From: Jarkko Hietaniemi Date: Wed, 30 Aug 2000 23:32:40 +0000 (+0000) Subject: Update to Unicode 3.0.1. X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=8836d2a580950b5454e04714000dc3f92e663d09;p=p5sagit%2Fp5-mst-13.2.git Update to Unicode 3.0.1. p4raw-id: //depot/perl@6930 --- diff --git a/MANIFEST b/MANIFEST index 854bd22..c309c27 100644 --- a/MANIFEST +++ b/MANIFEST @@ -707,9 +707,11 @@ lib/timelocal.pl Perl library supporting inverse of localtime, gmtime lib/unicode/ArabLink.pl Unicode character database lib/unicode/ArabLnkGrp.pl Unicode character database lib/unicode/ArabShap.txt Unicode character database +lib/unicode/BidiMirr.txt Unicode character database lib/unicode/Bidirectional.pl Unicode character database lib/unicode/Block.pl Unicode character database lib/unicode/Blocks.txt Unicode character database +lib/unicode/CaseFold.txt Unicode character database lib/unicode/Category.pl Unicode character database lib/unicode/CombiningClass.pl Unicode character database lib/unicode/CompExcl.txt Unicode character database @@ -954,17 +956,18 @@ lib/unicode/Name.pl Unicode character database lib/unicode/Names.txt Unicode character database lib/unicode/NamesList.html Unicode character database lib/unicode/Number.pl Unicode character database -lib/unicode/Props.txt Unicode character database +lib/unicode/PropList.txt Unicode character database lib/unicode/README.Ethiopic Unicode character database +lib/unicode/README.perl Unicode character database lib/unicode/ReadMe.txt Unicode character database info lib/unicode/SpecCase.txt Unicode character database lib/unicode/To/Digit.pl Unicode character database lib/unicode/To/Lower.pl Unicode character database lib/unicode/To/Title.pl Unicode character database lib/unicode/To/Upper.pl Unicode character database -lib/unicode/UCD300.html Unicode character database -lib/unicode/Unicode.300 Unicode character database -lib/unicode/Unicode3.html Unicode character database +lib/unicode/UCD301.html Unicode character database +lib/unicode/UCDFF301.html Unicode character database +lib/unicode/Unicode.301 Unicode character database lib/unicode/mktables.PL Unicode character database generator lib/unicode/syllables.txt Unicode character database lib/utf8.pm Pragma to control Unicode support diff --git a/lib/unicode/ArabLink.pl b/lib/unicode/ArabLink.pl index fd5ed8a..2ad1871 100644 --- a/lib/unicode/ArabLink.pl +++ b/lib/unicode/ArabLink.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0622 0625 R @@ -12,10 +12,9 @@ return <<'END'; 0633 063a D 0640 C 0641 0647 D -0648 0649 R -064a D -0671 U -0672 0673 R +0648 R +0649 064a D +0671 0673 R 0674 U 0675 0677 R 0678 0687 D diff --git a/lib/unicode/ArabLnkGrp.pl b/lib/unicode/ArabLnkGrp.pl index 61f30d4..1581a04 100644 --- a/lib/unicode/ArabLnkGrp.pl +++ b/lib/unicode/ArabLnkGrp.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0622 0623 ALEF @@ -27,8 +27,7 @@ return <<'END'; 0647 HEH 0648 WAW 0649 064a YEH -0671 -0672 0673 ALEF +0671 0673 ALEF 0674 0675 ALEF 0676 0677 WAW diff --git a/lib/unicode/ArabShap.txt b/lib/unicode/ArabShap.txt index 6092d62..9b60290 100644 --- a/lib/unicode/ArabShap.txt +++ b/lib/unicode/ArabShap.txt @@ -1,5 +1,32 @@ -# Unicode; Schematic Name; Link; Link Group +# ArabicShaping-3.txt +# +# This file is a normative contributory data file in the +# Unicode Character Database. +# +# This file defines the shaping classes for Arabic and Syriac +# positional shaping, repeating in machine readable form the +# information printed in Tables 8-6, 8-7, 8-8, 8-10, 8-11, and +# 8-13 of The Unicode Standard, Version 3.0. +# +# See sections 8.2 and 8.3 of The Unicode Standard, Version 3.0 +# for more information. +# +# Each line contains four fields, separated by a semicolon. +# +# The first field gives the code point, in 4-digit hexadecimal +# form, of an Arabic or Syriac character. +# The second field gives a short schematic name for that character, +# abbreviated from the normative Unicode character name. +# The third field defines the joining type: R right-joining, +# D dual-joining, U non-joining +# The fourth field defines the joining group. +# +# ############################################################# + +# Unicode; Schematic Name; Joining Type; Joining Group + # Arabic characters + 0622; MADDA ON ALEF; R; ALEF 0623; HAMZA ON ALEF; R; ALEF 0624; HAMZA ON WAW; R; WAW @@ -34,9 +61,9 @@ 0646; NOON; D; NOON 0647; HEH; D; HEH 0648; WAW; R; WAW -0649; ALEF MAKSURA; R; YEH +0649; ALEF MAKSURA; D; YEH 064A; YEH; D; YEH -0671; HAMZAT WASL ON ALEF; U; +0671; HAMZAT WASL ON ALEF; R; ALEF 0672; WAVY HAMZA ON ALEF; R; ALEF 0673; WAVY HAMZA UNDER ALEF; R; ALEF 0674; HIGH HAMZA; U; @@ -139,7 +166,9 @@ 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 + # Syriac characters + 0710; ALAPH; R; ALAPH 0712; BETH; D; BETH 0713; GAMAL; D; GAMAL diff --git a/lib/unicode/BidiMirr.txt b/lib/unicode/BidiMirr.txt new file mode 100644 index 0000000..8ac5be9 --- /dev/null +++ b/lib/unicode/BidiMirr.txt @@ -0,0 +1,238 @@ +# BidiMirroring-1.txt +# +# This file is an informative supplement to the UnicodeData file. It +# lists characters that have the mirrored property +# where there is another Unicode character that typically has a glyph +# that is the mirror image of the original character's glyph. +# The repertoire covered by the file is Unicode 3.0.1. +# +# The file contains a list of lines with mappings from one code point +# to another one for character-based mirroring. +# Note that for "real" mirroring, a rendering engine needs to select +# appropriate alternative glyphs, and that many Unicode characters do not +# have a mirror-image Unicode character. +# +# Each mapping line contains two fields, separated by a semicolon (';'). +# Each of the two fields contains a code point represented as a +# variable-length hexadecimal value with 4 to 6 digits. +# A comment indicates where the characters are "BEST FIT" mirroring. +# +# Code points with the "mirrored" property but no appropriate mirrors are +# listed as comments at the end of the file. +# +# For information on bidi mirroring, see UTR #21: Bidirectional Algorithm, +# at http://www.unicode.org/unicode/reports/tr9/ +# +# Please address any comments to . +# Note that this is an archival address: messages will be checked, +# but do not expect an immediate response. +# +# This file was originally created by Markus Scherer +# +# ############################################################ + +0028; 0029 # LEFT PARENTHESIS +0029; 0028 # RIGHT PARENTHESIS +003C; 003E # LESS-THAN SIGN +003E; 003C # GREATER-THAN SIGN +005B; 005D # LEFT SQUARE BRACKET +005D; 005B # RIGHT SQUARE BRACKET +007B; 007D # LEFT CURLY BRACKET +007D; 007B # RIGHT CURLY BRACKET +00AB; 00BB # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK +00BB; 00AB # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK +2039; 203A # SINGLE LEFT-POINTING ANGLE QUOTATION MARK +203A; 2039 # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK +2045; 2046 # LEFT SQUARE BRACKET WITH QUILL +2046; 2045 # RIGHT SQUARE BRACKET WITH QUILL +207D; 207E # SUPERSCRIPT LEFT PARENTHESIS +207E; 207D # SUPERSCRIPT RIGHT PARENTHESIS +208D; 208E # SUBSCRIPT LEFT PARENTHESIS +208E; 208D # SUBSCRIPT RIGHT PARENTHESIS +2208; 220B # ELEMENT OF +2209; 220C # NOT AN ELEMENT OF +220A; 220D # SMALL ELEMENT OF +220B; 2208 # CONTAINS AS MEMBER +220C; 2209 # DOES NOT CONTAIN AS MEMBER +220D; 220A # SMALL CONTAINS AS MEMBER +223C; 223D # TILDE OPERATOR +223D; 223C # REVERSED TILDE +2243; 22CD # ASYMPTOTICALLY EQUAL TO +2252; 2253 # APPROXIMATELY EQUAL TO OR THE IMAGE OF +2253; 2252 # IMAGE OF OR APPROXIMATELY EQUAL TO +2254; 2255 # COLON EQUALS +2255; 2254 # EQUALS COLON +2264; 2265 # LESS-THAN OR EQUAL TO +2265; 2264 # GREATER-THAN OR EQUAL TO +2266; 2267 # LESS-THAN OVER EQUAL TO +2267; 2266 # GREATER-THAN OVER EQUAL TO +2268; 2269 # [BEST FIT] LESS-THAN BUT NOT EQUAL TO +2269; 2268 # [BEST FIT] GREATER-THAN BUT NOT EQUAL TO +226A; 226B # MUCH LESS-THAN +226B; 226A # MUCH GREATER-THAN +226E; 226F # [BEST FIT] NOT LESS-THAN +226F; 226E # [BEST FIT] NOT GREATER-THAN +2270; 2271 # [BEST FIT] NEITHER LESS-THAN NOR EQUAL TO +2271; 2270 # [BEST FIT] NEITHER GREATER-THAN NOR EQUAL TO +2272; 2273 # [BEST FIT] LESS-THAN OR EQUIVALENT TO +2273; 2272 # [BEST FIT] GREATER-THAN OR EQUIVALENT TO +2274; 2275 # [BEST FIT] NEITHER LESS-THAN NOR EQUIVALENT TO +2275; 2274 # [BEST FIT] NEITHER GREATER-THAN NOR EQUIVALENT TO +2276; 2277 # LESS-THAN OR GREATER-THAN +2277; 2276 # GREATER-THAN OR LESS-THAN +2278; 2279 # NEITHER LESS-THAN NOR GREATER-THAN +2279; 2278 # NEITHER GREATER-THAN NOR LESS-THAN +227A; 227B # PRECEDES +227B; 227A # SUCCEEDS +227C; 227D # PRECEDES OR EQUAL TO +227D; 227C # SUCCEEDS OR EQUAL TO +227E; 227F # [BEST FIT] PRECEDES OR EQUIVALENT TO +227F; 227E # [BEST FIT] SUCCEEDS OR EQUIVALENT TO +2280; 2281 # [BEST FIT] DOES NOT PRECEDE +2281; 2280 # [BEST FIT] DOES NOT SUCCEED +2282; 2283 # SUBSET OF +2283; 2282 # SUPERSET OF +2284; 2285 # [BEST FIT] NOT A SUBSET OF +2285; 2284 # [BEST FIT] NOT A SUPERSET OF +2286; 2287 # SUBSET OF OR EQUAL TO +2287; 2286 # SUPERSET OF OR EQUAL TO +2288; 2289 # [BEST FIT] NEITHER A SUBSET OF NOR EQUAL TO +2289; 2288 # [BEST FIT] NEITHER A SUPERSET OF NOR EQUAL TO +228A; 228B # [BEST FIT] SUBSET OF WITH NOT EQUAL TO +228B; 228A # [BEST FIT] SUPERSET OF WITH NOT EQUAL TO +228F; 2290 # SQUARE IMAGE OF +2290; 228F # SQUARE ORIGINAL OF +2291; 2292 # SQUARE IMAGE OF OR EQUAL TO +2292; 2291 # SQUARE ORIGINAL OF OR EQUAL TO +22A2; 22A3 # RIGHT TACK +22A3; 22A2 # LEFT TACK +22B0; 22B1 # PRECEDES UNDER RELATION +22B1; 22B0 # SUCCEEDS UNDER RELATION +22B2; 22B3 # NORMAL SUBGROUP OF +22B3; 22B2 # CONTAINS AS NORMAL SUBGROUP +22B4; 22B5 # NORMAL SUBGROUP OF OR EQUAL TO +22B5; 22B4 # CONTAINS AS NORMAL SUBGROUP OR EQUAL TO +22B6; 22B7 # ORIGINAL OF +22B7; 22B6 # IMAGE OF +22C9; 22CA # LEFT NORMAL FACTOR SEMIDIRECT PRODUCT +22CA; 22C9 # RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT +22CB; 22CC # LEFT SEMIDIRECT PRODUCT +22CC; 22CB # RIGHT SEMIDIRECT PRODUCT +22CD; 2243 # REVERSED TILDE EQUALS +22D0; 22D1 # DOUBLE SUBSET +22D1; 22D0 # DOUBLE SUPERSET +22D6; 22D7 # LESS-THAN WITH DOT +22D7; 22D6 # GREATER-THAN WITH DOT +22D8; 22D9 # VERY MUCH LESS-THAN +22D9; 22D8 # VERY MUCH GREATER-THAN +22DA; 22DB # LESS-THAN EQUAL TO OR GREATER-THAN +22DB; 22DA # GREATER-THAN EQUAL TO OR LESS-THAN +22DC; 22DD # EQUAL TO OR LESS-THAN +22DD; 22DC # EQUAL TO OR GREATER-THAN +22DE; 22DF # EQUAL TO OR PRECEDES +22DF; 22DE # EQUAL TO OR SUCCEEDS +22E0; 22E1 # [BEST FIT] DOES NOT PRECEDE OR EQUAL +22E1; 22E0 # [BEST FIT] DOES NOT SUCCEED OR EQUAL +22E2; 22E3 # [BEST FIT] NOT SQUARE IMAGE OF OR EQUAL TO +22E3; 22E2 # [BEST FIT] NOT SQUARE ORIGINAL OF OR EQUAL TO +22E4; 22E5 # [BEST FIT] SQUARE IMAGE OF OR NOT EQUAL TO +22E5; 22E4 # [BEST FIT] SQUARE ORIGINAL OF OR NOT EQUAL TO +22E6; 22E7 # [BEST FIT] LESS-THAN BUT NOT EQUIVALENT TO +22E7; 22E6 # [BEST FIT] GREATER-THAN BUT NOT EQUIVALENT TO +22E8; 22E9 # [BEST FIT] PRECEDES BUT NOT EQUIVALENT TO +22E9; 22E8 # [BEST FIT] SUCCEEDS BUT NOT EQUIVALENT TO +22EA; 22EB # [BEST FIT] NOT NORMAL SUBGROUP OF +22EB; 22EA # [BEST FIT] DOES NOT CONTAIN AS NORMAL SUBGROUP +22EC; 22ED # [BEST FIT] NOT NORMAL SUBGROUP OF OR EQUAL TO +22ED; 22EC # [BEST FIT] DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL +22F0; 22F1 # UP RIGHT DIAGONAL ELLIPSIS +22F1; 22F0 # DOWN RIGHT DIAGONAL ELLIPSIS +2308; 2309 # LEFT CEILING +2309; 2308 # RIGHT CEILING +230A; 230B # LEFT FLOOR +230B; 230A # RIGHT FLOOR +2329; 232A # LEFT-POINTING ANGLE BRACKET +232A; 2329 # RIGHT-POINTING ANGLE BRACKET +3008; 3009 # LEFT ANGLE BRACKET +3009; 3008 # RIGHT ANGLE BRACKET +300A; 300B # LEFT DOUBLE ANGLE BRACKET +300B; 300A # RIGHT DOUBLE ANGLE BRACKET +300C; 300D # [BEST FIT] LEFT CORNER BRACKET +300D; 300C # [BEST FIT] RIGHT CORNER BRACKET +300E; 300F # [BEST FIT] LEFT WHITE CORNER BRACKET +300F; 300E # [BEST FIT] RIGHT WHITE CORNER BRACKET +3010; 3011 # LEFT BLACK LENTICULAR BRACKET +3011; 3010 # RIGHT BLACK LENTICULAR BRACKET +3014; 3015 # [BEST FIT] LEFT TORTOISE SHELL BRACKET +3015; 3014 # [BEST FIT] RIGHT TORTOISE SHELL BRACKET +3016; 3017 # LEFT WHITE LENTICULAR BRACKET +3017; 3016 # RIGHT WHITE LENTICULAR BRACKET +3018; 3019 # LEFT WHITE TORTOISE SHELL BRACKET +3019; 3018 # RIGHT WHITE TORTOISE SHELL BRACKET +301A; 301B # LEFT WHITE SQUARE BRACKET +301B; 301A # RIGHT WHITE SQUARE BRACKET + +# The following characters have no appropriate mirroring character + +# 2201; COMPLEMENT +# 2202; PARTIAL DIFFERENTIAL +# 2203; THERE EXISTS +# 2204; THERE DOES NOT EXIST +# 2211; N-ARY SUMMATION +# 2215; DIVISION SLASH +# 2216; SET MINUS +# 221A; SQUARE ROOT +# 221B; CUBE ROOT +# 221C; FOURTH ROOT +# 221D; PROPORTIONAL TO +# 221F; RIGHT ANGLE +# 2220; ANGLE +# 2221; MEASURED ANGLE +# 2222; SPHERICAL ANGLE +# 2224; DOES NOT DIVIDE +# 2226; NOT PARALLEL TO +# 222B; INTEGRAL +# 222C; DOUBLE INTEGRAL +# 222D; TRIPLE INTEGRAL +# 222E; CONTOUR INTEGRAL +# 222F; SURFACE INTEGRAL +# 2230; VOLUME INTEGRAL +# 2231; CLOCKWISE INTEGRAL +# 2232; CLOCKWISE CONTOUR INTEGRAL +# 2233; ANTICLOCKWISE CONTOUR INTEGRAL +# 2239; EXCESS +# 223B; HOMOTHETIC +# 223E; INVERTED LAZY S +# 223F; SINE WAVE +# 2240; WREATH PRODUCT +# 2241; NOT TILDE +# 2242; MINUS TILDE +# 2244; NOT ASYMPTOTICALLY EQUAL TO +# 2245; APPROXIMATELY EQUAL TO +# 2246; APPROXIMATELY BUT NOT ACTUALLY EQUAL TO +# 2247; NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO +# 2248; ALMOST EQUAL TO +# 2249; NOT ALMOST EQUAL TO +# 224A; ALMOST EQUAL OR EQUAL TO +# 224B; TRIPLE TILDE +# 224C; ALL EQUAL TO +# 225F; QUESTIONED EQUAL TO +# 2260; NOT EQUAL TO +# 2262; NOT IDENTICAL TO +# 228C; MULTISET +# 2298; CIRCLED DIVISION SLASH +# 22A6; ASSERTION +# 22A7; MODELS +# 22A8; TRUE +# 22A9; FORCES +# 22AA; TRIPLE VERTICAL BAR RIGHT TURNSTILE +# 22AB; DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE +# 22AC; DOES NOT PROVE +# 22AD; NOT TRUE +# 22AE; DOES NOT FORCE +# 22AF; NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE +# 22B8; MULTIMAP +# 22BE; RIGHT ANGLE WITH ARC +# 22BF; RIGHT TRIANGLE +# 2320; TOP HALF INTEGRAL +# 2321; BOTTOM HALF INTEGRAL diff --git a/lib/unicode/Bidirectional.pl b/lib/unicode/Bidirectional.pl index 73898b8..3cc2d0a 100644 --- a/lib/unicode/Bidirectional.pl +++ b/lib/unicode/Bidirectional.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 0008 BN @@ -635,4 +635,6 @@ ffe5 ffe6 ET ffe8 ffee ON fff9 fffb BN fffc fffd ON +f0000 ffffd L +100000 10fffd L END diff --git a/lib/unicode/Block.pl b/lib/unicode/Block.pl index ee680b7..2b5bfce 100644 --- a/lib/unicode/Block.pl +++ b/lib/unicode/Block.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 007F Basic Latin diff --git a/lib/unicode/CaseFold.txt b/lib/unicode/CaseFold.txt new file mode 100644 index 0000000..6529c41 --- /dev/null +++ b/lib/unicode/CaseFold.txt @@ -0,0 +1,821 @@ +# CaseFolding-2.txt +# +# Case Folding Properties +# +# This file is a supplement to the UnicodeData file. +# It provides a case folding mapping generated from the Unicode Character Database. +# If all characters are mapped according to this mapping, then +# case differences (according to UnicodeData.txt and SpecialCasing.txt) +# are eliminated. +# +# For information on case folding, see +# UTR #21 Case Mappings, at http://www.unicode.org/unicode/reports/tr21/ +# +# These are informative character properties. +# +# Send comments to mark@unicode.org +# +# ================================================================================ +# Format +# ================================================================================ +# The entries in this file are in the following machine-readable format: +# +# ; ; ; # +# +# The status is: +# L (for Lowercase) if the case mapping matches the standard 1-1 lowercase mapping +# E (for exception) if it does not. +# +# The mapping may consist of multiple characters. +# If so, they are separated by spaces. +# +# ================================================================= + +0041; L; 0061; #LATIN CAPITAL LETTER A +0042; L; 0062; #LATIN CAPITAL LETTER B +0043; L; 0063; #LATIN CAPITAL LETTER C +0044; L; 0064; #LATIN CAPITAL LETTER D +0045; L; 0065; #LATIN CAPITAL LETTER E +0046; L; 0066; #LATIN CAPITAL LETTER F +0047; L; 0067; #LATIN CAPITAL LETTER G +0048; L; 0068; #LATIN CAPITAL LETTER H +0049; L; 0069; #LATIN CAPITAL LETTER I +004A; L; 006A; #LATIN CAPITAL LETTER J +004B; L; 006B; #LATIN CAPITAL LETTER K +004C; L; 006C; #LATIN CAPITAL LETTER L +004D; L; 006D; #LATIN CAPITAL LETTER M +004E; L; 006E; #LATIN CAPITAL LETTER N +004F; L; 006F; #LATIN CAPITAL LETTER O +0050; L; 0070; #LATIN CAPITAL LETTER P +0051; L; 0071; #LATIN CAPITAL LETTER Q +0052; L; 0072; #LATIN CAPITAL LETTER R +0053; L; 0073; #LATIN CAPITAL LETTER S +0054; L; 0074; #LATIN CAPITAL LETTER T +0055; L; 0075; #LATIN CAPITAL LETTER U +0056; L; 0076; #LATIN CAPITAL LETTER V +0057; L; 0077; #LATIN CAPITAL LETTER W +0058; L; 0078; #LATIN CAPITAL LETTER X +0059; L; 0079; #LATIN CAPITAL LETTER Y +005A; L; 007A; #LATIN CAPITAL LETTER Z +00B5; E; 03BC; #MICRO SIGN +00C0; L; 00E0; #LATIN CAPITAL LETTER A WITH GRAVE +00C1; L; 00E1; #LATIN CAPITAL LETTER A WITH ACUTE +00C2; L; 00E2; #LATIN CAPITAL LETTER A WITH CIRCUMFLEX +00C3; L; 00E3; #LATIN CAPITAL LETTER A WITH TILDE +00C4; L; 00E4; #LATIN CAPITAL LETTER A WITH DIAERESIS +00C5; L; 00E5; #LATIN CAPITAL LETTER A WITH RING ABOVE +00C6; L; 00E6; #LATIN CAPITAL LETTER AE +00C7; L; 00E7; #LATIN CAPITAL LETTER C WITH CEDILLA +00C8; L; 00E8; #LATIN CAPITAL LETTER E WITH GRAVE +00C9; L; 00E9; #LATIN CAPITAL LETTER E WITH ACUTE +00CA; L; 00EA; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX +00CB; L; 00EB; #LATIN CAPITAL LETTER E WITH DIAERESIS +00CC; L; 00EC; #LATIN CAPITAL LETTER I WITH GRAVE +00CD; L; 00ED; #LATIN CAPITAL LETTER I WITH ACUTE +00CE; L; 00EE; #LATIN CAPITAL LETTER I WITH CIRCUMFLEX +00CF; L; 00EF; #LATIN CAPITAL LETTER I WITH DIAERESIS +00D0; L; 00F0; #LATIN CAPITAL LETTER ETH +00D1; L; 00F1; #LATIN CAPITAL LETTER N WITH TILDE +00D2; L; 00F2; #LATIN CAPITAL LETTER O WITH GRAVE +00D3; L; 00F3; #LATIN CAPITAL LETTER O WITH ACUTE +00D4; L; 00F4; #LATIN CAPITAL LETTER O WITH CIRCUMFLEX +00D5; L; 00F5; #LATIN CAPITAL LETTER O WITH TILDE +00D6; L; 00F6; #LATIN CAPITAL LETTER O WITH DIAERESIS +00D8; L; 00F8; #LATIN CAPITAL LETTER O WITH STROKE +00D9; L; 00F9; #LATIN CAPITAL LETTER U WITH GRAVE +00DA; L; 00FA; #LATIN CAPITAL LETTER U WITH ACUTE +00DB; L; 00FB; #LATIN CAPITAL LETTER U WITH CIRCUMFLEX +00DC; L; 00FC; #LATIN CAPITAL LETTER U WITH DIAERESIS +00DD; L; 00FD; #LATIN CAPITAL LETTER Y WITH ACUTE +00DE; L; 00FE; #LATIN CAPITAL LETTER THORN +00DF; E; 0073 0073; #LATIN SMALL LETTER SHARP S +0100; L; 0101; #LATIN CAPITAL LETTER A WITH MACRON +0102; L; 0103; #LATIN CAPITAL LETTER A WITH BREVE +0104; L; 0105; #LATIN CAPITAL LETTER A WITH OGONEK +0106; L; 0107; #LATIN CAPITAL LETTER C WITH ACUTE +0108; L; 0109; #LATIN CAPITAL LETTER C WITH CIRCUMFLEX +010A; L; 010B; #LATIN CAPITAL LETTER C WITH DOT ABOVE +010C; L; 010D; #LATIN CAPITAL LETTER C WITH CARON +010E; L; 010F; #LATIN CAPITAL LETTER D WITH CARON +0110; L; 0111; #LATIN CAPITAL LETTER D WITH STROKE +0112; L; 0113; #LATIN CAPITAL LETTER E WITH MACRON +0114; L; 0115; #LATIN CAPITAL LETTER E WITH BREVE +0116; L; 0117; #LATIN CAPITAL LETTER E WITH DOT ABOVE +0118; L; 0119; #LATIN CAPITAL LETTER E WITH OGONEK +011A; L; 011B; #LATIN CAPITAL LETTER E WITH CARON +011C; L; 011D; #LATIN CAPITAL LETTER G WITH CIRCUMFLEX +011E; L; 011F; #LATIN CAPITAL LETTER G WITH BREVE +0120; L; 0121; #LATIN CAPITAL LETTER G WITH DOT ABOVE +0122; L; 0123; #LATIN CAPITAL LETTER G WITH CEDILLA +0124; L; 0125; #LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0126; L; 0127; #LATIN CAPITAL LETTER H WITH STROKE +0128; L; 0129; #LATIN CAPITAL LETTER I WITH TILDE +012A; L; 012B; #LATIN CAPITAL LETTER I WITH MACRON +012C; L; 012D; #LATIN CAPITAL LETTER I WITH BREVE +012E; L; 012F; #LATIN CAPITAL LETTER I WITH OGONEK +0130; L; 0069; #LATIN CAPITAL LETTER I WITH DOT ABOVE +0131; E; 0069; #LATIN SMALL LETTER DOTLESS I +0132; L; 0133; #LATIN CAPITAL LIGATURE IJ +0134; L; 0135; #LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0136; L; 0137; #LATIN CAPITAL LETTER K WITH CEDILLA +0139; L; 013A; #LATIN CAPITAL LETTER L WITH ACUTE +013B; L; 013C; #LATIN CAPITAL LETTER L WITH CEDILLA +013D; L; 013E; #LATIN CAPITAL LETTER L WITH CARON +013F; L; 0140; #LATIN CAPITAL LETTER L WITH MIDDLE DOT +0141; L; 0142; #LATIN CAPITAL LETTER L WITH STROKE +0143; L; 0144; #LATIN CAPITAL LETTER N WITH ACUTE +0145; L; 0146; #LATIN CAPITAL LETTER N WITH CEDILLA +0147; L; 0148; #LATIN CAPITAL LETTER N WITH CARON +0149; E; 02BC 006E; #LATIN SMALL LETTER N PRECEDED BY APOSTROPHE +014A; L; 014B; #LATIN CAPITAL LETTER ENG +014C; L; 014D; #LATIN CAPITAL LETTER O WITH MACRON +014E; L; 014F; #LATIN CAPITAL LETTER O WITH BREVE +0150; L; 0151; #LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0152; L; 0153; #LATIN CAPITAL LIGATURE OE +0154; L; 0155; #LATIN CAPITAL LETTER R WITH ACUTE +0156; L; 0157; #LATIN CAPITAL LETTER R WITH CEDILLA +0158; L; 0159; #LATIN CAPITAL LETTER R WITH CARON +015A; L; 015B; #LATIN CAPITAL LETTER S WITH ACUTE +015C; L; 015D; #LATIN CAPITAL LETTER S WITH CIRCUMFLEX +015E; L; 015F; #LATIN CAPITAL LETTER S WITH CEDILLA +0160; L; 0161; #LATIN CAPITAL LETTER S WITH CARON +0162; L; 0163; #LATIN CAPITAL LETTER T WITH CEDILLA +0164; L; 0165; #LATIN CAPITAL LETTER T WITH CARON +0166; L; 0167; #LATIN CAPITAL LETTER T WITH STROKE +0168; L; 0169; #LATIN CAPITAL LETTER U WITH TILDE +016A; L; 016B; #LATIN CAPITAL LETTER U WITH MACRON +016C; L; 016D; #LATIN CAPITAL LETTER U WITH BREVE +016E; L; 016F; #LATIN CAPITAL LETTER U WITH RING ABOVE +0170; L; 0171; #LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0172; L; 0173; #LATIN CAPITAL LETTER U WITH OGONEK +0174; L; 0175; #LATIN CAPITAL LETTER W WITH CIRCUMFLEX +0176; L; 0177; #LATIN CAPITAL LETTER Y WITH CIRCUMFLEX +0178; L; 00FF; #LATIN CAPITAL LETTER Y WITH DIAERESIS +0179; L; 017A; #LATIN CAPITAL LETTER Z WITH ACUTE +017B; L; 017C; #LATIN CAPITAL LETTER Z WITH DOT ABOVE +017D; L; 017E; #LATIN CAPITAL LETTER Z WITH CARON +017F; E; 0073; #LATIN SMALL LETTER LONG S +0181; L; 0253; #LATIN CAPITAL LETTER B WITH HOOK +0182; L; 0183; #LATIN CAPITAL LETTER B WITH TOPBAR +0184; L; 0185; #LATIN CAPITAL LETTER TONE SIX +0186; L; 0254; #LATIN CAPITAL LETTER OPEN O +0187; L; 0188; #LATIN CAPITAL LETTER C WITH HOOK +0189; L; 0256; #LATIN CAPITAL LETTER AFRICAN D +018A; L; 0257; #LATIN CAPITAL LETTER D WITH HOOK +018B; L; 018C; #LATIN