] MYANMAR DIGIT ZERO..MYANMAR DIGIT NINE +104A..104F ; Myanmar # Po [6] MYANMAR SIGN LITTLE SECTION..MYANMAR SYMBOL GENITIVE +1050..1055 ; Myanmar # Lo [6] MYANMAR LETTER SHA..MYANMAR LETTER VOCALIC LL +1056..1057 ; Myanmar # Mc [2] MYANMAR VOWEL SIGN VOCALIC R..MYANMAR VOWEL SIGN VOCALIC RR +1058..1059 ; Myanmar # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL -# Total code points: 72 +# Total code points: 78 # ================================================ -10A0..10C5 ; GEORGIAN # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE -10D0..10F8 ; GEORGIAN # Lo [41] GEORGIAN LETTER AN..GEORGIAN LETTER ELIFI +10A0..10C5 ; Georgian # L& [38] GEORGIAN CAPITAL LETTER AN..GEORGIAN CAPITAL LETTER HOE +10D0..10F8 ; Georgian # Lo [41] GEORGIAN LETTER AN..GEORGIAN LETTER ELIFI # Total code points: 79 # ================================================ -1100..1159 ; HANGUL # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH -115F..11A2 ; HANGUL # Lo [68] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA -11A8..11F9 ; HANGUL # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH -3131..318E ; HANGUL # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE -AC00..D7A3 ; HANGUL # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH -FFA0..FFBE ; HANGUL # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH -FFC2..FFC7 ; HANGUL # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E -FFCA..FFCF ; HANGUL # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE -FFD2..FFD7 ; HANGUL # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU -FFDA..FFDC ; HANGUL # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I - -# Total code points: 11558 - -# ================================================ - -1200..1206 ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE HO -1208..1246 ; ETHIOPIC # Lo [63] ETHIOPIC SYLLABLE LA..ETHIOPIC SYLLABLE QO -1248 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE QWA -124A..124D ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE -1250..1256 ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO -1258 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE QHWA -125A..125D ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE -1260..1286 ; ETHIOPIC # Lo [39] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XO -1288 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE XWA -128A..128D ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE -1290..12AE ; ETHIOPIC # Lo [31] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KO -12B0 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE KWA -12B2..12B5 ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE -12B8..12BE ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO -12C0 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE KXWA -12C2..12C5 ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE -12C8..12CE ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE WO -12D0..12D6 ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE PHARYNGEAL A..ETHIOPIC SYLLABLE PHARYNGEAL O -12D8..12EE ; ETHIOPIC # Lo [23] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE YO -12F0..130E ; ETHIOPIC # Lo [31] ETHIOPIC SYLLABLE DA..ETHIOPIC SYLLABLE GO -1310 ; ETHIOPIC # Lo ETHIOPIC SYLLABLE GWA -1312..1315 ; ETHIOPIC # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE -1318..131E ; ETHIOPIC # Lo [7] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE GGO -1320..1346 ; ETHIOPIC # Lo [39] ETHIOPIC SYLLABLE THA..ETHIOPIC SYLLABLE TZO -1348..135A ; ETHIOPIC # Lo [19] ETHIOPIC SYLLABLE FA..ETHIOPIC SYLLABLE FYA -1369..1371 ; ETHIOPIC # Nd [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE -1372..137C ; ETHIOPIC # No [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND - -# Total code points: 337 - -# ================================================ - -13A0..13F4 ; CHEROKEE # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV +1100..1159 ; Hangul # Lo [90] HANGUL CHOSEONG KIYEOK..HANGUL CHOSEONG YEORINHIEUH +115F..11A2 ; Hangul # Lo [68] HANGUL CHOSEONG FILLER..HANGUL JUNGSEONG SSANGARAEA +11A8..11F9 ; Hangul # Lo [82] HANGUL JONGSEONG KIYEOK..HANGUL JONGSEONG YEORINHIEUH +3131..318E ; Hangul # Lo [94] HANGUL LETTER KIYEOK..HANGUL LETTER ARAEAE +3200..321E ; Hangul # So [31] PARENTHESIZED HANGUL KIYEOK..PARENTHESIZED KOREAN CHARACTER O HU +3260..327D ; Hangul # So [30] CIRCLED HANGUL KIYEOK..CIRCLED KOREAN CHARACTER JUEUI +AC00..D7A3 ; Hangul # Lo [11172] HANGUL SYLLABLE GA..HANGUL SYLLABLE HIH +FFA0..FFBE ; Hangul # Lo [31] HALFWIDTH HANGUL FILLER..HALFWIDTH HANGUL LETTER HIEUH +FFC2..FFC7 ; Hangul # Lo [6] HALFWIDTH HANGUL LETTER A..HALFWIDTH HANGUL LETTER E +FFCA..FFCF ; Hangul # Lo [6] HALFWIDTH HANGUL LETTER YEO..HALFWIDTH HANGUL LETTER OE +FFD2..FFD7 ; Hangul # Lo [6] HALFWIDTH HANGUL LETTER YO..HALFWIDTH HANGUL LETTER YU +FFDA..FFDC ; Hangul # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I + +# Total code points: 11619 + +# ================================================ + +1200..1206 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE HA..ETHIOPIC SYLLABLE HO +1208..1246 ; Ethiopic # Lo [63] ETHIOPIC SYLLABLE LA..ETHIOPIC SYLLABLE QO +1248 ; Ethiopic # Lo ETHIOPIC SYLLABLE QWA +124A..124D ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE QWI..ETHIOPIC SYLLABLE QWE +1250..1256 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE QHA..ETHIOPIC SYLLABLE QHO +1258 ; Ethiopic # Lo ETHIOPIC SYLLABLE QHWA +125A..125D ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE QHWI..ETHIOPIC SYLLABLE QHWE +1260..1286 ; Ethiopic # Lo [39] ETHIOPIC SYLLABLE BA..ETHIOPIC SYLLABLE XO +1288 ; Ethiopic # Lo ETHIOPIC SYLLABLE XWA +128A..128D ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE XWI..ETHIOPIC SYLLABLE XWE +1290..12AE ; Ethiopic # Lo [31] ETHIOPIC SYLLABLE NA..ETHIOPIC SYLLABLE KO +12B0 ; Ethiopic # Lo ETHIOPIC SYLLABLE KWA +12B2..12B5 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE KWI..ETHIOPIC SYLLABLE KWE +12B8..12BE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE KXA..ETHIOPIC SYLLABLE KXO +12C0 ; Ethiopic # Lo ETHIOPIC SYLLABLE KXWA +12C2..12C5 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE KXWI..ETHIOPIC SYLLABLE KXWE +12C8..12CE ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE WA..ETHIOPIC SYLLABLE WO +12D0..12D6 ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE PHARYNGEAL A..ETHIOPIC SYLLABLE PHARYNGEAL O +12D8..12EE ; Ethiopic # Lo [23] ETHIOPIC SYLLABLE ZA..ETHIOPIC SYLLABLE YO +12F0..130E ; Ethiopic # Lo [31] ETHIOPIC SYLLABLE DA..ETHIOPIC SYLLABLE GO +1310 ; Ethiopic # Lo ETHIOPIC SYLLABLE GWA +1312..1315 ; Ethiopic # Lo [4] ETHIOPIC SYLLABLE GWI..ETHIOPIC SYLLABLE GWE +1318..131E ; Ethiopic # Lo [7] ETHIOPIC SYLLABLE GGA..ETHIOPIC SYLLABLE GGO +1320..1346 ; Ethiopic # Lo [39] ETHIOPIC SYLLABLE THA..ETHIOPIC SYLLABLE TZO +1348..135A ; Ethiopic # Lo [19] ETHIOPIC SYLLABLE FA..ETHIOPIC SYLLABLE FYA +1361..1368 ; Ethiopic # Po [8] ETHIOPIC WORDSPACE..ETHIOPIC PARAGRAPH SEPARATOR +1369..1371 ; Ethiopic # Nd [9] ETHIOPIC DIGIT ONE..ETHIOPIC DIGIT NINE +1372..137C ; Ethiopic # No [11] ETHIOPIC NUMBER TEN..ETHIOPIC NUMBER TEN THOUSAND + +# Total code points: 345 + +# ================================================ + +13A0..13F4 ; Cherokee # Lo [85] CHEROKEE LETTER A..CHEROKEE LETTER YV # Total code points: 85 # ================================================ -1401..166C ; CANADIAN_ABORIGINAL # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA -166F..1676 ; CANADIAN_ABORIGINAL # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA +1401..166C ; Canadian_Aboriginal # Lo [620] CANADIAN SYLLABICS E..CANADIAN SYLLABICS CARRIER TTSA +166D..166E ; Canadian_Aboriginal # Po [2] CANADIAN SYLLABICS CHI SIGN..CANADIAN SYLLABICS FULL STOP +166F..1676 ; Canadian_Aboriginal # Lo [8] CANADIAN SYLLABICS QAI..CANADIAN SYLLABICS NNGAA -# Total code points: 628 +# Total code points: 630 # ================================================ -1681..169A ; OGHAM # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH +1680 ; Ogham # Zs OGHAM SPACE MARK +1681..169A ; Ogham # Lo [26] OGHAM LETTER BEITH..OGHAM LETTER PEITH +169B ; Ogham # Ps OGHAM FEATHER MARK +169C ; Ogham # Pe OGHAM REVERSED FEATHER MARK -# Total code points: 26 +# Total code points: 29 # ================================================ -16A0..16EA ; RUNIC # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X -16EE..16F0 ; RUNIC # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL +16A0..16EA ; Runic # Lo [75] RUNIC LETTER FEHU FEOH FE F..RUNIC LETTER X +16EE..16F0 ; Runic # Nl [3] RUNIC ARLAUG SYMBOL..RUNIC BELGTHOR SYMBOL # Total code points: 78 # ================================================ -1780..17B3 ; KHMER # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU -17B4..17B5 ; KHMER # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA -17B6 ; KHMER # Mc KHMER VOWEL SIGN AA -17B7..17BD ; KHMER # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA -17BE..17C5 ; KHMER # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU -17C6 ; KHMER # Mn KHMER SIGN NIKAHIT -17C7..17C8 ; KHMER # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU -17C9..17D3 ; KHMER # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT -17E0..17E9 ; KHMER # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE - -# Total code points: 94 +1780..17B3 ; Khmer # Lo [52] KHMER LETTER KA..KHMER INDEPENDENT VOWEL QAU +17B4..17B5 ; Khmer # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B6 ; Khmer # Mc KHMER VOWEL SIGN AA +17B7..17BD ; Khmer # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17BE..17C5 ; Khmer # Mc [8] KHMER VOWEL SIGN OE..KHMER VOWEL SIGN AU +17C6 ; Khmer # Mn KHMER SIGN NIKAHIT +17C7..17C8 ; Khmer # Mc [2] KHMER SIGN REAHMUK..KHMER SIGN YUUKALEAPINTU +17C9..17D3 ; Khmer # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17D4..17D6 ; Khmer # Po [3] KHMER SIGN KHAN..KHMER SIGN CAMNUC PII KUUH +17D7 ; Khmer # Lm KHMER SIGN LEK TOO +17D8..17DA ; Khmer # Po [3] KHMER SIGN BEYYAL..KHMER SIGN KOOMUUT +17DB ; Khmer # Sc KHMER CURRENCY SYMBOL RIEL +17DC ; Khmer # Lo KHMER SIGN AVAKRAHASANYA +17DD ; Khmer # Mn KHMER SIGN ATTHACAN +17E0..17E9 ; Khmer # Nd [10] KHMER DIGIT ZERO..KHMER DIGIT NINE +17F0..17F9 ; Khmer # No [10] KHMER SYMBOL LEK ATTAK SON..KHMER SYMBOL LEK ATTAK PRAM-BUON +19E0..19FF ; Khmer # So [32] KHMER SYMBOL PATHAMASAT..KHMER SYMBOL DAP-PRAM ROC + +# Total code points: 146 # ================================================ -1810..1819 ; MONGOLIAN # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE -1820..1842 ; MONGOLIAN # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI -1843 ; MONGOLIAN # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN -1844..1877 ; MONGOLIAN # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA -1880..18A8 ; MONGOLIAN # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA -18A9 ; MONGOLIAN # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1800..1805 ; Mongolian # Po [6] MONGOLIAN BIRGA..MONGOLIAN FOUR DOTS +1806 ; Mongolian # Pd MONGOLIAN TODO SOFT HYPHEN +1807..180A ; Mongolian # Po [4] MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER..MONGOLIAN NIRUGU +180B..180D ; Mongolian # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180E ; Mongolian # Zs MONGOLIAN VOWEL SEPARATOR +1810..1819 ; Mongolian # Nd [10] MONGOLIAN DIGIT ZERO..MONGOLIAN DIGIT NINE +1820..1842 ; Mongolian # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; Mongolian # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; Mongolian # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1880..18A8 ; Mongolian # Lo [41] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER MANCHU ALI GALI BHA +18A9 ; Mongolian # Mn MONGOLIAN LETTER ALI GALI DAGALGA -# Total code points: 140 +# Total code points: 155 # ================================================ -3041..3096 ; HIRAGANA # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE -309D..309E ; HIRAGANA # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK -309F ; HIRAGANA # Lo HIRAGANA DIGRAPH YORI +3041..3096 ; Hiragana # Lo [86] HIRAGANA LETTER SMALL A..HIRAGANA LETTER SMALL KE +309D..309E ; Hiragana # Lm [2] HIRAGANA ITERATION MARK..HIRAGANA VOICED ITERATION MARK +309F ; Hiragana # Lo HIRAGANA DIGRAPH YORI # Total code points: 89 # ================================================ -30A1..30FA ; KATAKANA # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO -30FD..30FE ; KATAKANA # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK -30FF ; KATAKANA # Lo KATAKANA DIGRAPH KOTO -31F0..31FF ; KATAKANA # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO -FF66..FF6F ; KATAKANA # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU -FF71..FF9D ; KATAKANA # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N +30A1..30FA ; Katakana # Lo [90] KATAKANA LETTER SMALL A..KATAKANA LETTER VO +30FD..30FE ; Katakana # Lm [2] KATAKANA ITERATION MARK..KATAKANA VOICED ITERATION MARK +30FF ; Katakana # Lo KATAKANA DIGRAPH KOTO +31F0..31FF ; Katakana # Lo [16] KATAKANA LETTER SMALL KU..KATAKANA LETTER SMALL RO +FF66..FF6F ; Katakana # Lo [10] HALFWIDTH KATAKANA LETTER WO..HALFWIDTH KATAKANA LETTER SMALL TU +FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAKANA LETTER N # Total code points: 164 # ================================================ -3105..312C ; BOPOMOFO # Lo [40] BOPOMOFO LETTER B..BOPOMOFO LETTER GN -31A0..31B7 ; BOPOMOFO # Lo [24] BOPOMOFO LETTER BU..BOPOMOFO FINAL LETTER H +3105..312C ; Bopomofo # Lo [40] BOPOMOFO LETTER B..BOPOMOFO LETTER GN +31A0..31B7 ; Bopomofo # Lo [24] BOPOMOFO LETTER BU..BOPOMOFO FINAL LETTER H # Total code points: 64 # ================================================ -2E80..2E99 ; HAN # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP -2E9B..2EF3 ; HAN # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE -2F00..2FD5 ; HAN # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE -3005 ; HAN # Lm IDEOGRAPHIC ITERATION MARK -3007 ; HAN # Nl IDEOGRAPHIC NUMBER ZERO -3021..3029 ; HAN # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE -3038..303A ; HAN # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY -303B ; HAN # Lm VERTICAL IDEOGRAPHIC ITERATION MARK -3400..4DB5 ; HAN # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 -4E00..9FA5 ; HAN # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5 -F900..FA2D ; HAN # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D -FA30..FA6A ; HAN # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A -20000..2A6D6 ; HAN # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 -2F800..2FA1D ; HAN # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D +2E80..2E99 ; Han # So [26] CJK RADICAL REPEAT..CJK RADICAL RAP +2E9B..2EF3 ; Han # So [89] CJK RADICAL CHOKE..CJK RADICAL C-SIMPLIFIED TURTLE +2F00..2FD5 ; Han # So [214] KANGXI RADICAL ONE..KANGXI RADICAL FLUTE +3005 ; Han # Lm IDEOGRAPHIC ITERATION MARK +3007 ; Han # Nl IDEOGRAPHIC NUMBER ZERO +3021..3029 ; Han # Nl [9] HANGZHOU NUMERAL ONE..HANGZHOU NUMERAL NINE +3038..303A ; Han # Nl [3] HANGZHOU NUMERAL TEN..HANGZHOU NUMERAL THIRTY +303B ; Han # Lm VERTICAL IDEOGRAPHIC ITERATION MARK +3400..4DB5 ; Han # Lo [6582] CJK UNIFIED IDEOGRAPH-3400..CJK UNIFIED IDEOGRAPH-4DB5 +4E00..9FA5 ; Han # Lo [20902] CJK UNIFIED IDEOGRAPH-4E00..CJK UNIFIED IDEOGRAPH-9FA5 +F900..FA2D ; Han # Lo [302] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA2D +FA30..FA6A ; Han # Lo [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A +20000..2A6D6 ; Han # Lo [42711] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6D6 +2F800..2FA1D ; Han # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D # Total code points: 71442 # ================================================ -A000..A48C ; YI # Lo [1165] YI SYLLABLE IT..YI SYLLABLE YYR -A490..A4C6 ; YI # So [55] YI RADICAL QOT..YI RADICAL KE +A000..A48C ; Yi # Lo [1165] YI SYLLABLE IT..YI SYLLABLE YYR +A490..A4C6 ; Yi # So [55] YI RADICAL QOT..YI RADICAL KE # Total code points: 1220 # ================================================ -10300..1031E ; OLD_ITALIC # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU +10300..1031E ; Old_Italic # Lo [31] OLD ITALIC LETTER A..OLD ITALIC LETTER UU +10320..10323 ; Old_Italic # No [4] OLD ITALIC NUMERAL ONE..OLD ITALIC NUMERAL FIFTY -# Total code points: 31 +# Total code points: 35 # ================================================ -10330..10349 ; GOTHIC # Lo [26] GOTHIC LETTER AHSA..GOTHIC LETTER OTHAL -1034A ; GOTHIC # Nl GOTHIC LETTER NINE HUNDRED +10330..10349 ; Gothic # Lo [26] GOTHIC LETTER AHSA..GOTHIC LETTER OTHAL +1034A ; Gothic # Nl GOTHIC LETTER NINE HUNDRED # Total code points: 27 # ================================================ -10400..1044F ; DESERET # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW +10400..1044F ; Deseret # L& [80] DESERET CAPITAL LETTER LONG I..DESERET SMALL LETTER EW # Total code points: 80 # ================================================ -0300..034F ; INHERITED # Mn [80] COMBINING GRAVE ACCENT..COMBINING GRAPHEME JOINER -0360..036F ; INHERITED # Mn [16] COMBINING DOUBLE TILDE..COMBINING LATIN SMALL LETTER X -0488..0489 ; INHERITED # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN -0591..05A1 ; INHERITED # Mn [17] HEBREW ACCENT ETNAHTA..HEBREW ACCENT PAZER -05A3..05B9 ; INHERITED # Mn [23] HEBREW ACCENT MUNAH..HEBREW POINT HOLAM -05BB..05BD ; INHERITED # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG -05BF ; INHERITED # Mn HEBREW POINT RAFE -05C1..05C2 ; INHERITED # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT -05C4 ; INHERITED # Mn HEBREW MARK UPPER DOT -064B..0655 ; INHERITED # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW -0670 ; INHERITED # Mn ARABIC LETTER SUPERSCRIPT ALEF -06D6..06DC ; INHERITED # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN -06DD ; INHERITED # Cf ARABIC END OF AYAH -06DE ; INHERITED # Me ARABIC START OF RUB EL HIZB -06DF..06E4 ; INHERITED # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA -06E7..06E8 ; INHERITED # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON -06EA..06ED ; INHERITED # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM -180B..180D ; INHERITED # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE -20D0..20DC ; INHERITED # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE -20DD..20E0 ; INHERITED # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH -20E1 ; INHERITED # Mn COMBINING LEFT RIGHT ARROW ABOVE -20E2..20E4 ; INHERITED # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE -20E5..20EA ; INHERITED # Mn [6] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LEFTWARDS ARROW OVERLAY -302A..302F ; INHERITED # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK -3099..309A ; INHERITED # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK -FB1E ; INHERITED # Mn HEBREW POINT JUDEO-SPANISH VARIKA -FE00..FE0F ; INHERITED # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 -FE20..FE23 ; INHERITED # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF -1D167..1D169 ; INHERITED # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 -1D17B..1D182 ; INHERITED # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE -1D185..1D18B ; INHERITED # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE -1D1AA..1D1AD ; INHERITED # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO - -# Total code points: 259 - -# ================================================ - -1700..170C ; TAGALOG # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA -170E..1711 ; TAGALOG # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA -1712..1714 ; TAGALOG # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +0300..0357 ; Inherited # Mn [88] COMBINING GRAVE ACCENT..COMBINING RIGHT HALF RING ABOVE +035D..036F ; Inherited # Mn [19] COMBINING DOUBLE BREVE..COMBINING LATIN SMALL LETTER X +064B..0655 ; Inherited # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW +0670 ; Inherited # Mn ARABIC LETTER SUPERSCRIPT ALEF +200C..200D ; Inherited # Cf [2] ZERO WIDTH NON-JOINER..ZERO WIDTH JOINER +20D0..20DC ; Inherited # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; Inherited # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; Inherited # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; Inherited # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20EA ; Inherited # Mn [6] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LEFTWARDS ARROW OVERLAY +302A..302F ; Inherited # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; Inherited # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +FE00..FE0F ; Inherited # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE23 ; Inherited # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF +1D167..1D169 ; Inherited # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D17B..1D182 ; Inherited # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; Inherited # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; Inherited # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +E0100..E01EF ; Inherited # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 438 + +# ================================================ + +1700..170C ; Tagalog # Lo [13] TAGALOG LETTER A..TAGALOG LETTER YA +170E..1711 ; Tagalog # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA +1712..1714 ; Tagalog # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA # Total code points: 20 # ================================================ -1720..1731 ; HANUNOO # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA -1732..1734 ; HANUNOO # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1720..1731 ; Hanunoo # Lo [18] HANUNOO LETTER A..HANUNOO LETTER HA +1732..1734 ; Hanunoo # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD # Total code points: 21 # ================================================ -1740..1751 ; BUHID # Lo [18] BUHID LETTER A..BUHID LETTER HA -1752..1753 ; BUHID # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1740..1751 ; Buhid # Lo [18] BUHID LETTER A..BUHID LETTER HA +1752..1753 ; Buhid # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U # Total code points: 20 # ================================================ -1760..176C ; TAGBANWA # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA -176E..1770 ; TAGBANWA # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA -1772..1773 ; TAGBANWA # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +1760..176C ; Tagbanwa # Lo [13] TAGBANWA LETTER A..TAGBANWA LETTER YA +176E..1770 ; Tagbanwa # Lo [3] TAGBANWA LETTER LA..TAGBANWA LETTER SA +1772..1773 ; Tagbanwa # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U # Total code points: 18 # ================================================ -1900..191C ; LIMBU # Lo [29] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER HA -1920..1922 ; LIMBU # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U -1923..1926 ; LIMBU # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU -1927..1928 ; LIMBU # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O -1929..192B ; LIMBU # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA -1930..1931 ; LIMBU # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA -1932 ; LIMBU # Mn LIMBU SMALL LETTER ANUSVARA -1933..1938 ; LIMBU # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA -1939..193B ; LIMBU # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I -1946..194F ; LIMBU # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE - -# Total code points: 63 +1900..191C ; Limbu # Lo [29] LIMBU VOWEL-CARRIER LETTER..LIMBU LETTER HA +1920..1922 ; Limbu # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1923..1926 ; Limbu # Mc [4] LIMBU VOWEL SIGN EE..LIMBU VOWEL SIGN AU +1927..1928 ; Limbu # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1929..192B ; Limbu # Mc [3] LIMBU SUBJOINED LETTER YA..LIMBU SUBJOINED LETTER WA +1930..1931 ; Limbu # Mc [2] LIMBU SMALL LETTER KA..LIMBU SMALL LETTER NGA +1932 ; Limbu # Mn LIMBU SMALL LETTER ANUSVARA +1933..1938 ; Limbu # Mc [6] LIMBU SMALL LETTER TA..LIMBU SMALL LETTER LA +1939..193B ; Limbu # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1940 ; Limbu # So LIMBU SIGN LOO +1944..1945 ; Limbu # Po [2] LIMBU EXCLAMATION MARK..LIMBU QUESTION MARK +1946..194F ; Limbu # Nd [10] LIMBU DIGIT ZERO..LIMBU DIGIT NINE + +# Total code points: 66 # ================================================ -1950..196D ; TAI_LE # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI -1970..1974 ; TAI_LE # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 +1950..196D ; Tai_Le # Lo [30] TAI LE LETTER KA..TAI LE LETTER AI +1970..1974 ; Tai_Le # Lo [5] TAI LE LETTER TONE-2..TAI LE LETTER TONE-6 # Total code points: 35 # ================================================ -10000..1000B ; LINEAR_B # Lo [12] LINEAR B SYLLABLE B008 A..LINEAR B SYLLABLE B046 JE -1000D..10026 ; LINEAR_B # Lo [26] LINEAR B SYLLABLE B036 JO..LINEAR B SYLLABLE B032 QO -10028..1003A ; LINEAR_B # Lo [19] LINEAR B SYLLABLE B060 RA..LINEAR B SYLLABLE B042 WO -1003C..1003D ; LINEAR_B # Lo [2] LINEAR B SYLLABLE B017 ZA..LINEAR B SYLLABLE B074 ZE -1003F..1004D ; LINEAR_B # Lo [15] LINEAR B SYLLABLE B020 ZO..LINEAR B SYLLABLE B091 TWO -10050..1005D ; LINEAR_B # Lo [14] LINEAR B SYMBOL B018..LINEAR B SYMBOL B089 -10080..100FA ; LINEAR_B # Lo [123] LINEAR B IDEOGRAM B100 MAN..LINEAR B IDEOGRAM VESSEL B305 +10000..1000B ; Linear_B # Lo [12] LINEAR B SYLLABLE B008 A..LINEAR B SYLLABLE B046 JE +1000D..10026 ; Linear_B # Lo [26] LINEAR B SYLLABLE B036 JO..LINEAR B SYLLABLE B032 QO +10028..1003A ; Linear_B # Lo [19] LINEAR B SYLLABLE B060 RA..LINEAR B SYLLABLE B042 WO +1003C..1003D ; Linear_B # Lo [2] LINEAR B SYLLABLE B017 ZA..LINEAR B SYLLABLE B074 ZE +1003F..1004D ; Linear_B # Lo [15] LINEAR B SYLLABLE B020 ZO..LINEAR B SYLLABLE B091 TWO +10050..1005D ; Linear_B # Lo [14] LINEAR B SYMBOL B018..LINEAR B SYMBOL B089 +10080..100FA ; Linear_B # Lo [123] LINEAR B IDEOGRAM B100 MAN..LINEAR B IDEOGRAM VESSEL B305 # Total code points: 211 # ================================================ -10380..1039D ; UGARITIC # Lo [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU +10380..1039D ; Ugaritic # Lo [30] UGARITIC LETTER ALPA..UGARITIC LETTER SSU +1039F ; Ugaritic # Po UGARITIC WORD DIVIDER -# Total code points: 30 +# Total code points: 31 # ================================================ -10450..1047F ; SHAVIAN # Lo [48] SHAVIAN LETTER PEEP..SHAVIAN LETTER YEW +10450..1047F ; Shavian # Lo [48] SHAVIAN LETTER PEEP..SHAVIAN LETTER YEW # Total code points: 48 # ================================================ -10480..1049D ; OSMANYA # Lo [30] OSMANYA LETTER ALEF..OSMANYA LETTER OO -104A0..104A9 ; OSMANYA # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE +10480..1049D ; Osmanya # Lo [30] OSMANYA LETTER ALEF..OSMANYA LETTER OO +104A0..104A9 ; Osmanya # Nd [10] OSMANYA DIGIT ZERO..OSMANYA DIGIT NINE # Total code points: 40 # ================================================ -10800..10805 ; CYPRIOT # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA -10808 ; CYPRIOT # Lo CYPRIOT SYLLABLE JO -1080A..10835 ; CYPRIOT # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO -10837..10838 ; CYPRIOT # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE -1083C ; CYPRIOT # Lo CYPRIOT SYLLABLE ZA -1083F ; CYPRIOT # Lo CYPRIOT SYLLABLE ZO +10800..10805 ; Cypriot # Lo [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA +10808 ; Cypriot # Lo CYPRIOT SYLLABLE JO +1080A..10835 ; Cypriot # Lo [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO +10837..10838 ; Cypriot # Lo [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE +1083C ; Cypriot # Lo CYPRIOT SYLLABLE ZA +1083F ; Cypriot # Lo CYPRIOT SYLLABLE ZO # Total code points: 55 # ================================================ -2800..28FF ; BRAILLE # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678 +2800..28FF ; Braille # So [256] BRAILLE PATTERN BLANK..BRAILLE PATTERN DOTS-12345678 # Total code points: 256 +# ================================================ + +3031..3035 ; Katakana_Or_Hiragana # Lm [5] VERTICAL KANA REPEAT MARK..VERTICAL KANA REPEAT MARK LOWER HALF +309B..309C ; Katakana_Or_Hiragana # Sk [2] KATAKANA-HIRAGANA VOICED SOUND MARK..KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +FF70 ; Katakana_Or_Hiragana # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK +FF9E..FF9F ; Katakana_Or_Hiragana # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK + +# Total code points: 10 diff --git a/lib/unicore/SpecialCasing.txt b/lib/unicore/SpecialCasing.txt index 34d1c61..c8401d6 100644 --- a/lib/unicore/SpecialCasing.txt +++ b/lib/unicore/SpecialCasing.txt @@ -1,5 +1,5 @@ -# SpecialCasing-4.0.0.txt -# Date: 2003-03-14, 20:22:04 GMT [MD] +# SpecialCasing-4.0.1.txt +# Date: 2003-10-06, 17:30:00 PST [KW] # # Special Casing Properties # @@ -170,7 +170,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH 1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI 1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI -# Some characters with YPOGEGRAMMENI are also have no corresponding titlecases +# Some characters with YPOGEGRAMMENI also have no corresponding titlecases 1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI 1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI diff --git a/lib/unicore/To/Digit.pl b/lib/unicore/To/Digit.pl index 3d6ee2f..05c62c6 100644 --- a/lib/unicore/To/Digit.pl +++ b/lib/unicore/To/Digit.pl @@ -162,15 +162,6 @@ return <<'END'; 1047 7 1048 8 1049 9 -1369 1 -136A 2 -136B 3 -136C 4 -136D 5 -136E 6 -136F 7 -1370 8 -1371 9 17E0 0 17E1 1 17E2 2 diff --git a/lib/unicore/UnicodeData.txt b/lib/unicore/UnicodeData.txt index 86ea1cf..3710e17 100644 --- a/lib/unicore/UnicodeData.txt +++ b/lib/unicore/UnicodeData.txt @@ -41,11 +41,11 @@ 0028;LEFT PARENTHESIS;Ps;0;ON;;;;;Y;OPENING PARENTHESIS;;;; 0029;RIGHT PARENTHESIS;Pe;0;ON;;;;;Y;CLOSING PARENTHESIS;;;; 002A;ASTERISK;Po;0;ON;;;;;N;;;;; -002B;PLUS SIGN;Sm;0;ET;;;;;N;;;;; +002B;PLUS SIGN;Sm;0;ES;;;;;N;;;;; 002C;COMMA;Po;0;CS;;;;;N;;;;; -002D;HYPHEN-MINUS;Pd;0;ET;;;;;N;;;;; +002D;HYPHEN-MINUS;Pd;0;ES;;;;;N;;;;; 002E;FULL STOP;Po;0;CS;;;;;N;PERIOD;;;; -002F;SOLIDUS;Po;0;ES;;;;;N;SLASH;;;; +002F;SOLIDUS;Po;0;CS;;;;;N;SLASH;;;; 0030;DIGIT ZERO;Nd;0;EN;;0;0;0;N;;;;; 0031;DIGIT ONE;Nd;0;EN;;1;1;1;N;;;;; 0032;DIGIT TWO;Nd;0;EN;;2;2;2;N;;;;; @@ -171,7 +171,7 @@ 00AA;FEMININE ORDINAL INDICATOR;Ll;0;L; 0061;;;;N;;;;; 00AB;LEFT-POINTING DOUBLE ANGLE QUOTATION MARK;Pi;0;ON;;;;;Y;LEFT POINTING GUILLEMET;*;;; 00AC;NOT SIGN;Sm;0;ON;;;;;N;;;;; -00AD;SOFT HYPHEN;Cf;0;ON;;;;;N;;;;; +00AD;SOFT HYPHEN;Cf;0;BN;;;;;N;;;;; 00AE;REGISTERED SIGN;So;0;ON;;;;;N;REGISTERED TRADE MARK SIGN;;;; 00AF;MACRON;Sk;0;ON; 0020 0304;;;;N;SPACING MACRON;;;; 00B0;DEGREE SIGN;So;0;ET;;;;;N;;;;; @@ -659,7 +659,7 @@ 02AB;LATIN SMALL LETTER LZ DIGRAPH;Ll;0;L;;;;;N;;;;; 02AC;LATIN LETTER BILABIAL PERCUSSIVE;Ll;0;L;;;;;N;;;;; 02AD;LATIN LETTER BIDENTAL PERCUSSIVE;Ll;0;L;;;;;N;;;;; -02AE;LATIN SMALL LETTER TURNED H WITH FISHHOOK ;Ll;0;L;;;;;N;;;;; +02AE;LATIN SMALL LETTER TURNED H WITH FISHHOOK;Ll;0;L;;;;;N;;;;; 02AF;LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL;Ll;0;L;;;;;N;;;;; 02B0;MODIFIER LETTER SMALL H;Lm;0;L; 0068;;;;N;;;;; 02B1;MODIFIER LETTER SMALL H WITH HOOK;Lm;0;L; 0266;;;;N;MODIFIER LETTER SMALL H HOOK;;;; @@ -1411,7 +1411,7 @@ 0612;ARABIC SIGN RAHMATULLAH ALAYHE;Mn;230;NSM;;;;;N;;;;; 0613;ARABIC SIGN RADI ALLAHOU ANHU;Mn;230;NSM;;;;;N;;;;; 0614;ARABIC SIGN TAKHALLUS;Mn;230;NSM;;;;;N;;;;; -0615;ARABIC SMALL HIGH TAH ;Mn;230;NSM;;;;;N;;;;; +0615;ARABIC SMALL HIGH TAH;Mn;230;NSM;;;;;N;;;;; 061B;ARABIC SEMICOLON;Po;0;AL;;;;;N;;;;; 061F;ARABIC QUESTION MARK;Po;0;AL;;;;;N;;;;; 0621;ARABIC LETTER HAMZA;Lo;0;AL;;;;;N;ARABIC LETTER HAMZAH;;;; @@ -3645,15 +3645,15 @@ 1366;ETHIOPIC PREFACE COLON;Po;0;L;;;;;N;;;;; 1367;ETHIOPIC QUESTION MARK;Po;0;L;;;;;N;;;;; 1368;ETHIOPIC PARAGRAPH SEPARATOR;Po;0;L;;;;;N;;;;; -1369;ETHIOPIC DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; -136A;ETHIOPIC DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; -136B;ETHIOPIC DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; -136C;ETHIOPIC DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; -136D;ETHIOPIC DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; -136E;ETHIOPIC DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; -136F;ETHIOPIC DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; -1370;ETHIOPIC DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; -1371;ETHIOPIC DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +1369;ETHIOPIC DIGIT ONE;Nd;0;L;;;1;1;N;;;;; +136A;ETHIOPIC DIGIT TWO;Nd;0;L;;;2;2;N;;;;; +136B;ETHIOPIC DIGIT THREE;Nd;0;L;;;3;3;N;;;;; +136C;ETHIOPIC DIGIT FOUR;Nd;0;L;;;4;4;N;;;;; +136D;ETHIOPIC DIGIT FIVE;Nd;0;L;;;5;5;N;;;;; +136E;ETHIOPIC DIGIT SIX;Nd;0;L;;;6;6;N;;;;; +136F;ETHIOPIC DIGIT SEVEN;Nd;0;L;;;7;7;N;;;;; +1370;ETHIOPIC DIGIT EIGHT;Nd;0;L;;;8;8;N;;;;; +1371;ETHIOPIC DIGIT NINE;Nd;0;L;;;9;9;N;;;;; 1372;ETHIOPIC NUMBER TEN;No;0;L;;;;10;N;;;;; 1373;ETHIOPIC NUMBER TWENTY;No;0;L;;;;20;N;;;;; 1374;ETHIOPIC NUMBER THIRTY;No;0;L;;;;30;N;;;;; @@ -5571,7 +5571,7 @@ 2008;PUNCTUATION SPACE;Zs;0;WS; 0020;;;;N;;;;; 2009;THIN SPACE;Zs;0;WS; 0020;;;;N;;;;; 200A;HAIR SPACE;Zs;0;WS; 0020;;;;N;;;;; -200B;ZERO WIDTH SPACE;Zs;0;BN;;;;;N;;;;; +200B;ZERO WIDTH SPACE;Cf;0;BN;;;;;N;;;;; 200C;ZERO WIDTH NON-JOINER;Cf;0;BN;;;;;N;;;;; 200D;ZERO WIDTH JOINER;Cf;0;BN;;;;;N;;;;; 200E;LEFT-TO-RIGHT MARK;Cf;0;L;;;;;N;;;;; @@ -5628,7 +5628,7 @@ 2041;CARET INSERTION POINT;Po;0;ON;;;;;N;;;;; 2042;ASTERISM;Po;0;ON;;;;;N;;;;; 2043;HYPHEN BULLET;Po;0;ON;;;;;N;;;;; -2044;FRACTION SLASH;Sm;0;ON;;;;;N;;;;; +2044;FRACTION SLASH;Sm;0;CS;;;;;N;;;;; 2045;LEFT SQUARE BRACKET WITH QUILL;Ps;0;ON;;;;;Y;;;;; 2046;RIGHT SQUARE BRACKET WITH QUILL;Pe;0;ON;;;;;Y;;;;; 2047;DOUBLE QUESTION MARK;Po;0;ON; 003F 003F;;;;N;;;;; @@ -6482,46 +6482,46 @@ 2448;OCR DASH;So;0;ON;;;;;N;;;;; 2449;OCR CUSTOMER ACCOUNT NUMBER;So;0;ON;;;;;N;;;;; 244A;OCR DOUBLE BACKSLASH;So;0;ON;;;;;N;;;;; -2460;CIRCLED DIGIT ONE;No;0;EN; 0031;;1;1;N;;;;; -2461;CIRCLED DIGIT TWO;No;0;EN; 0032;;2;2;N;;;;; -2462;CIRCLED DIGIT THREE;No;0;EN; 0033;;3;3;N;;;;; -2463;CIRCLED DIGIT FOUR;No;0;EN; 0034;;4;4;N;;;;; -2464;CIRCLED DIGIT FIVE;No;0;EN; 0035;;5;5;N;;;;; -2465;CIRCLED DIGIT SIX;No;0;EN; 0036;;6;6;N;;;;; -2466;CIRCLED DIGIT SEVEN;No;0;EN; 0037;;7;7;N;;;;; -2467;CIRCLED DIGIT EIGHT;No;0;EN; 0038;;8;8;N;;;;; -2468;CIRCLED DIGIT NINE;No;0;EN; 0039;;9;9;N;;;;; -2469;CIRCLED NUMBER TEN;No;0;EN; 0031 0030;;;10;N;;;;; -246A;CIRCLED NUMBER ELEVEN;No;0;EN; 0031 0031;;;11;N;;;;; -246B;CIRCLED NUMBER TWELVE;No;0;EN; 0031 0032;;;12;N;;;;; -246C;CIRCLED NUMBER THIRTEEN;No;0;EN; 0031 0033;;;13;N;;;;; -246D;CIRCLED NUMBER FOURTEEN;No;0;EN; 0031 0034;;;14;N;;;;; -246E;CIRCLED NUMBER FIFTEEN;No;0;EN; 0031 0035;;;15;N;;;;; -246F;CIRCLED NUMBER SIXTEEN;No;0;EN; 0031 0036;;;16;N;;;;; -2470;CIRCLED NUMBER SEVENTEEN;No;0;EN; 0031 0037;;;17;N;;;;; -2471;CIRCLED NUMBER EIGHTEEN;No;0;EN; 0031 0038;;;18;N;;;;; -2472;CIRCLED NUMBER NINETEEN;No;0;EN; 0031 0039;;;19;N;;;;; -2473;CIRCLED NUMBER TWENTY;No;0;EN; 0032 0030;;;20;N;;;;; -2474;PARENTHESIZED DIGIT ONE;No;0;EN; 0028 0031 0029;;1;1;N;;;;; -2475;PARENTHESIZED DIGIT TWO;No;0;EN; 0028 0032 0029;;2;2;N;;;;; -2476;PARENTHESIZED DIGIT THREE;No;0;EN; 0028 0033 0029;;3;3;N;;;;; -2477;PARENTHESIZED DIGIT FOUR;No;0;EN; 0028 0034 0029;;4;4;N;;;;; -2478;PARENTHESIZED DIGIT FIVE;No;0;EN; 0028 0035 0029;;5;5;N;;;;; -2479;PARENTHESIZED DIGIT SIX;No;0;EN; 0028 0036 0029;;6;6;N;;;;; -247A;PARENTHESIZED DIGIT SEVEN;No;0;EN; 0028 0037 0029;;7;7;N;;;;; -247B;PARENTHESIZED DIGIT EIGHT;No;0;EN; 0028 0038 0029;;8;8;N;;;;; -247C;PARENTHESIZED DIGIT NINE;No;0;EN; 0028 0039 0029;;9;9;N;;;;; -247D;PARENTHESIZED NUMBER TEN;No;0;EN; 0028 0031 0030 0029;;;10;N;;;;; -247E;PARENTHESIZED NUMBER ELEVEN;No;0;EN; 0028 0031 0031 0029;;;11;N;;;;; -247F;PARENTHESIZED NUMBER TWELVE;No;0;EN; 0028 0031 0032 0029;;;12;N;;;;; -2480;PARENTHESIZED NUMBER THIRTEEN;No;0;EN; 0028 0031 0033 0029;;;13;N;;;;; -2481;PARENTHESIZED NUMBER FOURTEEN;No;0;EN; 0028 0031 0034 0029;;;14;N;;;;; -2482;PARENTHESIZED NUMBER FIFTEEN;No;0;EN; 0028 0031 0035 0029;;;15;N;;;;; -2483;PARENTHESIZED NUMBER SIXTEEN;No;0;EN; 0028 0031 0036 0029;;;16;N;;;;; -2484;PARENTHESIZED NUMBER SEVENTEEN;No;0;EN; 0028 0031 0037 0029;;;17;N;;;;; -2485;PARENTHESIZED NUMBER EIGHTEEN;No;0;EN; 0028 0031 0038 0029;;;18;N;;;;; -2486;PARENTHESIZED NUMBER NINETEEN;No;0;EN; 0028 0031 0039 0029;;;19;N;;;;; -2487;PARENTHESIZED NUMBER TWENTY;No;0;EN; 0028 0032 0030 0029;;;20;N;;;;; +2460;CIRCLED DIGIT ONE;No;0;ON; 0031;;1;1;N;;;;; +2461;CIRCLED DIGIT TWO;No;0;ON; 0032;;2;2;N;;;;; +2462;CIRCLED DIGIT THREE;No;0;ON; 0033;;3;3;N;;;;; +2463;CIRCLED DIGIT FOUR;No;0;ON; 0034;;4;4;N;;;;; +2464;CIRCLED DIGIT FIVE;No;0;ON; 0035;;5;5;N;;;;; +2465;CIRCLED DIGIT SIX;No;0;ON; 0036;;6;6;N;;;;; +2466;CIRCLED DIGIT SEVEN;No;0;ON; 0037;;7;7;N;;;;; +2467;CIRCLED DIGIT EIGHT;No;0;ON; 0038;;8;8;N;;;;; +2468;CIRCLED DIGIT NINE;No;0;ON; 0039;;9;9;N;;;;; +2469;CIRCLED NUMBER TEN;No;0;ON; 0031 0030;;;10;N;;;;; +246A;CIRCLED NUMBER ELEVEN;No;0;ON; 0031 0031;;;11;N;;;;; +246B;CIRCLED NUMBER TWELVE;No;0;ON; 0031 0032;;;12;N;;;;; +246C;CIRCLED NUMBER THIRTEEN;No;0;ON; 0031 0033;;;13;N;;;;; +246D;CIRCLED NUMBER FOURTEEN;No;0;ON; 0031 0034;;;14;N;;;;; +246E;CIRCLED NUMBER FIFTEEN;No;0;ON; 0031 0035;;;15;N;;;;; +246F;CIRCLED NUMBER SIXTEEN;No;0;ON; 0031 0036;;;16;N;;;;; +2470;CIRCLED NUMBER SEVENTEEN;No;0;ON; 0031 0037;;;17;N;;;;; +2471;CIRCLED NUMBER EIGHTEEN;No;0;ON; 0031 0038;;;18;N;;;;; +2472;CIRCLED NUMBER NINETEEN;No;0;ON; 0031 0039;;;19;N;;;;; +2473;CIRCLED NUMBER TWENTY;No;0;ON; 0032 0030;;;20;N;;;;; +2474;PARENTHESIZED DIGIT ONE;No;0;ON; 0028 0031 0029;;1;1;N;;;;; +2475;PARENTHESIZED DIGIT TWO;No;0;ON; 0028 0032 0029;;2;2;N;;;;; +2476;PARENTHESIZED DIGIT THREE;No;0;ON; 0028 0033 0029;;3;3;N;;;;; +2477;PARENTHESIZED DIGIT FOUR;No;0;ON; 0028 0034 0029;;4;4;N;;;;; +2478;PARENTHESIZED DIGIT FIVE;No;0;ON; 0028 0035 0029;;5;5;N;;;;; +2479;PARENTHESIZED DIGIT SIX;No;0;ON; 0028 0036 0029;;6;6;N;;;;; +247A;PARENTHESIZED DIGIT SEVEN;No;0;ON; 0028 0037 0029;;7;7;N;;;;; +247B;PARENTHESIZED DIGIT EIGHT;No;0;ON; 0028 0038 0029;;8;8;N;;;;; +247C;PARENTHESIZED DIGIT NINE;No;0;ON; 0028 0039 0029;;9;9;N;;;;; +247D;PARENTHESIZED NUMBER TEN;No;0;ON; 0028 0031 0030 0029;;;10;N;;;;; +247E;PARENTHESIZED NUMBER ELEVEN;No;0;ON; 0028 0031 0031 0029;;;11;N;;;;; +247F;PARENTHESIZED NUMBER TWELVE;No;0;ON; 0028 0031 0032 0029;;;12;N;;;;; +2480;PARENTHESIZED NUMBER THIRTEEN;No;0;ON; 0028 0031 0033 0029;;;13;N;;;;; +2481;PARENTHESIZED NUMBER FOURTEEN;No;0;ON; 0028 0031 0034 0029;;;14;N;;;;; +2482;PARENTHESIZED NUMBER FIFTEEN;No;0;ON; 0028 0031 0035 0029;;;15;N;;;;; +2483;PARENTHESIZED NUMBER SIXTEEN;No;0;ON; 0028 0031 0036 0029;;;16;N;;;;; +2484;PARENTHESIZED NUMBER SEVENTEEN;No;0;ON; 0028 0031 0037 0029;;;17;N;;;;; +2485;PARENTHESIZED NUMBER EIGHTEEN;No;0;ON; 0028 0031 0038 0029;;;18;N;;;;; +2486;PARENTHESIZED NUMBER NINETEEN;No;0;ON; 0028 0031 0039 0029;;;19;N;;;;; +2487;PARENTHESIZED NUMBER TWENTY;No;0;ON; 0028 0032 0030 0029;;;20;N;;;;; 2488;DIGIT ONE FULL STOP;No;0;EN; 0031 002E;;1;1;N;DIGIT ONE PERIOD;;;; 2489;DIGIT TWO FULL STOP;No;0;EN; 0032 002E;;2;2;N;DIGIT TWO PERIOD;;;; 248A;DIGIT THREE FULL STOP;No;0;EN; 0033 002E;;3;3;N;DIGIT THREE PERIOD;;;; @@ -6620,7 +6620,7 @@ 24E7;CIRCLED LATIN SMALL LETTER X;So;0;L; 0078;;;;N;;;24CD;;24CD 24E8;CIRCLED LATIN SMALL LETTER Y;So;0;L; 0079;;;;N;;;24CE;;24CE 24E9;CIRCLED LATIN SMALL LETTER Z;So;0;L; 007A;;;;N;;;24CF;;24CF -24EA;CIRCLED DIGIT ZERO;No;0;EN; 0030;;0;0;N;;;;; +24EA;CIRCLED DIGIT ZERO;No;0;ON; 0030;;0;0;N;;;;; 24EB;NEGATIVE CIRCLED NUMBER ELEVEN;No;0;ON;;;;11;N;;;;; 24EC;NEGATIVE CIRCLED NUMBER TWELVE;No;0;ON;;;;12;N;;;;; 24ED;NEGATIVE CIRCLED NUMBER THIRTEEN;No;0;ON;;;;13;N;;;;; @@ -7261,262 +7261,262 @@ 27FD;LONG LEFTWARDS DOUBLE ARROW FROM BAR;Sm;0;ON;;;;;N;;;;; 27FE;LONG RIGHTWARDS DOUBLE ARROW FROM BAR;Sm;0;ON;;;;;N;;;;; 27FF;LONG RIGHTWARDS SQUIGGLE ARROW;Sm;0;ON;;;;;N;;;;; -2800;BRAILLE PATTERN BLANK;So;0;ON;;;;;N;;;;; -2801;BRAILLE PATTERN DOTS-1;So;0;ON;;;;;N;;;;; -2802;BRAILLE PATTERN DOTS-2;So;0;ON;;;;;N;;;;; -2803;BRAILLE PATTERN DOTS-12;So;0;ON;;;;;N;;;;; -2804;BRAILLE PATTERN DOTS-3;So;0;ON;;;;;N;;;;; -2805;BRAILLE PATTERN DOTS-13;So;0;ON;;;;;N;;;;; -2806;BRAILLE PATTERN DOTS-23;So;0;ON;;;;;N;;;;; -2807;BRAILLE PATTERN DOTS-123;So;0;ON;;;;;N;;;;; -2808;BRAILLE PATTERN DOTS-4;So;0;ON;;;;;N;;;;; -2809;BRAILLE PATTERN DOTS-14;So;0;ON;;;;;N;;;;; -280A;BRAILLE PATTERN DOTS-24;So;0;ON;;;;;N;;;;; -280B;BRAILLE PATTERN DOTS-124;So;0;ON;;;;;N;;;;; -280C;BRAILLE PATTERN DOTS-34;So;0;ON;;;;;N;;;;; -280D;BRAILLE PATTERN DOTS-134;So;0;ON;;;;;N;;;;; -280E;BRAILLE PATTERN DOTS-234;So;0;ON;;;;;N;;;;; -280F;BRAILLE PATTERN DOTS-1234;So;0;ON;;;;;N;;;;; -2810;BRAILLE PATTERN DOTS-5;So;0;ON;;;;;N;;;;; -2811;BRAILLE PATTERN DOTS-15;So;0;ON;;;;;N;;;;; -2812;BRAILLE PATTERN DOTS-25;So;0;ON;;;;;N;;;;; -2813;BRAILLE PATTERN DOTS-125;So;0;ON;;;;;N;;;;; -2814;BRAILLE PATTERN DOTS-35;So;0;ON;;;;;N;;;;; -2815;BRAILLE PATTERN DOTS-135;So;0;ON;;;;;N;;;;; -2816;BRAILLE PATTERN DOTS-235;So;0;ON;;;;;N;;;;; -2817;BRAILLE PATTERN DOTS-1235;So;0;ON;;;;;N;;;;; -2818;BRAILLE PATTERN DOTS-45;So;0;ON;;;;;N;;;;; -2819;BRAILLE PATTERN DOTS-145;So;0;ON;;;;;N;;;;; -281A;BRAILLE PATTERN DOTS-245;So;0;ON;;;;;N;;;;; -281B;BRAILLE PATTERN DOTS-1245;So;0;ON;;;;;N;;;;; -281C;BRAILLE PATTERN DOTS-345;So;0;ON;;;;;N;;;;; -281D;BRAILLE PATTERN DOTS-1345;So;0;ON;;;;;N;;;;; -281E;BRAILLE PATTERN DOTS-2345;So;0;ON;;;;;N;;;;; -281F;BRAILLE PATTERN DOTS-12345;So;0;ON;;;;;N;;;;; -2820;BRAILLE PATTERN DOTS-6;So;0;ON;;;;;N;;;;; -2821;BRAILLE PATTERN DOTS-16;So;0;ON;;;;;N;;;;; -2822;BRAILLE PATTERN DOTS-26;So;0;ON;;;;;N;;;;; -2823;BRAILLE PATTERN DOTS-126;So;0;ON;;;;;N;;;;; -2824;BRAILLE PATTERN DOTS-36;So;0;ON;;;;;N;;;;; -2825;BRAILLE PATTERN DOTS-136;So;0;ON;;;;;N;;;;; -2826;BRAILLE PATTERN DOTS-236;So;0;ON;;;;;N;;;;; -2827;BRAILLE PATTERN DOTS-1236;So;0;ON;;;;;N;;;;; -2828;BRAILLE PATTERN DOTS-46;So;0;ON;;;;;N;;;;; -2829;BRAILLE PATTERN DOTS-146;So;0;ON;;;;;N;;;;; -282A;BRAILLE PATTERN DOTS-246;So;0;ON;;;;;N;;;;; -282B;BRAILLE PATTERN DOTS-1246;So;0;ON;;;;;N;;;;; -282C;BRAILLE PATTERN DOTS-346;So;0;ON;;;;;N;;;;; -282D;BRAILLE PATTERN DOTS-1346;So;0;ON;;;;;N;;;;; -282E;BRAILLE PATTERN DOTS-2346;So;0;ON;;;;;N;;;;; -282F;BRAILLE PATTERN DOTS-12346;So;0;ON;;;;;N;;;;; -2830;BRAILLE PATTERN DOTS-56;So;0;ON;;;;;N;;;;; -2831;BRAILLE PATTERN DOTS-156;So;0;ON;;;;;N;;;;; -2832;BRAILLE PATTERN DOTS-256;So;0;ON;;;;;N;;;;; -2833;BRAILLE PATTERN DOTS-1256;So;0;ON;;;;;N;;;;; -2834;BRAILLE PATTERN DOTS-356;So;0;ON;;;;;N;;;;; -2835;BRAILLE PATTERN DOTS-1356;So;0;ON;;;;;N;;;;; -2836;BRAILLE PATTERN DOTS-2356;So;0;ON;;;;;N;;;;; -2837;BRAILLE PATTERN DOTS-12356;So;0;ON;;;;;N;;;;; -2838;BRAILLE PATTERN DOTS-456;So;0;ON;;;;;N;;;;; -2839;BRAILLE PATTERN DOTS-1456;So;0;ON;;;;;N;;;;; -283A;BRAILLE PATTERN DOTS-2456;So;0;ON;;;;;N;;;;; -283B;BRAILLE PATTERN DOTS-12456;So;0;ON;;;;;N;;;;; -283C;BRAILLE PATTERN DOTS-3456;So;0;ON;;;;;N;;;;; -283D;BRAILLE PATTERN DOTS-13456;So;0;ON;;;;;N;;;;; -283E;BRAILLE PATTERN DOTS-23456;So;0;ON;;;;;N;;;;; -283F;BRAILLE PATTERN DOTS-123456;So;0;ON;;;;;N;;;;; -2840;BRAILLE PATTERN