CAPITAL LETTER D WITH TOPBAR +018E; L; 01DD; #LATIN CAPITAL LETTER REVERSED E +018F; L; 0259; #LATIN CAPITAL LETTER SCHWA +0190; L; 025B; #LATIN CAPITAL LETTER OPEN E +0191; L; 0192; #LATIN CAPITAL LETTER F WITH HOOK +0193; L; 0260; #LATIN CAPITAL LETTER G WITH HOOK +0194; L; 0263; #LATIN CAPITAL LETTER GAMMA +0196; L; 0269; #LATIN CAPITAL LETTER IOTA +0197; L; 0268; #LATIN CAPITAL LETTER I WITH STROKE +0198; L; 0199; #LATIN CAPITAL LETTER K WITH HOOK +019C; L; 026F; #LATIN CAPITAL LETTER TURNED M +019D; L; 0272; #LATIN CAPITAL LETTER N WITH LEFT HOOK +019F; L; 0275; #LATIN CAPITAL LETTER O WITH MIDDLE TILDE +01A0; L; 01A1; #LATIN CAPITAL LETTER O WITH HORN +01A2; L; 01A3; #LATIN CAPITAL LETTER OI +01A4; L; 01A5; #LATIN CAPITAL LETTER P WITH HOOK +01A6; L; 0280; #LATIN LETTER YR +01A7; L; 01A8; #LATIN CAPITAL LETTER TONE TWO +01A9; L; 0283; #LATIN CAPITAL LETTER ESH +01AC; L; 01AD; #LATIN CAPITAL LETTER T WITH HOOK +01AE; L; 0288; #LATIN CAPITAL LETTER T WITH RETROFLEX HOOK +01AF; L; 01B0; #LATIN CAPITAL LETTER U WITH HORN +01B1; L; 028A; #LATIN CAPITAL LETTER UPSILON +01B2; L; 028B; #LATIN CAPITAL LETTER V WITH HOOK +01B3; L; 01B4; #LATIN CAPITAL LETTER Y WITH HOOK +01B5; L; 01B6; #LATIN CAPITAL LETTER Z WITH STROKE +01B7; L; 0292; #LATIN CAPITAL LETTER EZH +01B8; L; 01B9; #LATIN CAPITAL LETTER EZH REVERSED +01BC; L; 01BD; #LATIN CAPITAL LETTER TONE FIVE +01C4; L; 01C6; #LATIN CAPITAL LETTER DZ WITH CARON +01C5; L; 01C6; #LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON +01C7; L; 01C9; #LATIN CAPITAL LETTER LJ +01C8; L; 01C9; #LATIN CAPITAL LETTER L WITH SMALL LETTER J +01CA; L; 01CC; #LATIN CAPITAL LETTER NJ +01CB; L; 01CC; #LATIN CAPITAL LETTER N WITH SMALL LETTER J +01CD; L; 01CE; #LATIN CAPITAL LETTER A WITH CARON +01CF; L; 01D0; #LATIN CAPITAL LETTER I WITH CARON +01D1; L; 01D2; #LATIN CAPITAL LETTER O WITH CARON +01D3; L; 01D4; #LATIN CAPITAL LETTER U WITH CARON +01D5; L; 01D6; #LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON +01D7; L; 01D8; #LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE +01D9; L; 01DA; #LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON +01DB; L; 01DC; #LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE +01DE; L; 01DF; #LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON +01E0; L; 01E1; #LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON +01E2; L; 01E3; #LATIN CAPITAL LETTER AE WITH MACRON +01E4; L; 01E5; #LATIN CAPITAL LETTER G WITH STROKE +01E6; L; 01E7; #LATIN CAPITAL LETTER G WITH CARON +01E8; L; 01E9; #LATIN CAPITAL LETTER K WITH CARON +01EA; L; 01EB; #LATIN CAPITAL LETTER O WITH OGONEK +01EC; L; 01ED; #LATIN CAPITAL LETTER O WITH OGONEK AND MACRON +01EE; L; 01EF; #LATIN CAPITAL LETTER EZH WITH CARON +01F0; E; 006A 030C; #LATIN SMALL LETTER J WITH CARON +01F1; L; 01F3; #LATIN CAPITAL LETTER DZ +01F2; L; 01F3; #LATIN CAPITAL LETTER D WITH SMALL LETTER Z +01F4; L; 01F5; #LATIN CAPITAL LETTER G WITH ACUTE +01F6; L; 0195; #LATIN CAPITAL LETTER HWAIR +01F7; L; 01BF; #LATIN CAPITAL LETTER WYNN +01F8; L; 01F9; #LATIN CAPITAL LETTER N WITH GRAVE +01FA; L; 01FB; #LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE +01FC; L; 01FD; #LATIN CAPITAL LETTER AE WITH ACUTE +01FE; L; 01FF; #LATIN CAPITAL LETTER O WITH STROKE AND ACUTE +0200; L; 0201; #LATIN CAPITAL LETTER A WITH DOUBLE GRAVE +0202; L; 0203; #LATIN CAPITAL LETTER A WITH INVERTED BREVE +0204; L; 0205; #LATIN CAPITAL LETTER E WITH DOUBLE GRAVE +0206; L; 0207; #LATIN CAPITAL LETTER E WITH INVERTED BREVE +0208; L; 0209; #LATIN CAPITAL LETTER I WITH DOUBLE GRAVE +020A; L; 020B; #LATIN CAPITAL LETTER I WITH INVERTED BREVE +020C; L; 020D; #LATIN CAPITAL LETTER O WITH DOUBLE GRAVE +020E; L; 020F; #LATIN CAPITAL LETTER O WITH INVERTED BREVE +0210; L; 0211; #LATIN CAPITAL LETTER R WITH DOUBLE GRAVE +0212; L; 0213; #LATIN CAPITAL LETTER R WITH INVERTED BREVE +0214; L; 0215; #LATIN CAPITAL LETTER U WITH DOUBLE GRAVE +0216; L; 0217; #LATIN CAPITAL LETTER U WITH INVERTED BREVE +0218; L; 0219; #LATIN CAPITAL LETTER S WITH COMMA BELOW +021A; L; 021B; #LATIN CAPITAL LETTER T WITH COMMA BELOW +021C; L; 021D; #LATIN CAPITAL LETTER YOGH +021E; L; 021F; #LATIN CAPITAL LETTER H WITH CARON +0222; L; 0223; #LATIN CAPITAL LETTER OU +0224; L; 0225; #LATIN CAPITAL LETTER Z WITH HOOK +0226; L; 0227; #LATIN CAPITAL LETTER A WITH DOT ABOVE +0228; L; 0229; #LATIN CAPITAL LETTER E WITH CEDILLA +022A; L; 022B; #LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON +022C; L; 022D; #LATIN CAPITAL LETTER O WITH TILDE AND MACRON +022E; L; 022F; #LATIN CAPITAL LETTER O WITH DOT ABOVE +0230; L; 0231; #LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON +0232; L; 0233; #LATIN CAPITAL LETTER Y WITH MACRON +0345; E; 03B9; #COMBINING GREEK YPOGEGRAMMENI +0386; L; 03AC; #GREEK CAPITAL LETTER ALPHA WITH TONOS +0388; L; 03AD; #GREEK CAPITAL LETTER EPSILON WITH TONOS +0389; L; 03AE; #GREEK CAPITAL LETTER ETA WITH TONOS +038A; L; 03AF; #GREEK CAPITAL LETTER IOTA WITH TONOS +038C; L; 03CC; #GREEK CAPITAL LETTER OMICRON WITH TONOS +038E; L; 03CD; #GREEK CAPITAL LETTER UPSILON WITH TONOS +038F; L; 03CE; #GREEK CAPITAL LETTER OMEGA WITH TONOS +0390; E; 03B9 0308 0301; #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0391; L; 03B1; #GREEK CAPITAL LETTER ALPHA +0392; L; 03B2; #GREEK CAPITAL LETTER BETA +0393; L; 03B3; #GREEK CAPITAL LETTER GAMMA +0394; L; 03B4; #GREEK CAPITAL LETTER DELTA +0395; L; 03B5; #GREEK CAPITAL LETTER EPSILON +0396; L; 03B6; #GREEK CAPITAL LETTER ZETA +0397; L; 03B7; #GREEK CAPITAL LETTER ETA +0398; L; 03B8; #GREEK CAPITAL LETTER THETA +0399; L; 03B9; #GREEK CAPITAL LETTER IOTA +039A; L; 03BA; #GREEK CAPITAL LETTER KAPPA +039B; L; 03BB; #GREEK CAPITAL LETTER LAMDA +039C; L; 03BC; #GREEK CAPITAL LETTER MU +039D; L; 03BD; #GREEK CAPITAL LETTER NU +039E; L; 03BE; #GREEK CAPITAL LETTER XI +039F; L; 03BF; #GREEK CAPITAL LETTER OMICRON +03A0; L; 03C0; #GREEK CAPITAL LETTER PI +03A1; L; 03C1; #GREEK CAPITAL LETTER RHO +03A3; E; 03C2; #GREEK CAPITAL LETTER SIGMA +03A4; L; 03C4; #GREEK CAPITAL LETTER TAU +03A5; L; 03C5; #GREEK CAPITAL LETTER UPSILON +03A6; L; 03C6; #GREEK CAPITAL LETTER PHI +03A7; L; 03C7; #GREEK CAPITAL LETTER CHI +03A8; L; 03C8; #GREEK CAPITAL LETTER PSI +03A9; L; 03C9; #GREEK CAPITAL LETTER OMEGA +03AA; L; 03CA; #GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +03AB; L; 03CB; #GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +03B0; E; 03C5 0308 0301; #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +03C2; L; 03C2; #GREEK SMALL LETTER FINAL SIGMA +03C3; E; 03C2; #GREEK SMALL LETTER SIGMA +03D0; E; 03B2; #GREEK BETA SYMBOL +03D1; E; 03B8; #GREEK THETA SYMBOL +03D5; E; 03C6; #GREEK PHI SYMBOL +03D6; E; 03C0; #GREEK PI SYMBOL +03DA; L; 03DB; #GREEK LETTER STIGMA +03DC; L; 03DD; #GREEK LETTER DIGAMMA +03DE; L; 03DF; #GREEK LETTER KOPPA +03E0; L; 03E1; #GREEK LETTER SAMPI +03E2; L; 03E3; #COPTIC CAPITAL LETTER SHEI +03E4; L; 03E5; #COPTIC CAPITAL LETTER FEI +03E6; L; 03E7; #COPTIC CAPITAL LETTER KHEI +03E8; L; 03E9; #COPTIC CAPITAL LETTER HORI +03EA; L; 03EB; #COPTIC CAPITAL LETTER GANGIA +03EC; L; 03ED; #COPTIC CAPITAL LETTER SHIMA +03EE; L; 03EF; #COPTIC CAPITAL LETTER DEI +03F0; E; 03BA; #GREEK KAPPA SYMBOL +03F1; E; 03C1; #GREEK RHO SYMBOL +03F2; E; 03C2; #GREEK LUNATE SIGMA SYMBOL +0400; L; 0450; #CYRILLIC CAPITAL LETTER IE WITH GRAVE +0401; L; 0451; #CYRILLIC CAPITAL LETTER IO +0402; L; 0452; #CYRILLIC CAPITAL LETTER DJE +0403; L; 0453; #CYRILLIC CAPITAL LETTER GJE +0404; L; 0454; #CYRILLIC CAPITAL LETTER UKRAINIAN IE +0405; L; 0455; #CYRILLIC CAPITAL LETTER DZE +0406; L; 0456; #CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0407; L; 0457; #CYRILLIC CAPITAL LETTER YI +0408; L; 0458; #CYRILLIC CAPITAL LETTER JE +0409; L; 0459; #CYRILLIC CAPITAL LETTER LJE +040A; L; 045A; #CYRILLIC CAPITAL LETTER NJE +040B; L; 045B; #CYRILLIC CAPITAL LETTER TSHE +040C; L; 045C; #CYRILLIC CAPITAL LETTER KJE +040D; L; 045D; #CYRILLIC CAPITAL LETTER I WITH GRAVE +040E; L; 045E; #CYRILLIC CAPITAL LETTER SHORT U +040F; L; 045F; #CYRILLIC CAPITAL LETTER DZHE +0410; L; 0430; #CYRILLIC CAPITAL LETTER A +0411; L; 0431; #CYRILLIC CAPITAL LETTER BE +0412; L; 0432; #CYRILLIC CAPITAL LETTER VE +0413; L; 0433; #CYRILLIC CAPITAL LETTER GHE +0414; L; 0434; #CYRILLIC CAPITAL LETTER DE +0415; L; 0435; #CYRILLIC CAPITAL LETTER IE +0416; L; 0436; #CYRILLIC CAPITAL LETTER ZHE +0417; L; 0437; #CYRILLIC CAPITAL LETTER ZE +0418; L; 0438; #CYRILLIC CAPITAL LETTER I +0419; L; 0439; #CYRILLIC CAPITAL LETTER SHORT I +041A; L; 043A; #CYRILLIC CAPITAL LETTER KA +041B; L; 043B; #CYRILLIC CAPITAL LETTER EL +041C; L; 043C; #CYRILLIC CAPITAL LETTER EM +041D; L; 043D; #CYRILLIC CAPITAL LETTER EN +041E; L; 043E; #CYRILLIC CAPITAL LETTER O +041F; L; 043F; #CYRILLIC CAPITAL LETTER PE +0420; L; 0440; #CYRILLIC CAPITAL LETTER ER +0421; L; 0441; #CYRILLIC CAPITAL LETTER ES +0422; L; 0442; #CYRILLIC CAPITAL LETTER TE +0423; L; 0443; #CYRILLIC CAPITAL LETTER U +0424; L; 0444; #CYRILLIC CAPITAL LETTER EF +0425; L; 0445; #CYRILLIC CAPITAL LETTER HA +0426; L; 0446; #CYRILLIC CAPITAL LETTER TSE +0427; L; 0447; #CYRILLIC CAPITAL LETTER CHE +0428; L; 0448; #CYRILLIC CAPITAL LETTER SHA +0429; L; 0449; #CYRILLIC CAPITAL LETTER SHCHA +042A; L; 044A; #CYRILLIC CAPITAL LETTER HARD SIGN +042B; L; 044B; #CYRILLIC CAPITAL LETTER YERU +042C; L; 044C; #CYRILLIC CAPITAL LETTER SOFT SIGN +042D; L; 044D; #CYRILLIC CAPITAL LETTER E +042E; L; 044E; #CYRILLIC CAPITAL LETTER YU +042F; L; 044F; #CYRILLIC CAPITAL LETTER YA +0460; L; 0461; #CYRILLIC CAPITAL LETTER OMEGA +0462; L; 0463; #CYRILLIC CAPITAL LETTER YAT +0464; L; 0465; #CYRILLIC CAPITAL LETTER IOTIFIED E +0466; L; 0467; #CYRILLIC CAPITAL LETTER LITTLE YUS +0468; L; 0469; #CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS +046A; L; 046B; #CYRILLIC CAPITAL LETTER BIG YUS +046C; L; 046D; #CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS +046E; L; 046F; #CYRILLIC CAPITAL LETTER KSI +0470; L; 0471; #CYRILLIC CAPITAL LETTER PSI +0472; L; 0473; #CYRILLIC CAPITAL LETTER FITA +0474; L; 0475; #CYRILLIC CAPITAL LETTER IZHITSA +0476; L; 0477; #CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0478; L; 0479; #CYRILLIC CAPITAL LETTER UK +047A; L; 047B; #CYRILLIC CAPITAL LETTER ROUND OMEGA +047C; L; 047D; #CYRILLIC CAPITAL LETTER OMEGA WITH TITLO +047E; L; 047F; #CYRILLIC CAPITAL LETTER OT +0480; L; 0481; #CYRILLIC CAPITAL LETTER KOPPA +048C; L; 048D; #CYRILLIC CAPITAL LETTER SEMISOFT SIGN +048E; L; 048F; #CYRILLIC CAPITAL LETTER ER WITH TICK +0490; L; 0491; #CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0492; L; 0493; #CYRILLIC CAPITAL LETTER GHE WITH STROKE +0494; L; 0495; #CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK +0496; L; 0497; #CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER +0498; L; 0499; #CYRILLIC CAPITAL LETTER ZE WITH DESCENDER +049A; L; 049B; #CYRILLIC CAPITAL LETTER KA WITH DESCENDER +049C; L; 049D; #CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE +049E; L; 049F; #CYRILLIC CAPITAL LETTER KA WITH STROKE +04A0; L; 04A1; #CYRILLIC CAPITAL LETTER BASHKIR KA +04A2; L; 04A3; #CYRILLIC CAPITAL LETTER EN WITH DESCENDER +04A4; L; 04A5; #CYRILLIC CAPITAL LIGATURE EN GHE +04A6; L; 04A7; #CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK +04A8; L; 04A9; #CYRILLIC CAPITAL LETTER ABKHASIAN HA +04AA; L; 04AB; #CYRILLIC CAPITAL LETTER ES WITH DESCENDER +04AC; L; 04AD; #CYRILLIC CAPITAL LETTER TE WITH DESCENDER +04AE; L; 04AF; #CYRILLIC CAPITAL LETTER STRAIGHT U +04B0; L; 04B1; #CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE +04B2; L; 04B3; #CYRILLIC CAPITAL LETTER HA WITH DESCENDER +04B4; L; 04B5; #CYRILLIC CAPITAL LIGATURE TE TSE +04B6; L; 04B7; #CYRILLIC CAPITAL LETTER CHE WITH DESCENDER +04B8; L; 04B9; #CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE +04BA; L; 04BB; #CYRILLIC CAPITAL LETTER SHHA +04BC; L; 04BD; #CYRILLIC CAPITAL LETTER ABKHASIAN CHE +04BE; L; 04BF; #CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER +04C1; L; 04C2; #CYRILLIC CAPITAL LETTER ZHE WITH BREVE +04C3; L; 04C4; #CYRILLIC CAPITAL LETTER KA WITH HOOK +04C7; L; 04C8; #CYRILLIC CAPITAL LETTER EN WITH HOOK +04CB; L; 04CC; #CYRILLIC CAPITAL LETTER KHAKASSIAN CHE +04D0; L; 04D1; #CYRILLIC CAPITAL LETTER A WITH BREVE +04D2; L; 04D3; #CYRILLIC CAPITAL LETTER A WITH DIAERESIS +04D4; L; 04D5; #CYRILLIC CAPITAL LIGATURE A IE +04D6; L; 04D7; #CYRILLIC CAPITAL LETTER IE WITH BREVE +04D8; L; 04D9; #CYRILLIC CAPITAL LETTER SCHWA +04DA; L; 04DB; #CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS +04DC; L; 04DD; #CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS +04DE; L; 04DF; #CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS +04E0; L; 04E1; #CYRILLIC CAPITAL LETTER ABKHASIAN DZE +04E2; L; 04E3; #CYRILLIC CAPITAL LETTER I WITH MACRON +04E4; L; 04E5; #CYRILLIC CAPITAL LETTER I WITH DIAERESIS +04E6; L; 04E7; #CYRILLIC CAPITAL LETTER O WITH DIAERESIS +04E8; L; 04E9; #CYRILLIC CAPITAL LETTER BARRED O +04EA; L; 04EB; #CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS +04EC; L; 04ED; #CYRILLIC CAPITAL LETTER E WITH DIAERESIS +04EE; L; 04EF; #CYRILLIC CAPITAL LETTER U WITH MACRON +04F0; L; 04F1; #CYRILLIC CAPITAL LETTER U WITH DIAERESIS +04F2; L; 04F3; #CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE +04F4; L; 04F5; #CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS +04F8; L; 04F9; #CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS +0531; L; 0561; #ARMENIAN CAPITAL LETTER AYB +0532; L; 0562; #ARMENIAN CAPITAL LETTER BEN +0533; L; 0563; #ARMENIAN CAPITAL LETTER GIM +0534; L; 0564; #ARMENIAN CAPITAL LETTER DA +0535; L; 0565; #ARMENIAN CAPITAL LETTER ECH +0536; L; 0566; #ARMENIAN CAPITAL LETTER ZA +0537; L; 0567; #ARMENIAN CAPITAL LETTER EH +0538; L; 0568; #ARMENIAN CAPITAL LETTER ET +0539; L; 0569; #ARMENIAN CAPITAL LETTER TO +053A; L; 056A; #ARMENIAN CAPITAL LETTER ZHE +053B; L; 056B; #ARMENIAN CAPITAL LETTER INI +053C; L; 056C; #ARMENIAN CAPITAL LETTER LIWN +053D; L; 056D; #ARMENIAN CAPITAL LETTER XEH +053E; L; 056E; #ARMENIAN CAPITAL LETTER CA +053F; L; 056F; #ARMENIAN CAPITAL LETTER KEN +0540; L; 0570; #ARMENIAN CAPITAL LETTER HO +0541; L; 0571; #ARMENIAN CAPITAL LETTER JA +0542; L; 0572; #ARMENIAN CAPITAL LETTER GHAD +0543; L; 0573; #ARMENIAN CAPITAL LETTER CHEH +0544; L; 0574; #ARMENIAN CAPITAL LETTER MEN +0545; L; 0575; #ARMENIAN CAPITAL LETTER YI +0546; L; 0576; #ARMENIAN CAPITAL LETTER NOW +0547; L; 0577; #ARMENIAN CAPITAL LETTER SHA +0548; L; 0578; #ARMENIAN CAPITAL LETTER VO +0549; L; 0579; #ARMENIAN CAPITAL LETTER CHA +054A; L; 057A; #ARMENIAN CAPITAL LETTER PEH +054B; L; 057B; #ARMENIAN CAPITAL LETTER JHEH +054C; L; 057C; #ARMENIAN CAPITAL LETTER RA +054D; L; 057D; #ARMENIAN CAPITAL LETTER SEH +054E; L; 057E; #ARMENIAN CAPITAL LETTER VEW +054F; L; 057F; #ARMENIAN CAPITAL LETTER TIWN +0550; L; 0580; #ARMENIAN CAPITAL LETTER REH +0551; L; 0581; #ARMENIAN CAPITAL LETTER CO +0552; L; 0582; #ARMENIAN CAPITAL LETTER YIWN +0553; L; 0583; #ARMENIAN CAPITAL LETTER PIWR +0554; L; 0584; #ARMENIAN CAPITAL LETTER KEH +0555; L; 0585; #ARMENIAN CAPITAL LETTER OH +0556; L; 0586; #ARMENIAN CAPITAL LETTER FEH +0587; E; 0565 0582; #ARMENIAN SMALL LIGATURE ECH YIWN +1E00; L; 1E01; #LATIN CAPITAL LETTER A WITH RING BELOW +1E02; L; 1E03; #LATIN CAPITAL LETTER B WITH DOT ABOVE +1E04; L; 1E05; #LATIN CAPITAL LETTER B WITH DOT BELOW +1E06; L; 1E07; #LATIN CAPITAL LETTER B WITH LINE BELOW +1E08; L; 1E09; #LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE +1E0A; L; 1E0B; #LATIN CAPITAL LETTER D WITH DOT ABOVE +1E0C; L; 1E0D; #LATIN CAPITAL LETTER D WITH DOT BELOW +1E0E; L; 1E0F; #LATIN CAPITAL LETTER D WITH LINE BELOW +1E10; L; 1E11; #LATIN CAPITAL LETTER D WITH CEDILLA +1E12; L; 1E13; #LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW +1E14; L; 1E15; #LATIN CAPITAL LETTER E WITH MACRON AND GRAVE +1E16; L; 1E17; #LATIN CAPITAL LETTER E WITH MACRON AND ACUTE +1E18; L; 1E19; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW +1E1A; L; 1E1B; #LATIN CAPITAL LETTER E WITH TILDE BELOW +1E1C; L; 1E1D; #LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE +1E1E; L; 1E1F; #LATIN CAPITAL LETTER F WITH DOT ABOVE +1E20; L; 1E21; #LATIN CAPITAL LETTER G WITH MACRON +1E22; L; 1E23; #LATIN CAPITAL LETTER H WITH DOT ABOVE +1E24; L; 1E25; #LATIN CAPITAL LETTER H WITH DOT BELOW +1E26; L; 1E27; #LATIN CAPITAL LETTER H WITH DIAERESIS +1E28; L; 1E29; #LATIN CAPITAL LETTER H WITH CEDILLA +1E2A; L; 1E2B; #LATIN CAPITAL LETTER H WITH BREVE BELOW +1E2C; L; 1E2D; #LATIN CAPITAL LETTER I WITH TILDE BELOW +1E2E; L; 1E2F; #LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE +1E30; L; 1E31; #LATIN CAPITAL LETTER K WITH ACUTE +1E32; L; 1E33; #LATIN CAPITAL LETTER K WITH DOT BELOW +1E34; L; 1E35; #LATIN CAPITAL LETTER K WITH LINE BELOW +1E36; L; 1E37; #LATIN CAPITAL LETTER L WITH DOT BELOW +1E38; L; 1E39; #LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON +1E3A; L; 1E3B; #LATIN CAPITAL LETTER L WITH LINE BELOW +1E3C; L; 1E3D; #LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW +1E3E; L; 1E3F; #LATIN CAPITAL LETTER M WITH ACUTE +1E40; L; 1E41; #LATIN CAPITAL LETTER M WITH DOT ABOVE +1E42; L; 1E43; #LATIN CAPITAL LETTER M WITH DOT BELOW +1E44; L; 1E45; #LATIN CAPITAL LETTER N WITH DOT ABOVE +1E46; L; 1E47; #LATIN CAPITAL LETTER N WITH DOT BELOW +1E48; L; 1E49; #LATIN CAPITAL LETTER N WITH LINE BELOW +1E4A; L; 1E4B; #LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW +1E4C; L; 1E4D; #LATIN CAPITAL LETTER O WITH TILDE AND ACUTE +1E4E; L; 1E4F; #LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS +1E50; L; 1E51; #LATIN CAPITAL LETTER O WITH MACRON AND GRAVE +1E52; L; 1E53; #LATIN CAPITAL LETTER O WITH MACRON AND ACUTE +1E54; L; 1E55; #LATIN CAPITAL LETTER P WITH ACUTE +1E56; L; 1E57; #LATIN CAPITAL LETTER P WITH DOT ABOVE +1E58; L; 1E59; #LATIN CAPITAL LETTER R WITH DOT ABOVE +1E5A; L; 1E5B; #LATIN CAPITAL LETTER R WITH DOT BELOW +1E5C; L; 1E5D; #LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON +1E5E; L; 1E5F; #LATIN CAPITAL LETTER R WITH LINE BELOW +1E60; L; 1E61; #LATIN CAPITAL LETTER S WITH DOT ABOVE +1E62; L; 1E63; #LATIN CAPITAL LETTER S WITH DOT BELOW +1E64; L; 1E65; #LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE +1E66; L; 1E67; #LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE +1E68; L; 1E69; #LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE +1E6A; L; 1E6B; #LATIN CAPITAL LETTER T WITH DOT ABOVE +1E6C; L; 1E6D; #LATIN CAPITAL LETTER T WITH DOT BELOW +1E6E; L; 1E6F; #LATIN CAPITAL LETTER T WITH LINE BELOW +1E70; L; 1E71; #LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW +1E72; L; 1E73; #LATIN CAPITAL LETTER U WITH DIAERESIS BELOW +1E74; L; 1E75; #LATIN CAPITAL LETTER U WITH TILDE BELOW +1E76; L; 1E77; #LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW +1E78; L; 1E79; #LATIN CAPITAL LETTER U WITH TILDE AND ACUTE +1E7A; L; 1E7B; #LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS +1E7C; L; 1E7D; #LATIN CAPITAL LETTER V WITH TILDE +1E7E; L; 1E7F; #LATIN CAPITAL LETTER V WITH DOT BELOW +1E80; L; 1E81; #LATIN CAPITAL LETTER W WITH GRAVE +1E82; L; 1E83; #LATIN CAPITAL LETTER W WITH ACUTE +1E84; L; 1E85; #LATIN CAPITAL LETTER W WITH DIAERESIS +1E86; L; 1E87; #LATIN CAPITAL LETTER W WITH DOT ABOVE +1E88; L; 1E89; #LATIN CAPITAL LETTER W WITH DOT BELOW +1E8A; L; 1E8B; #LATIN CAPITAL LETTER X WITH DOT ABOVE +1E8C; L; 1E8D; #LATIN CAPITAL LETTER X WITH DIAERESIS +1E8E; L; 1E8F; #LATIN CAPITAL LETTER Y WITH DOT ABOVE +1E90; L; 1E91; #LATIN CAPITAL LETTER Z WITH CIRCUMFLEX +1E92; L; 1E93; #LATIN CAPITAL LETTER Z WITH DOT BELOW +1E94; L; 1E95; #LATIN CAPITAL LETTER Z WITH LINE BELOW +1E96; E; 0068 0331; #LATIN SMALL LETTER H WITH LINE BELOW +1E97; E; 0074 0308; #LATIN SMALL LETTER T WITH DIAERESIS +1E98; E; 0077 030A; #LATIN SMALL LETTER W WITH RING ABOVE +1E99; E; 0079 030A; #LATIN SMALL LETTER Y WITH RING ABOVE +1E9A; E; 0061 02BE; #LATIN SMALL LETTER A WITH RIGHT HALF RING +1E9B; E; 1E61; #LATIN SMALL LETTER LONG S WITH DOT ABOVE +1EA0; L; 1EA1; #LATIN CAPITAL LETTER A WITH DOT BELOW +1EA2; L; 1EA3; #LATIN CAPITAL LETTER A WITH HOOK ABOVE +1EA4; L; 1EA5; #LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE +1EA6; L; 1EA7; #LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE +1EA8; L; 1EA9; #LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +1EAA; L; 1EAB; #LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE +1EAC; L; 1EAD; #LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW +1EAE; L; 1EAF; #LATIN CAPITAL LETTER A WITH BREVE AND ACUTE +1EB0; L; 1EB1; #LATIN CAPITAL LETTER A WITH BREVE AND GRAVE +1EB2; L; 1EB3; #LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE +1EB4; L; 1EB5; #LATIN CAPITAL LETTER A WITH BREVE AND TILDE +1EB6; L; 1EB7; #LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW +1EB8; L; 1EB9; #LATIN CAPITAL LETTER E WITH DOT BELOW +1EBA; L; 1EBB; #LATIN CAPITAL LETTER E WITH HOOK ABOVE +1EBC; L; 1EBD; #LATIN CAPITAL LETTER E WITH TILDE +1EBE; L; 1EBF; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE +1EC0; L; 1EC1; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE +1EC2; L; 1EC3; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +1EC4; L; 1EC5; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE +1EC6; L; 1EC7; #LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW +1EC8; L; 1EC9; #LATIN CAPITAL LETTER I WITH HOOK ABOVE +1ECA; L; 1ECB; #LATIN CAPITAL LETTER I WITH DOT BELOW +1ECC; L; 1ECD; #LATIN CAPITAL LETTER O WITH DOT BELOW +1ECE; L; 1ECF; #LATIN CAPITAL LETTER O WITH HOOK ABOVE +1ED0; L; 1ED1; #LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED2; L; 1ED3; #LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED4; L; 1ED5; #LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED6; L; 1ED7; #LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +1ED8; L; 1ED9; #LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +1EDA; L; 1EDB; #LATIN CAPITAL LETTER O WITH HORN AND ACUTE +1EDC; L; 1EDD; #LATIN CAPITAL LETTER O WITH HORN AND GRAVE +1EDE; L; 1EDF; #LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE +1EE0; L; 1EE1; #LATIN CAPITAL LETTER O WITH HORN AND TILDE +1EE2; L; 1EE3; #LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW +1EE4; L; 1EE5; #LATIN CAPITAL LETTER U WITH DOT BELOW +1EE6; L; 1EE7; #LATIN CAPITAL LETTER U WITH HOOK ABOVE +1EE8; L; 1EE9; #LATIN CAPITAL LETTER U WITH HORN AND ACUTE +1EEA; L; 1EEB; #LATIN CAPITAL LETTER U WITH HORN AND GRAVE +1EEC; L; 1EED; #LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE +1EEE; L; 1EEF; #LATIN CAPITAL LETTER U WITH HORN AND TILDE +1EF0; L; 