DOTS-7;So;0;ON;;;;;N;;;;; -2841;BRAILLE PATTERN DOTS-17;So;0;ON;;;;;N;;;;; -2842;BRAILLE PATTERN DOTS-27;So;0;ON;;;;;N;;;;; -2843;BRAILLE PATTERN DOTS-127;So;0;ON;;;;;N;;;;; -2844;BRAILLE PATTERN DOTS-37;So;0;ON;;;;;N;;;;; -2845;BRAILLE PATTERN DOTS-137;So;0;ON;;;;;N;;;;; -2846;BRAILLE PATTERN DOTS-237;So;0;ON;;;;;N;;;;; -2847;BRAILLE PATTERN DOTS-1237;So;0;ON;;;;;N;;;;; -2848;BRAILLE PATTERN DOTS-47;So;0;ON;;;;;N;;;;; -2849;BRAILLE PATTERN DOTS-147;So;0;ON;;;;;N;;;;; -284A;BRAILLE PATTERN DOTS-247;So;0;ON;;;;;N;;;;; -284B;BRAILLE PATTERN DOTS-1247;So;0;ON;;;;;N;;;;; -284C;BRAILLE PATTERN DOTS-347;So;0;ON;;;;;N;;;;; -284D;BRAILLE PATTERN DOTS-1347;So;0;ON;;;;;N;;;;; -284E;BRAILLE PATTERN DOTS-2347;So;0;ON;;;;;N;;;;; -284F;BRAILLE PATTERN DOTS-12347;So;0;ON;;;;;N;;;;; -2850;BRAILLE PATTERN DOTS-57;So;0;ON;;;;;N;;;;; -2851;BRAILLE PATTERN DOTS-157;So;0;ON;;;;;N;;;;; -2852;BRAILLE PATTERN DOTS-257;So;0;ON;;;;;N;;;;; -2853;BRAILLE PATTERN DOTS-1257;So;0;ON;;;;;N;;;;; -2854;BRAILLE PATTERN DOTS-357;So;0;ON;;;;;N;;;;; -2855;BRAILLE PATTERN DOTS-1357;So;0;ON;;;;;N;;;;; -2856;BRAILLE PATTERN DOTS-2357;So;0;ON;;;;;N;;;;; -2857;BRAILLE PATTERN DOTS-12357;So;0;ON;;;;;N;;;;; -2858;BRAILLE PATTERN DOTS-457;So;0;ON;;;;;N;;;;; -2859;BRAILLE PATTERN DOTS-1457;So;0;ON;;;;;N;;;;; -285A;BRAILLE PATTERN DOTS-2457;So;0;ON;;;;;N;;;;; -285B;BRAILLE PATTERN DOTS-12457;So;0;ON;;;;;N;;;;; -285C;BRAILLE PATTERN DOTS-3457;So;0;ON;;;;;N;;;;; -285D;BRAILLE PATTERN DOTS-13457;So;0;ON;;;;;N;;;;; -285E;BRAILLE PATTERN DOTS-23457;So;0;ON;;;;;N;;;;; -285F;BRAILLE PATTERN DOTS-123457;So;0;ON;;;;;N;;;;; -2860;BRAILLE PATTERN DOTS-67;So;0;ON;;;;;N;;;;; -2861;BRAILLE PATTERN DOTS-167;So;0;ON;;;;;N;;;;; -2862;BRAILLE PATTERN DOTS-267;So;0;ON;;;;;N;;;;; -2863;BRAILLE PATTERN DOTS-1267;So;0;ON;;;;;N;;;;; -2864;BRAILLE PATTERN DOTS-367;So;0;ON;;;;;N;;;;; -2865;BRAILLE PATTERN DOTS-1367;So;0;ON;;;;;N;;;;; -2866;BRAILLE PATTERN DOTS-2367;So;0;ON;;;;;N;;;;; -2867;BRAILLE PATTERN DOTS-12367;So;0;ON;;;;;N;;;;; -2868;BRAILLE PATTERN DOTS-467;So;0;ON;;;;;N;;;;; -2869;BRAILLE PATTERN DOTS-1467;So;0;ON;;;;;N;;;;; -286A;BRAILLE PATTERN DOTS-2467;So;0;ON;;;;;N;;;;; -286B;BRAILLE PATTERN DOTS-12467;So;0;ON;;;;;N;;;;; -286C;BRAILLE PATTERN DOTS-3467;So;0;ON;;;;;N;;;;; -286D;BRAILLE PATTERN DOTS-13467;So;0;ON;;;;;N;;;;; -286E;BRAILLE PATTERN DOTS-23467;So;0;ON;;;;;N;;;;; -286F;BRAILLE PATTERN DOTS-123467;So;0;ON;;;;;N;;;;; -2870;BRAILLE PATTERN DOTS-567;So;0;ON;;;;;N;;;;; -2871;BRAILLE PATTERN DOTS-1567;So;0;ON;;;;;N;;;;; -2872;BRAILLE PATTERN DOTS-2567;So;0;ON;;;;;N;;;;; -2873;BRAILLE PATTERN DOTS-12567;So;0;ON;;;;;N;;;;; -2874;BRAILLE PATTERN DOTS-3567;So;0;ON;;;;;N;;;;; -2875;BRAILLE PATTERN DOTS-13567;So;0;ON;;;;;N;;;;; -2876;BRAILLE PATTERN DOTS-23567;So;0;ON;;;;;N;;;;; -2877;BRAILLE PATTERN DOTS-123567;So;0;ON;;;;;N;;;;; -2878;BRAILLE PATTERN DOTS-4567;So;0;ON;;;;;N;;;;; -2879;BRAILLE PATTERN DOTS-14567;So;0;ON;;;;;N;;;;; -287A;BRAILLE PATTERN DOTS-24567;So;0;ON;;;;;N;;;;; -287B;BRAILLE PATTERN DOTS-124567;So;0;ON;;;;;N;;;;; -287C;BRAILLE PATTERN DOTS-34567;So;0;ON;;;;;N;;;;; -287D;BRAILLE PATTERN DOTS-134567;So;0;ON;;;;;N;;;;; -287E;BRAILLE PATTERN DOTS-234567;So;0;ON;;;;;N;;;;; -287F;BRAILLE PATTERN DOTS-1234567;So;0;ON;;;;;N;;;;; -2880;BRAILLE PATTERN DOTS-8;So;0;ON;;;;;N;;;;; -2881;BRAILLE PATTERN DOTS-18;So;0;ON;;;;;N;;;;; -2882;BRAILLE PATTERN DOTS-28;So;0;ON;;;;;N;;;;; -2883;BRAILLE PATTERN DOTS-128;So;0;ON;;;;;N;;;;; -2884;BRAILLE PATTERN DOTS-38;So;0;ON;;;;;N;;;;; -2885;BRAILLE PATTERN DOTS-138;So;0;ON;;;;;N;;;;; -2886;BRAILLE PATTERN DOTS-238;So;0;ON;;;;;N;;;;; -2887;BRAILLE PATTERN DOTS-1238;So;0;ON;;;;;N;;;;; -2888;BRAILLE PATTERN DOTS-48;So;0;ON;;;;;N;;;;; -2889;BRAILLE PATTERN DOTS-148;So;0;ON;;;;;N;;;;; -288A;BRAILLE PATTERN DOTS-248;So;0;ON;;;;;N;;;;; -288B;BRAILLE PATTERN DOTS-1248;So;0;ON;;;;;N;;;;; -288C;BRAILLE PATTERN DOTS-348;So;0;ON;;;;;N;;;;; -288D;BRAILLE PATTERN DOTS-1348;So;0;ON;;;;;N;;;;; -288E;BRAILLE PATTERN DOTS-2348;So;0;ON;;;;;N;;;;; -288F;BRAILLE PATTERN DOTS-12348;So;0;ON;;;;;N;;;;; -2890;BRAILLE PATTERN DOTS-58;So;0;ON;;;;;N;;;;; -2891;BRAILLE PATTERN DOTS-158;So;0;ON;;;;;N;;;;; -2892;BRAILLE PATTERN DOTS-258;So;0;ON;;;;;N;;;;; -2893;BRAILLE PATTERN DOTS-1258;So;0;ON;;;;;N;;;;; -2894;BRAILLE PATTERN DOTS-358;So;0;ON;;;;;N;;;;; -2895;BRAILLE PATTERN DOTS-1358;So;0;ON;;;;;N;;;;; -2896;BRAILLE PATTERN DOTS-2358;So;0;ON;;;;;N;;;;; -2897;BRAILLE PATTERN DOTS-12358;So;0;ON;;;;;N;;;;; -2898;BRAILLE PATTERN DOTS-458;So;0;ON;;;;;N;;;;; -2899;BRAILLE PATTERN DOTS-1458;So;0;ON;;;;;N;;;;; -289A;BRAILLE PATTERN DOTS-2458;So;0;ON;;;;;N;;;;; -289B;BRAILLE PATTERN DOTS-12458;So;0;ON;;;;;N;;;;; -289C;BRAILLE PATTERN DOTS-3458;So;0;ON;;;;;N;;;;; -289D;BRAILLE PATTERN DOTS-13458;So;0;ON;;;;;N;;;;; -289E;BRAILLE PATTERN DOTS-23458;So;0;ON;;;;;N;;;;; -289F;BRAILLE PATTERN DOTS-123458;So;0;ON;;;;;N;;;;; -28A0;BRAILLE PATTERN DOTS-68;So;0;ON;;;;;N;;;;; -28A1;BRAILLE PATTERN DOTS-168;So;0;ON;;;;;N;;;;; -28A2;BRAILLE PATTERN DOTS-268;So;0;ON;;;;;N;;;;; -28A3;BRAILLE PATTERN DOTS-1268;So;0;ON;;;;;N;;;;; -28A4;BRAILLE PATTERN DOTS-368;So;0;ON;;;;;N;;;;; -28A5;BRAILLE PATTERN DOTS-1368;So;0;ON;;;;;N;;;;; -28A6;BRAILLE PATTERN DOTS-2368;So;0;ON;;;;;N;;;;; -28A7;BRAILLE PATTERN DOTS-12368;So;0;ON;;;;;N;;;;; -28A8;BRAILLE PATTERN DOTS-468;So;0;ON;;;;;N;;;;; -28A9;BRAILLE PATTERN DOTS-1468;So;0;ON;;;;;N;;;;; -28AA;BRAILLE PATTERN DOTS-2468;So;0;ON;;;;;N;;;;; -28AB;BRAILLE PATTERN DOTS-12468;So;0;ON;;;;;N;;;;; -28AC;BRAILLE PATTERN DOTS-3468;So;0;ON;;;;;N;;;;; -28AD;BRAILLE PATTERN DOTS-13468;So;0;ON;;;;;N;;;;; -28AE;BRAILLE PATTERN DOTS-23468;So;0;ON;;;;;N;;;;; -28AF;BRAILLE PATTERN DOTS-123468;So;0;ON;;;;;N;;;;; -28B0;BRAILLE PATTERN DOTS-568;So;0;ON;;;;;N;;;;; -28B1;BRAILLE PATTERN DOTS-1568;So;0;ON;;;;;N;;;;; -28B2;BRAILLE PATTERN DOTS-2568;So;0;ON;;;;;N;;;;; -28B3;BRAILLE PATTERN DOTS-12568;So;0;ON;;;;;N;;;;; -28B4;BRAILLE PATTERN DOTS-3568;So;0;ON;;;;;N;;;;; -28B5;BRAILLE PATTERN DOTS-13568;So;0;ON;;;;;N;;;;; -28B6;BRAILLE PATTERN DOTS-23568;So;0;ON;;;;;N;;;;; -28B7;BRAILLE PATTERN DOTS-123568;So;0;ON;;;;;N;;;;; -28B8;BRAILLE PATTERN DOTS-4568;So;0;ON;;;;;N;;;;; -28B9;BRAILLE PATTERN DOTS-14568;So;0;ON;;;;;N;;;;; -28BA;BRAILLE PATTERN DOTS-24568;So;0;ON;;;;;N;;;;; -28BB;BRAILLE PATTERN DOTS-124568;So;0;ON;;;;;N;;;;; -28BC;BRAILLE PATTERN DOTS-34568;So;0;ON;;;;;N;;;;; -28BD;BRAILLE PATTERN DOTS-134568;So;0;ON;;;;;N;;;;; -28BE;BRAILLE PATTERN DOTS-234568;So;0;ON;;;;;N;;;;; -28BF;BRAILLE PATTERN DOTS-1234568;So;0;ON;;;;;N;;;;; -28C0;BRAILLE PATTERN DOTS-78;So;0;ON;;;;;N;;;;; -28C1;BRAILLE PATTERN DOTS-178;So;0;ON;;;;;N;;;;; -28C2;BRAILLE PATTERN DOTS-278;So;0;ON;;;;;N;;;;; -28C3;BRAILLE PATTERN DOTS-1278;So;0;ON;;;;;N;;;;; -28C4;BRAILLE PATTERN DOTS-378;So;0;ON;;;;;N;;;;; -28C5;BRAILLE PATTERN DOTS-1378;So;0;ON;;;;;N;;;;; -28C6;BRAILLE PATTERN DOTS-2378;So;0;ON;;;;;N;;;;; -28C7;BRAILLE PATTERN DOTS-12378;So;0;ON;;;;;N;;;;; -28C8;BRAILLE PATTERN DOTS-478;So;0;ON;;;;;N;;;;; -28C9;BRAILLE PATTERN DOTS-1478;So;0;ON;;;;;N;;;;; -28CA;BRAILLE PATTERN DOTS-2478;So;0;ON;;;;;N;;;;; -28CB;BRAILLE PATTERN DOTS-12478;So;0;ON;;;;;N;;;;; -28CC;BRAILLE PATTERN DOTS-3478;So;0;ON;;;;;N;;;;; -28CD;BRAILLE PATTERN DOTS-13478;So;0;ON;;;;;N;;;;; -28CE;BRAILLE PATTERN DOTS-23478;So;0;ON;;;;;N;;;;; -28CF;BRAILLE PATTERN DOTS-123478;So;0;ON;;;;;N;;;;; -28D0;BRAILLE PATTERN DOTS-578;So;0;ON;;;;;N;;;;; -28D1;BRAILLE PATTERN DOTS-1578;So;0;ON;;;;;N;;;;; -28D2;BRAILLE PATTERN DOTS-2578;So;0;ON;;;;;N;;;;; -28D3;BRAILLE PATTERN DOTS-12578;So;0;ON;;;;;N;;;;; -28D4;BRAILLE PATTERN DOTS-3578;So;0;ON;;;;;N;;;;; -28D5;BRAILLE PATTERN DOTS-13578;So;0;ON;;;;;N;;;;; -28D6;BRAILLE PATTERN DOTS-23578;So;0;ON;;;;;N;;;;; -28D7;BRAILLE PATTERN DOTS-123578;So;0;ON;;;;;N;;;;; -28D8;BRAILLE PATTERN DOTS-4578;So;0;ON;;;;;N;;;;; -28D9;BRAILLE PATTERN DOTS-14578;So;0;ON;;;;;N;;;;; -28DA;BRAILLE PATTERN DOTS-24578;So;0;ON;;;;;N;;;;; -28DB;BRAILLE PATTERN DOTS-124578;So;0;ON;;;;;N;;;;; -28DC;BRAILLE PATTERN DOTS-34578;So;0;ON;;;;;N;;;;; -28DD;BRAILLE PATTERN DOTS-134578;So;0;ON;;;;;N;;;;; -28DE;BRAILLE PATTERN DOTS-234578;So;0;ON;;;;;N;;;;; -28DF;BRAILLE PATTERN DOTS-1234578;So;0;ON;;;;;N;;;;; -28E0;BRAILLE PATTERN DOTS-678;So;0;ON;;;;;N;;;;; -28E1;BRAILLE PATTERN DOTS-1678;So;0;ON;;;;;N;;;;; -28E2;BRAILLE PATTERN DOTS-2678;So;0;ON;;;;;N;;;;; -28E3;BRAILLE PATTERN DOTS-12678;So;0;ON;;;;;N;;;;; -28E4;BRAILLE PATTERN DOTS-3678;So;0;ON;;;;;N;;;;; -28E5;BRAILLE PATTERN DOTS-13678;So;0;ON;;;;;N;;;;; -28E6;BRAILLE PATTERN DOTS-23678;So;0;ON;;;;;N;;;;; -28E7;BRAILLE PATTERN DOTS-123678;So;0;ON;;;;;N;;;;; -28E8;BRAILLE PATTERN DOTS-4678;So;0;ON;;;;;N;;;;; -28E9;BRAILLE PATTERN DOTS-14678;So;0;ON;;;;;N;;;;; -28EA;BRAILLE PATTERN DOTS-24678;So;0;ON;;;;;N;;;;; -28EB;BRAILLE PATTERN DOTS-124678;So;0;ON;;;;;N;;;;; -28EC;BRAILLE PATTERN DOTS-34678;So;0;ON;;;;;N;;;;; -28ED;BRAILLE PATTERN DOTS-134678;So;0;ON;;;;;N;;;;; -28EE;BRAILLE PATTERN DOTS-234678;So;0;ON;;;;;N;;;;; -28EF;BRAILLE PATTERN DOTS-1234678;So;0;ON;;;;;N;;;;; -28F0;BRAILLE PATTERN DOTS-5678;So;0;ON;;;;;N;;;;; -28F1;BRAILLE PATTERN DOTS-15678;So;0;ON;;;;;N;;;;; -28F2;BRAILLE PATTERN DOTS-25678;So;0;ON;;;;;N;;;;; -28F3;BRAILLE PATTERN DOTS-125678;So;0;ON;;;;;N;;;;; -28F4;BRAILLE PATTERN DOTS-35678;So;0;ON;;;;;N;;;;; -28F5;BRAILLE PATTERN DOTS-135678;So;0;ON;;;;;N;;;;; -28F6;BRAILLE PATTERN DOTS-235678;So;0;ON;;;;;N;;;;; -28F7;BRAILLE PATTERN DOTS-1235678;So;0;ON;;;;;N;;;;; -28F8;BRAILLE PATTERN DOTS-45678;So;0;ON;;;;;N;;;;; -28F9;BRAILLE PATTERN DOTS-145678;So;0;ON;;;;;N;;;;; -28FA;BRAILLE PATTERN DOTS-245678;So;0;ON;;;;;N;;;;; -28FB;BRAILLE PATTERN DOTS-1245678;So;0;ON;;;;;N;;;;; -28FC;BRAILLE PATTERN DOTS-345678;So;0;ON;;;;;N;;;;; -28FD;BRAILLE PATTERN DOTS-1345678;So;0;ON;;;;;N;;;;; -28FE;BRAILLE PATTERN DOTS-2345678;So;0;ON;;;;;N;;;;; -28FF;BRAILLE PATTERN DOTS-12345678;So;0;ON;;;;;N;;;;; +2800;BRAILLE PATTERN BLANK;So;0;L;;;;;N;;;;; +2801;BRAILLE PATTERN DOTS-1;So;0;L;;;;;N;;;;; +2802;BRAILLE PATTERN DOTS-2;So;0;L;;;;;N;;;;; +2803;BRAILLE PATTERN DOTS-12;So;0;L;;;;;N;;;;; +2804;BRAILLE PATTERN DOTS-3;So;0;L;;;;;N;;;;; +2805;BRAILLE PATTERN DOTS-13;So;0;L;;;;;N;;;;; +2806;BRAILLE PATTERN DOTS-23;So;0;L;;;;;N;;;;; +2807;BRAILLE PATTERN DOTS-123;So;0;L;;;;;N;;;;; +2808;BRAILLE PATTERN DOTS-4;So;0;L;;;;;N;;;;; +2809;BRAILLE PATTERN DOTS-14;So;0;L;;;;;N;;;;; +280A;BRAILLE PATTERN DOTS-24;So;0;L;;;;;N;;;;; +280B;BRAILLE PATTERN DOTS-124;So;0;L;;;;;N;;;;; +280C;BRAILLE PATTERN DOTS-34;So;0;L;;;;;N;;;;; +280D;BRAILLE PATTERN DOTS-134;So;0;L;;;;;N;;;;; +280E;BRAILLE PATTERN DOTS-234;So;0;L;;;;;N;;;;; +280F;BRAILLE PATTERN DOTS-1234;So;0;L;;;;;N;;;;; +2810;BRAILLE PATTERN DOTS-5;So;0;L;;;;;N;;;;; +2811;BRAILLE PATTERN DOTS-15;So;0;L;;;;;N;;;;; +2812;BRAILLE PATTERN DOTS-25;So;0;L;;;;;N;;;;; +2813;BRAILLE PATTERN DOTS-125;So;0;L;;;;;N;;;;; +2814;BRAILLE PATTERN DOTS-35;So;0;L;;;;;N;;;;; +2815;BRAILLE PATTERN DOTS-135;So;0;L;;;;;N;;;;; +2816;BRAILLE PATTERN DOTS-235;So;0;L;;;;;N;;;;; +2817;BRAILLE PATTERN DOTS-1235;So;0;L;;;;;N;;;;; +2818;BRAILLE PATTERN DOTS-45;So;0;L;;;;;N;;;;; +2819;BRAILLE PATTERN DOTS-145;So;0;L;;;;;N;;;;; +281A;BRAILLE PATTERN DOTS-245;So;0;L;;;;;N;;;;; +281B;BRAILLE PATTERN DOTS-1245;So;0;L;;;;;N;;;;; +281C;BRAILLE PATTERN DOTS-345;So;0;L;;;;;N;;;;; +281D;BRAILLE PATTERN DOTS-1345;So;0;L;;;;;N;;;;; +281E;BRAILLE PATTERN DOTS-2345;So;0;L;;;;;N;;;;; +281F;BRAILLE PATTERN DOTS-12345;So;0;L;;;;;N;;;;; +2820;BRAILLE PATTERN DOTS-6;So;0;L;;;;;N;;;;; +2821;BRAILLE PATTERN DOTS-16;So;0;L;;;;;N;;;;; +2822;BRAILLE PATTERN DOTS-26;So;0;L;;;;;N;;;;; +2823;BRAILLE PATTERN DOTS-126;So;0;L;;;;;N;;;;; +2824;BRAILLE PATTERN DOTS-36;So;0;L;;;;;N;;;;; +2825;BRAILLE PATTERN DOTS-136;So;0;L;;;;;N;;;;; +2826;BRAILLE PATTERN DOTS-236;So;0;L;;;;;N;;;;; +2827;BRAILLE PATTERN DOTS-1236;So;0;L;;;;;N;;;;; +2828;BRAILLE PATTERN DOTS-46;So;0;L;;;;;N;;;;; +2829;BRAILLE PATTERN DOTS-146;So;0;L;;;;;N;;;;; +282A;BRAILLE PATTERN DOTS-246;So;0;L;;;;;N;;;;; +282B;BRAILLE PATTERN DOTS-1246;So;0;L;;;;;N;;;;; +282C;BRAILLE PATTERN DOTS-346;So;0;L;;;;;N;;;;; +282D;BRAILLE PATTERN DOTS-1346;So;0;L;;;;;N;;;;; +282E;BRAILLE PATTERN DOTS-2346;So;0;L;;;;;N;;;;; +282F;BRAILLE PATTERN DOTS-12346;So;0;L;;;;;N;;;;; +2830;BRAILLE PATTERN DOTS-56;So;0;L;;;;;N;;;;; +2831;BRAILLE PATTERN DOTS-156;So;0;L;;;;;N;;;;; +2832;BRAILLE PATTERN DOTS-256;So;0;L;;;;;N;;;;; +2833;BRAILLE PATTERN DOTS-1256;So;0;L;;;;;N;;;;; +2834;BRAILLE PATTERN DOTS-356;So;0;L;;;;;N;;;;; +2835;BRAILLE PATTERN DOTS-1356;So;0;L;;;;;N;;;;; +2836;BRAILLE PATTERN DOTS-2356;So;0;L;;;;;N;;;;; +2837;BRAILLE PATTERN DOTS-12356;So;0;L;;;;;N;;;;; +2838;BRAILLE PATTERN DOTS-456;So;0;L;;;;;N;;;;; +2839;BRAILLE PATTERN DOTS-1456;So;0;L;;;;;N;;;;; +283A;BRAILLE PATTERN DOTS-2456;So;0;L;;;;;N;;;;; +283B;BRAILLE PATTERN DOTS-12456;So;0;L;;;;;N;;;;; +283C;BRAILLE PATTERN DOTS-3456;So;0;L;;;;;N;;;;; +283D;BRAILLE PATTERN DOTS-13456;So;0;L;;;;;N;;;;; +283E;BRAILLE PATTERN DOTS-23456;So;0;L;;;;;N;;;;; +283F;BRAILLE PATTERN DOTS-123456;So;0;L;;;;;N;;;;; +2840;BRAILLE PATTERN DOTS-7;So;0;L;;;;;N;;;;; +2841;BRAILLE PATTERN DOTS-17;So;0;L;;;;;N;;;;; +2842;BRAILLE PATTERN DOTS-27;So;0;L;;;;;N;;;;; +2843;BRAILLE PATTERN DOTS-127;So;0;L;;;;;N;;;;; +2844;BRAILLE PATTERN DOTS-37;So;0;L;;;;;N;;;;; +2845;BRAILLE PATTERN DOTS-137;So;0;L;;;;;N;;;;; +2846;BRAILLE PATTERN DOTS-237;So;0;L;;;;;N;;;;; +2847;BRAILLE PATTERN DOTS-1237;So;0;L;;;;;N;;;;; +2848;BRAILLE PATTERN DOTS-47;So;0;L;;;;;N;;;;; +2849;BRAILLE PATTERN DOTS-147;So;0;L;;;;;N;;;;; +284A;BRAILLE PATTERN DOTS-247;So;0;L;;;;;N;;;;; +284B;BRAILLE PATTERN DOTS-1247;So;0;L;;;;;N;;;;; +284C;BRAILLE PATTERN DOTS-347;So;0;L;;;;;N;;;;; +284D;BRAILLE PATTERN DOTS-1347;So;0;L;;;;;N;;;;; +284E;BRAILLE PATTERN DOTS-2347;So;0;L;;;;;N;;;;; +284F;BRAILLE PATTERN DOTS-12347;So;0;L;;;;;N;;;;; +2850;BRAILLE PATTERN DOTS-57;So;0;L;;;;;N;;;;; +2851;BRAILLE PATTERN DOTS-157;So;0;L;;;;;N;;;;; +2852;BRAILLE PATTERN DOTS-257;So;0;L;;;;;N;;;;; +2853;BRAILLE PATTERN DOTS-1257;So;0;L;;;;;N;;;;; +2854;BRAILLE PATTERN DOTS-357;So;0;L;;;;;N;;;;; +2855;BRAILLE PATTERN DOTS-1357;So;0;L;;;;;N;;;;; +2856;BRAILLE PATTERN DOTS-2357;So;0;L;;;;;N;;;;; +2857;BRAILLE PATTERN DOTS-12357;So;0;L;;;;;N;;;;; +2858;BRAILLE PATTERN DOTS-457;So;0;L;;;;;N;;;;; +2859;BRAILLE PATTERN DOTS-1457;So;0;L;;;;;N;;;;; +285A;BRAILLE PATTERN DOTS-2457;So;0;L;;;;;N;;;;; +285B;BRAILLE PATTERN DOTS-12457;So;0;L;;;;;N;;;;; +285C;BRAILLE PATTERN DOTS-3457;So;0;L;;;;;N;;;;; +285D;BRAILLE