1EF1; #LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW +1EF2; L; 1EF3; #LATIN CAPITAL LETTER Y WITH GRAVE +1EF4; L; 1EF5; #LATIN CAPITAL LETTER Y WITH DOT BELOW +1EF6; L; 1EF7; #LATIN CAPITAL LETTER Y WITH HOOK ABOVE +1EF8; L; 1EF9; #LATIN CAPITAL LETTER Y WITH TILDE +1F08; L; 1F00; #GREEK CAPITAL LETTER ALPHA WITH PSILI +1F09; L; 1F01; #GREEK CAPITAL LETTER ALPHA WITH DASIA +1F0A; L; 1F02; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA +1F0B; L; 1F03; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA +1F0C; L; 1F04; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA +1F0D; L; 1F05; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA +1F0E; L; 1F06; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI +1F0F; L; 1F07; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI +1F18; L; 1F10; #GREEK CAPITAL LETTER EPSILON WITH PSILI +1F19; L; 1F11; #GREEK CAPITAL LETTER EPSILON WITH DASIA +1F1A; L; 1F12; #GREEK CAPITAL LETTER EPSILON WITH PSILI AND VARIA +1F1B; L; 1F13; #GREEK CAPITAL LETTER EPSILON WITH DASIA AND VARIA +1F1C; L; 1F14; #GREEK CAPITAL LETTER EPSILON WITH PSILI AND OXIA +1F1D; L; 1F15; #GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F28; L; 1F20; #GREEK CAPITAL LETTER ETA WITH PSILI +1F29; L; 1F21; #GREEK CAPITAL LETTER ETA WITH DASIA +1F2A; L; 1F22; #GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA +1F2B; L; 1F23; #GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA +1F2C; L; 1F24; #GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA +1F2D; L; 1F25; #GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA +1F2E; L; 1F26; #GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI +1F2F; L; 1F27; #GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI +1F38; L; 1F30; #GREEK CAPITAL LETTER IOTA WITH PSILI +1F39; L; 1F31; #GREEK CAPITAL LETTER IOTA WITH DASIA +1F3A; L; 1F32; #GREEK CAPITAL LETTER IOTA WITH PSILI AND VARIA +1F3B; L; 1F33; #GREEK CAPITAL LETTER IOTA WITH DASIA AND VARIA +1F3C; L; 1F34; #GREEK CAPITAL LETTER IOTA WITH PSILI AND OXIA +1F3D; L; 1F35; #GREEK CAPITAL LETTER IOTA WITH DASIA AND OXIA +1F3E; L; 1F36; #GREEK CAPITAL LETTER IOTA WITH PSILI AND PERISPOMENI +1F3F; L; 1F37; #GREEK CAPITAL LETTER IOTA WITH DASIA AND PERISPOMENI +1F48; L; 1F40; #GREEK CAPITAL LETTER OMICRON WITH PSILI +1F49; L; 1F41; #GREEK CAPITAL LETTER OMICRON WITH DASIA +1F4A; L; 1F42; #GREEK CAPITAL LETTER OMICRON WITH PSILI AND VARIA +1F4B; L; 1F43; #GREEK CAPITAL LETTER OMICRON WITH DASIA AND VARIA +1F4C; L; 1F44; #GREEK CAPITAL LETTER OMICRON WITH PSILI AND OXIA +1F4D; L; 1F45; #GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F50; E; 03C5 0313; #GREEK SMALL LETTER UPSILON WITH PSILI +1F52; E; 03C5 0313 0300; #GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA +1F54; E; 03C5 0313 0301; #GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA +1F56; E; 03C5 0313 0342; #GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI +1F59; L; 1F51; #GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B; L; 1F53; #GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D; L; 1F55; #GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F; L; 1F57; #GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F68; L; 1F60; #GREEK CAPITAL LETTER OMEGA WITH PSILI +1F69; L; 1F61; #GREEK CAPITAL LETTER OMEGA WITH DASIA +1F6A; L; 1F62; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA +1F6B; L; 1F63; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA +1F6C; L; 1F64; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA +1F6D; L; 1F65; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA +1F6E; L; 1F66; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI +1F6F; L; 1F67; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI +1F80; E; 1F00 03B9; #GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI +1F81; E; 1F01 03B9; #GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI +1F82; E; 1F02 03B9; #GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1F83; E; 1F03 03B9; #GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1F84; E; 1F04 03B9; #GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1F85; E; 1F05 03B9; #GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1F86; E; 1F06 03B9; #GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1F87; E; 1F07 03B9; #GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F88; E; 1F00 03B9; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI +1F89; E; 1F01 03B9; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI +1F8A; E; 1F02 03B9; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F8B; E; 1F03 03B9; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F8C; E; 1F04 03B9; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F8D; E; 1F05 03B9; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F8E; E; 1F06 03B9; #GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F8F; E; 1F07 03B9; #GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F90; E; 1F20 03B9; #GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI +1F91; E; 1F21 03B9; #GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI +1F92; E; 1F22 03B9; #GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1F93; E; 1F23 03B9; #GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1F94; E; 1F24 03B9; #GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1F95; E; 1F25 03B9; #GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1F96; E; 1F26 03B9; #GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1F97; E; 1F27 03B9; #GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F98; E; 1F20 03B9; #GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI +1F99; E; 1F21 03B9; #GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI +1F9A; E; 1F22 03B9; #GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F9B; E; 1F23 03B9; #GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F9C; E; 1F24 03B9; #GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F9D; E; 1F25 03B9; #GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F9E; E; 1F26 03B9; #GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F9F; E; 1F27 03B9; #GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FA0; E; 1F60 03B9; #GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI +1FA1; E; 1F61 03B9; #GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI +1FA2; E; 1F62 03B9; #GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1FA3; E; 1F63 03B9; #GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1FA4; E; 1F64 03B9; #GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1FA5; E; 1F65 03B9; #GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1FA6; E; 1F66 03B9; #GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1FA7; E; 1F67 03B9; #GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1FA8; E; 1F60 03B9; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI +1FA9; E; 1F61 03B9; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI +1FAA; E; 1F62 03B9; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1FAB; E; 1F63 03B9; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1FAC; E; 1F64 03B9; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1FAD; E; 1F65 03B9; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1FAE; E; 1F66 03B9; #GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1FAF; E; 1F67 03B9; #GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FB2; E; 1F70 03B9; #GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI +1FB3; E; 03B1 03B9; #GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI +1FB4; E; 03AC 03B9; #GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6; E; 03B1 0342; #GREEK SMALL LETTER ALPHA WITH PERISPOMENI +1FB7; E; 03B1 0342 03B9; #GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI +1FB8; L; 1FB0; #GREEK CAPITAL LETTER ALPHA WITH VRACHY +1FB9; L; 1FB1; #GREEK CAPITAL LETTER ALPHA WITH MACRON +1FBA; L; 1F70; #GREEK CAPITAL LETTER ALPHA WITH VARIA +1FBB; L; 1F71; #GREEK CAPITAL LETTER ALPHA WITH OXIA +1FBC; E; 03B1 03B9; #GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBE; E; 03B9; #GREEK PROSGEGRAMMENI +1FC2; E; 1F74 03B9; #GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI +1FC3; E; 03B7 03B9; #GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI +1FC4; E; 03AE 03B9; #GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6; E; 03B7 0342; #GREEK SMALL LETTER ETA WITH PERISPOMENI +1FC7; E; 03B7 0342 03B9; #GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI +1FC8; L; 1F72; #GREEK CAPITAL LETTER EPSILON WITH VARIA +1FC9; L; 1F73; #GREEK CAPITAL LETTER EPSILON WITH OXIA +1FCA; L; 1F74; #GREEK CAPITAL LETTER ETA WITH VARIA +1FCB; L; 1F75; #GREEK CAPITAL LETTER ETA WITH OXIA +1FCC; E; 03B7 03B9; #GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FD2; E; 03B9 0308 0300; #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA +1FD3; E; 03B9 0308 0301; #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6; E; 03B9 0342; #GREEK SMALL LETTER IOTA WITH PERISPOMENI +1FD7; E; 03B9 0308 0342; #GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI +1FD8; L; 1FD0; #GREEK CAPITAL LETTER IOTA WITH VRACHY +1FD9; L; 1FD1; #GREEK CAPITAL LETTER IOTA WITH MACRON +1FDA; L; 1F76; #GREEK CAPITAL LETTER IOTA WITH VARIA +1FDB; L; 1F77; #GREEK CAPITAL LETTER IOTA WITH OXIA +1FE2; E; 03C5 0308 0300; #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA +1FE3; E; 03C5 0308 0301; #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA +1FE4; E; 03C1 0313; #GREEK SMALL LETTER RHO WITH PSILI +1FE6; E; 03C5 0342; #GREEK SMALL LETTER UPSILON WITH PERISPOMENI +1FE7; E; 03C5 0308 0342; #GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI +1FE8; L; 1FE0; #GREEK CAPITAL LETTER UPSILON WITH VRACHY +1FE9; L; 1FE1; #GREEK CAPITAL LETTER UPSILON WITH MACRON +1FEA; L; 1F7A; #GREEK CAPITAL LETTER UPSILON WITH VARIA +1FEB; L; 1F7B; #GREEK CAPITAL LETTER UPSILON WITH OXIA +1FEC; L; 1FE5; #GREEK CAPITAL LETTER RHO WITH DASIA +1FF2; E; 1F7C 03B9; #GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI +1FF3; E; 03C9 03B9; #GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI +1FF4; E; 03CE 03B9; #GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6; E; 03C9 0342; #GREEK SMALL LETTER OMEGA WITH PERISPOMENI +1FF7; E; 03C9 0342 03B9; #GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI +1FF8; L; 1F78; #GREEK CAPITAL LETTER OMICRON WITH VARIA +1FF9; L; 1F79; #GREEK CAPITAL LETTER OMICRON WITH OXIA +1FFA; L; 1F7C; #GREEK CAPITAL LETTER OMEGA WITH VARIA +1FFB; L; 1F7D; #GREEK CAPITAL LETTER OMEGA WITH OXIA +1FFC; E; 03C9 03B9; #GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +2126; L; 03C9; #OHM SIGN +212A; L; 006B; #KELVIN SIGN +212B; L; 00E5; #ANGSTROM SIGN +2160; L; 2170; #ROMAN NUMERAL ONE +2161; L; 2171; #ROMAN NUMERAL TWO +2162; L; 2172; #ROMAN NUMERAL THREE +2163; L; 2173; #ROMAN NUMERAL FOUR +2164; L; 2174; #ROMAN NUMERAL FIVE +2165; L; 2175; #ROMAN NUMERAL SIX +2166; L; 2176; #ROMAN NUMERAL SEVEN +2167; L; 2177; #ROMAN NUMERAL EIGHT +2168; L; 2178; #ROMAN NUMERAL NINE +2169; L; 2179; #ROMAN NUMERAL TEN +216A; L; 217A; #ROMAN NUMERAL ELEVEN +216B; L; 217B; #ROMAN NUMERAL TWELVE +216C; L; 217C; #ROMAN NUMERAL FIFTY +216D; L; 217D; #ROMAN NUMERAL ONE HUNDRED +216E; L; 217E; #ROMAN NUMERAL FIVE HUNDRED +216F; L; 217F; #ROMAN NUMERAL ONE THOUSAND +24B6; L; 24D0; #CIRCLED LATIN CAPITAL LETTER A +24B7; L; 24D1; #CIRCLED LATIN CAPITAL LETTER B +24B8; L; 24D2; #CIRCLED LATIN CAPITAL LETTER C +24B9; L; 24D3; #CIRCLED LATIN CAPITAL LETTER D +24BA; L; 24D4; #CIRCLED LATIN CAPITAL LETTER E +24BB; L; 24D5; #CIRCLED LATIN CAPITAL LETTER F +24BC; L; 24D6; #CIRCLED LATIN CAPITAL LETTER G +24BD; L; 24D7; #CIRCLED LATIN CAPITAL LETTER H +24BE; L; 24D8; #CIRCLED LATIN CAPITAL LETTER I +24BF; L; 24D9; #CIRCLED LATIN CAPITAL LETTER J +24C0; L; 24DA; #CIRCLED LATIN CAPITAL LETTER K +24C1; L; 24DB; #CIRCLED LATIN CAPITAL LETTER L +24C2; L; 24DC; #CIRCLED LATIN CAPITAL LETTER M +24C3; L; 24DD; #CIRCLED LATIN CAPITAL LETTER N +24C4; L; 24DE; #CIRCLED LATIN CAPITAL LETTER O +24C5; L; 24DF; #CIRCLED LATIN CAPITAL LETTER P +24C6; L; 24E0; #CIRCLED LATIN CAPITAL LETTER Q +24C7; L; 24E1; #CIRCLED LATIN CAPITAL LETTER R +24C8; L; 24E2; #CIRCLED LATIN CAPITAL LETTER S +24C9; L; 24E3; #CIRCLED LATIN CAPITAL LETTER T +24CA; L; 24E4; #CIRCLED LATIN CAPITAL LETTER U +24CB; L; 24E5; #CIRCLED LATIN CAPITAL LETTER V +24CC; L; 24E6; #CIRCLED LATIN CAPITAL LETTER W +24CD; L; 24E7; #CIRCLED LATIN CAPITAL LETTER X +24CE; L; 24E8; #CIRCLED LATIN CAPITAL LETTER Y +24CF; L; 24E9; #CIRCLED LATIN CAPITAL LETTER Z +FB00; E; 0066 0066; #LATIN SMALL LIGATURE FF +FB01; E; 0066 0069; #LATIN SMALL LIGATURE FI +FB02; E; 0066 006C; #LATIN SMALL LIGATURE FL +FB03; E; 0066 0066 0069; #LATIN SMALL LIGATURE FFI +FB04; E; 0066 0066 006C; #LATIN SMALL LIGATURE FFL +FB05; E; 0073 0074; #LATIN SMALL LIGATURE LONG S T +FB06; E; 0073 0074; #LATIN SMALL LIGATURE ST +FB13; E; 0574 0576; #ARMENIAN SMALL LIGATURE MEN NOW +FB14; E; 0574 0565; #ARMENIAN SMALL LIGATURE MEN ECH +FB15; E; 0574 056B; #ARMENIAN SMALL LIGATURE MEN INI +FB16; E; 057E 0576; #ARMENIAN SMALL LIGATURE VEW NOW +FB17; E; 0574 056D; #ARMENIAN SMALL LIGATURE MEN XEH +FF21; L; FF41; #FULLWIDTH LATIN CAPITAL LETTER A +FF22; L; FF42; #FULLWIDTH LATIN CAPITAL LETTER B +FF23; L; FF43; #FULLWIDTH LATIN CAPITAL LETTER C +FF24; L; FF44; #FULLWIDTH LATIN CAPITAL LETTER D +FF25; L; FF45; #FULLWIDTH LATIN CAPITAL LETTER E +FF26; L; FF46; #FULLWIDTH LATIN CAPITAL LETTER F +FF27; L; FF47; #FULLWIDTH LATIN CAPITAL LETTER G +FF28; L; FF48; #FULLWIDTH LATIN CAPITAL LETTER H +FF29; L; FF49; #FULLWIDTH LATIN CAPITAL LETTER I +FF2A; L; FF4A; #FULLWIDTH LATIN CAPITAL LETTER J +FF2B; L; FF4B; #FULLWIDTH LATIN CAPITAL LETTER K +FF2C; L; FF4C; #FULLWIDTH LATIN CAPITAL LETTER L +FF2D; L; FF4D; #FULLWIDTH LATIN CAPITAL LETTER M +FF2E; L; FF4E; #FULLWIDTH LATIN CAPITAL LETTER N +FF2F; L; FF4F; #FULLWIDTH LATIN CAPITAL LETTER O +FF30; L; FF50; #FULLWIDTH LATIN CAPITAL LETTER P +FF31; L; FF51; #FULLWIDTH LATIN CAPITAL LETTER Q +FF32; L; FF52; #FULLWIDTH LATIN CAPITAL LETTER R +FF33; L; FF53; #FULLWIDTH LATIN CAPITAL LETTER S +FF34; L; FF54; #FULLWIDTH LATIN CAPITAL LETTER T +FF35; L; FF55; #FULLWIDTH LATIN CAPITAL LETTER U +FF36; L; FF56; #FULLWIDTH LATIN CAPITAL LETTER V +FF37; L; FF57; #FULLWIDTH LATIN CAPITAL LETTER W +FF38; L; FF58; #FULLWIDTH LATIN CAPITAL LETTER X +FF39; L; FF59; #FULLWIDTH LATIN CAPITAL LETTER Y +FF3A; L; FF5A; #FULLWIDTH LATIN CAPITAL LETTER Z + + diff --git a/lib/unicode/Category.pl b/lib/unicode/Category.pl index bffd116..9c81514 100644 --- a/lib/unicode/Category.pl +++ b/lib/unicode/Category.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 001f Cc @@ -1503,4 +1503,6 @@ ffe9 ffec Sm ffed ffee So fff9 fffb Cf fffc fffd So +f0000 ffffd Co +100000 10fffd Co END diff --git a/lib/unicode/CombiningClass.pl b/lib/unicode/CombiningClass.pl index a409498..628b9c6 100644 --- a/lib/unicode/CombiningClass.pl +++ b/lib/unicode/CombiningClass.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0300 0314 230 diff --git a/lib/unicode/CompExcl.txt b/lib/unicode/CompExcl.txt index 5ea46af..53f8467 100644 --- a/lib/unicode/CompExcl.txt +++ b/lib/unicode/CompExcl.txt @@ -1,3 +1,5 @@ +# CompositionExclusions-2.txt +# # Composition Exclusions # This file lists the characters from the UTR #15 Composition Exclusion Table. # @@ -133,8 +135,8 @@ FB4E # HEBREW LETTER PE WITH RAFE # (4) Non-Starter Decompositions # These characters can be derived from the UnicodeData file # by including all characters whose canonical decomposition consists -# of a sequence of characters, the first of which has a canonical -# class of zero. +# of a sequence of characters, the first of which has a non-zero +# combining class. # These characters are simply quoted here for reference. # 0344 COMBINING GREEK DIALYTIKA TONOS diff --git a/lib/unicode/Decomposition.pl b/lib/unicode/Decomposition.pl index ecc30b2..1fe29cd 100644 --- a/lib/unicode/Decomposition.pl +++ b/lib/unicode/Decomposition.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a0 0020 diff --git a/lib/unicode/In/AlphabeticPresentationForms.pl b/lib/unicode/In/AlphabeticPresentationForms.pl index c42e944..a85b9ca 100644 --- a/lib/unicode/In/AlphabeticPresentationForms.pl +++ b/lib/unicode/In/AlphabeticPresentationForms.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FB00 FB4F diff --git a/lib/unicode/In/Arabic.pl b/lib/unicode/In/Arabic.pl index 5010ab7..5fbbbfa 100644 --- a/lib/unicode/In/Arabic.pl +++ b/lib/unicode/In/Arabic.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0600 06FF diff --git a/lib/unicode/In/ArabicPresentationForms-A.pl b/lib/unicode/In/ArabicPresentationForms-A.pl index 6edd74d..62521bb 100644 --- a/lib/unicode/In/ArabicPresentationForms-A.pl +++ b/lib/unicode/In/ArabicPresentationForms-A.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FB50 FDFF diff --git a/lib/unicode/In/ArabicPresentationForms-B.pl b/lib/unicode/In/ArabicPresentationForms-B.pl index 9640739..6b2d447 100644 --- a/lib/unicode/In/ArabicPresentationForms-B.pl +++ b/lib/unicode/In/ArabicPresentationForms-B.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FE70 FEFE diff --git a/lib/unicode/In/Armenian.pl b/lib/unicode/In/Armenian.pl index 19b74ac..d4736a7 100644 --- a/lib/unicode/In/Armenian.pl +++ b/lib/unicode/In/Armenian.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0530 058F diff --git a/lib/unicode/In/Arrows.pl b/lib/unicode/In/Arrows.pl index 7ce4418..a7ef468 100644 --- a/lib/unicode/In/Arrows.pl +++ b/lib/unicode/In/Arrows.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2190 21FF diff --git a/lib/unicode/In/BasicLatin.pl b/lib/unicode/In/BasicLatin.pl index 39987f1..36d6456 100644 --- a/lib/unicode/In/BasicLatin.pl +++ b/lib/unicode/In/BasicLatin.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 007F diff --git a/lib/unicode/In/Bengali.pl b/lib/unicode/In/Bengali.pl index c0a47d3..07dc6ac 100644 --- a/lib/unicode/In/Bengali.pl +++ b/lib/unicode/In/Bengali.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0980 09FF diff --git a/lib/unicode/In/BlockElements.pl b/lib/unicode/In/BlockElements.pl index e96e64f..495629b 100644 --- a/lib/unicode/In/BlockElements.pl +++ b/lib/unicode/In/BlockElements.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2580 259F diff --git a/lib/unicode/In/Bopomofo.pl b/lib/unicode/In/Bopomofo.pl index 5535606..3dbf73a 100644 --- a/lib/unicode/In/Bopomofo.pl +++ b/lib/unicode/In/Bopomofo.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3100 312F diff --git a/lib/unicode/In/BopomofoExtended.pl b/lib/unicode/In/BopomofoExtended.pl index d0ee43a..f2ca6de 100644 --- a/lib/unicode/In/BopomofoExtended.pl +++ b/lib/unicode/In/BopomofoExtended.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 31A0 31BF diff --git a/lib/unicode/In/BoxDrawing.pl b/lib/unicode/In/BoxDrawing.pl index d580199..a3cd897 100644 --- a/lib/unicode/In/BoxDrawing.pl +++ b/lib/unicode/In/BoxDrawing.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2500 257F diff --git a/lib/unicode/In/BraillePatterns.pl b/lib/unicode/In/BraillePatterns.pl index e5c9e4c..58afc05 100644 --- a/lib/unicode/In/BraillePatterns.pl +++ b/lib/unicode/In/BraillePatterns.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2800 28FF diff --git a/lib/unicode/In/CJKCompatibility.pl b/lib/unicode/In/CJKCompatibility.pl index 07ab8ed..793520f 100644 --- a/lib/unicode/In/CJKCompatibility.pl +++ b/lib/unicode/In/CJKCompatibility.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3300 33FF diff --git a/lib/unicode/In/CJKCompatibilityForms.pl b/lib/unicode/In/CJKCompatibilityForms.pl index 122ccd7..a9ba270 100644 --- a/lib/unicode/In/CJKCompatibilityForms.pl +++ b/lib/unicode/In/CJKCompatibilityForms.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FE30 FE4F diff --git a/lib/unicode/In/CJKCompatibilityIdeographs.pl b/lib/unicode/In/CJKCompatibilityIdeographs.pl index 59c8e5d..d841bc5 100644 --- a/lib/unicode/In/CJKCompatibilityIdeographs.pl +++ b/lib/unicode/In/CJKCompatibilityIdeographs.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; F900 FAFF diff --git a/lib/unicode/In/CJKRadicalsSupplement.pl b/lib/unicode/In/CJKRadicalsSupplement.pl index d4c0c82..2d13707 100644 --- a/lib/unicode/In/CJKRadicalsSupplement.pl +++ b/lib/unicode/In/CJKRadicalsSupplement.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2E80 2EFF diff --git a/lib/unicode/In/CJKSymbolsandPunctuation.pl b/lib/unicode/In/CJKSymbolsandPunctuation.pl index 24ecc37..ca525ae 100644 --- a/lib/unicode/In/CJKSymbolsandPunctuation.pl +++ b/lib/unicode/In/CJKSymbolsandPunctuation.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3000 303F diff --git a/lib/unicode/In/CJKUnifiedIdeographs.pl b/lib/unicode/In/CJKUnifiedIdeographs.pl index 351cf74..729f4c6 100644 --- a/lib/unicode/In/CJKUnifiedIdeographs.pl +++ b/lib/unicode/In/CJKUnifiedIdeographs.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 4E00 9FFF diff --git a/lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl b/lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl index 012f54c..e92f091 100644 --- a/lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl +++ b/lib/unicode/In/CJKUnifiedIdeographsExtensionA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3400 4DB5 diff --git a/lib/unicode/In/Cherokee.pl b/lib/unicode/In/Cherokee.pl index 10cae1a..1e9ad74 100644 --- a/lib/unicode/In/Cherokee.pl +++ b/lib/unicode/In/Cherokee.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 13A0 13FF diff --git a/lib/unicode/In/CombiningDiacriticalMarks.pl b/lib/unicode/In/CombiningDiacriticalMarks.pl index a32f974..d3a45d4 100644 --- a/lib/unicode/In/CombiningDiacriticalMarks.pl +++ b/lib/unicode/In/CombiningDiacriticalMarks.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0300 036F diff --git a/lib/unicode/In/CombiningHalfMarks.pl b/lib/unicode/In/CombiningHalfMarks.pl index 100471b..4f0a573 100644 --- a/lib/unicode/In/CombiningHalfMarks.pl +++ b/lib/unicode/In/CombiningHalfMarks.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FE20 FE2F diff --git a/lib/unicode/In/CombiningMarksforSymbols.pl b/lib/unicode/In/CombiningMarksforSymbols.pl index f45e7e0..9dde706 100644 --- a/lib/unicode/In/CombiningMarksforSymbols.pl +++ b/lib/unicode/In/CombiningMarksforSymbols.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 20D0 20FF diff --git a/lib/unicode/In/ControlPictures.pl b/lib/unicode/In/ControlPictures.pl index 77a759f..78113e8 100644 --- a/lib/unicode/In/ControlPictures.pl +++ b/lib/unicode/In/ControlPictures.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2400 243F diff --git a/lib/unicode/In/CurrencySymbols.pl b/lib/unicode/In/CurrencySymbols.pl index 567ae97..8cbc160 100644 --- a/lib/unicode/In/CurrencySymbols.pl +++ b/lib/unicode/In/CurrencySymbols.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 20A0 20CF diff --git a/lib/unicode/In/Cyrillic.pl b/lib/unicode/In/Cyrillic.pl index 9ca104c..f057731 100644 --- a/lib/unicode/In/Cyrillic.pl +++ b/lib/unicode/In/Cyrillic.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0400 04FF diff --git a/lib/unicode/In/Devanagari.pl b/lib/unicode/In/Devanagari.pl index 61372b5..c99eff1 100644 --- a/lib/unicode/In/Devanagari.pl +++ b/lib/unicode/In/Devanagari.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0900 097F diff --git a/lib/unicode/In/Dingbats.pl b/lib/unicode/In/Dingbats.pl index 0f820ca..1bbb102 100644 --- a/lib/unicode/In/Dingbats.pl +++ b/lib/unicode/In/Dingbats.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2700 27BF diff --git a/lib/unicode/In/EnclosedAlphanumerics.pl b/lib/unicode/In/EnclosedAlphanumerics.pl index de52aa8..46b4cf5 100644 --- a/lib/unicode/In/EnclosedAlphanumerics.pl +++ b/lib/unicode/In/EnclosedAlphanumerics.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2460 24FF diff --git a/lib/unicode/In/EnclosedCJKLettersandMonths.pl b/lib/unicode/In/EnclosedCJKLettersandMonths.pl index e4de0e0..da5a7a1 100644 --- a/lib/unicode/In/EnclosedCJKLettersandMonths.pl +++ b/lib/unicode/In/EnclosedCJKLettersandMonths.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3200 32FF diff --git a/lib/unicode/In/Ethiopic.pl b/lib/unicode/In/Ethiopic.pl index 13c3090..5b472c4 100644 --- a/lib/unicode/In/Ethiopic.pl +++ b/lib/unicode/In/Ethiopic.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1200 137F diff --git a/lib/unicode/In/GeneralPunctuation.pl b/lib/unicode/In/GeneralPunctuation.pl index 81c7699..aa82c30 100644 --- a/lib/unicode/In/GeneralPunctuation.pl +++ b/lib/unicode/In/GeneralPunctuation.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2000 206F diff --git a/lib/unicode/In/GeometricShapes.pl b/lib/unicode/In/GeometricShapes.pl index 170422d..6cf8ea7 100644 --- a/lib/unicode/In/GeometricShapes.pl +++ b/lib/unicode/In/GeometricShapes.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 25A0 25FF diff --git a/lib/unicode/In/Georgian.pl b/lib/unicode/In/Georgian.pl index 773ed15..493f570 100644 --- a/lib/unicode/In/Georgian.pl +++ b/lib/unicode/In/Georgian.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 10A0 10FF diff --git a/lib/unicode/In/Greek.pl b/lib/unicode/In/Greek.pl index ff753d1..ac4bbee 100644 --- a/lib/unicode/In/Greek.pl +++ b/lib/unicode/In/Greek.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0370 03FF diff --git a/lib/unicode/In/GreekExtended.pl b/lib/unicode/In/GreekExtended.pl index b8f02e7..acd43be 100644 --- a/lib/unicode/In/GreekExtended.pl +++ b/lib/unicode/In/GreekExtended.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1F00 1FFF diff --git a/lib/unicode/In/Gujarati.pl b/lib/unicode/In/Gujarati.pl index ff6c650..0e3c8e9 100644 --- a/lib/unicode/In/Gujarati.pl +++ b/lib/unicode/In/Gujarati.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0A80 0AFF diff --git a/lib/unicode/In/Gurmukhi.pl b/lib/unicode/In/Gurmukhi.pl index b888df6..32ff239 100644 --- a/lib/unicode/In/Gurmukhi.pl +++ b/lib/unicode/In/Gurmukhi.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0A00 0A7F diff --git a/lib/unicode/In/HalfwidthandFullwidthForms.pl b/lib/unicode/In/HalfwidthandFullwidthForms.pl index e452653..fd3ba32 100644 --- a/lib/unicode/In/HalfwidthandFullwidthForms.pl +++ b/lib/unicode/In/HalfwidthandFullwidthForms.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FF00 FFEF diff --git a/lib/unicode/In/HangulCompatibilityJamo.pl b/lib/unicode/In/HangulCompatibilityJamo.pl index c15379f..744e572 100644 --- a/lib/unicode/In/HangulCompatibilityJamo.pl +++ b/lib/unicode/In/HangulCompatibilityJamo.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3130 318F diff --git a/lib/unicode/In/HangulJamo.pl b/lib/unicode/In/HangulJamo.pl index c329b54..a1d1c67 100644 --- a/lib/unicode/In/HangulJamo.pl +++ b/lib/unicode/In/HangulJamo.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1100 11FF diff --git a/lib/unicode/In/HangulSyllables.pl b/lib/unicode/In/HangulSyllables.pl index 7d91a36..80cd4a4 100644 --- a/lib/unicode/In/HangulSyllables.pl +++ b/lib/unicode/In/HangulSyllables.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; AC00 D7A3 diff --git a/lib/unicode/In/Hebrew.pl b/lib/unicode/In/Hebrew.pl index abe7b9e..2e29a28 100644 --- a/lib/unicode/In/Hebrew.pl +++ b/lib/unicode/In/Hebrew.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0590 05FF diff --git a/lib/unicode/In/HighPrivateUseSurrogates.pl b/lib/unicode/In/HighPrivateUseSurrogates.pl index 6ed7ac9..0e1320d 100644 --- a/lib/unicode/In/HighPrivateUseSurrogates.pl +++ b/lib/unicode/In/HighPrivateUseSurrogates.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; DB80 DBFF diff --git a/lib/unicode/In/HighSurrogates.pl b/lib/unicode/In/HighSurrogates.pl index 924a0c9..6acc6c4 100644 --- a/lib/unicode/In/HighSurrogates.pl +++ b/lib/unicode/In/HighSurrogates.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; D800 DB7F diff --git a/lib/unicode/In/Hiragana.pl b/lib/unicode/In/Hiragana.pl index 7a65302..5905fe9 100644 --- a/lib/unicode/In/Hiragana.pl +++ b/lib/unicode/In/Hiragana.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3040 309F diff --git a/lib/unicode/In/IPAExtensions.pl b/lib/unicode/In/IPAExtensions.pl index 20906d6..5365373 100644 --- a/lib/unicode/In/IPAExtensions.pl +++ b/lib/unicode/In/IPAExtensions.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0250 02AF diff --git a/lib/unicode/In/IdeographicDescriptionCharacters.pl b/lib/unicode/In/IdeographicDescriptionCharacters.pl index 4baae88..dafb5b4 100644 --- a/lib/unicode/In/IdeographicDescriptionCharacters.pl +++ b/lib/unicode/In/IdeographicDescriptionCharacters.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2FF0 2FFF diff --git a/lib/unicode/In/Kanbun.pl b/lib/unicode/In/Kanbun.pl index 57d6bd2..9ad03a6 100644 --- a/lib/unicode/In/Kanbun.pl +++ b/lib/unicode/In/Kanbun.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3190 319F diff --git a/lib/unicode/In/KangxiRadicals.pl b/lib/unicode/In/KangxiRadicals.pl index d26fd6c..165398c 100644 --- a/lib/unicode/In/KangxiRadicals.pl +++ b/lib/unicode/In/KangxiRadicals.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2F00 2FDF diff --git a/lib/unicode/In/Kannada.pl b/lib/unicode/In/Kannada.pl index 109197a..a679445 100644 --- a/lib/unicode/In/Kannada.pl +++ b/lib/unicode/In/Kannada.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0C80 0CFF diff --git a/lib/unicode/In/Katakana.pl b/lib/unicode/In/Katakana.pl index 93bd5a0..2976d25 100644 --- a/lib/unicode/In/Katakana.pl +++ b/lib/unicode/In/Katakana.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 30A0 30FF diff --git a/lib/unicode/In/Khmer.pl b/lib/unicode/In/Khmer.pl index f3e8685..6a85224 100644 --- a/lib/unicode/In/Khmer.pl +++ b/lib/unicode/In/Khmer.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1780 17FF diff --git a/lib/unicode/In/Lao.pl b/lib/unicode/In/Lao.pl index 41ff11f..fdddd86 100644 --- a/lib/unicode/In/Lao.pl +++ b/lib/unicode/In/Lao.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0E80 0EFF diff --git a/lib/unicode/In/Latin-1Supplement.pl b/lib/unicode/In/Latin-1Supplement.pl index 1b252eb..6a901fb 100644 --- a/lib/unicode/In/Latin-1Supplement.pl +++ b/lib/unicode/In/Latin-1Supplement.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0080 00FF diff --git a/lib/unicode/In/LatinExtended-A.pl b/lib/unicode/In/LatinExtended-A.pl index b8be987..a042350 100644 --- a/lib/unicode/In/LatinExtended-A.pl +++ b/lib/unicode/In/LatinExtended-A.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0100 017F diff --git a/lib/unicode/In/LatinExtended-B.pl b/lib/unicode/In/LatinExtended-B.pl index b9aff43..b7106c6 100644 --- a/lib/unicode/In/LatinExtended-B.pl +++ b/lib/unicode/In/LatinExtended-B.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0180 024F diff --git a/lib/unicode/In/LatinExtendedAdditional.pl b/lib/unicode/In/LatinExtendedAdditional.pl index d309e90..e17cc3d 100644 --- a/lib/unicode/In/LatinExtendedAdditional.pl +++ b/lib/unicode/In/LatinExtendedAdditional.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1E00 1EFF diff --git a/lib/unicode/In/LetterlikeSymbols.pl b/lib/unicode/In/LetterlikeSymbols.pl index 1768740..c2249a7 100644 --- a/lib/unicode/In/LetterlikeSymbols.pl +++ b/lib/unicode/In/LetterlikeSymbols.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2100 214F diff --git a/lib/unicode/In/LowSurrogates.pl b/lib/unicode/In/LowSurrogates.pl index 752b264..025bd13 100644 --- a/lib/unicode/In/LowSurrogates.pl +++ b/lib/unicode/In/LowSurrogates.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; DC00 DFFF diff --git a/lib/unicode/In/Malayalam.pl b/lib/unicode/In/Malayalam.pl index 8fb57cd..5a01d40 100644 --- a/lib/unicode/In/Malayalam.pl +++ b/lib/unicode/In/Malayalam.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0D00 0D7F diff --git a/lib/unicode/In/MathematicalOperators.pl b/lib/unicode/In/MathematicalOperators.pl index 055f19e..8b45e18 100644 --- a/lib/unicode/In/MathematicalOperators.pl +++ b/lib/unicode/In/MathematicalOperators.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2200 22FF diff --git a/lib/unicode/In/MiscellaneousSymbols.pl b/lib/unicode/In/MiscellaneousSymbols.pl index 9dcdd26..cc5b02f 100644 --- a/lib/unicode/In/MiscellaneousSymbols.pl +++ b/lib/unicode/In/MiscellaneousSymbols.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2600 26FF diff --git a/lib/unicode/In/MiscellaneousTechnical.pl b/lib/unicode/In/MiscellaneousTechnical.pl index 370c00f..a1058a0 100644 --- a/lib/unicode/In/MiscellaneousTechnical.pl +++ b/lib/unicode/In/MiscellaneousTechnical.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2300 23FF diff --git a/lib/unicode/In/Mongolian.pl b/lib/unicode/In/Mongolian.pl index 394014d..98a4914 100644 --- a/lib/unicode/In/Mongolian.pl +++ b/lib/unicode/In/Mongolian.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1800 18AF diff --git a/lib/unicode/In/Myanmar.pl b/lib/unicode/In/Myanmar.pl index 4b3f318..3aa2f41 100644 --- a/lib/unicode/In/Myanmar.pl +++ b/lib/unicode/In/Myanmar.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1000 109F diff --git a/lib/unicode/In/NumberForms.pl b/lib/unicode/In/NumberForms.pl index d33ece0..2a606a6 100644 --- a/lib/unicode/In/NumberForms.pl +++ b/lib/unicode/In/NumberForms.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2150 218F diff --git a/lib/unicode/In/Ogham.pl b/lib/unicode/In/Ogham.pl index e097d90..de320a9 100644 --- a/lib/unicode/In/Ogham.pl +++ b/lib/unicode/In/Ogham.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1680 169F diff --git a/lib/unicode/In/OpticalCharacterRecognition.pl b/lib/unicode/In/OpticalCharacterRecognition.pl index be1d981..7f0aff8 100644 --- a/lib/unicode/In/OpticalCharacterRecognition.pl +++ b/lib/unicode/In/OpticalCharacterRecognition.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2440 245F diff --git a/lib/unicode/In/Oriya.pl b/lib/unicode/In/Oriya.pl index 5a680f6..771a245 100644 --- a/lib/unicode/In/Oriya.pl +++ b/lib/unicode/In/Oriya.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0B00 0B7F diff --git a/lib/unicode/In/PrivateUse.pl b/lib/unicode/In/PrivateUse.pl index 0c118f4..0b0c004 100644 --- a/lib/unicode/In/PrivateUse.pl +++ b/lib/unicode/In/PrivateUse.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; E000 F8FF diff --git a/lib/unicode/In/Runic.pl b/lib/unicode/In/Runic.pl index 0bd42df..52ca7aa 100644 --- a/lib/unicode/In/Runic.pl +++ b/lib/unicode/In/Runic.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 16A0 16FF diff --git a/lib/unicode/In/Sinhala.pl b/lib/unicode/In/Sinhala.pl index 37e007c..5a892fd 100644 --- a/lib/unicode/In/Sinhala.pl +++ b/lib/unicode/In/Sinhala.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0D80 0DFF diff --git a/lib/unicode/In/SmallFormVariants.pl b/lib/unicode/In/SmallFormVariants.pl index 736415e..148e6e8 100644 --- a/lib/unicode/In/SmallFormVariants.pl +++ b/lib/unicode/In/SmallFormVariants.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FE50 FE6F diff --git a/lib/unicode/In/SpacingModifierLetters.pl b/lib/unicode/In/SpacingModifierLetters.pl index 6e9cdf0..0e31fea 100644 --- a/lib/unicode/In/SpacingModifierLetters.pl +++ b/lib/unicode/In/SpacingModifierLetters.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 02B0 02FF diff --git a/lib/unicode/In/Specials.pl b/lib/unicode/In/Specials.pl index f9f730f..03f69a3 100644 --- a/lib/unicode/In/Specials.pl +++ b/lib/unicode/In/Specials.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; FFF0 FFFD diff --git a/lib/unicode/In/SuperscriptsandSubscripts.pl b/lib/unicode/In/SuperscriptsandSubscripts.pl index efcec0b..b0f90cd 100644 --- a/lib/unicode/In/SuperscriptsandSubscripts.pl +++ b/lib/unicode/In/SuperscriptsandSubscripts.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2070 209F diff --git a/lib/unicode/In/Syriac.pl b/lib/unicode/In/Syriac.pl index 7c81fb6..f85f1a9 100644 --- a/lib/unicode/In/Syriac.pl +++ b/lib/unicode/In/Syriac.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0700 074F diff --git a/lib/unicode/In/Tamil.pl b/lib/unicode/In/Tamil.pl index e65ed2f..71fa923 100644 --- a/lib/unicode/In/Tamil.pl +++ b/lib/unicode/In/Tamil.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0B80 0BFF diff --git a/lib/unicode/In/Telugu.pl b/lib/unicode/In/Telugu.pl index d5ed236..ff09b1e 100644 --- a/lib/unicode/In/Telugu.pl +++ b/lib/unicode/In/Telugu.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0C00 0C7F diff --git a/lib/unicode/In/Thaana.pl b/lib/unicode/In/Thaana.pl index 361bd4d..f88768c 100644 --- a/lib/unicode/In/Thaana.pl +++ b/lib/unicode/In/Thaana.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0780 07BF diff --git a/lib/unicode/In/Thai.pl b/lib/unicode/In/Thai.pl index 3376de4..e77c0c5 100644 --- a/lib/unicode/In/Thai.pl +++ b/lib/unicode/In/Thai.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0E00 0E7F diff --git a/lib/unicode/In/Tibetan.pl b/lib/unicode/In/Tibetan.pl index 50837ad..35436b3 100644 --- a/lib/unicode/In/Tibetan.pl +++ b/lib/unicode/In/Tibetan.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0F00 0FFF diff --git a/lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl b/lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl index ad4eb27..83c6a78 100644 --- a/lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl +++ b/lib/unicode/In/UnifiedCanadianAboriginalSyllabics.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1400 167F diff --git a/lib/unicode/In/YiRadicals.pl b/lib/unicode/In/YiRadicals.pl index f25c695..7350871 100644 --- a/lib/unicode/In/YiRadicals.pl +++ b/lib/unicode/In/YiRadicals.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; A490 A4CF diff --git a/lib/unicode/In/YiSyllables.pl b/lib/unicode/In/YiSyllables.pl index f4e3a8b..baa038e 100644 --- a/lib/unicode/In/YiSyllables.pl +++ b/lib/unicode/In/YiSyllables.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; A000 A48F diff --git a/lib/unicode/Is/ASCII.pl b/lib/unicode/Is/ASCII.pl index 63f95ae..1434a55 100644 --- a/lib/unicode/Is/ASCII.pl +++ b/lib/unicode/Is/ASCII.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 007f diff --git a/lib/unicode/Is/Alnum.pl b/lib/unicode/Is/Alnum.pl index 203860b..94f9a5c 100644 --- a/lib/unicode/Is/Alnum.pl +++ b/lib/unicode/Is/Alnum.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/Alpha.pl b/lib/unicode/Is/Alpha.pl index 90020b8..de5046f 100644 --- a/lib/unicode/Is/Alpha.pl +++ b/lib/unicode/Is/Alpha.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0041 005a diff --git a/lib/unicode/Is/BidiAL.pl b/lib/unicode/Is/BidiAL.pl index e04f2f5..a8d43b8 100644 --- a/lib/unicode/Is/BidiAL.pl +++ b/lib/unicode/Is/BidiAL.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 061b diff --git a/lib/unicode/Is/BidiAN.pl b/lib/unicode/Is/BidiAN.pl index 4a71ae5..4519c6d 100644 --- a/lib/unicode/Is/BidiAN.pl +++ b/lib/unicode/Is/BidiAN.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0660 0669 diff --git a/lib/unicode/Is/BidiB.pl b/lib/unicode/Is/BidiB.pl index e4ba165..33bdb45 100644 --- a/lib/unicode/Is/BidiB.pl +++ b/lib/unicode/Is/BidiB.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 000a diff --git a/lib/unicode/Is/BidiBN.pl b/lib/unicode/Is/BidiBN.pl index 795a4a9..75b8871 100644 --- a/lib/unicode/Is/BidiBN.pl +++ b/lib/unicode/Is/BidiBN.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 0008 diff --git a/lib/unicode/Is/BidiCS.pl b/lib/unicode/Is/BidiCS.pl index f8d037d..e217653 100644 --- a/lib/unicode/Is/BidiCS.pl +++ b/lib/unicode/Is/BidiCS.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002c diff --git a/lib/unicode/Is/BidiEN.pl b/lib/unicode/Is/BidiEN.pl index d63270a..113de87 100644 --- a/lib/unicode/Is/BidiEN.pl +++ b/lib/unicode/Is/BidiEN.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/BidiES.pl b/lib/unicode/Is/BidiES.pl index 5a1a36a..d1cd305 100644 --- a/lib/unicode/Is/BidiES.pl +++ b/lib/unicode/Is/BidiES.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002f diff --git a/lib/unicode/Is/BidiET.pl b/lib/unicode/Is/BidiET.pl index 5e7af2b..0a66fa8 100644 --- a/lib/unicode/Is/BidiET.pl +++ b/lib/unicode/Is/BidiET.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0023 0025 diff --git a/lib/unicode/Is/BidiL.pl b/lib/unicode/Is/BidiL.pl index 8dc4ca8..a08d8b8 100644 --- a/lib/unicode/Is/BidiL.pl +++ b/lib/unicode/Is/BidiL.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0041 005a @@ -320,4 +320,6 @@ ffc2 ffc7 ffca ffcf ffd2 ffd7 ffda ffdc +f0000 ffffd +100000 10fffd END diff --git a/lib/unicode/Is/BidiLRE.pl b/lib/unicode/Is/BidiLRE.pl index ef2a6e4..2570421 100644 --- a/lib/unicode/Is/BidiLRE.pl +++ b/lib/unicode/Is/BidiLRE.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 202a diff --git a/lib/unicode/Is/BidiLRO.pl b/lib/unicode/Is/BidiLRO.pl index e9958c4..721a223 100644 --- a/lib/unicode/Is/BidiLRO.pl +++ b/lib/unicode/Is/BidiLRO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 202d diff --git a/lib/unicode/Is/BidiNSM.pl b/lib/unicode/Is/BidiNSM.pl index 191bc05..a5c3af4 100644 --- a/lib/unicode/Is/BidiNSM.pl +++ b/lib/unicode/Is/BidiNSM.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0300 034e diff --git a/lib/unicode/Is/BidiON.pl b/lib/unicode/Is/BidiON.pl index bde00ff..ec0f18f 100644 --- a/lib/unicode/Is/BidiON.pl +++ b/lib/unicode/Is/BidiON.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0021 0022 diff --git a/lib/unicode/Is/BidiPDF.pl b/lib/unicode/Is/BidiPDF.pl index 4a3eedd..20e3d9d 100644 --- a/lib/unicode/Is/BidiPDF.pl +++ b/lib/unicode/Is/BidiPDF.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 202c diff --git a/lib/unicode/Is/BidiR.pl b/lib/unicode/Is/BidiR.pl index fccc1f6..9f776ae 100644 --- a/lib/unicode/Is/BidiR.pl +++ b/lib/unicode/Is/BidiR.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 05be diff --git a/lib/unicode/Is/BidiRLE.pl b/lib/unicode/Is/BidiRLE.pl index d789246..eaf7ab7 100644 --- a/lib/unicode/Is/BidiRLE.pl +++ b/lib/unicode/Is/BidiRLE.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 202b diff --git a/lib/unicode/Is/BidiRLO.pl b/lib/unicode/Is/BidiRLO.pl index fcb81ac..8974dd9 100644 --- a/lib/unicode/Is/BidiRLO.pl +++ b/lib/unicode/Is/BidiRLO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 202e diff --git a/lib/unicode/Is/BidiS.pl b/lib/unicode/Is/BidiS.pl index b28b331..ac2655d 100644 --- a/lib/unicode/Is/BidiS.pl +++ b/lib/unicode/Is/BidiS.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0009 diff --git a/lib/unicode/Is/BidiWS.pl b/lib/unicode/Is/BidiWS.pl index 25d8b8f..ebd24e5 100644 --- a/lib/unicode/Is/BidiWS.pl +++ b/lib/unicode/Is/BidiWS.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 000c diff --git a/lib/unicode/Is/C.pl b/lib/unicode/Is/C.pl index 0db83c4..51e4ede 100644 --- a/lib/unicode/Is/C.pl +++ b/lib/unicode/Is/C.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 001f @@ -15,4 +15,6 @@ dc00 dfff e000 f8ff feff fff9 fffb +f0000 ffffd +100000 10fffd END diff --git a/lib/unicode/Is/Cc.pl b/lib/unicode/Is/Cc.pl index d7184e3..6b97adc 100644 --- a/lib/unicode/Is/Cc.pl +++ b/lib/unicode/Is/Cc.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 001f diff --git a/lib/unicode/Is/Cf.pl b/lib/unicode/Is/Cf.pl index 896c3e6..cef5ac4 100644 --- a/lib/unicode/Is/Cf.pl +++ b/lib/unicode/Is/Cf.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 070f diff --git a/lib/unicode/Is/Cn.pl b/lib/unicode/Is/Cn.pl index 3c68615..fb75e87 100644 --- a/lib/unicode/Is/Cn.pl +++ b/lib/unicode/Is/Cn.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0220 0221 @@ -356,4 +356,18 @@ ffd8 ffd9 ffdd ffdf ffe7 ffef fff8 +10000 1fffd +20000 2fffd +30000 3fffd +40000 4fffd +50000 5fffd +60000 6fffd +70000 7fffd +80000 8fffd +90000 9fffd +a0000 afffd +b0000 bfffd +c0000 cfffd +d0000 dfffd +e0000 efffd END diff --git a/lib/unicode/Is/Cntrl.pl b/lib/unicode/Is/Cntrl.pl index 0db83c4..51e4ede 100644 --- a/lib/unicode/Is/Cntrl.pl +++ b/lib/unicode/Is/Cntrl.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 001f @@ -15,4 +15,6 @@ dc00 dfff e000 f8ff feff fff9 fffb +f0000 ffffd +100000 10fffd END diff --git a/lib/unicode/Is/Co.pl b/lib/unicode/Is/Co.pl index c456d33..d077fd2 100644 --- a/lib/unicode/Is/Co.pl +++ b/lib/unicode/Is/Co.pl @@ -1,6 +1,8 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; e000 f8ff +f0000 ffffd +100000 10fffd END diff --git a/lib/unicode/Is/Cs.pl b/lib/unicode/Is/Cs.pl index 8888fb5..33e1dac 100644 --- a/lib/unicode/Is/Cs.pl +++ b/lib/unicode/Is/Cs.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; d800 db7f diff --git a/lib/unicode/Is/DCcircle.pl b/lib/unicode/Is/DCcircle.pl index 4c47b28..82c9edc 100644 --- a/lib/unicode/Is/DCcircle.pl +++ b/lib/unicode/Is/DCcircle.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2460 2473 diff --git a/lib/unicode/Is/DCcompat.pl b/lib/unicode/Is/DCcompat.pl index 75d2569..5ae2b6a 100644 --- a/lib/unicode/Is/DCcompat.pl +++ b/lib/unicode/Is/DCcompat.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a8 diff --git a/lib/unicode/Is/DCfinal.pl b/lib/unicode/Is/DCfinal.pl index 33fbf6a..3c81bcc 100644 --- a/lib/unicode/Is/DCfinal.pl +++ b/lib/unicode/Is/DCfinal.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fb51 diff --git a/lib/unicode/Is/DCfont.pl b/lib/unicode/Is/DCfont.pl index c72234b..7feff18 100644 --- a/lib/unicode/Is/DCfont.pl +++ b/lib/unicode/Is/DCfont.