PATTERN DOTS-13457;So;0;L;;;;;N;;;;; +285E;BRAILLE PATTERN DOTS-23457;So;0;L;;;;;N;;;;; +285F;BRAILLE PATTERN DOTS-123457;So;0;L;;;;;N;;;;; +2860;BRAILLE PATTERN DOTS-67;So;0;L;;;;;N;;;;; +2861;BRAILLE PATTERN DOTS-167;So;0;L;;;;;N;;;;; +2862;BRAILLE PATTERN DOTS-267;So;0;L;;;;;N;;;;; +2863;BRAILLE PATTERN DOTS-1267;So;0;L;;;;;N;;;;; +2864;BRAILLE PATTERN DOTS-367;So;0;L;;;;;N;;;;; +2865;BRAILLE PATTERN DOTS-1367;So;0;L;;;;;N;;;;; +2866;BRAILLE PATTERN DOTS-2367;So;0;L;;;;;N;;;;; +2867;BRAILLE PATTERN DOTS-12367;So;0;L;;;;;N;;;;; +2868;BRAILLE PATTERN DOTS-467;So;0;L;;;;;N;;;;; +2869;BRAILLE PATTERN DOTS-1467;So;0;L;;;;;N;;;;; +286A;BRAILLE PATTERN DOTS-2467;So;0;L;;;;;N;;;;; +286B;BRAILLE PATTERN DOTS-12467;So;0;L;;;;;N;;;;; +286C;BRAILLE PATTERN DOTS-3467;So;0;L;;;;;N;;;;; +286D;BRAILLE PATTERN DOTS-13467;So;0;L;;;;;N;;;;; +286E;BRAILLE PATTERN DOTS-23467;So;0;L;;;;;N;;;;; +286F;BRAILLE PATTERN DOTS-123467;So;0;L;;;;;N;;;;; +2870;BRAILLE PATTERN DOTS-567;So;0;L;;;;;N;;;;; +2871;BRAILLE PATTERN DOTS-1567;So;0;L;;;;;N;;;;; +2872;BRAILLE PATTERN DOTS-2567;So;0;L;;;;;N;;;;; +2873;BRAILLE PATTERN DOTS-12567;So;0;L;;;;;N;;;;; +2874;BRAILLE PATTERN DOTS-3567;So;0;L;;;;;N;;;;; +2875;BRAILLE PATTERN DOTS-13567;So;0;L;;;;;N;;;;; +2876;BRAILLE PATTERN DOTS-23567;So;0;L;;;;;N;;;;; +2877;BRAILLE PATTERN DOTS-123567;So;0;L;;;;;N;;;;; +2878;BRAILLE PATTERN DOTS-4567;So;0;L;;;;;N;;;;; +2879;BRAILLE PATTERN DOTS-14567;So;0;L;;;;;N;;;;; +287A;BRAILLE PATTERN DOTS-24567;So;0;L;;;;;N;;;;; +287B;BRAILLE PATTERN DOTS-124567;So;0;L;;;;;N;;;;; +287C;BRAILLE PATTERN DOTS-34567;So;0;L;;;;;N;;;;; +287D;BRAILLE PATTERN DOTS-134567;So;0;L;;;;;N;;;;; +287E;BRAILLE PATTERN DOTS-234567;So;0;L;;;;;N;;;;; +287F;BRAILLE PATTERN DOTS-1234567;So;0;L;;;;;N;;;;; +2880;BRAILLE PATTERN DOTS-8;So;0;L;;;;;N;;;;; +2881;BRAILLE PATTERN DOTS-18;So;0;L;;;;;N;;;;; +2882;BRAILLE PATTERN DOTS-28;So;0;L;;;;;N;;;;; +2883;BRAILLE PATTERN DOTS-128;So;0;L;;;;;N;;;;; +2884;BRAILLE PATTERN DOTS-38;So;0;L;;;;;N;;;;; +2885;BRAILLE PATTERN DOTS-138;So;0;L;;;;;N;;;;; +2886;BRAILLE PATTERN DOTS-238;So;0;L;;;;;N;;;;; +2887;BRAILLE PATTERN DOTS-1238;So;0;L;;;;;N;;;;; +2888;BRAILLE PATTERN DOTS-48;So;0;L;;;;;N;;;;; +2889;BRAILLE PATTERN DOTS-148;So;0;L;;;;;N;;;;; +288A;BRAILLE PATTERN DOTS-248;So;0;L;;;;;N;;;;; +288B;BRAILLE PATTERN DOTS-1248;So;0;L;;;;;N;;;;; +288C;BRAILLE PATTERN DOTS-348;So;0;L;;;;;N;;;;; +288D;BRAILLE PATTERN DOTS-1348;So;0;L;;;;;N;;;;; +288E;BRAILLE PATTERN DOTS-2348;So;0;L;;;;;N;;;;; +288F;BRAILLE PATTERN DOTS-12348;So;0;L;;;;;N;;;;; +2890;BRAILLE PATTERN DOTS-58;So;0;L;;;;;N;;;;; +2891;BRAILLE PATTERN DOTS-158;So;0;L;;;;;N;;;;; +2892;BRAILLE PATTERN DOTS-258;So;0;L;;;;;N;;;;; +2893;BRAILLE PATTERN DOTS-1258;So;0;L;;;;;N;;;;; +2894;BRAILLE PATTERN DOTS-358;So;0;L;;;;;N;;;;; +2895;BRAILLE PATTERN DOTS-1358;So;0;L;;;;;N;;;;; +2896;BRAILLE PATTERN DOTS-2358;So;0;L;;;;;N;;;;; +2897;BRAILLE PATTERN DOTS-12358;So;0;L;;;;;N;;;;; +2898;BRAILLE PATTERN DOTS-458;So;0;L;;;;;N;;;;; +2899;BRAILLE PATTERN DOTS-1458;So;0;L;;;;;N;;;;; +289A;BRAILLE PATTERN DOTS-2458;So;0;L;;;;;N;;;;; +289B;BRAILLE PATTERN DOTS-12458;So;0;L;;;;;N;;;;; +289C;BRAILLE PATTERN DOTS-3458;So;0;L;;;;;N;;;;; +289D;BRAILLE PATTERN DOTS-13458;So;0;L;;;;;N;;;;; +289E;BRAILLE PATTERN DOTS-23458;So;0;L;;;;;N;;;;; +289F;BRAILLE PATTERN DOTS-123458;So;0;L;;;;;N;;;;; +28A0;BRAILLE PATTERN DOTS-68;So;0;L;;;;;N;;;;; +28A1;BRAILLE PATTERN DOTS-168;So;0;L;;;;;N;;;;; +28A2;BRAILLE PATTERN DOTS-268;So;0;L;;;;;N;;;;; +28A3;BRAILLE PATTERN DOTS-1268;So;0;L;;;;;N;;;;; +28A4;BRAILLE PATTERN DOTS-368;So;0;L;;;;;N;;;;; +28A5;BRAILLE PATTERN DOTS-1368;So;0;L;;;;;N;;;;; +28A6;BRAILLE PATTERN DOTS-2368;So;0;L;;;;;N;;;;; +28A7;BRAILLE PATTERN DOTS-12368;So;0;L;;;;;N;;;;; +28A8;BRAILLE PATTERN DOTS-468;So;0;L;;;;;N;;;;; +28A9;BRAILLE PATTERN DOTS-1468;So;0;L;;;;;N;;;;; +28AA;BRAILLE PATTERN DOTS-2468;So;0;L;;;;;N;;;;; +28AB;BRAILLE PATTERN DOTS-12468;So;0;L;;;;;N;;;;; +28AC;BRAILLE PATTERN DOTS-3468;So;0;L;;;;;N;;;;; +28AD;BRAILLE PATTERN DOTS-13468;So;0;L;;;;;N;;;;; +28AE;BRAILLE PATTERN DOTS-23468;So;0;L;;;;;N;;;;; +28AF;BRAILLE PATTERN DOTS-123468;So;0;L;;;;;N;;;;; +28B0;BRAILLE PATTERN DOTS-568;So;0;L;;;;;N;;;;; +28B1;BRAILLE PATTERN DOTS-1568;So;0;L;;;;;N;;;;; +28B2;BRAILLE PATTERN DOTS-2568;So;0;L;;;;;N;;;;; +28B3;BRAILLE PATTERN DOTS-12568;So;0;L;;;;;N;;;;; +28B4;BRAILLE PATTERN DOTS-3568;So;0;L;;;;;N;;;;; +28B5;BRAILLE PATTERN DOTS-13568;So;0;L;;;;;N;;;;; +28B6;BRAILLE PATTERN DOTS-23568;So;0;L;;;;;N;;;;; +28B7;BRAILLE PATTERN DOTS-123568;So;0;L;;;;;N;;;;; +28B8;BRAILLE PATTERN DOTS-4568;So;0;L;;;;;N;;;;; +28B9;BRAILLE PATTERN DOTS-14568;So;0;L;;;;;N;;;;; +28BA;BRAILLE PATTERN DOTS-24568;So;0;L;;;;;N;;;;; +28BB;BRAILLE PATTERN DOTS-124568;So;0;L;;;;;N;;;;; +28BC;BRAILLE PATTERN DOTS-34568;So;0;L;;;;;N;;;;; +28BD;BRAILLE PATTERN DOTS-134568;So;0;L;;;;;N;;;;; +28BE;BRAILLE PATTERN DOTS-234568;So;0;L;;;;;N;;;;; +28BF;BRAILLE PATTERN DOTS-1234568;So;0;L;;;;;N;;;;; +28C0;BRAILLE PATTERN DOTS-78;So;0;L;;;;;N;;;;; +28C1;BRAILLE PATTERN DOTS-178;So;0;L;;;;;N;;;;; +28C2;BRAILLE PATTERN DOTS-278;So;0;L;;;;;N;;;;; +28C3;BRAILLE PATTERN DOTS-1278;So;0;L;;;;;N;;;;; +28C4;BRAILLE PATTERN DOTS-378;So;0;L;;;;;N;;;;; +28C5;BRAILLE PATTERN DOTS-1378;So;0;L;;;;;N;;;;; +28C6;BRAILLE PATTERN DOTS-2378;So;0;L;;;;;N;;;;; +28C7;BRAILLE PATTERN DOTS-12378;So;0;L;;;;;N;;;;; +28C8;BRAILLE PATTERN DOTS-478;So;0;L;;;;;N;;;;; +28C9;BRAILLE PATTERN DOTS-1478;So;0;L;;;;;N;;;;; +28CA;BRAILLE PATTERN DOTS-2478;So;0;L;;;;;N;;;;; +28CB;BRAILLE PATTERN DOTS-12478;So;0;L;;;;;N;;;;; +28CC;BRAILLE PATTERN DOTS-3478;So;0;L;;;;;N;;;;; +28CD;BRAILLE PATTERN DOTS-13478;So;0;L;;;;;N;;;;; +28CE;BRAILLE PATTERN DOTS-23478;So;0;L;;;;;N;;;;; +28CF;BRAILLE PATTERN DOTS-123478;So;0;L;;;;;N;;;;; +28D0;BRAILLE PATTERN DOTS-578;So;0;L;;;;;N;;;;; +28D1;BRAILLE PATTERN DOTS-1578;So;0;L;;;;;N;;;;; +28D2;BRAILLE PATTERN DOTS-2578;So;0;L;;;;;N;;;;; +28D3;BRAILLE PATTERN DOTS-12578;So;0;L;;;;;N;;;;; +28D4;BRAILLE PATTERN DOTS-3578;So;0;L;;;;;N;;;;; +28D5;BRAILLE PATTERN DOTS-13578;So;0;L;;;;;N;;;;; +28D6;BRAILLE PATTERN DOTS-23578;So;0;L;;;;;N;;;;; +28D7;BRAILLE PATTERN DOTS-123578;So;0;L;;;;;N;;;;; +28D8;BRAILLE PATTERN DOTS-4578;So;0;L;;;;;N;;;;; +28D9;BRAILLE PATTERN DOTS-14578;So;0;L;;;;;N;;;;; +28DA;BRAILLE PATTERN DOTS-24578;So;0;L;;;;;N;;;;; +28DB;BRAILLE PATTERN DOTS-124578;So;0;L;;;;;N;;;;; +28DC;BRAILLE PATTERN DOTS-34578;So;0;L;;;;;N;;;;; +28DD;BRAILLE PATTERN DOTS-134578;So;0;L;;;;;N;;;;; +28DE;BRAILLE PATTERN DOTS-234578;So;0;L;;;;;N;;;;; +28DF;BRAILLE PATTERN DOTS-1234578;So;0;L;;;;;N;;;;; +28E0;BRAILLE PATTERN DOTS-678;So;0;L;;;;;N;;;;; +28E1;BRAILLE PATTERN DOTS-1678;So;0;L;;;;;N;;;;; +28E2;BRAILLE PATTERN DOTS-2678;So;0;L;;;;;N;;;;; +28E3;BRAILLE PATTERN DOTS-12678;So;0;L;;;;;N;;;;; +28E4;BRAILLE PATTERN DOTS-3678;So;0;L;;;;;N;;;;; +28E5;BRAILLE PATTERN DOTS-13678;So;0;L;;;;;N;;;;; +28E6;BRAILLE PATTERN DOTS-23678;So;0;L;;;;;N;;;;; +28E7;BRAILLE PATTERN DOTS-123678;So;0;L;;;;;N;;;;; +28E8;BRAILLE PATTERN DOTS-4678;So;0;L;;;;;N;;;;; +28E9;BRAILLE PATTERN DOTS-14678;So;0;L;;;;;N;;;;; +28EA;BRAILLE PATTERN DOTS-24678;So;0;L;;;;;N;;;;; +28EB;BRAILLE PATTERN DOTS-124678;So;0;L;;;;;N;;;;; +28EC;BRAILLE PATTERN DOTS-34678;So;0;L;;;;;N;;;;; +28ED;BRAILLE PATTERN DOTS-134678;So;0;L;;;;;N;;;;; +28EE;BRAILLE PATTERN DOTS-234678;So;0;L;;;;;N;;;;; +28EF;BRAILLE PATTERN DOTS-1234678;So;0;L;;;;;N;;;;; +28F0;BRAILLE PATTERN DOTS-5678;So;0;L;;;;;N;;;;; +28F1;BRAILLE PATTERN DOTS-15678;So;0;L;;;;;N;;;;; +28F2;BRAILLE PATTERN DOTS-25678;So;0;L;;;;;N;;;;; +28F3;BRAILLE PATTERN DOTS-125678;So;0;L;;;;;N;;;;; +28F4;BRAILLE PATTERN DOTS-35678;So;0;L;;;;;N;;;;; +28F5;BRAILLE PATTERN DOTS-135678;So;0;L;;;;;N;;;;; +28F6;BRAILLE PATTERN DOTS-235678;So;0;L;;;;;N;;;;; +28F7;BRAILLE PATTERN DOTS-1235678;So;0;L;;;;;N;;;;; +28F8;BRAILLE PATTERN DOTS-45678;So;0;L;;;;;N;;;;; +28F9;BRAILLE PATTERN DOTS-145678;So;0;L;;;;;N;;;;; +28FA;BRAILLE PATTERN DOTS-245678;So;0;L;;;;;N;;;;; +28FB;BRAILLE PATTERN DOTS-1245678;So;0;L;;;;;N;;;;; +28FC;BRAILLE PATTERN DOTS-345678;So;0;L;;;;;N;;;;; +28FD;BRAILLE PATTERN DOTS-1345678;So;0;L;;;;;N;;;;; +28FE;BRAILLE PATTERN DOTS-2345678;So;0;L;;;;;N;;;;; +28FF;BRAILLE PATTERN DOTS-12345678;So;0;L;;;;;N;;;;; 2900;RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE;Sm;0;ON;;;;;N;;;;; 2901;RIGHTWARDS TWO-HEADED ARROW WITH DOUBLE VERTICAL STROKE;Sm;0;ON;;;;;N;;;;; 2902;LEFTWARDS DOUBLE ARROW WITH VERTICAL STROKE;Sm;0;ON;;;;;N;;;;; @@ -12080,9 +12080,9 @@ FFEB;HALFWIDTH RIGHTWARDS ARROW;Sm;0;ON; 2192;;;;N;;;;; FFEC;HALFWIDTH DOWNWARDS ARROW;Sm;0;ON; 2193;;;;N;;;;; FFED;HALFWIDTH BLACK SQUARE;So;0;ON; 25A0;;;;N;;;;; FFEE;HALFWIDTH WHITE CIRCLE;So;0;ON; 25CB;;;;N;;;;; -FFF9;INTERLINEAR ANNOTATION ANCHOR;Cf;0;BN;;;;;N;;;;; -FFFA;INTERLINEAR ANNOTATION SEPARATOR;Cf;0;BN;;;;;N;;;;; -FFFB;INTERLINEAR ANNOTATION TERMINATOR;Cf;0;BN;;;;;N;;;;; +FFF9;INTERLINEAR ANNOTATION ANCHOR;Cf;0;ON;;;;;N;;;;; +FFFA;INTERLINEAR ANNOTATION SEPARATOR;Cf;0;ON;;;;;N;;;;; +FFFB;INTERLINEAR ANNOTATION TERMINATOR;Cf;0;ON;;;;;N;;;;; FFFC;OBJECT REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10000;LINEAR B SYLLABLE B008 A;Lo;0;L;;;;;N;;;;; diff --git a/lib/unicore/lib/Arabic.pl b/lib/unicore/lib/Arabic.pl index c2859e2..ee69fbd 100644 --- a/lib/unicore/lib/Arabic.pl +++ b/lib/unicore/lib/Arabic.pl @@ -6,23 +6,21 @@ # This file supports: # \p{Arabic} (and fuzzy permutations) # -# Meaning: Script 'ARABIC' +# Meaning: Script 'Arabic' # return <<'END'; -0621 063A ARABIC -0641 064A ARABIC -066E 066F ARABIC -0671 06D3 ARABIC -06D5 ARABIC -06E5 06E6 ARABIC -06EE 06EF ARABIC -06FA 06FC ARABIC -06FF ARABIC -FB50 FBB1 ARABIC -FBD3 FD3D ARABIC -FD50 FD8F ARABIC -FD92 FDC7 ARABIC -FDF0 FDFB ARABIC -FE70 FE74 ARABIC -FE76 FEFC ARABIC +060D 0615 Arabic +0621 063A Arabic +0641 064A Arabic +0656 0658 Arabic +066A 066F Arabic +0671 06DC Arabic +06DE 06FF Arabic +FB50 FBB1 Arabic +FBD3 FD3D Arabic +FD50 FD8F Arabic +FD92 FDC7 Arabic +FDF0 FDFC Arabic +FE70 FE74 Arabic +FE76 FEFC Arabic END diff --git a/lib/unicore/lib/Armenian.pl b/lib/unicore/lib/Armenian.pl index 6652079..a3d64d5 100644 --- a/lib/unicore/lib/Armenian.pl +++ b/lib/unicore/lib/Armenian.pl @@ -6,11 +6,12 @@ # This file supports: # \p{Armenian} (and fuzzy permutations) # -# Meaning: Script 'ARMENIAN' +# Meaning: Script 'Armenian' # return <<'END'; -0531 0556 ARMENIAN -0559 ARMENIAN -0561 0587 ARMENIAN -FB13 FB17 ARMENIAN +0531 0556 Armenian +0559 055F Armenian +0561 0587 Armenian +058A Armenian +FB13 FB17 Armenian END diff --git a/lib/unicore/lib/Bengali.pl b/lib/unicore/lib/Bengali.pl index 08a4f3e..ababd01 100644 --- a/lib/unicore/lib/Bengali.pl +++ b/lib/unicore/lib/Bengali.pl @@ -6,21 +6,21 @@ # This file supports: # \p{Bengali} (and fuzzy permutations) # -# Meaning: Script 'BENGALI' +# Meaning: Script 'Bengali' # return <<'END'; -0981 0983 BENGALI -0985 098C BENGALI -098F 0990 BENGALI -0993 09A8 BENGALI -09AA 09B0 BENGALI -09B2 BENGALI -09B6 09B9 BENGALI -09BC 09C4 BENGALI -09C7 09C8 BENGALI -09CB 09CD BENGALI -09D7 BENGALI -09DC 09DD BENGALI -09DF 09E3 BENGALI -09E6 09F1 BENGALI +0981 0983 Bengali +0985 098C Bengali +098F 0990 Bengali +0993 09A8 Bengali +09AA 09B0 Bengali +09B2 Bengali +09B6 09B9 Bengali +09BC 09C4 Bengali +09C7 09C8 Bengali +09CB 09CD Bengali +09D7 Bengali +09DC 09DD Bengali +09DF 09E3 Bengali +09E6 09FA Bengali END diff --git a/lib/unicore/lib/BidiBN.pl b/lib/unicore/lib/BidiBN.pl index 0dfe3ba..8078069 100644 --- a/lib/unicore/lib/BidiBN.pl +++ b/lib/unicore/lib/BidiBN.pl @@ -13,12 +13,12 @@ return <<'END'; 000E 001B 007F 0084 0086 009F +00AD 070F 200B 200D 2060 2063 206A 206F FEFF -FFF9 FFFB 1D173 1D17A E0001 E0020 E007F diff --git a/lib/unicore/lib/BidiCS.pl b/lib/unicore/lib/BidiCS.pl index 7f17238..1b595df 100644 --- a/lib/unicore/lib/BidiCS.pl +++ b/lib/unicore/lib/BidiCS.pl @@ -10,10 +10,11 @@ # return <<'END'; 002C -002E +002E 002F 003A 00A0 060C +2044 FE50 FE52 FE55 diff --git a/lib/unicore/lib/BidiEN.pl b/lib/unicore/lib/BidiEN.pl index 24a291f..8675128 100644 --- a/lib/unicore/lib/BidiEN.pl +++ b/lib/unicore/lib/BidiEN.pl @@ -16,8 +16,7 @@ return <<'END'; 2070 2074 2079 2080 2089 -2460 249B -24EA +2488 249B FF10 FF19 1D7CE 1D7FF END diff --git a/lib/unicore/lib/BidiES.pl b/lib/unicore/lib/BidiES.pl index 9810f81..ba9962d 100644 --- a/lib/unicore/lib/BidiES.pl +++ b/lib/unicore/lib/BidiES.pl @@ -9,6 +9,7 @@ # Meaning: Bi-directional category 'ES' # return <<'END'; -002F +002B +002D FF0F END diff --git a/lib/unicore/lib/BidiET.pl b/lib/unicore/lib/BidiET.pl index 50073b7..8772d9e 100644 --- a/lib/unicore/lib/BidiET.pl +++ b/lib/unicore/lib/BidiET.pl @@ -10,8 +10,6 @@ # return <<'END'; 0023 0025 -002B -002D 00A2 00A5 00B0 00B1 066A diff --git a/lib/unicore/lib/BidiL.pl b/lib/unicore/lib/BidiL.pl index a21fab5..ee22810 100644 --- a/lib/unicore/lib/BidiL.pl +++ b/lib/unicore/lib/BidiL.pl @@ -301,6 +301,7 @@ return <<'END'; 2336 237A 2395 249C 24E9 +2800 28FF 3005 3007 3021 3029 3031 3035 diff --git a/lib/unicore/lib/BidiON.pl b/lib/unicore/lib/BidiON.pl index 5ad57f4..9442176 100644 --- a/lib/unicore/lib/BidiON.pl +++ b/lib/unicore/lib/BidiON.pl @@ -16,7 +16,8 @@ return <<'END'; 007B 007E 00A1 00A6 00A9 -00AB 00AF +00AB 00AC +00AE 00AF 00B4 00B6 00B8 00BB 00BF @@ -51,7 +52,8 @@ return <<'END'; 1FED 1FEF 1FFD 1FFE 2010 2027 -2035 2054 +2035 2043 +2045 2054 2057 207C 207E 208C 208E @@ -75,7 +77,8 @@ return <<'END'; 2396 23D0 2400 2426 2440 244A -24EB 2617 +2460 2487 +24EA 2617 2619 267D 2680 2691 26A0 26A1 @@ -91,7 +94,8 @@ return <<'END'; 2798 27AF 27B1 27BE 27D0 27EB -27F0 2B0D +27F0 27FF +2900 2B0D 2E80 2E99 2E9B 2EF3 2F00 2FD5 @@ -131,7 +135,7 @@ FF3B FF40 FF5B FF65 FFE2 FFE4 FFE8 FFEE -FFFC FFFD +FFF9 FFFD 10101 1D300 1D356 END diff --git a/lib/unicore/lib/Bopomofo.pl b/lib/unicore/lib/Bopomofo.pl index 525797c..9ec7a36 100644 --- a/lib/unicore/lib/Bopomofo.pl +++ b/lib/unicore/lib/Bopomofo.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Bopomofo} (and fuzzy permutations) # -# Meaning: Script 'BOPOMOFO' +# Meaning: Script 'Bopomofo' # return <<'END'; -3105 312C BOPOMOFO -31A0 31B7 BOPOMOFO +3105 312C Bopomofo +31A0 31B7 Bopomofo END diff --git a/lib/unicore/lib/Braille.pl b/lib/unicore/lib/Braille.pl index dfa506a..3a9d9b4 100644 --- a/lib/unicore/lib/Braille.pl +++ b/lib/unicore/lib/Braille.