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2102 diff --git a/lib/unicode/Is/DCfraction.pl b/lib/unicode/Is/DCfraction.pl index fc2dd67..abac9d9 100644 --- a/lib/unicode/Is/DCfraction.pl +++ b/lib/unicode/Is/DCfraction.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00bc 00be diff --git a/lib/unicode/Is/DCinital.pl b/lib/unicode/Is/DCinital.pl index 2c9cf47..8778a75 100644 --- a/lib/unicode/Is/DCinital.pl +++ b/lib/unicode/Is/DCinital.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fb55 diff --git a/lib/unicode/Is/DCinitial.pl b/lib/unicode/Is/DCinitial.pl index 0145b7d..c6d7802 100644 --- a/lib/unicode/Is/DCinitial.pl +++ b/lib/unicode/Is/DCinitial.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fb54 diff --git a/lib/unicode/Is/DCisolated.pl b/lib/unicode/Is/DCisolated.pl index cc8541e..e4e24f7 100644 --- a/lib/unicode/Is/DCisolated.pl +++ b/lib/unicode/Is/DCisolated.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fb50 diff --git a/lib/unicode/Is/DCnarrow.pl b/lib/unicode/Is/DCnarrow.pl index 9417de1..7887452 100644 --- a/lib/unicode/Is/DCnarrow.pl +++ b/lib/unicode/Is/DCnarrow.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; ff61 ffbe diff --git a/lib/unicode/Is/DCnoBreak.pl b/lib/unicode/Is/DCnoBreak.pl index 1fd9e87..18c0105 100644 --- a/lib/unicode/Is/DCnoBreak.pl +++ b/lib/unicode/Is/DCnoBreak.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a0 diff --git a/lib/unicode/Is/DCsmall.pl b/lib/unicode/Is/DCsmall.pl index f6c8069..3a37931 100644 --- a/lib/unicode/Is/DCsmall.pl +++ b/lib/unicode/Is/DCsmall.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fe50 fe52 diff --git a/lib/unicode/Is/DCsquare.pl b/lib/unicode/Is/DCsquare.pl index b55fdd9..f27993d 100644 --- a/lib/unicode/Is/DCsquare.pl +++ b/lib/unicode/Is/DCsquare.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3300 3357 diff --git a/lib/unicode/Is/DCsub.pl b/lib/unicode/Is/DCsub.pl index 98c4dfa..f709a22 100644 --- a/lib/unicode/Is/DCsub.pl +++ b/lib/unicode/Is/DCsub.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2080 208e diff --git a/lib/unicode/Is/DCsuper.pl b/lib/unicode/Is/DCsuper.pl index 865a26d..1e6a0c5 100644 --- a/lib/unicode/Is/DCsuper.pl +++ b/lib/unicode/Is/DCsuper.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00aa diff --git a/lib/unicode/Is/DCvertical.pl b/lib/unicode/Is/DCvertical.pl index 5d55483..33b9feb 100644 --- a/lib/unicode/Is/DCvertical.pl +++ b/lib/unicode/Is/DCvertical.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fe30 fe44 diff --git a/lib/unicode/Is/DCwide.pl b/lib/unicode/Is/DCwide.pl index 09dae19..afe1e06 100644 --- a/lib/unicode/Is/DCwide.pl +++ b/lib/unicode/Is/DCwide.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3000 diff --git a/lib/unicode/Is/DecoCanon.pl b/lib/unicode/Is/DecoCanon.pl index c5a59f6..57c167b 100644 --- a/lib/unicode/Is/DecoCanon.pl +++ b/lib/unicode/Is/DecoCanon.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00c0 00c5 diff --git a/lib/unicode/Is/DecoCompat.pl b/lib/unicode/Is/DecoCompat.pl index 43d34fc..940d956 100644 --- a/lib/unicode/Is/DecoCompat.pl +++ b/lib/unicode/Is/DecoCompat.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a0 diff --git a/lib/unicode/Is/Digit.pl b/lib/unicode/Is/Digit.pl index 2ab8156..259bb89 100644 --- a/lib/unicode/Is/Digit.pl +++ b/lib/unicode/Is/Digit.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/Graph.pl b/lib/unicode/Is/Graph.pl index 156f171..40d3506 100644 --- a/lib/unicode/Is/Graph.pl +++ b/lib/unicode/Is/Graph.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0021 007e diff --git a/lib/unicode/Is/L.pl b/lib/unicode/Is/L.pl index c32f830..bfe2c27 100644 --- a/lib/unicode/Is/L.pl +++ b/lib/unicode/Is/L.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0041 005a diff --git a/lib/unicode/Is/LbrkAI.pl b/lib/unicode/Is/LbrkAI.pl index a15f760..297f5cf 100644 --- a/lib/unicode/Is/LbrkAI.pl +++ b/lib/unicode/Is/LbrkAI.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a1 diff --git a/lib/unicode/Is/LbrkAL.pl b/lib/unicode/Is/LbrkAL.pl index c705dc8..c1fc416 100644 --- a/lib/unicode/Is/LbrkAL.pl +++ b/lib/unicode/Is/LbrkAL.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0023 diff --git a/lib/unicode/Is/LbrkB2.pl b/lib/unicode/Is/LbrkB2.pl index 527e4c8..a1410da 100644 --- a/lib/unicode/Is/LbrkB2.pl +++ b/lib/unicode/Is/LbrkB2.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2014 diff --git a/lib/unicode/Is/LbrkBA.pl b/lib/unicode/Is/LbrkBA.pl index 053369b..93ec04e 100644 --- a/lib/unicode/Is/LbrkBA.pl +++ b/lib/unicode/Is/LbrkBA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0009 diff --git a/lib/unicode/Is/LbrkBB.pl b/lib/unicode/Is/LbrkBB.pl index 5d3952a..b9bc7e8 100644 --- a/lib/unicode/Is/LbrkBB.pl +++ b/lib/unicode/Is/LbrkBB.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 02c8 diff --git a/lib/unicode/Is/LbrkBK.pl b/lib/unicode/Is/LbrkBK.pl index 2c314fb..17bb551 100644 --- a/lib/unicode/Is/LbrkBK.pl +++ b/lib/unicode/Is/LbrkBK.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 000c diff --git a/lib/unicode/Is/LbrkCB.pl b/lib/unicode/Is/LbrkCB.pl index 95f8b80..8da9eba 100644 --- a/lib/unicode/Is/LbrkCB.pl +++ b/lib/unicode/Is/LbrkCB.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; fffc diff --git a/lib/unicode/Is/LbrkCL.pl b/lib/unicode/Is/LbrkCL.pl index a73130a..353c594 100644 --- a/lib/unicode/Is/LbrkCL.pl +++ b/lib/unicode/Is/LbrkCL.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0029 diff --git a/lib/unicode/Is/LbrkCM.pl b/lib/unicode/Is/LbrkCM.pl index 3d0f347..87c7833 100644 --- a/lib/unicode/Is/LbrkCM.pl +++ b/lib/unicode/Is/LbrkCM.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 0008 diff --git a/lib/unicode/Is/LbrkCR.pl b/lib/unicode/Is/LbrkCR.pl index c61a527..2548269 100644 --- a/lib/unicode/Is/LbrkCR.pl +++ b/lib/unicode/Is/LbrkCR.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 000d diff --git a/lib/unicode/Is/LbrkEX.pl b/lib/unicode/Is/LbrkEX.pl index d847092..173bf58 100644 --- a/lib/unicode/Is/LbrkEX.pl +++ b/lib/unicode/Is/LbrkEX.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0021 diff --git a/lib/unicode/Is/LbrkGL.pl b/lib/unicode/Is/LbrkGL.pl index b03a627..49bb985 100644 --- a/lib/unicode/Is/LbrkGL.pl +++ b/lib/unicode/Is/LbrkGL.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a0 diff --git a/lib/unicode/Is/LbrkHY.pl b/lib/unicode/Is/LbrkHY.pl index 6989bc8..71e5886 100644 --- a/lib/unicode/Is/LbrkHY.pl +++ b/lib/unicode/Is/LbrkHY.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002d diff --git a/lib/unicode/Is/LbrkID.pl b/lib/unicode/Is/LbrkID.pl index 0b1cc84..6e6100c 100644 --- a/lib/unicode/Is/LbrkID.pl +++ b/lib/unicode/Is/LbrkID.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1100 1159 diff --git a/lib/unicode/Is/LbrkIN.pl b/lib/unicode/Is/LbrkIN.pl index 825198d..1758673 100644 --- a/lib/unicode/Is/LbrkIN.pl +++ b/lib/unicode/Is/LbrkIN.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2024 2026 diff --git a/lib/unicode/Is/LbrkIS.pl b/lib/unicode/Is/LbrkIS.pl index afa01a8..32dcfb0 100644 --- a/lib/unicode/Is/LbrkIS.pl +++ b/lib/unicode/Is/LbrkIS.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002c diff --git a/lib/unicode/Is/LbrkLF.pl b/lib/unicode/Is/LbrkLF.pl index dcb5490..9b845ae 100644 --- a/lib/unicode/Is/LbrkLF.pl +++ b/lib/unicode/Is/LbrkLF.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 000a diff --git a/lib/unicode/Is/LbrkNS.pl b/lib/unicode/Is/LbrkNS.pl index af9f337..b7ff279 100644 --- a/lib/unicode/Is/LbrkNS.pl +++ b/lib/unicode/Is/LbrkNS.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0e5a 0e5b diff --git a/lib/unicode/Is/LbrkNU.pl b/lib/unicode/Is/LbrkNU.pl index 5c55d22..eb51418 100644 --- a/lib/unicode/Is/LbrkNU.pl +++ b/lib/unicode/Is/LbrkNU.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/LbrkOP.pl b/lib/unicode/Is/LbrkOP.pl index a7dee37..90f1809 100644 --- a/lib/unicode/Is/LbrkOP.pl +++ b/lib/unicode/Is/LbrkOP.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0028 diff --git a/lib/unicode/Is/LbrkPO.pl b/lib/unicode/Is/LbrkPO.pl index cdfb56e..07f7bf7 100644 --- a/lib/unicode/Is/LbrkPO.pl +++ b/lib/unicode/Is/LbrkPO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0025 diff --git a/lib/unicode/Is/LbrkPR.pl b/lib/unicode/Is/LbrkPR.pl index c2d20da..03466c9 100644 --- a/lib/unicode/Is/LbrkPR.pl +++ b/lib/unicode/Is/LbrkPR.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0024 diff --git a/lib/unicode/Is/LbrkQU.pl b/lib/unicode/Is/LbrkQU.pl index 46a6ee3..35dac98 100644 --- a/lib/unicode/Is/LbrkQU.pl +++ b/lib/unicode/Is/LbrkQU.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0022 diff --git a/lib/unicode/Is/LbrkSA.pl b/lib/unicode/Is/LbrkSA.pl index bae4ced..4539e09 100644 --- a/lib/unicode/Is/LbrkSA.pl +++ b/lib/unicode/Is/LbrkSA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0e01 0e30 diff --git a/lib/unicode/Is/LbrkSG.pl b/lib/unicode/Is/LbrkSG.pl index 8888fb5..33e1dac 100644 --- a/lib/unicode/Is/LbrkSG.pl +++ b/lib/unicode/Is/LbrkSG.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; d800 db7f diff --git a/lib/unicode/Is/LbrkSP.pl b/lib/unicode/Is/LbrkSP.pl index e786a0c..2153e12 100644 --- a/lib/unicode/Is/LbrkSP.pl +++ b/lib/unicode/Is/LbrkSP.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0020 diff --git a/lib/unicode/Is/LbrkSY.pl b/lib/unicode/Is/LbrkSY.pl index d2a33ae..ce65fe1 100644 --- a/lib/unicode/Is/LbrkSY.pl +++ b/lib/unicode/Is/LbrkSY.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002f diff --git a/lib/unicode/Is/LbrkXX.pl b/lib/unicode/Is/LbrkXX.pl index ec287c4..c3b32ac 100644 --- a/lib/unicode/Is/LbrkXX.pl +++ b/lib/unicode/Is/LbrkXX.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; END diff --git a/lib/unicode/Is/LbrkZW.pl b/lib/unicode/Is/LbrkZW.pl index 96d8e99..63c9dcf 100644 --- a/lib/unicode/Is/LbrkZW.pl +++ b/lib/unicode/Is/LbrkZW.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 200b diff --git a/lib/unicode/Is/Ll.pl b/lib/unicode/Is/Ll.pl index 2814794..03dafcc 100644 --- a/lib/unicode/Is/Ll.pl +++ b/lib/unicode/Is/Ll.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0061 007a diff --git a/lib/unicode/Is/Lm.pl b/lib/unicode/Is/Lm.pl index 4380afe..23a3c55 100644 --- a/lib/unicode/Is/Lm.pl +++ b/lib/unicode/Is/Lm.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 02b0 02b8 diff --git a/lib/unicode/Is/Lo.pl b/lib/unicode/Is/Lo.pl index 78fab4c..d82c6bb 100644 --- a/lib/unicode/Is/Lo.pl +++ b/lib/unicode/Is/Lo.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 01bb diff --git a/lib/unicode/Is/Lower.pl b/lib/unicode/Is/Lower.pl index 2814794..03dafcc 100644 --- a/lib/unicode/Is/Lower.pl +++ b/lib/unicode/Is/Lower.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0061 007a diff --git a/lib/unicode/Is/Lt.pl b/lib/unicode/Is/Lt.pl index 809c37a..b19755c 100644 --- a/lib/unicode/Is/Lt.pl +++ b/lib/unicode/Is/Lt.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 01c5 diff --git a/lib/unicode/Is/Lu.pl b/lib/unicode/Is/Lu.pl index 8dde274..07dee48 100644 --- a/lib/unicode/Is/Lu.pl +++ b/lib/unicode/Is/Lu.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0041 005a diff --git a/lib/unicode/Is/M.pl b/lib/unicode/Is/M.pl index 9367775..e3ef7f3 100644 --- a/lib/unicode/Is/M.pl +++ b/lib/unicode/Is/M.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0300 034e diff --git a/lib/unicode/Is/Mc.pl b/lib/unicode/Is/Mc.pl index 937d8d4..a76d66c 100644 --- a/lib/unicode/Is/Mc.pl +++ b/lib/unicode/Is/Mc.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0903 diff --git a/lib/unicode/Is/Me.pl b/lib/unicode/Is/Me.pl index 00f446d..23ef860 100644 --- a/lib/unicode/Is/Me.pl +++ b/lib/unicode/Is/Me.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0488 0489 diff --git a/lib/unicode/Is/Mirrored.pl b/lib/unicode/Is/Mirrored.pl index e2c55a6..d324f50 100644 --- a/lib/unicode/Is/Mirrored.pl +++ b/lib/unicode/Is/Mirrored.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0028 0029 diff --git a/lib/unicode/Is/Mn.pl b/lib/unicode/Is/Mn.pl index aba40af..803e038 100644 --- a/lib/unicode/Is/Mn.pl +++ b/lib/unicode/Is/Mn.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0300 034e diff --git a/lib/unicode/Is/N.pl b/lib/unicode/Is/N.pl index 1291f27..8667e77 100644 --- a/lib/unicode/Is/N.pl +++ b/lib/unicode/Is/N.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/Nd.pl b/lib/unicode/Is/Nd.pl index 2ab8156..259bb89 100644 --- a/lib/unicode/Is/Nd.pl +++ b/lib/unicode/Is/Nd.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/Nl.pl b/lib/unicode/Is/Nl.pl index 8f1af46..bdeefd5 100644 --- a/lib/unicode/Is/Nl.pl +++ b/lib/unicode/Is/Nl.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2160 2183 diff --git a/lib/unicode/Is/No.pl b/lib/unicode/Is/No.pl index 6a57dc5..13cac3b 100644 --- a/lib/unicode/Is/No.pl +++ b/lib/unicode/Is/No.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00b2 00b3 diff --git a/lib/unicode/Is/P.pl b/lib/unicode/Is/P.pl index 8fd1e8e..97330ec 100644 --- a/lib/unicode/Is/P.pl +++ b/lib/unicode/Is/P.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0021 0023 diff --git a/lib/unicode/Is/Pc.pl b/lib/unicode/Is/Pc.pl index 342efac..e14874d 100644 --- a/lib/unicode/Is/Pc.pl +++ b/lib/unicode/Is/Pc.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 005f diff --git a/lib/unicode/Is/Pd.pl b/lib/unicode/Is/Pd.pl index 58997ca..b4a2ffb 100644 --- a/lib/unicode/Is/Pd.pl +++ b/lib/unicode/Is/Pd.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002d diff --git a/lib/unicode/Is/Pe.pl b/lib/unicode/Is/Pe.pl index 8879191..2b5bd3e 100644 --- a/lib/unicode/Is/Pe.pl +++ b/lib/unicode/Is/Pe.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0029 diff --git a/lib/unicode/Is/Pf.pl b/lib/unicode/Is/Pf.pl index 166c64b..b27a4f6 100644 --- a/lib/unicode/Is/Pf.pl +++ b/lib/unicode/Is/Pf.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00bb diff --git a/lib/unicode/Is/Pi.pl b/lib/unicode/Is/Pi.pl index 7f2243d..dbbae44 100644 --- a/lib/unicode/Is/Pi.pl +++ b/lib/unicode/Is/Pi.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00ab diff --git a/lib/unicode/Is/Po.pl b/lib/unicode/Is/Po.pl index e6b8b02..849ee17 100644 --- a/lib/unicode/Is/Po.pl +++ b/lib/unicode/Is/Po.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0021 0023 diff --git a/lib/unicode/Is/Print.pl b/lib/unicode/Is/Print.pl index 9560586..c3adba6 100644 --- a/lib/unicode/Is/Print.pl +++ b/lib/unicode/Is/Print.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0020 007e diff --git a/lib/unicode/Is/Ps.pl b/lib/unicode/Is/Ps.pl index a7dee37..90f1809 100644 --- a/lib/unicode/Is/Ps.pl +++ b/lib/unicode/Is/Ps.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0028 diff --git a/lib/unicode/Is/Punct.pl b/lib/unicode/Is/Punct.pl index 9e8684d..9e088ba 100644 --- a/lib/unicode/Is/Punct.pl +++ b/lib/unicode/Is/Punct.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0021 0023 diff --git a/lib/unicode/Is/S.pl b/lib/unicode/Is/S.pl index 8851766..a304e17 100644 --- a/lib/unicode/Is/S.pl +++ b/lib/unicode/Is/S.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0024 diff --git a/lib/unicode/Is/Sc.pl b/lib/unicode/Is/Sc.pl index 5776bd6..adeb3e4 100644 --- a/lib/unicode/Is/Sc.pl +++ b/lib/unicode/Is/Sc.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0024 diff --git a/lib/unicode/Is/Sk.pl b/lib/unicode/Is/Sk.pl index b5f6e59..52f88ae 100644 --- a/lib/unicode/Is/Sk.pl +++ b/lib/unicode/Is/Sk.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 005e diff --git a/lib/unicode/Is/Sm.pl b/lib/unicode/Is/Sm.pl index ae9424c..540da63 100644 --- a/lib/unicode/Is/Sm.pl +++ b/lib/unicode/Is/Sm.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 002b diff --git a/lib/unicode/Is/So.pl b/lib/unicode/Is/So.pl index 4e9dfc2..3caf617 100644 --- a/lib/unicode/Is/So.pl +++ b/lib/unicode/Is/So.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 00a6 00a7 diff --git a/lib/unicode/Is/Space.pl b/lib/unicode/Is/Space.pl index 701329f..1625dce 100644 --- a/lib/unicode/Is/Space.pl +++ b/lib/unicode/Is/Space.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0009 000d diff --git a/lib/unicode/Is/SylA.pl b/lib/unicode/Is/SylA.pl index be11078..6a3fc47 100644 --- a/lib/unicode/Is/SylA.pl +++ b/lib/unicode/Is/SylA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1203 diff --git a/lib/unicode/Is/SylAA.pl b/lib/unicode/Is/SylAA.pl index 45d6692..6d1bd6d 100644 --- a/lib/unicode/Is/SylAA.pl +++ b/lib/unicode/Is/SylAA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 140b diff --git a/lib/unicode/Is/SylAAI.pl b/lib/unicode/Is/SylAAI.pl index a8b03d4..83134b6 100644 --- a/lib/unicode/Is/SylAAI.pl +++ b/lib/unicode/Is/SylAAI.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1402 diff --git a/lib/unicode/Is/SylAI.pl b/lib/unicode/Is/SylAI.pl index b70d793..e639bd0 100644 --- a/lib/unicode/Is/SylAI.pl +++ b/lib/unicode/Is/SylAI.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 141c diff --git a/lib/unicode/Is/SylC.pl b/lib/unicode/Is/SylC.pl index e2a1601..fb8b08e 100644 --- a/lib/unicode/Is/SylC.pl +++ b/lib/unicode/Is/SylC.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1205 diff --git a/lib/unicode/Is/SylE.pl b/lib/unicode/Is/SylE.pl index b3c3e60..d762748 100644 --- a/lib/unicode/Is/SylE.pl +++ b/lib/unicode/Is/SylE.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1204 diff --git a/lib/unicode/Is/SylEE.pl b/lib/unicode/Is/SylEE.pl index 0a22f78..9f8ff07 100644 --- a/lib/unicode/Is/SylEE.pl +++ b/lib/unicode/Is/SylEE.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1408 diff --git a/lib/unicode/Is/SylI.pl b/lib/unicode/Is/SylI.pl index f80790c..29bc70f 100644 --- a/lib/unicode/Is/SylI.pl +++ b/lib/unicode/Is/SylI.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1202 diff --git a/lib/unicode/Is/SylII.pl b/lib/unicode/Is/SylII.pl index 4516d7a..2dcd49f 100644 --- a/lib/unicode/Is/SylII.pl +++ b/lib/unicode/Is/SylII.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1404 diff --git a/lib/unicode/Is/SylN.pl b/lib/unicode/Is/SylN.pl index 215463f..d7d90c7 100644 --- a/lib/unicode/Is/SylN.pl +++ b/lib/unicode/Is/SylN.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 3093 diff --git a/lib/unicode/Is/SylO.pl b/lib/unicode/Is/SylO.pl index a0a6f7d..2c795f0 100644 --- a/lib/unicode/Is/SylO.pl +++ b/lib/unicode/Is/SylO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1206 diff --git a/lib/unicode/Is/SylOO.pl b/lib/unicode/Is/SylOO.pl index 1228053..27c8032 100644 --- a/lib/unicode/Is/SylOO.pl +++ b/lib/unicode/Is/SylOO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1406 1407 diff --git a/lib/unicode/Is/SylU.pl b/lib/unicode/Is/SylU.pl index c458382..117d981 100644 --- a/lib/unicode/Is/SylU.pl +++ b/lib/unicode/Is/SylU.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1201 diff --git a/lib/unicode/Is/SylV.pl b/lib/unicode/Is/SylV.pl index b6e76f8..e5a39ed 100644 --- a/lib/unicode/Is/SylV.pl +++ b/lib/unicode/Is/SylV.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1200 diff --git a/lib/unicode/Is/SylWA.pl b/lib/unicode/Is/SylWA.pl index 9bb529e..39e94ca 100644 --- a/lib/unicode/Is/SylWA.pl +++ b/lib/unicode/Is/SylWA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 120f diff --git a/lib/unicode/Is/SylWAA.pl b/lib/unicode/Is/SylWAA.pl index 5f3b784..cd560eb 100644 --- a/lib/unicode/Is/SylWAA.pl +++ b/lib/unicode/Is/SylWAA.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1419 141b diff --git a/lib/unicode/Is/SylWC.pl b/lib/unicode/Is/SylWC.pl index 3ad968c..4272b89 100644 --- a/lib/unicode/Is/SylWC.pl +++ b/lib/unicode/Is/SylWC.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 124d diff --git a/lib/unicode/Is/SylWE.pl b/lib/unicode/Is/SylWE.pl index 9e32c0e..c4c5ba9 100644 --- a/lib/unicode/Is/SylWE.pl +++ b/lib/unicode/Is/SylWE.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 124c diff --git a/lib/unicode/Is/SylWEE.pl b/lib/unicode/Is/SylWEE.pl index c4bccb5..d316029 100644 --- a/lib/unicode/Is/SylWEE.pl +++ b/lib/unicode/Is/SylWEE.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 15d9 diff --git a/lib/unicode/Is/SylWI.pl b/lib/unicode/Is/SylWI.pl index 4cd6c67..c914b07 100644 --- a/lib/unicode/Is/SylWI.pl +++ b/lib/unicode/Is/SylWI.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 124a diff --git a/lib/unicode/Is/SylWII.pl b/lib/unicode/Is/SylWII.pl index bd68aea..c990e43 100644 --- a/lib/unicode/Is/SylWII.pl +++ b/lib/unicode/Is/SylWII.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1410 1411 diff --git a/lib/unicode/Is/SylWO.pl b/lib/unicode/Is/SylWO.pl index 7676564..a73cbdd 100644 --- a/lib/unicode/Is/SylWO.pl +++ b/lib/unicode/Is/SylWO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1412 1413 diff --git a/lib/unicode/Is/SylWOO.pl b/lib/unicode/Is/SylWOO.pl index 0ab766a..6e92f85 100644 --- a/lib/unicode/Is/SylWOO.pl +++ b/lib/unicode/Is/SylWOO.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1414 1416 diff --git a/lib/unicode/Is/SylWU.pl b/lib/unicode/Is/SylWU.pl index 76af7ae..d165f41 100644 --- a/lib/unicode/Is/SylWU.pl +++ b/lib/unicode/Is/SylWU.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 15d6 diff --git a/lib/unicode/Is/SylWV.pl b/lib/unicode/Is/SylWV.pl index 8bd8849..6a06ae9 100644 --- a/lib/unicode/Is/SylWV.pl +++ b/lib/unicode/Is/SylWV.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 1248 diff --git a/lib/unicode/Is/Upper.pl b/lib/unicode/Is/Upper.pl index 4fda655..16f8752 100644 --- a/lib/unicode/Is/Upper.pl +++ b/lib/unicode/Is/Upper.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0041 005a diff --git a/lib/unicode/Is/Word.pl b/lib/unicode/Is/Word.pl index 2f13b38..1c76c60 100644 --- a/lib/unicode/Is/Word.pl +++ b/lib/unicode/Is/Word.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/XDigit.pl b/lib/unicode/Is/XDigit.pl index e556825..b26a3b4 100644 --- a/lib/unicode/Is/XDigit.pl +++ b/lib/unicode/Is/XDigit.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 diff --git a/lib/unicode/Is/Z.pl b/lib/unicode/Is/Z.pl index 22a9792..03416c0 100644 --- a/lib/unicode/Is/Z.pl +++ b/lib/unicode/Is/Z.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0020 diff --git a/lib/unicode/Is/Zl.pl b/lib/unicode/Is/Zl.pl index 0989e1d..5f127ce 100644 --- a/lib/unicode/Is/Zl.pl +++ b/lib/unicode/Is/Zl.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2028 diff --git a/lib/unicode/Is/Zp.pl b/lib/unicode/Is/Zp.pl index 3b23446..4e38303 100644 --- a/lib/unicode/Is/Zp.pl +++ b/lib/unicode/Is/Zp.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 2029 diff --git a/lib/unicode/Is/Zs.pl b/lib/unicode/Is/Zs.pl index db18055..56cf9e4 100644 --- a/lib/unicode/Is/Zs.pl +++ b/lib/unicode/Is/Zs.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0020 diff --git a/lib/unicode/Jamo.txt b/lib/unicode/Jamo.txt index 6910ab9..ea288f0 100644 --- a/lib/unicode/Jamo.txt +++ b/lib/unicode/Jamo.txt @@ -1,69 +1,91 @@ -#Value; Short Name; Unicode Name -U+1100; G; HANGUL CHOSEONG KIYEOK -U+1101; GG; HANGUL CHOSEONG SSANGKIYEOK -U+1102; N; HANGUL CHOSEONG NIEUN -U+1103; D; HANGUL CHOSEONG TIKEUT -U+1104; DD; HANGUL CHOSEONG SSANGTIKEUT -U+1105; R; HANGUL CHOSEONG RIEUL -U+1106; M; HANGUL CHOSEONG MIEUM -U+1107; B; HANGUL CHOSEONG PIEUP -U+1108; BB; HANGUL CHOSEONG SSANGPIEUP -U+1109; S; HANGUL CHOSEONG SIOS -U+110A; SS; HANGUL CHOSEONG SSANGSIOS -U+110B; ; HANGUL CHOSEONG IEUNG -U+110C; J; HANGUL CHOSEONG CIEUC -U+110D; JJ; HANGUL CHOSEONG SSANGCIEUC -U+110E; C; HANGUL CHOSEONG CHIEUCH -U+110F; K; HANGUL CHOSEONG KHIEUKH -U+1110; T; HANGUL CHOSEONG THIEUTH -U+1111; P; HANGUL CHOSEONG PHIEUPH -U+1112; H; HANGUL CHOSEONG HIEUH -U+1161; A; HANGUL JUNGSEONG A -U+1162; AE; HANGUL JUNGSEONG AE -U+1163; YA; HANGUL JUNGSEONG YA -U+1164; YAE; HANGUL JUNGSEONG YAE -U+1165; EO; HANGUL JUNGSEONG EO -U+1166; E; HANGUL JUNGSEONG E -U+1167; YEO; HANGUL JUNGSEONG YEO -U+1168; YE; HANGUL JUNGSEONG YE -U+1169; O; HANGUL JUNGSEONG O -U+116A; WA; HANGUL JUNGSEONG WA -U+116B; WAE; HANGUL JUNGSEONG WAE -U+116C; OE; HANGUL JUNGSEONG OE -U+116D; YO; HANGUL JUNGSEONG YO -U+116E; U; HANGUL JUNGSEONG U -U+116F; WEO; HANGUL JUNGSEONG WEO -U+1170; WE; HANGUL JUNGSEONG WE -U+1171; WI; HANGUL JUNGSEONG WI -U+1172; YU; HANGUL JUNGSEONG YU -U+1173; EU; HANGUL JUNGSEONG EU -U+1174; YI; HANGUL JUNGSEONG YI -U+1175; I; HANGUL JUNGSEONG I -U+11A8; G; HANGUL JONGSEONG KIYEOK -U+11A9; GG; HANGUL JONGSEONG SSANGKIYEOK -U+11AA; GS; HANGUL JONGSEONG KIYEOK-SIOS -U+11AB; N; HANGUL JONGSEONG NIEUN -U+11AC; NJ; HANGUL JONGSEONG NIEUN-CIEUC -U+11AD; NH; HANGUL JONGSEONG NIEUN-HIEUH -U+11AE; D; HANGUL JONGSEONG TIKEUT -U+11AF; L; HANGUL JONGSEONG RIEUL -U+11B0; LG; HANGUL JONGSEONG RIEUL-KIYEOK -U+11B1; LM; HANGUL JONGSEONG RIEUL-MIEUM -U+11B2; LB; HANGUL JONGSEONG RIEUL-PIEUP -U+11B3; LS; HANGUL JONGSEONG RIEUL-SIOS -U+11B4; LT; HANGUL JONGSEONG RIEUL-THIEUTH -U+11B5; LP; HANGUL JONGSEONG RIEUL-PHIEUPH -U+11B6; LH; HANGUL JONGSEONG RIEUL-HIEUH -U+11B7; M; HANGUL JONGSEONG MIEUM -U+11B8; B; HANGUL JONGSEONG PIEUP -U+11B9; BS; HANGUL JONGSEONG PIEUP-SIOS -U+11BA; S; HANGUL JONGSEONG SIOS -U+11BB; SS; HANGUL JONGSEONG SSANGSIOS -U+11BC; NG; HANGUL JONGSEONG IEUNG -U+11BD; J; HANGUL JONGSEONG CIEUC -U+11BE; C; HANGUL JONGSEONG CHIEUCH -U+11BF; K; HANGUL JONGSEONG KHIEUKH -U+11C0; T; HANGUL JONGSEONG THIEUTH -U+11C1; P; HANGUL JONGSEONG PHIEUPH -U+11C2; H; HANGUL JONGSEONG HIEUH +# Jamo-3.txt +# +# This file is a normative contributory data file in the +# Unicode Character Database. +# +# 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. +# +# See sections 3.11 and 4.4 of The Unicode Standard, Version 3.0 +# for more information. +# +# Each line contains two fields, separated by a semicolon. +# +# The first field gives the code point, in 4-digit hexadecimal +# form, of a combining jamo character that participates in +# the algorithmic determination Hangul syllable character names. +# The second field gives the Jamo Short Name as a one-, two-, +# or three-character ASCII string (or in one case, for U+110B, +# the null string). +# +# ############################################################# + +1100; G # HANGUL CHOSEONG KIYEOK +1101; GG # HANGUL CHOSEONG SSANGKIYEOK +1102; N # HANGUL CHOSEONG NIEUN +1103; D # HANGUL CHOSEONG TIKEUT +1104; DD # HANGUL CHOSEONG SSANGTIKEUT +1105; R # HANGUL CHOSEONG RIEUL +1106; M # HANGUL CHOSEONG MIEUM +1107; B # HANGUL CHOSEONG PIEUP +1108; BB # HANGUL CHOSEONG SSANGPIEUP +1109; S # HANGUL CHOSEONG SIOS +110A; SS # HANGUL CHOSEONG SSANGSIOS +110B; # HANGUL CHOSEONG IEUNG +110C; J # HANGUL CHOSEONG CIEUC +110D; JJ # HANGUL CHOSEONG SSANGCIEUC +110E; C # HANGUL CHOSEONG CHIEUCH +110F; K # HANGUL CHOSEONG KHIEUKH +1110; T # HANGUL CHOSEONG THIEUTH +1111; P # HANGUL CHOSEONG PHIEUPH +1112; H # HANGUL CHOSEONG HIEUH +1161; A # HANGUL JUNGSEONG A +1162; AE # HANGUL JUNGSEONG AE +1163; YA # HANGUL JUNGSEONG YA +1164; YAE # HANGUL JUNGSEONG YAE +1165; EO # HANGUL JUNGSEONG EO +1166; E # HANGUL JUNGSEONG E +1167; YEO # HANGUL JUNGSEONG YEO +1168; YE # HANGUL JUNGSEONG YE +1169; O # HANGUL JUNGSEONG O +116A; WA # HANGUL JUNGSEONG WA +116B; WAE # HANGUL JUNGSEONG WAE +116C; OE # HANGUL JUNGSEONG OE +116D; YO # HANGUL JUNGSEONG YO +116E; U # HANGUL JUNGSEONG U +116F; WEO # HANGUL JUNGSEONG WEO +1170; WE # HANGUL JUNGSEONG WE +1171; WI # HANGUL JUNGSEONG WI +1172; YU # HANGUL JUNGSEONG YU +1173; EU # HANGUL JUNGSEONG EU +1174; YI # HANGUL JUNGSEONG YI +1175; I # HANGUL JUNGSEONG I +11A8; G # HANGUL JONGSEONG KIYEOK +11A9; GG # HANGUL JONGSEONG SSANGKIYEOK +11AA; GS # HANGUL JONGSEONG KIYEOK-SIOS +11AB; N # HANGUL JONGSEONG NIEUN +11AC; NJ # HANGUL JONGSEONG NIEUN-CIEUC +11AD; NH # HANGUL JONGSEONG NIEUN-HIEUH +11AE; D # HANGUL JONGSEONG TIKEUT +11AF; L # HANGUL JONGSEONG RIEUL +11B0; LG # HANGUL JONGSEONG RIEUL-KIYEOK +11B1; LM # HANGUL JONGSEONG RIEUL-MIEUM +11B2; LB # HANGUL JONGSEONG RIEUL-PIEUP +11B3; LS # HANGUL JONGSEONG RIEUL-SIOS +11B4; LT # HANGUL JONGSEONG RIEUL-THIEUTH +11B5; LP # HANGUL JONGSEONG RIEUL-PHIEUPH +11B6; LH # HANGUL JONGSEONG RIEUL-HIEUH +11B7; M # HANGUL JONGSEONG MIEUM +11B8; B # HANGUL JONGSEONG PIEUP +11B9; BS # HANGUL JONGSEONG PIEUP-SIOS +11BA; S # HANGUL JONGSEONG SIOS +11BB; SS # HANGUL JONGSEONG SSANGSIOS +11BC; NG # HANGUL JONGSEONG IEUNG +11BD; J # HANGUL JONGSEONG CIEUC +11BE; C # HANGUL JONGSEONG CHIEUCH +11BF; K # HANGUL JONGSEONG KHIEUKH +11C0; T # HANGUL JONGSEONG THIEUTH +11C1; P # HANGUL JONGSEONG PHIEUPH +11C2; H # HANGUL JONGSEONG HIEUH diff --git a/lib/unicode/JamoShort.pl b/lib/unicode/JamoShort.pl index 760bcba..19cd429 100644 --- a/lib/unicode/JamoShort.pl +++ b/lib/unicode/JamoShort.pl @@ -1,72 +1,72 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; -1100 G -1101 GG -1102 N -1103 D -1104 DD -1105 R -1106 M -1107 B -1108 BB -1109 S -110a SS -110b -110c J -110d JJ -110e C -110f K -1110 T -1111 P -1112 H -1161 A -1162 AE -1163 YA -1164 YAE -1165 EO -1166 E -1167 YEO -1168 YE -1169 O -116a WA -116b WAE -116c OE -116d YO -116e U -116f WEO -1170 WE -1171 WI -1172 YU -1173 EU -1174 YI -1175 I -11a8 G -11a9 GG -11aa GS -11ab N -11ac NJ -11ad NH -11ae D -11af L -11b0 LG -11b1 LM -11b2 LB -11b3 LS -11b4 LT -11b5 LP -11b6 LH -11b7 M -11b8 B -11b9 BS -11ba S -11bb SS -11bc NG -11bd J -11be C -11bf K -11c0 T -11c1 P -11c2 H +1100 G # HANGUL CHOSEONG KIYEOK +1101 GG # HANGUL CHOSEONG SSANGKIYEOK +1102 N # HANGUL CHOSEONG NIEUN +1103 D # HANGUL CHOSEONG TIKEUT +1104 DD # HANGUL CHOSEONG SSANGTIKEUT +1105 R # HANGUL CHOSEONG RIEUL +1106 M # HANGUL CHOSEONG MIEUM +1107 B # HANGUL CHOSEONG PIEUP +1108 BB # HANGUL CHOSEONG SSANGPIEUP +1109 S # HANGUL CHOSEONG SIOS +110a SS # HANGUL CHOSEONG SSANGSIOS +110b # HANGUL CHOSEONG IEUNG +110c J # HANGUL CHOSEONG CIEUC +110d JJ # HANGUL CHOSEONG SSANGCIEUC +110e C # HANGUL CHOSEONG CHIEUCH +110f K # HANGUL CHOSEONG KHIEUKH +1110 T # HANGUL CHOSEONG THIEUTH +1111 P # HANGUL CHOSEONG PHIEUPH +1112 H # HANGUL CHOSEONG HIEUH +1161 A # HANGUL JUNGSEONG A +1162 AE # HANGUL JUNGSEONG AE +1163 YA # HANGUL JUNGSEONG YA +1164 YAE # HANGUL JUNGSEONG YAE +1165 EO # HANGUL JUNGSEONG EO +1166 E # HANGUL JUNGSEONG E +1167 YEO # HANGUL JUNGSEONG YEO +1168 YE # HANGUL JUNGSEONG YE +1169 O # HANGUL JUNGSEONG O +116a WA # HANGUL JUNGSEONG WA +116b WAE # HANGUL JUNGSEONG WAE +116c OE # HANGUL JUNGSEONG OE +116d YO # HANGUL JUNGSEONG YO +116e U # HANGUL JUNGSEONG U +116f WEO # HANGUL JUNGSEONG WEO +1170 WE # HANGUL JUNGSEONG WE +1171 WI # HANGUL JUNGSEONG WI +1172 YU # HANGUL JUNGSEONG YU +1173 EU # HANGUL JUNGSEONG EU +1174 YI # HANGUL JUNGSEONG YI +1175 I # HANGUL JUNGSEONG I +11a8 G # HANGUL JONGSEONG KIYEOK +11a9 GG # HANGUL JONGSEONG SSANGKIYEOK +11aa GS # HANGUL JONGSEONG KIYEOK-SIOS +11ab N # HANGUL JONGSEONG NIEUN +11ac NJ # HANGUL JONGSEONG NIEUN-CIEUC +11ad NH # HANGUL JONGSEONG NIEUN-HIEUH +11ae D # HANGUL JONGSEONG TIKEUT +11af L # HANGUL JONGSEONG RIEUL +11b0 LG # HANGUL JONGSEONG RIEUL-KIYEOK +11b1 LM # HANGUL JONGSEONG RIEUL-MIEUM +11b2 LB # HANGUL JONGSEONG RIEUL-PIEUP +11b3 LS # HANGUL JONGSEONG RIEUL-SIOS +11b4 LT # HANGUL JONGSEONG RIEUL-THIEUTH +11b5 LP # HANGUL JONGSEONG RIEUL-PHIEUPH +11b6 LH # HANGUL JONGSEONG RIEUL-HIEUH +11b7 M # HANGUL JONGSEONG MIEUM +11b8 B # HANGUL JONGSEONG PIEUP +11b9 BS # HANGUL JONGSEONG PIEUP-SIOS +11ba S # HANGUL JONGSEONG SIOS +11bb SS # HANGUL JONGSEONG SSANGSIOS +11bc NG # HANGUL JONGSEONG IEUNG +11bd J # HANGUL JONGSEONG CIEUC +11be C # HANGUL JONGSEONG CHIEUCH +11bf K # HANGUL JONGSEONG KHIEUKH +11c0 T # HANGUL JONGSEONG THIEUTH +11c1 P # HANGUL JONGSEONG PHIEUPH +11c2 H # HANGUL JONGSEONG HIEUH END diff --git a/lib/unicode/Name.pl b/lib/unicode/Name.pl index ef8979f..f5c4c56 100644 --- a/lib/unicode/Name.pl +++ b/lib/unicode/Name.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0000 001f @@ -10549,4 +10549,6 @@ fffa INTERLINEAR ANNOTATION SEPARATOR fffb INTERLINEAR ANNOTATION TERMINATOR fffc OBJECT REPLACEMENT CHARACTER fffd REPLACEMENT CHARACTER +f0000 ffffd +100000 10fffd END diff --git a/lib/unicode/Number.pl b/lib/unicode/Number.pl index b9e596f..1f5c2c8 100644 --- a/lib/unicode/Number.pl +++ b/lib/unicode/Number.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0 @@ -165,6 +165,16 @@ return <<'END'; 0f27 7 0f28 8 0f29 9 +0f2a 1/2 +0f2b 3/2 +0f2c 5/2 +0f2d 7/2 +0f2e 9/2 +0f2f 11/2 +0f30 13/2 +0f31 15/2 +0f32 17/2 +0f33 -1/2 1040 0 1041 1 1042 2 @@ -385,6 +395,20 @@ return <<'END'; 3038 10 3039 20 303a 30 +3192 1 +3193 2 +3194 3 +3195 4 +3220 1 +3221 2 +3222 3 +3223 4 +3224 5 +3225 6 +3226 7 +3227 8 +3228 9 +3229 10 3280 1 3281 2 3282 3 diff --git a/lib/unicode/Props.txt b/lib/unicode/PropList.txt similarity index 97% rename from lib/unicode/Props.txt rename to lib/unicode/PropList.txt index b3548e1..e47f127 100644 --- a/lib/unicode/Props.txt +++ b/lib/unicode/PropList.txt @@ -1,4 +1,4 @@ -Property dump: UnicodeData-3.0.0.txt +Property dump: UnicodeData-3.0.1.txt ******************************************* @@ -192,89 +192,6 @@ FF61..FF65 (5 chars) ******************************************* -Property dump for: 0x00800000 (Delimiter) - -0000 -0009..000D (5 chars) -001C..0023 (8 chars) -0028..0029 (2 chars) -002C -002E..002F (2 chars) -003A..003B (2 chars) -003F -005B..005D (3 chars) -007B..007D (3 chars) -0085 -00A0..00A1 (2 chars) -00A6..00A7 (2 chars) -00AB -00B6 -00BB -00BF -037E -0387 -055C..055E (3 chars) -0589 -060C -061B -061F -066B..066C (2 chars) -06D4 -0700..0709 (10 chars) -070B..070D (3 chars) -0964..0965 (2 chars) -0DF4 -0E5A..0E5B (2 chars) -0F0B -0F0D..0F12 (6 chars) -0F3A..0F3D (4 chars) -104A..104B (2 chars) -10FB -1361..1368 (8 chars) -166D..166E (2 chars) -1680 -169B..169C (2 chars) -16EB..16ED (3 chars) -17D4..17D6 (3 chars) -17DA -1802..1805 (4 chars) -1808..1809 (2 chars) -2000..200B (12 chars) -2016 -2018..201F (8 chars) -2028..2029 (2 chars) -202F -2039..203A (2 chars) -203C..203D (2 chars) -2045..2046 (2 chars) -2048..2049 (2 chars) -207D..207E (2 chars) -208D..208E (2 chars) -2329..232A (2 chars) -3000..3002 (3 chars) -3008..3011 (10 chars) -3014..301B (8 chars) -301D..301F (3 chars) -30FB -FD3E..FD3F (2 chars) -FE35..FE44 (16 chars) -FE50..FE52 (3 chars) -FE54..FE57 (4 chars) -FE59..FE5F (7 chars) -FE68 -FF01..FF03 (3 chars) -FF08..FF09 (2 chars) -FF0C -FF0E..FF0F (2 chars) -FF1A..FF1B (2 chars) -FF1F -FF3B..FF3D (3 chars) -FF5B..FF5D (3 chars) -FF61..FF65 (5 chars) -FFE4 - -******************************************* - Property dump for: 0x80000003 (Line Separator) 2028 @@ -591,7 +508,6 @@ Property dump for: 0x20000004 (Combining) 20D0..20E3 (20 chars) 302A..302F (6 chars) 3099..309A (2 chars) -F8F0..F8FF (16 chars) FB1E FE20..FE23 (4 chars) @@ -689,7 +605,6 @@ Property dump for: 0x20040000 (Non-spacing) 20D0..20E3 (20 chars) 302A..302F (6 chars) 3099..309A (2 chars) -F8F0..F8FF (16 chars) FB1E FE20..FE23 (4 chars) @@ -1161,7 +1076,6 @@ Property dump for: 0x20000001 (Alphabetic) 0DF2..0DF3 (2 chars) 0E01..0E3A (58 chars) 0E40..0E45 (6 chars) -0E47 0E4D 0E81..0E82 (2 chars) 0E84 @@ -1355,7 +1269,7 @@ Property dump for: 0x20010000 (Diacritic) 0CCD 0D4D 0DCA -0E48..0E4C (5 chars) +0E47..0E4C (6 chars) 0E4E 0EC8..0ECC (5 chars) 0F18..0F19 (2 chars) @@ -2077,8 +1991,7 @@ Property dump for: 0x01000000 (Bidi: Left-to-Right) 4E00..9FA5 (20902 chars) A000..A48C (1165 chars) AC00..D7A3 (11172 chars) -D800..F7FF (8192 chars) -F900..FA2D (302 chars) +D800..FA2D (8750 chars) FB00..FB06 (7 chars) FB13..FB17 (5 chars) FF21..FF3A (26 chars) @@ -2088,6 +2001,8 @@ FFC2..FFC7 (6 chars) FFCA..FFCF (6 chars) FFD2..FFD7 (6 chars) FFDA..FFDC (3 chars) +F0000..FFFFD (65534 chars) +100000..10FFFD (65534 chars) ******************************************* @@ -2331,7 +2246,6 @@ Property dump for: 0x0C000000 (Bidi: Non-spacing Mark) 20D0..20E3 (20 chars) 302A..302F (6 chars) 3099..309A (2 chars) -F8F0..F8FF (16 chars) FB1E FE20..FE23 (4 chars) @@ -2483,6 +2397,8 @@ FFFC..FFFD (2 chars) Property dump for: 0x80000005 (Private Use) E000..F8FF (6400 chars) +F0000..FFFFD (65534 chars) +100000..10FFFD (65534 chars) ******************************************* @@ -3281,6 +3197,28 @@ DB80..DBFF (128 chars) ******************************************* +Property dump for: 0x8000000A (Not a Character) + +FFFE..FFFF (2 chars) +1FFFE..1FFFF (2 chars) +2FFFE..2FFFF (2 chars) +3FFFE..3FFFF (2 chars) +4FFFE..4FFFF (2 chars) +5FFFE..5FFFF (2 chars) +6FFFE..6FFFF (2 chars) +7FFFE..7FFFF (2 chars) +8FFFE..8FFFF (2 chars) +9FFFE..9FFFF (2 chars) +AFFFE..AFFFF (2 chars) +BFFFE..BFFFF (2 chars) +CFFFE..CFFFF (2 chars) +DFFFE..DFFFF (2 chars) +EFFFE..EFFFF (2 chars) +FFFFE..FFFFF (2 chars) +10FFFE..10FFFF (2 chars) + +******************************************* + Property dump for: 0x00000000 (Unassigned Code Value) 0220..0221 (2 chars) @@ -3637,4 +3575,18 @@ FFD8..FFD9 (2 chars) FFDD..FFDF (3 chars) FFE7 FFEF..FFF8 (10 chars) +10000..1FFFD (65534 chars) +20000..2FFFD (65534 chars) +30000..3FFFD (65534 chars) +40000..4FFFD (65534 chars) +50000..5FFFD (65534 chars) +60000..6FFFD (65534 chars) +70000..7FFFD (65534 chars) +80000..8FFFD (65534 chars) +90000..9FFFD (65534 chars) +A0000..AFFFD (65534 chars) +B0000..BFFFD (65534 chars) +C0000..CFFFD (65534 chars) +D0000..DFFFD (65534 chars) +E0000..EFFFD (65534 chars) diff --git a/lib/unicode/README.perl b/lib/unicode/README.perl new file mode 100644 index 0000000..2294bd3 --- /dev/null +++ b/lib/unicode/README.perl @@ -0,0 +1,37 @@ +The *.txt files were copied 30 Aug 2000 from + + http://www.unicode.org/Public/UNIDATA/ + +and most of them were renamed to better fit 8.3 filename limitations, +by which the Perl distribution tries to live. + + www.unicode.org Perl distribution + + ArabicShaping.txt ArabShap.txt + BidiMirroring.txt BidiMirr.txt + Blocks.txt Blocks.txt + CaseFolding.txt CaseFold.txt + CompositionExclusions.txt CompExcl.txt + EastAsianWidth.txt EAWidth.txt (0) + Index.txt Index.txt + Jamo.txt Jamo.txt + LineBreak.txt LineBrk.txt (0) + NamesList.html NamesList.html (0) + NamesList.txt Names.txt + PropList.txt PropList.txt + ReadMe.txt ReadMe.txt + SpecialCasing.txt SpecCase.txt + UnicodeCharacterDatabase.html UCD301.html + UnicodeData.html UCDFF301.html + UnicodeData.txt Unicode.301 + +The two big files, NormalizationTest.txt (1.7MB) and Unihan.txt (15.8MB) +were not copied for space considerations. The files marked with (0) had +not been updated since Unicode 3.0.0 (10 Sep 1999) + +The *.pl files are generated from these files by the 'mktables.PL' script. + +While the files have been renamed the links in the html files haven't. + +-- +jhi@iki.fi diff --git a/lib/unicode/ReadMe.txt b/lib/unicode/ReadMe.txt index c2c4aee..b8a643c 100644 --- a/lib/unicode/ReadMe.txt +++ b/lib/unicode/ReadMe.txt @@ -1,45 +1,13 @@ -June 23, 1999 +August 30, 2000 -This directory contains the initial release for Unicode 3.0. +This directory contains the first update release for Unicode 3.0. This release consists of corrections and additions to the -Unicode Character Database, to match the publication of -The Unicode Standard, Version 3.0. +Unicode Character Database for the Unicode Standard, +Version 3.0.1. Detailed documentation of the files constituting the Unicode Character Database (contributory data files for the standard itself) can now be found in UnicodeCharacterDatabase.html. --------------------------------------------------------------------------- -NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE NOTE - -The files have been copied from - - ftp://ftp.unicode.org/Public/3.0-Update/ - -and most of them have been renamed to better fit 8.3 filename limitations. - -long name at unicode.org short name latest '#' ------------------------- ---------- ---------- -ArabicShaping-#.txt ArabShap.txt 2 -Blocks-#.txt Blocks.txt 3 -CompositionExclusions-#.txt CompExcl.txt 1 -EastAsianWidth-#.txt EAWidth.txt 3 -Index-#.txt Index.txt 3.0.0 -Jamo-#.txt Jamo.txt 2 -LineBreak-#.txt LineBrk.txt 5 -NamesList-#.txt Names.txt 3.0.0 -NamesList-#.html NamesList.html 1 -PropList-#.txt Props.txt 3.0.0 -SpecialCasing-#.txt SpecCase.txt 2 -UnicodeData-#.txt Unicode.300 3.0.0 -UnicodeData-#.html Unicode3.html 3.0.0 -UnicodeCharacterDatabase-#.html UCD300.html 3.0.0 - -The *.pl files are generated from these files by the 'mktables.PL' script. - -While the files have been renamed the links in the html files haven't. - --- -jhi@iki.fi diff --git a/lib/unicode/SpecCase.txt b/lib/unicode/SpecCase.txt index af002ef..94662d3 100644 --- a/lib/unicode/SpecCase.txt +++ b/lib/unicode/SpecCase.txt @@ -1,4 +1,4 @@ -# SpecialCasing-2.txt +# SpecialCasing-3.txt # # Special Casing Properties # @@ -26,26 +26,33 @@ # := # := (+ )* # := -# := [0-1A-Fa-f] +# := [0-9A-Fa-f] # := # -# := ? (+ )* -# := ( "_" )? ( "_" )? +# := ? (+ )* +# := ( "_" )? ( "_" )? # := 2-letter country code, # as in http://www.unicode.org/unicode/onlinedat/countries.html # := 2-letter code, # as in http://www.unicode.org/unicode/onlinedat/languages.html -# := "FINAL" | "NON_FINAL" | "MODERN" | "NON_MODERN" +# := "FINAL" | "NON_FINAL" | "MODERN" | "NON_MODERN" | "AFTER_i" +# +# A condition list overrides the normal behavior if all of the listed conditions are true. +# Case distinctions in the condition list are not significant. # -# A condition list overrides the normal behavior if any of the listed conditions is true. # FINAL: The letter is not followed by a letter of category L* (e.g. Ll, Lt, Lu, Lm, or Lo). # MODERN: The mapping is only used for modern text. +# AFTER_i: The last base character was "i" 0069 +# # Conditions preceded by "NON_" represent the negation of the condition # # New contexts may be added in the future. -# Parsers of this file must be prepared to deal with that situation. # Additional whitespace around elements is optional. Blank lines are ignored in parsing. # On any line, all text following "#" is a comment, and are ignored in parsing. +# +# Parsers of this file must be prepared to deal future additions to this format: +# * Additional contexts +# * Additional fields # ================================================================================ # ================================================================================ @@ -76,7 +83,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH # No corresponding uppercase precomposed character -0149; 0149; 02BC 006E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE +0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE 0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS 03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS 01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON @@ -199,7 +206,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH # 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA # 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA -# Note: the following cases are not included, since they would normalize in lowercasing +# Note: the following cases are not included, since they would case-fold in lowercasing # 03C3; 03C2; 03A3; 03A3; FINAL; # GREEK SMALL LETTER SIGMA # 03C2; 03C3; 03A3; 03A3; NON_FINAL; # GREEK SMALL LETTER FINAL SIGMA @@ -208,12 +215,16 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH # Locale-sensitive mappings # ================================================================================ +# Lithuanian + +0307; 0307; ; ; lt AFTER_i; # Remove DOT ABOVE after "i" with upper or titlecase + # Turkish -0049; 0131; 0049; 0049; TR; # LATIN CAPITAL LETTER I -0069; 0069; 0130; 0130; TR; # LATIN SMALL LETTER I +0049; 0131; 0049; 0049; tr; # LATIN CAPITAL LETTER I +0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I # Note: the following cases are already in the UnicodeData file. -# 0131; 0131; 0049; 0049; TR; # LATIN SMALL LETTER DOTLESS I -# 0130; 0069; 0130; 0130; TR; # LATIN CAPITAL LETTER I WITH DOT ABOVE +# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I +# 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE diff --git a/lib/unicode/To/Digit.pl b/lib/unicode/To/Digit.pl index a96bc1c..4bace1e 100644 --- a/lib/unicode/To/Digit.pl +++ b/lib/unicode/To/Digit.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0030 0039 0000 diff --git a/lib/unicode/To/Lower.pl b/lib/unicode/To/Lower.pl index a78a7e4..89755b7 100644 --- a/lib/unicode/To/Lower.pl +++ b/lib/unicode/To/Lower.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0041 005a 0061 diff --git a/lib/unicode/To/Title.pl b/lib/unicode/To/Title.pl index d8f5c04..cadeaf9 100644 --- a/lib/unicode/To/Title.pl +++ b/lib/unicode/To/Title.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0061 007a 0041 diff --git a/lib/unicode/To/Upper.pl b/lib/unicode/To/Upper.pl index 1fc7637..d6c03d3 100644 --- a/lib/unicode/To/Upper.pl +++ b/lib/unicode/To/Upper.pl @@ -1,5 +1,5 @@ # !!!!!!! DO NOT EDIT THIS FILE !!!!!!! -# This file is built by mktables.PL from e.g. Unicode.300. +# This file is built by mktables.PL from e.g. Unicode.301. # Any changes made here will be lost! return <<'END'; 0061 007a 0041 diff --git a/lib/unicode/UCD300.html b/lib/unicode/UCD301.html similarity index 54% rename from lib/unicode/UCD300.html rename to lib/unicode/UCD301.html index 113d311..284349e 100644 --- a/lib/unicode/UCD300.html +++ b/lib/unicode/UCD301.html @@ -4,342 +4,198 @@ - - - - - - - - Unicode Character Database - - - - - -