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Braille} (and fuzzy permutations) # -# Meaning: Script 'BRAILLE' +# Meaning: Script 'Braille' # return <<'END'; -2800 28FF BRAILLE +2800 28FF Braille END diff --git a/lib/unicore/lib/Buhid.pl b/lib/unicore/lib/Buhid.pl index c1ad8f8..a3214c3 100644 --- a/lib/unicore/lib/Buhid.pl +++ b/lib/unicore/lib/Buhid.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Buhid} (and fuzzy permutations) # -# Meaning: Script 'BUHID' +# Meaning: Script 'Buhid' # return <<'END'; -1740 1753 BUHID +1740 1753 Buhid END diff --git a/lib/unicore/lib/C.pl b/lib/unicore/lib/C.pl index 52c3f44..daecb74 100644 --- a/lib/unicore/lib/C.pl +++ b/lib/unicore/lib/C.pl @@ -282,7 +282,7 @@ return <<'END'; 1FF0 1FF1 1FF5 1FFF -200C 200F +200B 200F 202A 202E 2055 2056 2058 205E diff --git a/lib/unicore/lib/Canadian.pl b/lib/unicore/lib/Canadian.pl index e4942b1..276c269 100644 --- a/lib/unicore/lib/Canadian.pl +++ b/lib/unicore/lib/Canadian.pl @@ -6,9 +6,8 @@ # This file supports: # \p{CanadianAboriginal} (and fuzzy permutations) # -# Meaning: Script 'CANADIAN_ABORIGINAL' +# Meaning: Script 'Canadian_Aboriginal' # return <<'END'; -1401 166C CANADIAN_ABORIGINAL -166F 1676 CANADIAN_ABORIGINAL +1401 1676 Canadian_Aboriginal END diff --git a/lib/unicore/lib/Cf.pl b/lib/unicore/lib/Cf.pl index 8e1c324..44ed908 100644 --- a/lib/unicore/lib/Cf.pl +++ b/lib/unicore/lib/Cf.pl @@ -15,7 +15,7 @@ return <<'END'; 06DD 070F 17B4 17B5 -200C 200F +200B 200F 202A 202E 2060 2063 206A 206F diff --git a/lib/unicore/lib/Cherokee.pl b/lib/unicore/lib/Cherokee.pl index 4844ef4..f22a09c 100644 --- a/lib/unicore/lib/Cherokee.pl +++ b/lib/unicore/lib/Cherokee.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Cherokee} (and fuzzy permutations) # -# Meaning: Script 'CHEROKEE' +# Meaning: Script 'Cherokee' # return <<'END'; -13A0 13F4 CHEROKEE +13A0 13F4 Cherokee END diff --git a/lib/unicore/lib/Cntrl.pl b/lib/unicore/lib/Cntrl.pl index c1db31a..e3ec0bf 100644 --- a/lib/unicore/lib/Cntrl.pl +++ b/lib/unicore/lib/Cntrl.pl @@ -16,7 +16,7 @@ return <<'END'; 06DD 070F 17B4 17B5 -200C 200F +200B 200F 202A 202E 2060 2063 206A 206F diff --git a/lib/unicore/lib/Common.pl b/lib/unicore/lib/Common.pl index 92b42ee..a660faa 100644 --- a/lib/unicore/lib/Common.pl +++ b/lib/unicore/lib/Common.pl @@ -6,377 +6,130 @@ # This file supports: # \p{Common} (and fuzzy permutations) # -# Meaning: Pseudo-Script of codepoints not in other Unicode scripts +# Meaning: Script 'Common' # return <<'END'; -0000 0040 -005B 0060 -007B 00A9 -00AB 00B4 -00B6 00B9 -00BB 00BF -00D7 -00F7 -0237 024F -02B9 02DF -02E5 02FF -0350 035F -0370 0379 -037B 0385 -0387 -038B -038D -03A2 -03CF -03F6 -03FC 03FF -0482 -0487 -04CF -04F6 04F7 -04FA 04FF -0510 0530 -0557 0558 -055A 0560 -0588 0590 -05A2 -05BA -05BE -05C0 -05C3 -05C5 05CF -05EB 05EF -05F3 0620 -063B 0640 -0656 066D -06D4 -06E9 -06F0 06F9 -06FD 06FE -0700 070F -074B 074C -0750 077F -07B2 0900 -093A 093B -094E 094F -0955 0957 -0964 0965 -0970 0980 -0984 -098D 098E -0991 0992 -09A9 -09B1 -09B3 09B5 -09BA 09BB -09C5 09C6 -09C9 09CA -09CE 09D6 -09D8 09DB -09DE -09E4 09E5 -09F2 0A01 -0A04 -0A0B 0A0E -0A11 0A12 -0A29 -0A31 -0A34 -0A37 -0A3A 0A3B -0A3D -0A43 0A46 -0A49 0A4A -0A4E 0A58 -0A5D -0A5F 0A65 -0A75 0A80 -0A84 -0A8E -0A92 -0AA9 -0AB1 -0AB4 -0ABA 0ABB -0AC6 -0ACA -0ACE 0ACF -0AD1 0ADF -0AE4 0AE5 -0AF0 0B00 -0B04 -0B0D 0B0E -0B11 0B12 -0B29 -0B31 -0B34 -0B3A 0B3B -0B44 0B46 -0B49 0B4A -0B4E 0B55 -0B58 0B5B -0B5E -0B62 0B65 -0B70 -0B72 0B81 -0B84 -0B8B 0B8D -0B91 -0B96 0B98 -0B9B -0B9D -0BA0 0BA2 -0BA5 0BA7 -0BAB 0BAD -0BB6 -0BBA 0BBD -0BC3 0BC5 -0BC9 -0BCE 0BD6 -0BD8 0BE6 -0BF3 0C00 -0C04 -0C0D -0C11 -0C29 -0C34 -0C3A 0C3D -0C45 -0C49 -0C4E 0C54 -0C57 0C5F -0C62 0C65 -0C70 0C81 -0C84 -0C8D -0C91 -0CA9 -0CB4 -0CBA 0CBC -0CC5 -0CC9 -0CCE 0CD4 -0CD7 0CDD -0CDF -0CE2 0CE5 -0CF0 0D01 -0D04 -0D0D -0D11 -0D29 -0D3A 0D3D -0D44 0D45 -0D49 -0D4E 0D56 -0D58 0D5F -0D62 0D65 -0D70 0D81 -0D84 -0D97 0D99 -0DB2 -0DBC -0DBE 0DBF -0DC7 0DC9 -0DCB 0DCE -0DD5 -0DD7 -0DE0 0DF1 -0DF4 0E00 -0E3B 0E3F -0E4F -0E5A 0E80 -0E83 -0E85 0E86 -0E89 -0E8B 0E8C -0E8E 0E93 -0E98 -0EA0 -0EA4 -0EA6 -0EA8 0EA9 -0EAC -0EBA -0EBE 0EBF -0EC5 -0EC7 -0ECE 0ECF -0EDA 0EDB -0EDE 0EFF -0F01 0F17 -0F1A 0F1F -0F34 -0F36 -0F38 -0F3A 0F3F -0F48 -0F6B 0F70 -0F85 -0F8C 0F8F -0F98 -0FBD 0FC5 -0FC7 0FFF -1022 -1028 -102B -1033 1035 -103A 103F -104A 104F -105A 109F -10C6 10CF -10F9 10FF -115A 115E -11A3 11A7 -11FA 11FF -1207 -1247 -1249 -124E 124F -1257 -1259 -125E 125F -1287 -1289 -128E 128F -12AF -12B1 -12B6 12B7 -12BF -12C1 -12C6 12C7 -12CF -12D7 -12EF -130F -1311 -1316 1317 -131F -1347 -135B 1368 -137D 139F -13F5 1400 -166D 166E -1677 1680 -169B 169F -16EB 16ED -16F1 16FF -170D -1715 171F -1735 173F -1754 175F -176D -1771 -1774 177F -17D4 17DF -17EA 180A -180E 180F -181A 181F -1878 187F -18AA 18FF -191D 191F -192C 192F -193C 1945 -196E 196F -1975 1CFF -1D6C 1DFF -1E9C 1E9F -1EFA 1EFF -1F16 1F17 -1F1E 1F1F -1F46 1F47 -1F4E 1F4F -1F58 -1F5A -1F5C -1F5E -1F7E 1F7F -1FB5 -1FBD -1FBF 1FC1 -1FC5 -1FCD 1FCF -1FD4 1FD5 -1FDC 1FDF -1FED 1FF1 -1FF5 -1FFD 2070 -2072 207E -2080 20CF -20EB 2125 -2127 2129 -212C 27FF -2900 2E7F -2E9A -2EF4 2EFF -2FD6 3004 -3006 -3008 3020 -3030 3037 -303C 3040 -3097 3098 -309B 309C -30A0 -30FB 30FC -3100 3104 -312D 3130 -318F 319F -31B8 31EF -3200 33FF -4DB6 4DFF -9FA6 9FFF -A48D A48F -A4C7 ABFF -D7A4 F8FF -FA2E FA2F -FA6B FAFF -FB07 FB12 -FB18 FB1C -FB29 -FB37 -FB3D -FB3F -FB42 -FB45 -FBB2 FBD2 -FD3E FD4F -FD90 FD91 -FDC8 FDEF -FDFC FDFF -FE10 FE1F -FE24 FE6F -FE75 -FEFD FF20 -FF3B FF40 -FF5B FF65 -FF70 -FF9E FF9F -FFBF FFC1 -FFC8 FFC9 -FFD0 FFD1 -FFD8 FFD9 -FFDD FFFF -1000C -10027 -1003B -1003E -1004E 1004F -1005E 1007F -100FB 102FF -1031F 1032F -1034B 1037F -1039E 103FF -1049E 1049F -104AA 107FF -10806 10807 -10809 -10836 -10839 1083B -1083D 1083E -10840 1D166 -1D16A 1D17A -1D183 1D184 -1D18C 1D1A9 -1D1AE 1FFFF -2A6D7 2F7FF -2FA1E 10FFFF +0000 0040 Common +005B 0060 Common +007B 00A9 Common +00AB 00B9 Common +00BB 00BF Common +00D7 Common +00F7 Common +02B9 02DF Common +02E5 02FF Common +037E Common +0387 Common +0589 Common +0600 0603 Common +060C Common +061B Common +061F Common +0640 Common +0660 0669 Common +06DD Common +0964 0965 Common +0970 Common +0E3F Common +10FB Common +16EB 16ED Common +1735 1736 Common +2000 200B Common +200E 2054 Common +2057 Common +205F 2063 Common +206A 2070 Common +2074 207E Common +2080 208E Common +20A0 20B1 Common +2100 2125 Common +2127 2129 Common +212C 213B Common +213D 214B Common +2153 2183 Common +2190 23D0 Common +2400 2426 Common +2440 244A Common +2460 2617 Common +2619 267D Common +2680 2691 Common +26A0 26A1 Common +2701 2704 Common +2706 2709 Common +270C 2727 Common +2729 274B Common +274D Common +274F 2752 Common +2756 Common +2758 275E Common +2761 2794 Common +2798 27AF Common +27B1 27BE Common +27D0 27EB Common +27F0 27FF Common +2900 2B0D Common +2FF0 2FFB Common +3000 3004 Common +3006 Common +3008 3020 Common +3030 Common +3036 3037 Common +303C 303F Common +30A0 Common +30FB 30FC Common +3190 319F Common +3220 3243 Common +3250 325F Common +327F 32FE Common +3300 33FF Common +4DC0 4DFF Common +E000 F8FF Common +FD3E FD3F Common +FDFD Common +FE30 FE52 Common +FE54 FE66 Common +FE68 FE6B Common +FEFF Common +FF01 FF20 Common +FF3B FF40 Common +FF5B FF65 Common +FFE0 FFE6 Common +FFE8 FFEE Common +FFF9 FFFD Common +10100 10102 Common +10107 10133 Common +10137 1013F Common +1D000 1D0F5 Common +1D100 1D126 Common +1D12A 1D166 Common +1D16A 1D17A Common +1D183 1D184 Common +1D18C 1D1A9 Common +1D1AE 1D1DD Common +1D300 1D356 Common +1D400 1D454 Common +1D456 1D49C Common +1D49E 1D49F Common +1D4A2 Common +1D4A5 1D4A6 Common +1D4A9 1D4AC Common +1D4AE 1D4B9 Common +1D4BB Common +1D4BD 1D4C3 Common +1D4C5 1D505 Common +1D507 1D50A Common +1D50D 1D514 Common +1D516 1D51C Common +1D51E 1D539 Common +1D53B 1D53E Common +1D540 1D544 Common +1D546 Common +1D54A 1D550 Common +1D552 1D6A3 Common +1D6A8 1D7C9 Common +1D7CE 1D7FF Common +E0001 Common +E0020 E007F Common +F0000 FFFFD Common +100000 10FFFD Common END diff --git a/lib/unicore/lib/Cypriot.pl b/lib/unicore/lib/Cypriot.pl index 4e43cf4..8dc7227 100644 --- a/lib/unicore/lib/Cypriot.pl +++ b/lib/unicore/lib/Cypriot.pl @@ -6,13 +6,13 @@ # This file supports: # \p{Cypriot} (and fuzzy permutations) # -# Meaning: Script 'CYPRIOT' +# Meaning: Script 'Cypriot' # return <<'END'; -10800 10805 CYPRIOT -10808 CYPRIOT -1080A 10835 CYPRIOT -10837 10838 CYPRIOT -1083C CYPRIOT -1083F CYPRIOT +10800 10805 Cypriot +10808 Cypriot +1080A 10835 Cypriot +10837 10838 Cypriot +1083C Cypriot +1083F Cypriot END diff --git a/lib/unicore/lib/Cyrillic.pl b/lib/unicore/lib/Cyrillic.pl index 73f6726..e8ca471 100644 --- a/lib/unicore/lib/Cyrillic.pl +++ b/lib/unicore/lib/Cyrillic.pl @@ -6,14 +6,13 @@ # This file supports: # \p{Cyrillic} (and fuzzy permutations) # -# Meaning: Script 'CYRILLIC' +# Meaning: Script 'Cyrillic' # return <<'END'; -0400 0481 CYRILLIC -0483 0486 CYRILLIC -048A 04CE CYRILLIC -04D0 04F5 CYRILLIC -04F8 04F9 CYRILLIC -0500 050F CYRILLIC -1D2B CYRILLIC +0400 0486 Cyrillic +0488 04CE Cyrillic +04D0 04F5 Cyrillic +04F8 04F9 Cyrillic +0500 050F Cyrillic +1D2B Cyrillic END diff --git a/lib/unicore/lib/Deseret.pl b/lib/unicore/lib/Deseret.pl index 9111e08..fc7f0d2 100644 --- a/lib/unicore/lib/Deseret.pl +++ b/lib/unicore/lib/Deseret.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Deseret} (and fuzzy permutations) # -# Meaning: Script 'DESERET' +# Meaning: Script 'Deseret' # return <<'END'; -10400 1044F DESERET +10400 1044F Deseret END diff --git a/lib/unicore/lib/Devanaga.pl b/lib/unicore/lib/Devanaga.pl index 12f6a9d..43fe33c 100644 --- a/lib/unicore/lib/Devanaga.pl +++ b/lib/unicore/lib/Devanaga.pl @@ -6,12 +6,12 @@ # This file supports: # \p{Devanagari} (and fuzzy permutations) # -# Meaning: Script 'DEVANAGARI' +# Meaning: Script 'Devanagari' # return <<'END'; -0901 0939 DEVANAGARI -093C 094D DEVANAGARI -0950 0954 DEVANAGARI -0958 0963 DEVANAGARI -0966 096F DEVANAGARI +0901 0939 Devanagari +093C 094D Devanagari +0950 0954 Devanagari +0958 0963 Devanagari +0966 096F Devanagari END diff --git a/lib/unicore/lib/Ethiopic.pl b/lib/unicore/lib/Ethiopic.pl index 433d7d8..0ce5901 100644 --- a/lib/unicore/lib/Ethiopic.pl +++ b/lib/unicore/lib/Ethiopic.pl @@ -6,33 +6,33 @@ # This file supports: # \p{Ethiopic} (and fuzzy permutations) # -# Meaning: Script 'ETHIOPIC' +# Meaning: Script 'Ethiopic' # return <<'END'; -1200 1206 ETHIOPIC -1208 1246 ETHIOPIC -1248 ETHIOPIC -124A 124D ETHIOPIC -1250 1256 ETHIOPIC -1258 ETHIOPIC -125A 125D ETHIOPIC -1260 1286 ETHIOPIC -1288 ETHIOPIC -128A 128D ETHIOPIC -1290 12AE ETHIOPIC -12B0 ETHIOPIC -12B2 12B5 ETHIOPIC -12B8 12BE ETHIOPIC -12C0 ETHIOPIC -12C2 12C5 ETHIOPIC -12C8 12CE ETHIOPIC -12D0 12D6 ETHIOPIC -12D8 12EE ETHIOPIC -12F0 130E ETHIOPIC -1310 ETHIOPIC -1312 1315 ETHIOPIC -1318 131E ETHIOPIC -1320 1346 ETHIOPIC -1348 135A ETHIOPIC -1369 137C ETHIOPIC +1200 1206 Ethiopic +1208 1246 Ethiopic +1248 Ethiopic +124A 124D Ethiopic +1250 1256 Ethiopic +1258 Ethiopic +125A 125D Ethiopic +1260 1286 Ethiopic +1288 Ethiopic +128A 128D Ethiopic +1290 12AE Ethiopic +12B0 Ethiopic +12B2 12B5 Ethiopic +12B8 12BE Ethiopic +12C0 Ethiopic +12C2 12C5 Ethiopic +12C8 12CE Ethiopic +12D0 12D6 Ethiopic +12D8 12EE Ethiopic +12F0 130E Ethiopic +1310 Ethiopic +1312 1315 Ethiopic +1318 131E Ethiopic +1320 1346 Ethiopic +1348 135A Ethiopic +1361 137C Ethiopic END diff --git a/lib/unicore/lib/Georgian.pl b/lib/unicore/lib/Georgian.pl index cd56aaa..0f3170c 100644 --- a/lib/unicore/lib/Georgian.pl +++ b/lib/unicore/lib/Georgian.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Georgian} (and fuzzy permutations) # -# Meaning: Script 'GEORGIAN' +# Meaning: Script 'Georgian' # return <<'END'; -10A0 10C5 GEORGIAN -10D0 10F8 GEORGIAN +10A0 10C5 Georgian +10D0 10F8 Georgian END diff --git a/lib/unicore/lib/Gothic.pl b/lib/unicore/lib/Gothic.pl index 321d723..994aff1 100644 --- a/lib/unicore/lib/Gothic.pl +++ b/lib/unicore/lib/Gothic.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Gothic} (and fuzzy permutations) # -# Meaning: Script 'GOTHIC' +# Meaning: Script 'Gothic' # return <<'END'; -10330 1034A GOTHIC +10330 1034A Gothic END diff --git a/lib/unicore/lib/Greek.pl b/lib/unicore/lib/Greek.pl index b2cd729..09dd15f 100644 --- a/lib/unicore/lib/Greek.pl +++ b/lib/unicore/lib/Greek.pl @@ -6,39 +6,35 @@ # This file supports: # \p{Greek} (and fuzzy permutations) # -# Meaning: Script 'GREEK' +# Meaning: Script 'Greek' # return <<'END'; -00B5 GREEK -037A GREEK -0386 GREEK -0388 038A GREEK -038C GREEK -038E 03A1 GREEK -03A3 03CE GREEK -03D0 03F5 GREEK -03F7 03FB GREEK -1D26 1D2A GREEK -1D5D 1D61 GREEK -1D66 1D6A GREEK -1F00 1F15 GREEK -1F18 1F1D GREEK -1F20 1F45 GREEK -1F48 1F4D GREEK -1F50 1F57 GREEK -1F59 GREEK -1F5B GREEK -1F5D GREEK -1F5F 1F7D GREEK -1F80 1FB4 GREEK -1FB6 1FBC GREEK -1FBE GREEK -1FC2 1FC4 GREEK -1FC6 1FCC GREEK -1FD0 1FD3 GREEK -1FD6 1FDB GREEK -1FE0 1FEC GREEK -1FF2 1FF4 GREEK -1FF6 1FFC GREEK -2126 GREEK +0374 0375 Greek +037A Greek +0384 0386 Greek +0388 038A Greek +038C Greek +038E 03A1 Greek +03A3 03CE Greek +03D0 03FB Greek +1D26 1D2A Greek +1D5D 1D61 Greek +1D66 1D6A Greek +1F00 1F15 Greek +1F18 1F1D Greek +1F20 1F45 Greek +1F48 1F4D Greek +1F50 1F57 Greek +1F59 Greek +1F5B Greek +1F5D Greek +1F5F 1F7D Greek +1F80 1FB4 Greek +1FB6 1FC4 Greek +1FC6 1FD3 Greek +1FD6 1FDB Greek +1FDD 1FEF Greek +1FF2 1FF4 Greek +1FF6 1FFE Greek +2126 Greek END diff --git a/lib/unicore/lib/Gujarati.pl b/lib/unicore/lib/Gujarati.pl index 94776d2..7ba8c36 100644 --- a/lib/unicore/lib/Gujarati.pl +++ b/lib/unicore/lib/Gujarati.pl @@ -6,20 +6,21 @@ # This file supports: # \p{Gujarati} (and fuzzy permutations) # -# Meaning: Script 'GUJARATI' +# Meaning: Script 'Gujarati' # return <<'END'; -0A81 0A83 GUJARATI -0A85 0A8D GUJARATI -0A8F 0A91 GUJARATI -0A93 0AA8 GUJARATI -0AAA 0AB0 GUJARATI -0AB2 0AB3 GUJARATI -0AB5 0AB9 GUJARATI -0ABC 0AC5 GUJARATI -0AC7 0AC9 GUJARATI -0ACB 0ACD GUJARATI -0AD0 GUJARATI -0AE0 0AE3 GUJARATI -0AE6 0AEF GUJARATI +0A81 0A83 Gujarati +0A85 0A8D Gujarati +0A8F 0A91 Gujarati +0A93 0AA8 Gujarati +0AAA 0AB0 Gujarati +0AB2 0AB3 Gujarati +0AB5 0AB9 Gujarati +0ABC 0AC5 Gujarati +0AC7 0AC9 Gujarati +0ACB 0ACD Gujarati +0AD0 Gujarati +0AE0 0AE3 Gujarati +0AE6 0AEF Gujarati +0AF1 Gujarati END diff --git a/lib/unicore/lib/Gurmukhi.pl b/lib/unicore/lib/Gurmukhi.pl index 2a14896..eaa5c49 100644 --- a/lib/unicore/lib/Gurmukhi.pl +++ b/lib/unicore/lib/Gurmukhi.pl @@ -6,22 +6,22 @@ # This file supports: # \p{Gurmukhi} (and fuzzy permutations) # -# Meaning: Script 'GURMUKHI' +# Meaning: Script 'Gurmukhi' # return <<'END'; -0A02 0A03 GURMUKHI -0A05 0A0A GURMUKHI -0A0F 0A10 GURMUKHI -0A13 0A28 GURMUKHI -0A2A 0A30 GURMUKHI -0A32 0A33 GURMUKHI -0A35 0A36 GURMUKHI -0A38 0A39 GURMUKHI -0A3C GURMUKHI -0A3E 0A42 GURMUKHI -0A47 0A48 GURMUKHI -0A4B 0A4D GURMUKHI -0A59 0A5C GURMUKHI -0A5E GURMUKHI -0A66 0A74 GURMUKHI +0A01 0A03 Gurmukhi +0A05 0A0A Gurmukhi +0A0F 0A10 Gurmukhi +0A13 0A28 Gurmukhi +0A2A 0A30 Gurmukhi +0A32 0A33 Gurmukhi +0A35 0A36 Gurmukhi +0A38 0A39 Gurmukhi +0A3C Gurmukhi +0A3E 0A42 Gurmukhi +0A47 0A48 Gurmukhi +0A4B 0A4D Gurmukhi +0A59 0A5C Gurmukhi +0A5E Gurmukhi +0A66 0A74 Gurmukhi END diff --git a/lib/unicore/lib/Han.pl b/lib/unicore/lib/Han.pl index 903bbf2..7035486 100644 --- a/lib/unicore/lib/Han.pl +++ b/lib/unicore/lib/Han.pl @@ -6,20 +6,20 @@ # This file supports: # \p{Han} (and fuzzy permutations) # -# Meaning: Script 'HAN' +# Meaning: Script 'Han' # return <<'END'; -2E80 2E99 HAN -2E9B 2EF3 HAN -2F00 2FD5 HAN -3005 HAN -3007 HAN -3021 3029 HAN -3038 303B HAN -3400 4DB5 HAN -4E00 9FA5 HAN -F900 FA2D HAN -FA30 FA6A HAN -20000 2A6D6 HAN -2F800 2FA1D HAN +2E80 2E99 Han +2E9B 2EF3 Han +2F00 2FD5 Han +3005 Han +3007 Han +3021 3029 Han +3038 303B Han +3400 4DB5 Han +4E00 9FA5 Han +F900 FA2D Han +FA30 FA6A Han +20000 2A6D6 Han +2F800 2FA1D Han END diff --git a/lib/unicore/lib/Hangul.pl b/lib/unicore/lib/Hangul.pl index afa24a0..54676bc 100644 --- a/lib/unicore/lib/Hangul.pl +++ b/lib/unicore/lib/Hangul.pl @@ -6,17 +6,19 @@ # This file supports: # \p{Hangul} (and fuzzy permutations) # -# Meaning: Script 'HANGUL' +# Meaning: Script 'Hangul' # return <<'END'; -1100 1159 HANGUL -115F 11A2 HANGUL -11A8 11F9 HANGUL -3131 318E HANGUL -AC00 D7A3 HANGUL -FFA0 FFBE HANGUL -FFC2 FFC7 HANGUL -FFCA FFCF HANGUL -FFD2 FFD7 HANGUL -FFDA FFDC HANGUL +1100 1159 Hangul +115F 11A2 Hangul +11A8 11F9 Hangul +3131 318E Hangul +3200 321E Hangul +3260 327D Hangul +AC00 D7A3 Hangul +FFA0 FFBE Hangul +FFC2 FFC7 Hangul +FFCA FFCF Hangul +FFD2 FFD7 Hangul +FFDA FFDC Hangul END diff --git a/lib/unicore/lib/Hanunoo.pl b/lib/unicore/lib/Hanunoo.pl index 077cc07..623ce9a 100644 --- a/lib/unicore/lib/Hanunoo.pl +++ b/lib/unicore/lib/Hanunoo.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Hanunoo} (and fuzzy permutations) # -# Meaning: Script 'HANUNOO' +# Meaning: Script 'Hanunoo' # return <<'END'; -1720 1734 HANUNOO +1720 1734 Hanunoo END diff --git a/lib/unicore/lib/Hebrew.pl b/lib/unicore/lib/Hebrew.pl index 4ec1444..ae3d775 100644 --- a/lib/unicore/lib/Hebrew.pl +++ b/lib/unicore/lib/Hebrew.pl @@ -6,17 +6,18 @@ # This file supports: # \p{Hebrew} (and fuzzy permutations) # -# Meaning: Script 'HEBREW' +# Meaning: Script 'Hebrew' # return <<'END'; -05D0 05EA HEBREW -05F0 05F2 HEBREW -FB1D HEBREW -FB1F FB28 HEBREW -FB2A FB36 HEBREW -FB38 FB3C HEBREW -FB3E HEBREW -FB40 FB41 HEBREW -FB43 FB44 HEBREW -FB46 FB4F HEBREW +0591 05A1 Hebrew +05A3 05B9 Hebrew +05BB 05C4 Hebrew +05D0 05EA Hebrew +05F0 05F4 Hebrew +FB1D FB36 Hebrew +FB38 FB3C Hebrew +FB3E Hebrew +FB40 FB41 Hebrew +FB43 FB44 Hebrew +FB46 FB4F Hebrew END diff --git a/lib/unicore/lib/Hiragana.pl b/lib/unicore/lib/Hiragana.pl index dddb82d..c5ba141 100644 --- a/lib/unicore/lib/Hiragana.pl +++ b/lib/unicore/lib/Hiragana.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Hiragana} (and fuzzy permutations) # -# Meaning: Script 'HIRAGANA' +# Meaning: Script 'Hiragana' # return <<'END'; -3041 3096 HIRAGANA -309D 309F HIRAGANA +3041 3096 Hiragana +309D 309F Hiragana END diff --git a/lib/unicore/lib/InCyril2.pl b/lib/unicore/lib/InCyril2.pl index 41f8f20..b648190 100644 --- a/lib/unicore/lib/InCyril2.pl +++ b/lib/unicore/lib/InCyril2.pl @@ -4,10 +4,10 @@ # # This file supports: -# \p{InCyrillicSupplementary} (and fuzzy permutations) +# \p{InCyrillicSupplement} (and fuzzy permutations) # -# Meaning: Block 'Cyrillic Supplementary' +# Meaning: Block 'Cyrillic Supplement' # return <<'END'; -0500 052F Cyrillic Supplementary +0500 052F Cyrillic Supplement END diff --git a/lib/unicore/lib/Inherite.pl b/lib/unicore/lib/Inherite.pl index 49d8112..b34e66c 100644 --- a/lib/unicore/lib/Inherite.pl +++ b/lib/unicore/lib/Inherite.pl @@ -6,32 +6,22 @@ # This file supports: # \p{Inherited} (and fuzzy permutations) # -# Meaning: Script 'INHERITED' +# Meaning: Script 'Inherited' # return <<'END'; -0300 034F INHERITED -0360 036F INHERITED -0488 0489 INHERITED -0591 05A1 INHERITED -05A3 05B9 INHERITED -05BB 05BD INHERITED -05BF INHERITED -05C1 05C2 INHERITED -05C4 INHERITED -064B 0655 INHERITED -0670 INHERITED -06D6 06E4 INHERITED -06E7 06E8 INHERITED -06EA 06ED INHERITED -180B 180D INHERITED -20D0 20EA INHERITED -302A 302F INHERITED -3099 309A INHERITED -FB1E INHERITED -FE00 FE0F INHERITED -FE20 FE23 INHERITED -1D167 1D169 INHERITED -1D17B 1D182 INHERITED -1D185 1D18B INHERITED -1D1AA 1D1AD INHERITED +0300 0357 Inherited +035D 036F Inherited +064B 0655 Inherited +0670 Inherited +200C 200D Inherited +20D0 20EA Inherited +302A 302F Inherited +3099 309A Inherited +FE00 FE0F Inherited +FE20 FE23 Inherited +1D167 1D169 Inherited +1D17B 1D182 Inherited +1D185 1D18B Inherited +1D1AA 1D1AD Inherited +E0100 E01EF Inherited END diff --git a/lib/unicore/lib/Kannada.pl b/lib/unicore/lib/Kannada.pl index d15255b..3fe5ea8 100644 --- a/lib/unicore/lib/Kannada.pl +++ b/lib/unicore/lib/Kannada.pl @@ -6,20 +6,20 @@ # This file supports: # \p{Kannada} (and fuzzy permutations) # -# Meaning: Script 'KANNADA' +# Meaning: Script 'Kannada' # return <<'END'; -0C82 0C83 KANNADA -0C85 0C8C KANNADA -0C8E 0C90 KANNADA -0C92 0CA8 KANNADA -0CAA 0CB3 KANNADA -0CB5 0CB9 KANNADA -0CBD 0CC4 KANNADA -0CC6 0CC8 KANNADA -0CCA 0CCD KANNADA -0CD5 0CD6 KANNADA -0CDE KANNADA -0CE0 0CE1 KANNADA -0CE6 0CEF KANNADA +0C82 0C83 Kannada +0C85 0C8C Kannada +0C8E 0C90 Kannada +0C92 0CA8 Kannada +0CAA 0CB3 Kannada +0CB5 0CB9 Kannada +0CBC 0CC4 Kannada +0CC6 0CC8 Kannada +0CCA 0CCD Kannada +0CD5 0CD6 Kannada +0CDE Kannada +0CE0 0CE1 Kannada +0CE6 0CEF Kannada END diff --git a/lib/unicore/lib/Katakan2.pl b/lib/unicore/lib/Katakan2.pl new file mode 100644 index 0000000..bad5636 --- /dev/null +++ b/lib/unicore/lib/Katakan2.pl @@ -0,0 +1,16 @@ +# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! +# This file is built by ./mktables from e.g. UnicodeData.txt. +# Any changes made here will be lost! + +# +# This file supports: +# \p{KatakanaOrHiragana} (and fuzzy permutations) +# +# Meaning: Script 'Katakana_Or_Hiragana' +# +return <<'END'; +3031 3035 Katakana_Or_Hiragana +309B 309C Katakana_Or_Hiragana +FF70 Katakana_Or_Hiragana +FF9E FF9F Katakana_Or_Hiragana +END diff --git a/lib/unicore/lib/Katakana.pl b/lib/unicore/lib/Katakana.pl index b650350..2822cd6 100644 --- a/lib/unicore/lib/Katakana.pl +++ b/lib/unicore/lib/Katakana.pl @@ -6,12 +6,12 @@ # This file supports: # \p{Katakana} (and fuzzy permutations) # -# Meaning: Script 'KATAKANA' +# Meaning: Script 'Katakana' # return <<'END'; -30A1 30FA KATAKANA -30FD 30FF KATAKANA -31F0 31FF KATAKANA -FF66 FF6F KATAKANA -FF71 FF9D KATAKANA +30A1 30FA Katakana +30FD 30FF Katakana +31F0 31FF Katakana +FF66 FF6F Katakana +FF71 FF9D Katakana END diff --git a/lib/unicore/lib/Khmer.pl b/lib/unicore/lib/Khmer.pl index 1e69e00..ebe3290 100644 --- a/lib/unicore/lib/Khmer.pl +++ b/lib/unicore/lib/Khmer.pl @@ -6,9 +6,11 @@ # This file supports: # \p{Khmer} (and fuzzy permutations) # -# Meaning: Script 'KHMER' +# Meaning: Script 'Khmer' # return <<'END'; -1780 17D3 KHMER -17E0 17E9 KHMER +1780 17DD Khmer +17E0 17E9 Khmer +17F0 17F9 Khmer +19E0 19FF Khmer END diff --git a/lib/unicore/lib/Lao.pl b/lib/unicore/lib/Lao.pl index 83bc60c..6509371 100644 --- a/lib/unicore/lib/Lao.pl +++ b/lib/unicore/lib/Lao.pl @@ -6,25 +6,25 @@ # This file supports: # \p{Lao} (and fuzzy permutations) # -# Meaning: Script 'LAO' +# Meaning: Script 'Lao' # return <<'END'; -0E81 0E82 LAO -0E84 LAO -0E87 0E88 LAO -0E8A LAO -0E8D LAO -0E94 0E97 LAO -0E99 0E9F LAO -0EA1 0EA3 LAO -0EA5 LAO -0EA7 LAO -0EAA 0EAB LAO -0EAD 0EB9 LAO -0EBB 0EBD LAO -0EC0 0EC4 LAO -0EC6 LAO -0EC8 0ECD LAO -0ED0 0ED9 LAO -0EDC 0EDD LAO +0E81 0E82 Lao +0E84 Lao +0E87 0E88 Lao +0E8A Lao +0E8D Lao +0E94 0E97 Lao +0E99 0E9F Lao +0EA1 0EA3 Lao +0EA5 Lao +0EA7 Lao +0EAA 0EAB Lao +0EAD 0EB9 Lao +0EBB 0EBD Lao +0EC0 0EC4 Lao +0EC6 Lao +0EC8 0ECD Lao +0ED0 0ED9 Lao +0EDC 0EDD Lao END diff --git a/lib/unicore/lib/Latin.pl b/lib/unicore/lib/Latin.pl index b14498e..022d5bf 100644 --- a/lib/unicore/lib/Latin.pl +++ b/lib/unicore/lib/Latin.pl @@ -6,28 +6,28 @@ # This file supports: # \p{Latin} (and fuzzy permutations) # -# Meaning: Script 'LATIN' +# Meaning: Script 'Latin' # return <<'END'; -0041 005A LATIN -0061 007A LATIN -00AA LATIN -00BA LATIN -00C0 00D6 LATIN -00D8 00F6 LATIN -00F8 0236 LATIN -0250 02B8 LATIN -02E0 02E4 LATIN -1D00 1D25 LATIN -1D2C 1D5C LATIN -1D62 1D65 LATIN -1D6B LATIN -1E00 1E9B LATIN -1EA0 1EF9 LATIN -2071 LATIN -207F LATIN -212A 212B LATIN -FB00 FB06 LATIN -FF21 FF3A LATIN -FF41 FF5A LATIN +0041 005A Latin +0061 007A Latin +00AA Latin +00BA Latin +00C0 00D6 Latin +00D8 00F6 Latin +00F8 0236 Latin +0250 02B8 Latin +02E0 02E4 Latin +1D00 1D25 Latin +1D2C 1D5C Latin +1D62 1D65 Latin +1D6B Latin +1E00 1E9B Latin +1EA0 1EF9 Latin +2071 Latin +207F Latin +212A 212B Latin +FB00 FB06 Latin +FF21 FF3A Latin +FF41 FF5A Latin END diff --git a/lib/unicore/lib/Limbu.pl b/lib/unicore/lib/Limbu.pl index 86dd814..b501ca5 100644 --- a/lib/unicore/lib/Limbu.pl +++ b/lib/unicore/lib/Limbu.pl @@ -6,11 +6,12 @@ # This file supports: # \p{Limbu} (and fuzzy permutations) # -# Meaning: Script 'LIMBU' +# Meaning: Script 'Limbu' # return <<'END'; -1900 191C LIMBU -1920 192B LIMBU -1930 193B LIMBU -1946 194F LIMBU +1900 191C Limbu +1920 192B Limbu +1930 193B Limbu +1940 Limbu +1944 194F Limbu END diff --git a/lib/unicore/lib/LinearB.pl b/lib/unicore/lib/LinearB.pl index 0f670ce..3f0353c 100644 --- a/lib/unicore/lib/LinearB.pl +++ b/lib/unicore/lib/LinearB.pl @@ -6,14 +6,14 @@ # This file supports: # \p{LinearB} (and fuzzy permutations) # -# Meaning: Script 'LINEAR_B' +# Meaning: Script 'Linear_B' # return <<'END'; -10000 1000B LINEAR_B -1000D 10026 LINEAR_B -10028 1003A LINEAR_B -1003C 1003D LINEAR_B -1003F 1004D LINEAR_B -10050 1005D LINEAR_B -10080 100FA LINEAR_B +10000 1000B Linear_B +1000D 10026 Linear_B +10028 1003A Linear_B +1003C 1003D Linear_B +1003F 1004D Linear_B +10050 1005D Linear_B +10080 100FA Linear_B END diff --git a/lib/unicore/lib/Malayala.pl b/lib/unicore/lib/Malayala.pl index eb1c736..52235bb 100644 --- a/lib/unicore/lib/Malayala.pl +++ b/lib/unicore/lib/Malayala.pl @@ -6,18 +6,18 @@ # This file supports: # \p{Malayalam} (and fuzzy permutations) # -# Meaning: Script 'MALAYALAM' +# Meaning: Script 'Malayalam' # return <<'END'; -0D02 0D03 MALAYALAM -0D05 0D0C MALAYALAM -0D0E 0D10 MALAYALAM -0D12 0D28 MALAYALAM -0D2A 0D39 MALAYALAM -0D3E 0D43 MALAYALAM -0D46 0D48 MALAYALAM -0D4A 0D4D MALAYALAM -0D57 MALAYALAM -0D60 0D61 MALAYALAM -0D66 0D6F MALAYALAM +0D02 0D03 Malayalam +0D05 0D0C Malayalam +0D0E 0D10 Malayalam +0D12 0D28 Malayalam +0D2A 0D39 Malayalam +0D3E 0D43 Malayalam +0D46 0D48 Malayalam +0D4A 0D4D Malayalam +0D57 Malayalam +0D60 0D61 Malayalam +0D66 0D6F Malayalam END diff --git a/lib/unicore/lib/Math.pl b/lib/unicore/lib/Math.pl index d026104..590963b 100644 --- a/lib/unicore/lib/Math.pl +++ b/lib/unicore/lib/Math.pl @@ -9,35 +9,40 @@ # Meaning: [\p{Sm}\p{OtherMath}] # return <<'END'; -0028 002B -002D -002F +002B 003C 003E -005B 005E -007B 007E +005E +007C +007E 00AC 00B1 00D7 00F7 -03F6 +03D0 03D2 +03D5 +03F0 03F1 +03F4 03F6 2016 2032 2034 +2040 2044 2052 +2061 2063 207A 207E 208A 208E 20D0 20DC 20E1 +20E5 20E6 2102 210A 2113 2115 2119 211D 2124 -2128 +2128 2129 212C 212D 212F 2131 2133 2138 -2140 2144 +213D 2149 214B 2190 2194 219A 219B @@ -53,28 +58,24 @@ return <<'END'; 2320 2321 237C 239B 23B3 +23B7 +23D0 25B7 25C1 25F8 25FF 266F -27D0 27E5 +27D0 27EB 27F0 27FF -2900 2982 -2999 29D7 -29DC 29FB -29FE 2AFF +2900 2AFF FB29 -FE35 FE38 -FE47 FE48 -FE59 FE5C FE61 FE66 FE68 -FF08 FF0B -FF0D -FF0F +FF0B FF1C FF1E -FF3B FF3E -FF5B FF5E +FF3C +FF3E +FF5C +FF5E FFE2 FFE9 FFEC 1D400 1D454 diff --git a/lib/unicore/lib/Mongolia.pl b/lib/unicore/lib/Mongolia.pl index 5cdc083..042e76a 100644 --- a/lib/unicore/lib/Mongolia.pl +++ b/lib/unicore/lib/Mongolia.pl @@ -6,10 +6,11 @@ # This file supports: # \p{Mongolian} (and fuzzy permutations) # -# Meaning: Script 'MONGOLIAN' +# Meaning: Script 'Mongolian' # return <<'END'; -1810 1819 MONGOLIAN -1820 1877 MONGOLIAN -1880 18A9 MONGOLIAN +1800 180E Mongolian +1810 1819 Mongolian +1820 1877 Mongolian +1880 18A9 Mongolian END diff --git a/lib/unicore/lib/Myanmar.pl b/lib/unicore/lib/Myanmar.pl index 49385bb..bed45ec 100644 --- a/lib/unicore/lib/Myanmar.pl +++ b/lib/unicore/lib/Myanmar.pl @@ -6,14 +6,13 @@ # This file supports: # \p{Myanmar} (and fuzzy permutations) # -# Meaning: Script 'MYANMAR' +# Meaning: Script 'Myanmar' # return <<'END'; -1000 1021 MYANMAR -1023 1027 MYANMAR -1029 102A MYANMAR -102C 1032 MYANMAR -1036 1039 MYANMAR -1040 1049 MYANMAR -1050 1059 MYANMAR +1000 1021 Myanmar +1023 1027 Myanmar +1029 102A Myanmar +102C 1032 Myanmar +1036 1039 Myanmar +1040 1059 Myanmar END diff --git a/lib/unicore/lib/Ogham.pl b/lib/unicore/lib/Ogham.pl index 6b95384..29e418c 100644 --- a/lib/unicore/lib/Ogham.pl +++ b/lib/unicore/lib/Ogham.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Ogham} (and fuzzy permutations) # -# Meaning: Script 'OGHAM' +# Meaning: Script 'Ogham' # return <<'END'; -1681 169A OGHAM +1680 169C Ogham END diff --git a/lib/unicore/lib/OldItali.pl b/lib/unicore/lib/OldItali.pl index 7fe3725..c9f9107 100644 --- a/lib/unicore/lib/OldItali.pl +++ b/lib/unicore/lib/OldItali.pl @@ -6,8 +6,9 @@ # This file supports: # \p{OldItalic} (and fuzzy permutations) # -# Meaning: Script 'OLD_ITALIC' +# Meaning: Script 'Old_Italic' # return <<'END'; -10300 1031E OLD_ITALIC +10300 1031E Old_Italic +10320 10323 Old_Italic END diff --git a/lib/unicore/lib/Oriya.pl b/lib/unicore/lib/Oriya.pl index dfc461f..a6d3c63 100644 --- a/lib/unicore/lib/Oriya.pl +++ b/lib/unicore/lib/Oriya.pl @@ -6,22 +6,21 @@ # This file supports: # \p{Oriya} (and fuzzy permutations) # -# Meaning: Script 'ORIYA' +# Meaning: Script 'Oriya' # return <<'END'; -0B01 0B03 ORIYA -0B05 0B0C ORIYA -0B0F 0B10 ORIYA -0B13 0B28 ORIYA -0B2A 0B30 ORIYA -0B32 0B33 ORIYA -0B35 0B39 ORIYA -0B3C 0B43 ORIYA -0B47 0B48 ORIYA -0B4B 0B4D ORIYA -0B56 0B57 ORIYA -0B5C 0B5D ORIYA -0B5F 0B61 ORIYA -0B66 0B6F ORIYA -0B71 ORIYA +0B01 0B03 Oriya +0B05 0B0C Oriya +0B0F 0B10 Oriya +0B13 0B28 Oriya +0B2A 0B30 Oriya +0B32 0B33 Oriya +0B35 0B39 Oriya +0B3C 0B43 Oriya +0B47 0B48 Oriya +0B4B 0B4D Oriya +0B56 0B57 Oriya +0B5C 0B5D Oriya +0B5F 0B61 Oriya +0B66 0B71 Oriya END diff --git a/lib/unicore/lib/Osmanya.pl b/lib/unicore/lib/Osmanya.pl index 19ffe7a..976a04f 100644 --- a/lib/unicore/lib/Osmanya.pl +++ b/lib/unicore/lib/Osmanya.