UNICODE CHARACTER DATABASE
-Version 3.0.0

- +

UNICODE CHARACTER DATABASE
+Version 3.0.1

- - - - - + - - - - - - - - - + - - - - - + - - - - - + - - - - - + -
Revision3.0.03.0.1
AuthorsMark Davis and Ken Whistler
Date1999-09-112000-08-17
This Versionftp://ftp.unicode.org/Public/3.0-Update/UnicodeCharacterDatabase-3.0.0.htmlhttp://www.unicode.org/Public/3.0-Update1/UnicodeCharacterDatabase-3.0.1.html
Previous Versionn/ahttp://www.unicode.org/Public/3.0-Update/UnicodeCharacterDatabase-3.0.0.html
Latest Versionftp://ftp.unicode.org/Public/3.0-Update/UnicodeCharacterDatabase-3.0.0.htmlhttp://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html
- -

Copyright © 1995-1999 Unicode, Inc. All Rights reserved.

- -

Disclaimer

- -

The Unicode Character Database is provided as is by Unicode, Inc. No claims - -are made as to fitness for any particular purpose. No warranties of any kind are - -expressed or implied. The recipient agrees to determine applicability of - -information provided. If this file has been purchased on magnetic or optical - -media from Unicode, Inc., the sole remedy for any claim will be exchange of - -defective media within 90 days of receipt.

- -

This disclaimer is applicable for all other data files accompanying the - -Unicode Character Database, some of which have been compiled by the Unicode - -Consortium, and some of which have been supplied by other sources.

- -

Limitations on Rights to Redistribute This Data

- -

Recipient is granted the right to make copies in any form for internal - -distribution and to freely use the information supplied in the creation of - -products supporting the UnicodeTM Standard. The files in the Unicode - -Character Database can be redistributed to third parties or other organizations - -(whether for profit or not) as long as this notice and the disclaimer notice are - -retained. Information can be extracted from these files and used in - -documentation or programs, as long as there is an accompanying notice indicating - -the source.

- -

Introduction

- -

The Unicode Character Database is a set of files that define the Unicode - -character properties and internal mappings. For more information about character - -properties and mappings, see The - -Unicode Standard.

- -

The Unicode Character Database has been updated to reflect Version 3.0 of the - -Unicode Standard, with many characters added to those published in Version 2.0. - -A number of corrections have also been made to case mappings or other errors in - -the database noted since the publication of Version 2.0. Normative bidirectional - -properties have also been modified to reflect decisions of the Unicode Technical - -Committee.

- -

For more information on versions of the Unicode Standard and how to reference - -them, see http://www.unicode.org/unicode/standard/versions/.

- -

Conformance

- -

Character properties may be either normative or informative. Normative - -means that implementations that claim conformance to the Unicode Standard (at a - -particular version) and which make use of a particular property or field must - -follow the specifications of the standard for that property or field in order to - -be conformant. The term normative when applied to a property or field of - -the Unicode Character Database, does not mean that the value of that - -field will never change. Corrections and extensions to the standard in the - -future may require minor changes to normative values, even though the Unicode - -Technical Committee strives to minimize such changes. An informative property - -or field is strongly recommended, but a conformant implementation is free to use - -or change such values as it may require while still being conformant to the - -standard. Particular implementations may choose to override the properties and - -mappings that are not normative. In that case, it is up to the implementer to - -establish a protocol to convey that information.

- -

Files

- -

The following summarizes the files in the Unicode Character Database.  For - -more information about these files, see the referenced technical report or - -section of Unicode Standard, Version 3.0.

- -

UnicodeData.txt (Chapter 4) - -

    - -
  • The main file in the Unicode Character Database.
    • - -
  • For detailed information on the format, see UnicodeData.html. - - This file also characterizes which properties are normative and which are - - informative.
    • - -
- -

PropList.txt (Chapter 4) - -

    - -
  • Additional informative properties list: Alphabetic, Ideographic, - - and Mathematical, among others.
    • - -
- -

SpecialCasing.txt (Chapter 4) - -

    - -
  • List of informative special casing properties, including one-to-many - - mappings such as SHARP S => "SS", and locale-specific mappings, - - such as for Turkish dotless i.
    • - -
- -

Blocks.txt (Chapter 14) - -

    - -
  • List of normative block names.
    • - -
- -

Jamo.txt (Chapter 4) - -

    - -
  • List of normative Jamo short names, used in deriving HANGUL SYLLABLE names - - algorithmically.
    • - -
- -

ArabicShaping.txt (Section 8.2) - -

    - -
  • Basic Arabic and Syriac character shaping properties, such as initial, - - medial and final shapes. These properties are normative for minimal shaping - - of Arabic and Syriac.
    • - -
- -

NamesList.txt (Chapter 14) - -

    - -
  • This file duplicates some of the material in the UnicodeData file, and - - adds informative annotations uses in the character charts, as printed in the - - Unicode Standard.
    • - -
  • Note: The information in NamesList.txt and Index.txt files matches - - the appropriate version of the book. Changes in the Unicode Character - - Database since then may not be reflected in these files, since they are - - primarily of archival interest.
    • - -
- -

Index.txt (Chapter 14) - -

    - -
  • Informative index to Unicode characters, as printed in the Unicode - - Standard
    • - -
  • Note: The information in NamesList.txt and Index.txt files matches - - the appropriate version of the book. Changes in the Unicode Character - - Database since then may not be reflected in these files, since they are - - primarily of archival interest.
    • - -
- -

CompositionExclusions.txt (UTR#15 - -Unicode Normalization Forms) - -

    - -
  • Normative properties for normalization.
    • - -
- -

LineBreak.txt (UTR - -#14: Line Breaking Properties) - -

    - -
  • Normative and informative properties for line breaking. To see which - - properties are informative and which are normative, consult UTR#14.
    • - -
- -

EastAsianWidth.txt (UTR - -#11: East Asian Character Width) - -

    - -
  • Informative properties for determining the choice of wide vs. narrow - - glyphs in East Asian contexts.
    • - -
- -

diffXvY.txt - -

    - -
  • Mechanically-generated informative files containing accumulated - - differences between successive versions of UnicodeData.txt
    • - -
- - - - - - - - - +

Copyright © 1995-2000 Unicode, Inc. All Rights reserved.

+

Disclaimer

+

The Unicode Character Database is provided as is by Unicode, Inc. No claims +are made as to fitness for any particular purpose. No warranties of any kind are +expressed or implied. The recipient agrees to determine applicability of +information provided. If this file has been purchased on magnetic or optical +media from Unicode, Inc., the sole remedy for any claim will be exchange of +defective media within 90 days of receipt.

+

This disclaimer is applicable for all other data files accompanying the +Unicode Character Database, some of which have been compiled by the Unicode +Consortium, and some of which have been supplied by other sources.

+

Limitations on Rights to Redistribute This Data

+

Recipient is granted the right to make copies in any form for internal +distribution and to freely use the information supplied in the creation of +products supporting the UnicodeTM Standard. The files in the Unicode +Character Database can be redistributed to third parties or other organizations +(whether for profit or not) as long as this notice and the disclaimer notice are +retained. Information can be extracted from these files and used in +documentation or programs, as long as there is an accompanying notice indicating +the source.

+

Introduction

+

The Unicode Character Database is a set of files that define the Unicode +character properties and internal mappings. For more information about character +properties and mappings, see The Unicode Standard.

+

The Unicode Character Database has been updated to reflect Version 3.0 of the +Unicode Standard, with many characters added to those published in Version 2.0. +A number of corrections have also been made to case mappings or other errors in +the database noted since the publication of Version 2.0. Normative bidirectional +properties have also been modified to reflect decisions of the Unicode Technical +Committee.

+

For more information on versions of the Unicode Standard and how to reference +them, see http://www.unicode.org/unicode/standard/versions/.

+

Conformance

+

Character properties may be either normative or informative. Normative +means that implementations that claim conformance to the Unicode Standard (at a +particular version) and which make use of a particular property or field must +follow the specifications of the standard for that property or field in order to +be conformant. The term normative when applied to a property or field of +the Unicode Character Database, does not mean that the value of that +field will never change. Corrections and extensions to the standard in the +future may require minor changes to normative values, even though the Unicode +Technical Committee strives to minimize such changes. An informative property +or field is strongly recommended, but a conformant implementation is free to use +or change such values as it may require while still being conformant to the +standard. Particular implementations may choose to override the properties and +mappings that are not normative. In that case, it is up to the implementer to +establish a protocol to convey that information.

+

Files

+

The following summarizes the files in the Unicode Character Database.  For +more information about these files, see the referenced technical report(s) or +section of Unicode Standard, Version 3.0.

+

UnicodeData.txt (Chapter 4, UTR #21: Case Mappings, UAX #15 Unicode Normalization +Forms) +

    +
  • The main file in the Unicode Character Database.
    • +
  • For detailed information on the format, see UnicodeData.html. + This file also characterizes which properties are normative and which are + informative.
    • +
+

PropList.txt (Chapter 4) +

    +
  • Additional informative properties list: Alphabetic, Ideographic, + and Mathematical, among others.
    • +
+

SpecialCasing.txt (Chapter 4, UTR #21: Case Mappings) +

    +
  • List of informative special casing properties, including one-to-many + mappings such as SHARP S => "SS", and locale-specific mappings, + such as for Turkish dotless i.
    • +
+

Blocks.txt (Chapter 14) +

    +
  • List of normative block names.
    • +
+

Jamo.txt (Chapter 4) +

    +
  • List of normative Jamo short names, used in deriving HANGUL SYLLABLE names + algorithmically.
    • +
+

ArabicShaping.txt (Section 8.2) +

    +
  • Basic Arabic and Syriac character shaping properties, such as initial, + medial and final shapes. These properties are normative for minimal shaping + of Arabic and Syriac.
    • +
+

NamesList.txt (Chapter 14) +

    +
  • This file duplicates some of the material in the UnicodeData file, and + adds informative annotations uses in the character charts, as printed in the + Unicode Standard.
    • +
  • Note: The information in NamesList.txt and Index.txt files matches + the appropriate version of the book. Changes in the Unicode Character + Database since then may not be reflected in these files, since they are + primarily of archival interest.
    • +
+

Index.txt (Chapter 14) +

    +
  • Informative index to Unicode characters, as printed in the Unicode + Standard
    • +
  • Note: The information in NamesList.txt and Index.txt files matches + the appropriate version of the book. Changes in the Unicode Character + Database since then may not be reflected in these files, since they are + primarily of archival interest.
    • +
+

CompositionExclusions.txt (UAX #15 Unicode Normalization +Forms) +

    +
  • Normative properties for normalization.
    • +
+

LineBreak.txt (UAX +#14: Line Breaking Properties) +

    +
  • Normative and informative properties for line breaking. To see which + properties are informative and which are normative, consult UAX #14.
    • +
+

EastAsianWidth.txt (UAX +#11: East Asian Character Width) +

    +
  • Informative properties for determining the choice of wide vs. narrow + glyphs in East Asian contexts.
    • +
+

BidiMirroring.txt (UAX #9: The +Bidirectional Algorithm)

+
    +
  • Informative properties for substituting characters in an implementation of + bidirectional mirroring.
    • +
+

CaseFolding.txt (UTR +#21: Case Mappings)

+
    +
  • Informative file mapping characters to their case-folded form.
    • +
+

NormalizationTest.txt (UAX #15 Unicode Normalization +Forms)

+
    +
  • Normative test file for conformance to Unicode Normalization Forms.
    • +
+

diffXvY.txt +

    +
  • Mechanically-generated informative files containing accumulated + differences between successive versions of UnicodeData.txt
    • +
+ + + + diff --git a/lib/unicode/Unicode.300 b/lib/unicode/Unicode.301 similarity index 99% rename from lib/unicode/Unicode.300 rename to lib/unicode/Unicode.301 index 6a54d3d..6804a75 100644 --- a/lib/unicode/Unicode.300 +++ b/lib/unicode/Unicode.301 @@ -130,7 +130,7 @@ 0081;;Cc;0;BN;;;;;N;;;;; 0082;;Cc;0;BN;;;;;N;BREAK PERMITTED HERE;;;; 0083;;Cc;0;BN;;;;;N;NO BREAK HERE;;;; -0084;;Cc;0;BN;;;;;N;INDEX;;;; +0084;;Cc;0;BN;;;;;N;;;;; 0085;;Cc;0;B;;;;;N;NEXT LINE;;;; 0086;;Cc;0;BN;;;;;N;START OF SELECTED AREA;;;; 0087;;Cc;0;BN;;;;;N;END OF SELECTED AREA;;;; @@ -420,7 +420,7 @@ 01A3;LATIN SMALL LETTER OI;Ll;0;L;;;;;N;LATIN SMALL LETTER O I;gha;01A2;;01A2 01A4;LATIN CAPITAL LETTER P WITH HOOK;Lu;0;L;;;;;N;LATIN CAPITAL LETTER P HOOK;;;01A5; 01A5;LATIN SMALL LETTER P WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER P HOOK;;01A4;;01A4 -01A6;LATIN LETTER YR;Lu;0;L;;;;;N;LATIN LETTER Y R;;;0280; +01A6;LATIN LETTER YR;Lu;0;L;;;;;N;LATIN LETTER Y R;*;;0280; 01A7;LATIN CAPITAL LETTER TONE TWO;Lu;0;L;;;;;N;;;;01A8; 01A8;LATIN SMALL LETTER TONE TWO;Ll;0;L;;;;;N;;;01A7;;01A7 01A9;LATIN CAPITAL LETTER ESH;Lu;0;L;;;;;N;;;;0283; @@ -608,7 +608,7 @@ 027D;LATIN SMALL LETTER R WITH TAIL;Ll;0;L;;;;;N;LATIN SMALL LETTER R HOOK;;;; 027E;LATIN SMALL LETTER R WITH FISHHOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER FISHHOOK R;;;; 027F;LATIN SMALL LETTER REVERSED R WITH FISHHOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER REVERSED FISHHOOK R;;;; -0280;LATIN LETTER SMALL CAPITAL R;Ll;0;L;;;;;N;;;01A6;;01A6 +0280;LATIN LETTER SMALL CAPITAL R;Ll;0;L;;;;;N;;*;01A6;;01A6 0281;LATIN LETTER SMALL CAPITAL INVERTED R;Ll;0;L;;;;;N;;;;; 0282;LATIN SMALL LETTER S WITH HOOK;Ll;0;L;;;;;N;LATIN SMALL LETTER S HOOK;;;; 0283;LATIN SMALL LETTER ESH;Ll;0;L;;;;;N;;;01A9;;01A9 @@ -2639,16 +2639,16 @@ 0F27;TIBETAN DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 0F28;TIBETAN DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 0F29;TIBETAN DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; -0F2A;TIBETAN DIGIT HALF ONE;No;0;L;;;;;N;;;;; -0F2B;TIBETAN DIGIT HALF TWO;No;0;L;;;;;N;;;;; -0F2C;TIBETAN DIGIT HALF THREE;No;0;L;;;;;N;;;;; -0F2D;TIBETAN DIGIT HALF FOUR;No;0;L;;;;;N;;;;; -0F2E;TIBETAN DIGIT HALF FIVE;No;0;L;;;;;N;;;;; -0F2F;TIBETAN DIGIT HALF SIX;No;0;L;;;;;N;;;;; -0F30;TIBETAN DIGIT HALF SEVEN;No;0;L;;;;;N;;;;; -0F31;TIBETAN DIGIT HALF EIGHT;No;0;L;;;;;N;;;;; -0F32;TIBETAN DIGIT HALF NINE;No;0;L;;;;;N;;;;; -0F33;TIBETAN DIGIT HALF ZERO;No;0;L;;;;;N;;;;; +0F2A;TIBETAN DIGIT HALF ONE;No;0;L;;;;1/2;N;;;;; +0F2B;TIBETAN DIGIT HALF TWO;No;0;L;;;;3/2;N;;;;; +0F2C;TIBETAN DIGIT HALF THREE;No;0;L;;;;5/2;N;;;;; +0F2D;TIBETAN DIGIT HALF FOUR;No;0;L;;;;7/2;N;;;;; +0F2E;TIBETAN DIGIT HALF FIVE;No;0;L;;;;9/2;N;;;;; +0F2F;TIBETAN DIGIT HALF SIX;No;0;L;;;;11/2;N;;;;; +0F30;TIBETAN DIGIT HALF SEVEN;No;0;L;;;;13/2;N;;;;; +0F31;TIBETAN DIGIT HALF EIGHT;No;0;L;;;;15/2;N;;;;; +0F32;TIBETAN DIGIT HALF NINE;No;0;L;;;;17/2;N;;;;; +0F33;TIBETAN DIGIT HALF ZERO;No;0;L;;;;-1/2;N;;;;; 0F34;TIBETAN MARK BSDUS RTAGS;So;0;L;;;;;N;;du ta;;; 0F35;TIBETAN MARK NGAS BZUNG NYI ZLA;Mn;220;NSM;;;;;N;TIBETAN HONORIFIC UNDER RING;nge zung nyi da;;; 0F36;TIBETAN MARK CARET -DZUD RTAGS BZHI MIG CAN;So;0;L;;;;;N;;dzu ta shi mig chen;;; @@ -2789,7 +2789,7 @@ 0FCA;TIBETAN SYMBOL NOR BU NYIS -KHYIL;So;0;L;;;;;N;;norbu nyi khyi;;; 0FCB;TIBETAN SYMBOL NOR BU GSUM -KHYIL;So;0;L;;;;;N;;norbu sum khyi;;; 0FCC;TIBETAN SYMBOL NOR BU BZHI -KHYIL;So;0;L;;;;;N;;norbu shi khyi;;; -0FCF;TIBETAN SIGN RDEL NAG GSUM;So;0;L;;;;;N;;;;; +0FCF;TIBETAN SIGN RDEL NAG GSUM;So;0;L;;;;;N;;dena sum;;; 1000;MYANMAR LETTER KA;Lo;0;L;;;;;N;;;;; 1001;MYANMAR LETTER KHA;Lo;0;L;;;;;N;;;;; 1002;MYANMAR LETTER GA;Lo;0;L;;;;;N;;;;; @@ -7518,10 +7518,10 @@ 318E;HANGUL LETTER ARAEAE;Lo;0;L; 11A1;;;;N;HANGUL LETTER ALAE AE;;;; 3190;IDEOGRAPHIC ANNOTATION LINKING MARK;So;0;L;;;;;N;KANBUN TATETEN;Kanbun Tateten;;; 3191;IDEOGRAPHIC ANNOTATION REVERSE MARK;So;0;L;;;;;N;KAERITEN RE;Kaeriten;;; -3192;IDEOGRAPHIC ANNOTATION ONE MARK;No;0;L; 4E00;;;;N;KAERITEN ITI;Kaeriten;;; -3193;IDEOGRAPHIC ANNOTATION TWO MARK;No;0;L; 4E8C;;;;N;KAERITEN NI;Kaeriten;;; -3194;IDEOGRAPHIC ANNOTATION THREE MARK;No;0;L; 4E09;;;;N;KAERITEN SAN;Kaeriten;;; -3195;IDEOGRAPHIC ANNOTATION FOUR MARK;No;0;L; 56DB;;;;N;KAERITEN SI;Kaeriten;;; +3192;IDEOGRAPHIC ANNOTATION ONE MARK;No;0;L; 4E00;;;1;N;KAERITEN ITI;Kaeriten;;; +3193;IDEOGRAPHIC ANNOTATION TWO MARK;No;0;L; 4E8C;;;2;N;KAERITEN NI;Kaeriten;;; +3194;IDEOGRAPHIC ANNOTATION THREE MARK;No;0;L; 4E09;;;3;N;KAERITEN SAN;Kaeriten;;; +3195;IDEOGRAPHIC ANNOTATION FOUR MARK;No;0;L; 56DB;;;4;N;KAERITEN SI;Kaeriten;;; 3196;IDEOGRAPHIC ANNOTATION TOP MARK;So;0;L; 4E0A;;;;N;KAERITEN ZYOU;Kaeriten;;; 3197;IDEOGRAPHIC ANNOTATION MIDDLE MARK;So;0;L; 4E2D;;;;N;KAERITEN TYUU;Kaeriten;;; 3198;IDEOGRAPHIC ANNOTATION BOTTOM MARK;So;0;L; 4E0B;;;;N;KAERITEN GE;Kaeriten;;; @@ -7585,16 +7585,16 @@ 321A;PARENTHESIZED HANGUL PHIEUPH A;So;0;L; 0028 1111 1161 0029;;;;N;PARENTHESIZED HANGUL PA;;;; 321B;PARENTHESIZED HANGUL HIEUH A;So;0;L; 0028 1112 1161 0029;;;;N;PARENTHESIZED HANGUL HA;;;; 321C;PARENTHESIZED HANGUL CIEUC U;So;0;L; 0028 110C 116E 0029;;;;N;PARENTHESIZED HANGUL JU;;;; -3220;PARENTHESIZED IDEOGRAPH ONE;No;0;L; 0028 4E00 0029;;;;N;;;;; -3221;PARENTHESIZED IDEOGRAPH TWO;No;0;L; 0028 4E8C 0029;;;;N;;;;; -3222;PARENTHESIZED IDEOGRAPH THREE;No;0;L; 0028 4E09 0029;;;;N;;;;; -3223;PARENTHESIZED IDEOGRAPH FOUR;No;0;L; 0028 56DB 0029;;;;N;;;;; -3224;PARENTHESIZED IDEOGRAPH FIVE;No;0;L; 0028 4E94 0029;;;;N;;;;; -3225;PARENTHESIZED IDEOGRAPH SIX;No;0;L; 0028 516D 0029;;;;N;;;;; -3226;PARENTHESIZED IDEOGRAPH SEVEN;No;0;L; 0028 4E03 0029;;;;N;;;;; -3227;PARENTHESIZED IDEOGRAPH EIGHT;No;0;L; 0028 516B 0029;;;;N;;;;; -3228;PARENTHESIZED IDEOGRAPH NINE;No;0;L; 0028 4E5D 0029;;;;N;;;;; -3229;PARENTHESIZED IDEOGRAPH TEN;No;0;L; 0028 5341 0029;;;;N;;;;; +3220;PARENTHESIZED IDEOGRAPH ONE;No;0;L; 0028 4E00 0029;;;1;N;;;;; +3221;PARENTHESIZED IDEOGRAPH TWO;No;0;L; 0028 4E8C 0029;;;2;N;;;;; +3222;PARENTHESIZED IDEOGRAPH THREE;No;0;L; 0028 4E09 0029;;;3;N;;;;; +3223;PARENTHESIZED IDEOGRAPH FOUR;No;0;L; 0028 56DB 0029;;;4;N;;;;; +3224;PARENTHESIZED IDEOGRAPH FIVE;No;0;L; 0028 4E94 0029;;;5;N;;;;; +3225;PARENTHESIZED IDEOGRAPH SIX;No;0;L; 0028 516D 0029;;;6;N;;;;; +3226;PARENTHESIZED IDEOGRAPH SEVEN;No;0;L; 0028 4E03 0029;;;7;N;;;;; +3227;PARENTHESIZED IDEOGRAPH EIGHT;No;0;L; 0028 516B 0029;;;8;N;;;;; +3228;PARENTHESIZED IDEOGRAPH NINE;No;0;L; 0028 4E5D 0029;;;9;N;;;;; +3229;PARENTHESIZED IDEOGRAPH TEN;No;0;L; 0028 5341 0029;;;10;N;;;;; 322A;PARENTHESIZED IDEOGRAPH MOON;So;0;L; 0028 6708 0029;;;;N;;;;; 322B;PARENTHESIZED IDEOGRAPH FIRE;So;0;L; 0028 706B 0029;;;;N;;;;; 322C;PARENTHESIZED IDEOGRAPH WATER;So;0;L; 0028 6C34 0029;;;;N;;;;; @@ -10615,3 +10615,7 @@ FFFA;INTERLINEAR ANNOTATION SEPARATOR;Cf;0;BN;;;;;N;;;;; FFFB;INTERLINEAR ANNOTATION TERMINATOR;Cf;0;BN;;;;;N;;;;; FFFC;OBJECT REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; +F0000;;Co;0;L;;;;;N;;;;; +FFFFD;;Co;0;L;;;;;N;;;;; +100000;;Co;0;L;;;;;N;;;;; +10FFFD;;Co;0;L;;;;;N;;;;; diff --git a/lib/unicode/Unicode3.html b/lib/unicode/Unicode3.html deleted file mode 100644 index a08a25e..0000000 --- a/lib/unicode/Unicode3.html +++ /dev/null @@ -1,1988 +0,0 @@ - - - - - - - - - - - - -UnicodeData File Format - - - - - - - - - -

UnicodeData File Format
-Version 3.0.0

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Revision3.0.0
AuthorsMark Davis and Ken Whistler
Date1999-09-12
This Versionftp://ftp.unicode.org/Public/3.0-Update/UnicodeData-3.0.0.html
Previous Versionn/a
Latest Versionftp://ftp.unicode.org/Public/3.0-Update/UnicodeData-3.0.0.html
- - - -

Copyright © 1995-1999 Unicode, Inc. All Rights reserved.
- -For more information, including Disclamer and Limitations, see UnicodeCharacterDatabase-3.0.0.html

- - - -

This document describes the format of the UnicodeData.txt file, which is one of the - -files in the Unicode Character Database. The document is divided into the following - -sections: - - - -

- - - -

Warning: the information in this file does not completely describe the use and - -interpretation of Unicode character properties and behavior. It must be used in - -conjunction with the data in the other files in the Unicode Character Database, and relies - -on the notation and definitions supplied in The Unicode -Standard. All chapter references - -are to Version 3.0 of the standard.

- - - -

Field Formats

- - - -

The file consists of lines containing fields terminated by semicolons. Each line - -represents the data for one encoded character in the Unicode Standard. Every encoded - -character has a data entry, with the exception of certain special ranges, as detailed - -below. - - - -

    - -
  • There are six special ranges of characters that are represented only by their start and - - end characters, since the properties in the file are uniform, except for code values - - (which are all sequential and assigned).
    • - -
  • The names of CJK ideograph characters and the names and decompositions of Hangul - - syllable characters are algorithmically derivable. (See the Unicode Standard and Unicode Technical Report #15 for - - more information).
    • - -
  • Surrogate code values and private use characters have no names.
    • - -
  • The Private Use character outside of the BMP (U+F0000..U+FFFFD, U+100000..U+10FFFD) are - - not listed. These correspond to surrogate pairs where the first surrogate is in the High - - Surrogate Private Use section.
    • - -
- - - -

The exact ranges represented by start and end characters are: - - - -

    - -
  • CJK Ideographs Extension A (U+3400 - U+4DB5)
    • - -
  • CJK Ideographs (U+4E00 - U+9FA5)
    • - -
  • Hangul Syllables (U+AC00 - U+D7A3)
    • - -
  • Non-Private Use High Surrogates (U+D800 - U+DB7F)
    • - -
  • Private Use High Surrogates (U+DB80 - U+DBFF)
    • - -
  • Low Surrogates (U+DC00 - U+DFFF)
    • - -
  • The Private Use Area (U+E000 - U+F8FF)
    • - -
- - - -

The following table describes the format and meaning of each field in a data entry in - -the UnicodeData file. Fields which contain normative information are so indicated.

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Field

Name

Status

Explanation

0Code valuenormativeCode value in 4-digit hexadecimal format.
1Character namenormativeThese names match exactly the names published in Chapter 14 of the - - Unicode Standard, Version 3.0.
2General Category normative / informative
- - (see below)		This is a useful breakdown into various "character types" which - - can be used as a default categorization in implementations. See below for a brief - - explanation.
3Canonical Combining Classes normativeThe classes used for the Canonical Ordering Algorithm in the Unicode - - Standard. These classes are also printed in Chapter 4 of the Unicode Standard.
4Bidirectional Category normativeSee the list below for an explanation of the abbreviations used in this - - field. These are the categories required by the Bidirectional Behavior Algorithm in the - - Unicode Standard. These categories are summarized in Chapter 3 of the Unicode Standard.
5Character Decomposition - MappingnormativeIn the Unicode Standard, not all of the mappings are full (maximal) - - decompositions. Recursive application of look-up for decompositions will, in all cases, - - lead to a maximal decomposition. The decomposition mappings match exactly the - - decomposition mappings published with the character names in the Unicode Standard.
6Decimal digit valuenormativeThis is a numeric field. If the character has the decimal digit property, - - as specified in Chapter 4 of the Unicode Standard, the value of that digit is represented - - with an integer value in this field
7Digit valuenormativeThis is a numeric field. If the character represents a digit, not - - necessarily a decimal digit, the value is here. This covers digits which do not form - - decimal radix forms, such as the compatibility superscript digits
8Numeric valuenormativeThis is a numeric field. If the character has the numeric property, as - - specified in Chapter 4 of the Unicode Standard, the value of that character is represented - - with an integer or rational number in this field. This includes fractions as, e.g., - - "1/5" for U+2155 VULGAR FRACTION ONE FIFTH Also included are numerical values - - for compatibility characters such as circled numbers.
8MirrorednormativeIf the character has been identified as a "mirrored" character - - in bidirectional text, this field has the value "Y"; otherwise "N". - - The list of mirrored characters is also printed in Chapter 4 of the Unicode Standard.
10Unicode 1.0 NameinformativeThis is the old name as published in Unicode 1.0. This name is only - - provided when it is significantly different from the Unicode 3.0 name for the character.
1110646 comment fieldinformativeThis is the ISO 10646 comment field. It is in parantheses in the 10646 - - names list.
12Uppercase MappinginformativeUpper case equivalent mapping. If a character is part of an alphabet with - - case distinctions, and has an upper case equivalent, then the upper case equivalent is in - - this field. See the explanation below on case distinctions. These mappings are always - - one-to-one, not one-to-many or many-to-one. This field is informative.
13Lowercase MappinginformativeSimilar to Uppercase mapping
14Titlecase MappinginformativeSimilar to Uppercase mapping
- - - -

General Category

- - - -

The values in this field are abbreviations for the following. Some of the values are - -normative, and some are informative. For more information, see the Unicode Standard.

- - - -

Note: the standard does not assign information to control characters (except for - -certain cases in the Bidirectional Algorithm). Implementations will generally also assign - -categories to certain control characters, notably CR and LF, according to platform - -conventions.

- - - -

Normative Categories

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Abbr.

Description

LuLetter, Uppercase
LlLetter, Lowercase
LtLetter, Titlecase
MnMark, Non-Spacing
McMark, Spacing Combining
MeMark, Enclosing
NdNumber, Decimal Digit
NlNumber, Letter
NoNumber, Other
ZsSeparator, Space
ZlSeparator, Line
ZpSeparator, Paragraph
CcOther, Control
CfOther, Format
CsOther, Surrogate
CoOther, Private Use
CnOther, Not Assigned (no characters in the file have this property)
- - - -

Informative Categories

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Abbr.

Description

LmLetter, Modifier
LoLetter, Other
PcPunctuation, Connector
PdPunctuation, Dash
PsPunctuation, Open
PePunctuation, Close
PiPunctuation, Initial quote (may behave like Ps or Pe depending on usage)
PfPunctuation, Final quote (may behave like Ps or Pe depending on usage)
PoPunctuation, Other
SmSymbol, Math
ScSymbol, Currency
SkSymbol, Modifier
SoSymbol, Other
- - - -

Bidirectional Category

- - - -

Please refer to Chapter 3 for an explanation of the algorithm for Bidirectional - -Behavior and an explanation of the significance of these categories. An up-to-date version - -can be found on Unicode Technical - -Report #9: The Bidirectional Algorithm. These values are normative.

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Type

Description

LLeft-to-Right
LRELeft-to-Right Embedding
LROLeft-to-Right Override
RRight-to-Left
ALRight-to-Left Arabic
RLERight-to-Left Embedding
RLORight-to-Left Override
PDFPop Directional Format
ENEuropean Number
ESEuropean Number Separator
ETEuropean Number Terminator
ANArabic Number
CSCommon Number Separator
NSMNon-Spacing Mark
BNBoundary Neutral
BParagraph Separator
SSegment Separator
WSWhitespace
ONOther Neutrals
- - - -

Character Decomposition Mapping

- - - -

The decomposition is a normative property of a character. The tags supplied with - -certain decomposition mappings generally indicate formatting information. Where no such - -tag is given, the mapping is designated as canonical. Conversely, the presence of a - -formatting tag also indicates that the mapping is a compatibility mapping and not a - -canonical mapping. In the absence of other formatting information in a compatibility - -mapping, the tag is used to distinguish it from canonical mappings.

- - - -

In some instances a canonical mapping or a compatibility mapping may consist of a - -single character. For a canonical mapping, this indicates that the character is a - -canonical equivalent of another single character. For a compatibility mapping, this - -indicates that the character is a compatibility equivalent of another single character. - -The compatibility formatting tags used are:

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Tag

Description

<font>  A font variant (e.g. a blackletter form).
<noBreak>  A no-break version of a space or hyphen.
<initial>  An initial presentation form (Arabic).
<medial>  A medial presentation form (Arabic).
<final>  A final presentation form (Arabic).
<isolated>  An isolated presentation form (Arabic).
<circle>  An encircled form.
<super>  A superscript form.
<sub>  A subscript form.
<vertical>  A vertical layout presentation form.
<wide>  A wide (or zenkaku) compatibility character.
<narrow>  A narrow (or hankaku) compatibility character.
<small>  A small variant form (CNS compatibility).
<square>  A CJK squared font variant.
<fraction>  A vulgar fraction form.
<compat>  Otherwise unspecified compatibility character.
- - - -

Reminder: There is a difference between decomposition and decomposition mapping. - -The decomposition mappings are defined in the UnicodeData, while the decomposition (also - -termed "full decomposition") is defined in Chapter 3 to use those mappings - - -recursively. - - - -

    - -
  • The canonical decomposition is formed by recursively applying the canonical mappings, - - then applying the canonical reordering algorithm.
    • - -
  • The compatibility decomposition is formed by recursively applying the canonical and - - compatibility mappings, then applying the canonical reordering algorithm.
    • - -
- - - -

Canonical Combining Classes

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

Value

Description

0:Spacing, split, enclosing, reordrant, and Tibetan subjoined
1:Overlays and interior
7:Nuktas
8:Hiragana/Katakana voicing marks
9:Viramas
10:Start of fixed position classes
199:End of fixed position classes
200:Below left attached
202:Below attached
204:Below right attached
208:Left attached (reordrant around single base character)
210:Right attached
212:Above left attached
214:Above attached
216:Above right attached
218:Below left
220:Below
222:Below right
224:Left (reordrant around single base character)
226:Right
228:Above left
230:Above
232:Above right
233:Double below
234:Double above
240:Below (iota subscript)
- - - -

Note: some of the combining classes in this list do not currently have - -members but are specified here for completeness.

- - - -

Decompositions and Normalization

- - - -

Decomposition is specified in Chapter 3. Unicode Technical Report #15: - -Normalization Forms specifies the interaction between decomposition and normalization. The - -most up-to-date version is found on http://www.unicode.org/unicode/reports/tr15/. - -That report specifies how the decompositions defined in UnicodeData.txt are used to derive - -normalized forms of Unicode text.

- - - -

Note that as of the 2.1.9 update of the Unicode Character Database, the decompositions - -in the UnicodeData.txt file can be used to recursively derive the full decomposition in - -canonical order, without the need to separately apply canonical reordering. However, - -canonical reordering of combining character sequences must still be applied in - -decomposition when normalizing source text which contains any combining marks.

- - - -

Case Mappings

- - - -

The case mapping is an informative, default mapping. Case itself, on the other hand, - -has normative status. Thus, for example, 0041 LATIN CAPITAL LETTER A is normatively - -uppercase, but its lowercase mapping the 0061 LATIN SMALL LETTER A is informative. The - -reason for this is that case can be considered to be an inherent property of a particular - -character (and is usually, but not always, derivable from the presence of the terms - -"CAPITAL" or "SMALL" in the character name), but case mappings between - -characters are occasionally influenced by local conventions. For example, certain - -languages, such as Turkish, German, French, or Greek may have small deviations from the - -default mappings listed in UnicodeData.

- - - -

In addition to uppercase and lowercase, because of the inclusion of certain composite - -characters for compatibility, such as 01F1 LATIN CAPITAL LETTER DZ, there is a third case, - -called titlecase, which is used where the first letter of a word is to be - -capitalized (e.g. UPPERCASE, Titlecase, lowercase). An example of such a titlecase letter - -is 01F2 LATIN CAPITAL LETTER D WITH SMALL LETTER Z.

- - - -

The uppercase, titlecase and lowercase fields are only included for characters that - -have a single corresponding character of that type. Composite characters (such as - -"339D SQUARE CM") that do not have a single corresponding character of that type - -can be cased by decomposition.

- - - -

For compatibility with existing parsers, UnicodeData only contains case mappings for - -characters where they are one-to-one mappings; it also omits information about - -context-sensitive case mappings. Information about these special cases can be found in a - -separate data file, SpecialCasing.txt, - -which has been added starting with the 2.1.8 update to the Unicode data files. - -SpecialCasing.txt contains additional informative case mappings that are either not - -one-to-one or which are context-sensitive.

- - - -

Property Invariants

- - - -

Values in UnicodeData.txt are subject to correction as errors are found; however, some - -characteristics of the categories themselves can be considered invariants. Applications - -may wish to take these invariants into account when choosing how to implement character - -properties. The following is a partial list of known invariants for the Unicode Character - -Database.

- - - -

Database Fields

- - - -
    - -
  • The number of fields in UnicodeData.txt is fixed.
    • - -
  • The order of the fields is also fixed.
      - -
    • Any additional information about character properties to be added in the future will - - appear in separate data tables, rather than being added on to the existing table or by - - subdivision or reinterpretation of existing fields.
      • - -
    - -
    • - -
- - - -

General Category

- - - -
    - -
  • There will never be more than 32 General Category values.
      - -
    • It is very unlikely that the Unicode Technical Committee will subdivide the General - - Category partition any further, since that can cause implementations to misbehave. Because - - the General Category is limited to 32 values, 5 bits can be used to represent the - - information, and a 32-bit integer can be used as a bitmask to represent arbitrary sets of - - categories.
      • - -
    - -
    • - -
- - - -

Combining Classes

- - - -
    - -
  • Combining classes are limited to the values 0 to 255.
      - -
    • In practice, there are far fewer than 256 values used. Implementations may take - - advantage of this fact for compression, since only the ordering of the non-zero values - - matters for the Canonical Reordering Algorithm. It is possible for up to 256 values to be - - used in the future; however, UTC decisions in the future may restrict the number of values - - to 128, since this has implementation advantages. [Signed bytes can be used without - - widening to ints in Java, for example.]
      • - -
    - -
    • - -
  • All characters other than those of General Category M* have the combining class 0.
      - -
    • Currently, all characters other than those of General Category Mn have the value 0. - - However, some characters of General Category Me or Mc may be given non-zero values in the - - future.
      • - -
    • The precise values above the value 0 are not invariant--only the relative ordering is - - considered normative. For example, it is not guaranteed in future versions that the class - - of U+05B4 will be precisely 14.
      • - -
    - -
    • - -
- - - -

Case

- - - -
    - -
  • Characters of type Lu, Lt, or Ll are called cased. All characters with an Upper, - - Lower, or Titlecase mapping are cased characters.
      - -
    • However, characters with the General Categories of Lu, Ll, or Lt may not always have - - case mappings, and case mappings may vary by locale. (See - - ftp://ftp.unicode.org/Public/UNIDATA/SpecialCasing.txt).
      • - -
    - -
    • - -
- - - -

Canonical Decomposition

- - - -
    - -
  • Canonical mappings are always in canonical order.
    • - -
  • Canonical mappings have only the first of a pair possibly further decomposing.
    • - -
  • Canonical decompositions are "transparent" to other character data:
      - -
    • BIDI(a) = BIDI(principal(canonicalDecomposition(a))
      • - -
    • Category(a) = Category(principal(canonicalDecomposition(a))
      • - -
    • CombiningClass(a) = CombiningClass(principal(canonicalDecomposition(a))
      - - where principal(a) is the first character not of type Mn, or the first character if all - - characters are of type Mn.
      • - -
    - -
    • - -
  • However, because there are sometimes missing case pairs, and because of some legacy - - characters, it is only generally true that:
      - -
    • upper(canonicalDecomposition(a)) = canonicalDecomposition(upper(a))
      • - -
    • lower(canonicalDecomposition(a)) = canonicalDecomposition(lower(a))
      • - -
    • title(canonicalDecomposition(a)) = canonicalDecomposition(title(a))
      • - -
    - -
    • - -
- - - -

Modification History

- - - -

This section provides a summary of the changes between update versions of the Unicode - -Standard.

- - - -

Unicode 3.0.0

- - - -

Modifications made for Version 3.0.0 of UnicodeData.txt include many new characters and - -a number of property changes. These are summarized in Appendex D of The Unicode - -Standard, Version 3.0.

- - - -

Unicode 2.1.9

- - - -

Modifications made for Version 2.1.9 of UnicodeData.txt include: - - - -

    - -
  • Corrected combining class for U+05AE HEBREW ACCENT ZINOR.
    • - -
  • Corrected combining class for U+20E1 COMBINING LEFT RIGHT ARROW ABOVE
    • - -
  • Corrected combining class for U+0F35 and U+0F37 to 220.
    • - -
  • Corrected combining class for U+0F71 to 129.
    • - -
  • Added a decomposition for U+0F0C TIBETAN MARK DELIMITER TSHEG BSTAR.
    • - -
  • Added  decompositions for several Greek symbol letters: U+03D0..U+03D2, U+03D5, - - U+03D6, U+03F0..U+03F2.
    • - -
  • Removed  decompositions from the conjoining jamo block: U+1100..U+11F8.
    • - -
  • Changes to decomposition mappings for some Tibetan vowels for consistency in - - normalization. (U+0F71, U+0F73, U+0F77, U+0F79, U+0F81)
    • - -
  • Updated the decomposition mappings for several Vietnamese characters with two diacritics - - (U+1EAC, U+1EAD, U+1EB6, U+1EB7, U+1EC6, U+1EC7, U+1ED8, U+1ED9), so that the recursive - - decomposition can be generated directly in canonically reordered form (not a normative - - change).
    • - -
  • Updated the decomposition mappings for several Arabic compatibility characters involving - - shadda (U+FC5E..U+FC62, U+FCF2..U+FCF4), and two Latin characters (U+1E1C, U+1E1D), so - - that the decompositions are generated directly in canonically reordered form (not a - - normative change).
    • - -
  • Changed BIDI category for: U+00A0 NO-BREAK SPACE, U+2007 FIGURE SPACE, U+2028 LINE - - SEPARATOR.
    • - -
  • Changed BIDI category for extenders of General Category Lm: U+3005, U+3021..U+3035, - - U+FF9E, U+FF9F.
    • - -
  • Changed General Category and BIDI category for the Greek numeral signs: U+0374, U+0375.
    • - -
  • Corrected General Category for U+FFE8 HALFWIDTH FORMS LIGHT VERTICAL.
    • - -
  • Added Unicode 1.0 names for many Tibetan characters (informative).
    • - -
- - - -

Unicode 2.1.8

- - - -

Modifications made for Version 2.1.8 of UnicodeData.txt include: - - - -

    - -
  • Added combining class 240 for U+0345 COMBINING GREEK YPOGEGRAMMENI so that - - decompositions involving iota subscript are derivable directly in canonically reordered - - form; this also has a bearing on simplification of casing of polytonic Greek.
    • - -
  • Changes in decompositions related to Greek tonos. These result from the clarification - - that monotonic Greek "tonos" should be equated with U+0301 COMBINING ACUTE, - - rather than with U+030D COMBINING VERTICAL LINE ABOVE. (All Greek characters in the Greek - - block involving "tonos"; some Greek characters in the polytonic Greek in the - - 1FXX block.)
    • - -
  • Changed decompositions involving dialytika tonos. (U+0390, U+03B0)
    • - -
  • Changed ternary decompositions to binary. (U+0CCB, U+FB2C, U+FB2D) These changes - - simplify normalization.
    • - -
  • Removed canonical decomposition for Latin Candrabindu. (U+0310)
    • - -
  • Corrected error in canonical decomposition for U+1FF4.
    • - -
  • Added compatibility decompositions to clarify collation tables. (U+2100, U+2101, U+2105, - - U+2106, U+1E9A)
    • - -
  • A series of general category changes to assist the convergence of of Unicode definition - - of identifier with ISO TR 10176:
      - -
    • So > Lo: U+0950, U+0AD0, U+0F00, U+0F88..U+0F8B
      • - -
    • Po > Lo: U+0E2F, U+0EAF, U+3006
      • - -
    • Lm > Sk: U+309B, U+309C
      • - -
    • Po > Pc: U+30FB, U+FF65
      • - -
    • Ps/Pe > Mn: U+0F3E, U+0F3F
      • - -
    - -
    • - -
  • A series of bidi property changes for consistency.
      - -
    • L > ET: U+09F2, U+09F3
      • - -
    • ON > L: U+3007
      • - -
    • L > ON: U+0F3A..U+0F3D, U+037E, U+0387
      • - -
    - -
    • - -
  • Add case mapping: U+01A6 <-> U+0280
    • - -
  • Updated symmetric swapping value for guillemets: U+00AB, U+00BB, U+2039, U+203A.
    • - -
  • Changes to combining class values. Most Indic fixed position class non-spacing marks - - were changed to combining class 0. This fixes some inconsistencies in how canonical - - reordering would apply to Indic scripts, including Tibetan. Indic interacting top/bottom - - fixed position classes were merged into single (non-zero) classes as part of this change. - - Tibetan subjoined consonants are changed from combining class 6 to combining class 0. Thai - - pinthu (U+0E3A) moved to combining class 9. Moved two Devanagari stress marks into generic - - above and below combining classes (U+0951, U+0952).
    • - -
  • Corrected placement of semicolon near symmetric swapping field. (U+FA0E, etc., scattered - - positions to U+FA29)
    • - -
- - - -

Version 2.1.7

- - - -

This version was for internal change tracking only, and never publicly released.

- - - -

Version 2.1.6

- - - -

This version was for internal change tracking only, and never publicly released.

- - - -

Unicode 2.1.5

- - - -

Modifications made for Version 2.1.5 of UnicodeData.txt include: - - - -

    - -
  • Changed decomposition for U+FF9E and U+FF9F so that correct collation weighting will - - automatically result from the canonical equivalences.
    • - -
  • Removed canonical decompositions for U+04D4, U+04D5, U+04D8, U+04D9, U+04E0, U+04E1, - - U+04E8, U+04E9 (the implication being that no canonical equivalence is claimed between - - these 8 characters and similar Latin letters), and updated 4 canonical decompositions for - - U+04DB, U+04DC, U+04EA, U+04EB to reflect the implied difference in the base character.
    • - -
  • Added Pi, and Pf categories and assigned the relevant quotation marks to those - - categories, based on the Unicode Technical Corrigendum on Quotation Characters.
    • - -
  • Updating of many bidi properties, following the advice of the ad hoc committee on bidi, - - and to make the bidi properties of compatibility characters more consistent.
    • - -
  • Changed category of several Tibetan characters: U+0F3E, U+0F3F, U+0F88..U+0F8B to make - - them non-combining, reflecting the combined opinion of Tibetan experts.
    • - -
  • Added case mapping for U+03F2.
    • - -
  • Corrected case mapping for U+0275.
    • - -
  • Added titlecase mappings for U+03D0, U+03D1, U+03D5, U+03D6, U+03F0.. U+03F2.
    • - -
  • Corrected compatibility label for U+2121.
    • - -
  • Add specific entries for all the CJK compatibility ideographs, U+F900..U+FA2D, so the - - canonical decomposition for each (the URO character it is equivalent to) can be carried in - - the database.
    • - -
- - - -

Version 2.1.4

- - - -

This version was for internal change tracking only, and never publicly released.

- - - -

Version 2.1.3

- - - -

This version was for internal change tracking only, and never publicly released.

- - - -

Unicode 2.1.2

- - - -

Modifications made in updating UnicodeData.txt to Version 2.1.2 for the Unicode - -Standard, Version 2.1 (from Version 2.0) include: - - - -

    - -
  • Added two characters (U+20AC and U+FFFC).
    • - -
  • Amended bidi properties for U+0026, U+002E, U+0040, U+2007.
    • - -
  • Corrected case mappings for U+018E, U+019F, U+01DD, U+0258, U+0275, U+03C2, U+1E9B.
    • - -
  • Changed combining order class for U+0F71.
    • - -
  • Corrected canonical decompositions for U+0F73, U+1FBE.
    • - -
  • Changed decomposition for U+FB1F from compatibility to canonical.
    • - -
  • Added compatibility decompositions for U+FBE8, U+FBE9, U+FBF9..U+FBFB.
    • - -
  • Corrected compatibility decompositions for U+2469, U+246A, U+3358.
    • - -
- - - -

Version 2.1.1

- - - -

This version was for internal change tracking only, and never publicly released.

- - - -

Unicode 2.0.0

- - - -

The modifications made in updating UnicodeData.txt for the Unicode - -Standard, Version 2.0 include: - - - -

    - -
  • Fixed decompositions with TONOS to use correct NSM: 030D.
    • - -
  • Removed old Hangul Syllables; mapping to new characters are in a separate table.
    • - -
  • Marked compatibility decompositions with additional tags.
    • - -
  • Changed old tag names for clarity.
    • - -
  • Revision of decompositions to use first-level decomposition, instead of maximal - - decomposition.
    • - -
  • Correction of all known errors in decompositions from earlier versions.
    • - -
  • Added control code names (as old Unicode names).
    • - -
  • Added Hangul Jamo decompositions.
    • - -
  • Added Number category to match properties list in book.
    • - -
  • Fixed categories of Koranic Arabic marks.
    • - -
  • Fixed categories of precomposed characters to match decomposition where possible.
    • - -
  • Added Hebrew cantillation marks and the Tibetan script.
    • - -
  • Added place holders for ranges such as CJK Ideographic Area and the Private Use Area.
    • - -
  • Added categories Me, Sk, Pc, Nl, Cs, Cf, and rectified a number of mistakes in the - - database.
    • - -
- - - - - diff --git a/lib/unicode/mktables.PL b/lib/unicode/mktables.PL index 2380139..608a325 100755 --- a/lib/unicode/mktables.PL +++ b/lib/unicode/mktables.PL @@ -2,9 +2,9 @@ use bytes; -$UnicodeData = "Unicode.300"; +$UnicodeData = "Unicode.301"; $SyllableData = "syllables.txt"; -$PropData = "Props.txt"; +$PropData = "PropList.txt"; # Note: we try to keep filenames unique within first 8 chars. Using