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Osmanya} (and fuzzy permutations) # -# Meaning: Script 'OSMANYA' +# Meaning: Script 'Osmanya' # return <<'END'; -10480 1049D OSMANYA -104A0 104A9 OSMANYA +10480 1049D Osmanya +104A0 104A9 Osmanya END diff --git a/lib/unicore/lib/OtherDef.pl b/lib/unicore/lib/OtherDef.pl index 373aa6d..4ac4db1 100644 --- a/lib/unicore/lib/OtherDef.pl +++ b/lib/unicore/lib/OtherDef.pl @@ -11,14 +11,13 @@ return <<'END'; 034F Other_Default_Ignorable_Code_Point 115F 1160 Other_Default_Ignorable_Code_Point -180B 180D Other_Default_Ignorable_Code_Point 200B Other_Default_Ignorable_Code_Point 2064 2069 Other_Default_Ignorable_Code_Point 3164 Other_Default_Ignorable_Code_Point -FE00 FE0F Other_Default_Ignorable_Code_Point FFA0 Other_Default_Ignorable_Code_Point FFF0 FFF8 Other_Default_Ignorable_Code_Point E0000 Other_Default_Ignorable_Code_Point E0002 E001F Other_Default_Ignorable_Code_Point -E0080 E0FFF Other_Default_Ignorable_Code_Point +E0080 E00FF Other_Default_Ignorable_Code_Point +E01F0 E0FFF Other_Default_Ignorable_Code_Point END diff --git a/lib/unicore/lib/OtherGra.pl b/lib/unicore/lib/OtherGra.pl index c846fe5..744cd5e 100644 --- a/lib/unicore/lib/OtherGra.pl +++ b/lib/unicore/lib/OtherGra.pl @@ -21,6 +21,7 @@ return <<'END'; 0D57 Other_Grapheme_Extend 0DCF Other_Grapheme_Extend 0DDF Other_Grapheme_Extend +200C 200D Other_Grapheme_Extend 1D165 Other_Grapheme_Extend 1D16E 1D16F Other_Grapheme_Extend END diff --git a/lib/unicore/lib/OtherMat.pl b/lib/unicore/lib/OtherMat.pl index d332e32..d2e9a98 100644 --- a/lib/unicore/lib/OtherMat.pl +++ b/lib/unicore/lib/OtherMat.pl @@ -9,39 +9,42 @@ # Meaning: Extended property 'Other_Math' # return <<'END'; -0028 002A Other_Math -002D Other_Math -002F Other_Math -005B 005E Other_Math -007B Other_Math -007D Other_Math +005E Other_Math +03D0 03D2 Other_Math +03D5 Other_Math +03F0 03F1 Other_Math +03F4 03F5 Other_Math 2016 Other_Math 2032 2034 Other_Math +2040 Other_Math +2061 2063 Other_Math 207D 207E Other_Math 208D 208E Other_Math 20D0 20DC Other_Math 20E1 Other_Math +20E5 20E6 Other_Math 2102 Other_Math 210A 2113 Other_Math 2115 Other_Math 2119 211D Other_Math 2124 Other_Math -2128 Other_Math +2128 2129 Other_Math 212C 212D Other_Math 212F 2131 Other_Math 2133 2138 Other_Math -FE35 FE38 Other_Math -FE47 FE48 Other_Math -FE59 FE5C Other_Math +213D 213F Other_Math +2145 2149 Other_Math +23B7 Other_Math +23D0 Other_Math +27E6 27EB Other_Math +2983 2998 Other_Math +29D8 29DB Other_Math +29FC 29FD Other_Math FE61 Other_Math FE63 Other_Math FE68 Other_Math -FF08 FF0A Other_Math -FF0D Other_Math -FF0F Other_Math -FF3B FF3E Other_Math -FF5B Other_Math -FF5D Other_Math +FF3C Other_Math +FF3E Other_Math 1D400 1D454 Other_Math 1D456 1D49C Other_Math 1D49E 1D49F Other_Math diff --git a/lib/unicore/lib/Runic.pl b/lib/unicore/lib/Runic.pl index 01eef2b..ac6ad34 100644 --- a/lib/unicore/lib/Runic.pl +++ b/lib/unicore/lib/Runic.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Runic} (and fuzzy permutations) # -# Meaning: Script 'RUNIC' +# Meaning: Script 'Runic' # return <<'END'; -16A0 16EA RUNIC -16EE 16F0 RUNIC +16A0 16EA Runic +16EE 16F0 Runic END diff --git a/lib/unicore/lib/Shavian.pl b/lib/unicore/lib/Shavian.pl index a6e3436..917e573 100644 --- a/lib/unicore/lib/Shavian.pl +++ b/lib/unicore/lib/Shavian.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Shavian} (and fuzzy permutations) # -# Meaning: Script 'SHAVIAN' +# Meaning: Script 'Shavian' # return <<'END'; -10450 1047F SHAVIAN +10450 1047F Shavian END diff --git a/lib/unicore/lib/Sinhala.pl b/lib/unicore/lib/Sinhala.pl index 3288efe..2b57a88 100644 --- a/lib/unicore/lib/Sinhala.pl +++ b/lib/unicore/lib/Sinhala.pl @@ -6,18 +6,18 @@ # This file supports: # \p{Sinhala} (and fuzzy permutations) # -# Meaning: Script 'SINHALA' +# Meaning: Script 'Sinhala' # return <<'END'; -0D82 0D83 SINHALA -0D85 0D96 SINHALA -0D9A 0DB1 SINHALA -0DB3 0DBB SINHALA -0DBD SINHALA -0DC0 0DC6 SINHALA -0DCA SINHALA -0DCF 0DD4 SINHALA -0DD6 SINHALA -0DD8 0DDF SINHALA -0DF2 0DF3 SINHALA +0D82 0D83 Sinhala +0D85 0D96 Sinhala +0D9A 0DB1 Sinhala +0DB3 0DBB Sinhala +0DBD Sinhala +0DC0 0DC6 Sinhala +0DCA Sinhala +0DCF 0DD4 Sinhala +0DD6 Sinhala +0DD8 0DDF Sinhala +0DF2 0DF4 Sinhala END diff --git a/lib/unicore/lib/SoftDott.pl b/lib/unicore/lib/SoftDott.pl index 9a827b3..dfd39d2 100644 --- a/lib/unicore/lib/SoftDott.pl +++ b/lib/unicore/lib/SoftDott.pl @@ -12,10 +12,27 @@ return <<'END'; 0069 006A Soft_Dotted 012F Soft_Dotted 0268 Soft_Dotted +029D Soft_Dotted +02B2 Soft_Dotted +03F3 Soft_Dotted 0456 Soft_Dotted 0458 Soft_Dotted 1D62 Soft_Dotted 1E2D Soft_Dotted 1ECB Soft_Dotted 2071 Soft_Dotted +2148 2149 Soft_Dotted +1D422 1D423 Soft_Dotted +1D456 1D457 Soft_Dotted +1D48A 1D48B Soft_Dotted +1D4BE 1D4BF Soft_Dotted +1D4F2 1D4F3 Soft_Dotted +1D526 1D527 Soft_Dotted +1D55A 1D55B Soft_Dotted +1D58E 1D58F Soft_Dotted +1D5C2 1D5C3 Soft_Dotted +1D5F6 1D5F7 Soft_Dotted +1D62A 1D62B Soft_Dotted +1D65E 1D65F Soft_Dotted +1D692 1D693 Soft_Dotted END diff --git a/lib/unicore/lib/Sterm.pl b/lib/unicore/lib/Sterm.pl new file mode 100644 index 0000000..25472c4 --- /dev/null +++ b/lib/unicore/lib/Sterm.pl @@ -0,0 +1,38 @@ +# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! +# This file is built by ./mktables from e.g. UnicodeData.txt. +# Any changes made here will be lost! + +# +# This file supports: +# \p{Sterm} (and fuzzy permutations) +# +# Meaning: Extended property 'STerm' +# +return <<'END'; +0021 STerm +002E STerm +003F STerm +055C STerm +055E STerm +0589 STerm +061F STerm +06D4 STerm +0700 0702 STerm +0964 0965 STerm +104A 104B STerm +1362 STerm +1367 1368 STerm +166E STerm +1803 STerm +1809 STerm +1944 1945 STerm +203C 203D STerm +2047 2049 STerm +3002 STerm +FE52 STerm +FE56 FE57 STerm +FF01 STerm +FF0E STerm +FF1F STerm +FF61 STerm +END diff --git a/lib/unicore/lib/Syriac.pl b/lib/unicore/lib/Syriac.pl index a18248a..12afbfa 100644 --- a/lib/unicore/lib/Syriac.pl +++ b/lib/unicore/lib/Syriac.pl @@ -6,9 +6,10 @@ # This file supports: # \p{Syriac} (and fuzzy permutations) # -# Meaning: Script 'SYRIAC' +# Meaning: Script 'Syriac' # return <<'END'; -0710 074A SYRIAC -074D 074F SYRIAC +0700 070D Syriac +070F 074A Syriac +074D 074F Syriac END diff --git a/lib/unicore/lib/Tagalog.pl b/lib/unicore/lib/Tagalog.pl index 78ab346..4cdfe29 100644 --- a/lib/unicore/lib/Tagalog.pl +++ b/lib/unicore/lib/Tagalog.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Tagalog} (and fuzzy permutations) # -# Meaning: Script 'TAGALOG' +# Meaning: Script 'Tagalog' # return <<'END'; -1700 170C TAGALOG -170E 1714 TAGALOG +1700 170C Tagalog +170E 1714 Tagalog END diff --git a/lib/unicore/lib/Tagbanwa.pl b/lib/unicore/lib/Tagbanwa.pl index a7ecbf2..d084234 100644 --- a/lib/unicore/lib/Tagbanwa.pl +++ b/lib/unicore/lib/Tagbanwa.pl @@ -6,10 +6,10 @@ # This file supports: # \p{Tagbanwa} (and fuzzy permutations) # -# Meaning: Script 'TAGBANWA' +# Meaning: Script 'Tagbanwa' # return <<'END'; -1760 176C TAGBANWA -176E 1770 TAGBANWA -1772 1773 TAGBANWA +1760 176C Tagbanwa +176E 1770 Tagbanwa +1772 1773 Tagbanwa END diff --git a/lib/unicore/lib/TaiLe.pl b/lib/unicore/lib/TaiLe.pl index f2f4d94..d4b2f83 100644 --- a/lib/unicore/lib/TaiLe.pl +++ b/lib/unicore/lib/TaiLe.pl @@ -6,9 +6,9 @@ # This file supports: # \p{TaiLe} (and fuzzy permutations) # -# Meaning: Script 'TAI_LE' +# Meaning: Script 'Tai_Le' # return <<'END'; -1950 196D TAI_LE -1970 1974 TAI_LE +1950 196D Tai_Le +1970 1974 Tai_Le END diff --git a/lib/unicore/lib/Tamil.pl b/lib/unicore/lib/Tamil.pl index b9777a3..0d5cc0a 100644 --- a/lib/unicore/lib/Tamil.pl +++ b/lib/unicore/lib/Tamil.pl @@ -6,23 +6,23 @@ # This file supports: # \p{Tamil} (and fuzzy permutations) # -# Meaning: Script 'TAMIL' +# Meaning: Script 'Tamil' # return <<'END'; -0B82 0B83 TAMIL -0B85 0B8A TAMIL -0B8E 0B90 TAMIL -0B92 0B95 TAMIL -0B99 0B9A TAMIL -0B9C TAMIL -0B9E 0B9F TAMIL -0BA3 0BA4 TAMIL -0BA8 0BAA TAMIL -0BAE 0BB5 TAMIL -0BB7 0BB9 TAMIL -0BBE 0BC2 TAMIL -0BC6 0BC8 TAMIL -0BCA 0BCD TAMIL -0BD7 TAMIL -0BE7 0BF2 TAMIL +0B82 0B83 Tamil +0B85 0B8A Tamil +0B8E 0B90 Tamil +0B92 0B95 Tamil +0B99 0B9A Tamil +0B9C Tamil +0B9E 0B9F Tamil +0BA3 0BA4 Tamil +0BA8 0BAA Tamil +0BAE 0BB5 Tamil +0BB7 0BB9 Tamil +0BBE 0BC2 Tamil +0BC6 0BC8 Tamil +0BCA 0BCD Tamil +0BD7 Tamil +0BE7 0BFA Tamil END diff --git a/lib/unicore/lib/Telugu.pl b/lib/unicore/lib/Telugu.pl index 1c161eb..6a764d2 100644 --- a/lib/unicore/lib/Telugu.pl +++ b/lib/unicore/lib/Telugu.pl @@ -6,19 +6,19 @@ # This file supports: # \p{Telugu} (and fuzzy permutations) # -# Meaning: Script 'TELUGU' +# Meaning: Script 'Telugu' # return <<'END'; -0C01 0C03 TELUGU -0C05 0C0C TELUGU -0C0E 0C10 TELUGU -0C12 0C28 TELUGU -0C2A 0C33 TELUGU -0C35 0C39 TELUGU -0C3E 0C44 TELUGU -0C46 0C48 TELUGU -0C4A 0C4D TELUGU -0C55 0C56 TELUGU -0C60 0C61 TELUGU -0C66 0C6F TELUGU +0C01 0C03 Telugu +0C05 0C0C Telugu +0C0E 0C10 Telugu +0C12 0C28 Telugu +0C2A 0C33 Telugu +0C35 0C39 Telugu +0C3E 0C44 Telugu +0C46 0C48 Telugu +0C4A 0C4D Telugu +0C55 0C56 Telugu +0C60 0C61 Telugu +0C66 0C6F Telugu END diff --git a/lib/unicore/lib/Terminal.pl b/lib/unicore/lib/Terminal.pl index 280cb51..cf829e9 100644 --- a/lib/unicore/lib/Terminal.pl +++ b/lib/unicore/lib/Terminal.pl @@ -17,6 +17,7 @@ return <<'END'; 037E Terminal_Punctuation 0387 Terminal_Punctuation 0589 Terminal_Punctuation +05C3 Terminal_Punctuation 060C Terminal_Punctuation 061B Terminal_Punctuation 061F Terminal_Punctuation @@ -25,6 +26,8 @@ return <<'END'; 070C Terminal_Punctuation 0964 0965 Terminal_Punctuation 0E5A 0E5B Terminal_Punctuation +0F08 Terminal_Punctuation +0F0D 0F12 Terminal_Punctuation 104A 104B Terminal_Punctuation 1361 1368 Terminal_Punctuation 166D 166E Terminal_Punctuation diff --git a/lib/unicore/lib/Thaana.pl b/lib/unicore/lib/Thaana.pl index 9c2be21..3b60d90 100644 --- a/lib/unicore/lib/Thaana.pl +++ b/lib/unicore/lib/Thaana.pl @@ -6,8 +6,8 @@ # This file supports: # \p{Thaana} (and fuzzy permutations) # -# Meaning: Script 'THAANA' +# Meaning: Script 'Thaana' # return <<'END'; -0780 07B1 THAANA +0780 07B1 Thaana END diff --git a/lib/unicore/lib/Thai.pl b/lib/unicore/lib/Thai.pl index b09ced7..5e4108c 100644 --- a/lib/unicore/lib/Thai.pl +++ b/lib/unicore/lib/Thai.pl @@ -6,10 +6,9 @@ # This file supports: # \p{Thai} (and fuzzy permutations) # -# Meaning: Script 'THAI' +# Meaning: Script 'Thai' # return <<'END'; -0E01 0E3A THAI -0E40 0E4E THAI -0E50 0E59 THAI +0E01 0E3A Thai +0E40 0E5B Thai END diff --git a/lib/unicore/lib/Tibetan.pl b/lib/unicore/lib/Tibetan.pl index cdf7d5b..ca4daa7 100644 --- a/lib/unicore/lib/Tibetan.pl +++ b/lib/unicore/lib/Tibetan.pl @@ -6,20 +6,14 @@ # This file supports: # \p{Tibetan} (and fuzzy permutations) # -# Meaning: Script 'TIBETAN' +# Meaning: Script 'Tibetan' # return <<'END'; -0F00 TIBETAN -0F18 0F19 TIBETAN -0F20 0F33 TIBETAN -0F35 TIBETAN -0F37 TIBETAN -0F39 TIBETAN -0F40 0F47 TIBETAN -0F49 0F6A TIBETAN -0F71 0F84 TIBETAN -0F86 0F8B TIBETAN -0F90 0F97 TIBETAN -0F99 0FBC TIBETAN -0FC6 TIBETAN +0F00 0F47 Tibetan +0F49 0F6A Tibetan +0F71 0F8B Tibetan +0F90 0F97 Tibetan +0F99 0FBC Tibetan +0FBE 0FCC Tibetan +0FCF Tibetan END diff --git a/lib/unicore/lib/Ugaritic.pl b/lib/unicore/lib/Ugaritic.pl index d0041f4..4b235b6 100644 --- a/lib/unicore/lib/Ugaritic.pl +++ b/lib/unicore/lib/Ugaritic.pl @@ -6,8 +6,9 @@ # This file supports: # \p{Ugaritic} (and fuzzy permutations) # -# Meaning: Script 'UGARITIC' +# Meaning: Script 'Ugaritic' # return <<'END'; -10380 1039D UGARITIC +10380 1039D Ugaritic +1039F Ugaritic END diff --git a/lib/unicore/lib/Variatio.pl b/lib/unicore/lib/Variatio.pl new file mode 100644 index 0000000..7117902 --- /dev/null +++ b/lib/unicore/lib/Variatio.pl @@ -0,0 +1,15 @@ +# !!!!!!! DO NOT EDIT THIS FILE !!!!!!! +# This file is built by ./mktables from e.g. UnicodeData.txt. +# Any changes made here will be lost! + +# +# This file supports: +# \p{VariationSelector} (and fuzzy permutations) +# +# Meaning: Extended property 'Variation_Selector' +# +return <<'END'; +180B 180D Variation_Selector +FE00 FE0F Variation_Selector +E0100 E01EF Variation_Selector +END diff --git a/lib/unicore/lib/Yi.pl b/lib/unicore/lib/Yi.pl index 5c44ece..40980c3 100644 --- a/lib/unicore/lib/Yi.pl +++ b/lib/unicore/lib/Yi.pl @@ -6,9 +6,9 @@ # This file supports: # \p{Yi} (and fuzzy permutations) # -# Meaning: Script 'YI' +# Meaning: Script 'Yi' # return <<'END'; -A000 A48C YI -A490 A4C6 YI +A000 A48C Yi +A490 A4C6 Yi END diff --git a/lib/unicore/lib/Z.pl b/lib/unicore/lib/Z.pl index 27873b8..e380968 100644 --- a/lib/unicore/lib/Z.pl +++ b/lib/unicore/lib/Z.pl @@ -14,7 +14,7 @@ return <<'END'; 00A0 1680 180E -2000 200B +2000 200A 2028 2029 202F 205F diff --git a/lib/unicore/lib/Zs.pl b/lib/unicore/lib/Zs.pl index 754cb70..5f93f18 100644 --- a/lib/unicore/lib/Zs.pl +++ b/lib/unicore/lib/Zs.pl @@ -14,7 +14,7 @@ return <<'END'; 00A0 1680 180E -2000 200B +2000 200A 202F 205F 3000 diff --git a/lib/unicore/version b/lib/unicore/version index fcdb2e1..1454f6e 100644 --- a/lib/unicore/version +++ b/lib/unicore/version @@ -1 +1 @@ -4.0.0 +4.0.1 diff --git a/t/op/pat.t b/t/op/pat.t index 2348c33..13dc180 100755 --- a/t/op/pat.t +++ b/t/op/pat.t @@ -1908,9 +1908,10 @@ print "ok 663\n"; print "not " unless chr(0xfb4f) =~ /\p{IsHebrew}/; # outside InHebrew print "ok 664\n"; -# singleton (not in a range, this test must be ignored on EBCDIC) -print "not " unless chr(0xb5) =~ /\p{IsGreek}/ or ord("A") == 193; -print "ok 665\n"; +# # singleton (not in a range, this test must be ignored on EBCDIC) +# print "not " unless chr(0xb5) =~ /\p{IsGreek}/ or ord("A") == 193; +# print "ok 665\n"; +print "ok 665 # 0xb5 moved from Greek to Common with Unicode 4.0.1\n"; print "not " unless chr(0x37a) =~ /\p{IsGreek}/; # singleton print "ok 666\n";