From 192296d852011f4a2abb6e9fd1ee741fa7f81673 Mon Sep 17 00:00:00 2001 From: Keith Packard Date: Wed, 29 Dec 2004 09:15:17 +0000 Subject: [PATCH] Adopt some RedHat suggestions for standard font configuration. Add new helper program 'fc-case' to construct case folding tables from standard Unicode CaseFolding.txt file Re-implement case insensitive functions with Unicode aware versions (including full case folding mappings) --- ChangeLog | 26 ++ Makefile.am | 2 +- configure.in | 1 + fc-case/CaseFolding.txt | 924 ++++++++++++++++++++++++++++++++++++++++ fc-case/Makefile.am | 52 +++ fc-case/fc-case.c | 363 ++++++++++++++++ fc-case/fccase.tmpl.h | 25 ++ fonts.conf.in | 73 +++- src/fcint.h | 34 ++ src/fclist.c | 16 +- src/fcstr.c | 263 +++++++++--- 11 files changed, 1685 insertions(+), 94 deletions(-) create mode 100644 fc-case/CaseFolding.txt create mode 100644 fc-case/Makefile.am create mode 100644 fc-case/fc-case.c create mode 100644 fc-case/fccase.tmpl.h diff --git a/ChangeLog b/ChangeLog index 9563919..8e0d8b7 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,29 @@ +2004-12-29 Keith Packard + + * fonts.conf.in: + Adopt some RedHat suggestions for standard font configuration. + + * Makefile.am: + * configure.in: + * fc-case/CaseFolding.txt: + * fc-case/Makefile.am: + * fc-case/fc-case.c: (panic), (addFold), (ucs4_to_utf8), + (utf8_size), (addChar), (foldExtends), (case_fold_method_name), + (dump), (parseRaw), (caseFoldReadRaw), (main): + * fc-case/fccase.tmpl.h: + Add new helper program 'fc-case' to construct case folding + tables from standard Unicode CaseFolding.txt file + + * src/fcint.h: + * src/fclist.c: (FcListValueHash): + * src/fcstr.c: (FcStrCaseWalkerInit), (FcStrCaseWalkerLong), + (FcStrCaseWalkerNext), (FcStrCaseWalkerNextIgnoreBlanks), + (FcStrCmpIgnoreCase), (FcStrCmpIgnoreBlanksAndCase), + (FcStrHashIgnoreCase), (FcStrIsAtIgnoreBlanksAndCase), + (FcStrIsAtIgnoreCase), (FcStrStrIgnoreCase): + Re-implement case insensitive functions with Unicode + aware versions (including full case folding mappings) + 2004-12-13 Keith Packard reviewed by: Owen Taylor diff --git a/Makefile.am b/Makefile.am index e10124c..53c1920 100644 --- a/Makefile.am +++ b/Makefile.am @@ -22,7 +22,7 @@ # PERFORMANCE OF THIS SOFTWARE. DOCSRC=@DOCSRC@ -SUBDIRS=fontconfig fc-lang fc-glyphname src fc-cache fc-list fc-match $(DOCSRC) test +SUBDIRS=fontconfig fc-lang fc-glyphname fc-case src fc-cache fc-list fc-match $(DOCSRC) test EXTRA_DIST = \ fontconfig.pc.in \ diff --git a/configure.in b/configure.in index af0b1c2..a8d32bf 100644 --- a/configure.in +++ b/configure.in @@ -411,6 +411,7 @@ Makefile fontconfig/Makefile fc-lang/Makefile fc-glyphname/Makefile +fc-case/Makefile src/Makefile src/fontconfig.def fc-cache/Makefile diff --git a/fc-case/CaseFolding.txt b/fc-case/CaseFolding.txt new file mode 100644 index 0000000..65f78ff --- /dev/null +++ b/fc-case/CaseFolding.txt @@ -0,0 +1,924 @@ +# CaseFolding-4.0.1.txt +# Date: 2004-03-02, 02:41:24 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2004 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html +# Case Folding Properties +# +# This file is a supplement to the UnicodeData file. +# It provides a case folding mapping generated from the Unicode Character Database. +# If all characters are mapped according to the full mapping below, then +# case differences (according to UnicodeData.txt and SpecialCasing.txt) +# are eliminated. +# +# The data supports both implementations that require simple case foldings +# (where string lengths don't change), and implementations that allow full case folding +# (where string lengths may grow). Note that where they can be supported, the +# full case foldings are superior: for example, they allow "MASSE" and "Maße" to match. +# +# All code points not listed in this file map to themselves. +# +# NOTE: case folding does not preserve normalization formats! +# +# For information on case folding, see +# UTR #21 Case Mappings, at http://www.unicode.org/unicode/reports/tr21/ +# +# ================================================================================ +# Format +# ================================================================================ +# The entries in this file are in the following machine-readable format: +# +# ; ; ; # +# +# The status field is: +# C: common case folding, common mappings shared by both simple and full mappings. +# F: full case folding, mappings that cause strings to grow in length. Multiple characters are separated by spaces. +# S: simple case folding, mappings to single characters where different from F. +# T: special case for uppercase I and dotted uppercase I +# - For non-Turkic languages, this mapping is normally not used. +# - For Turkic languages (tr, az), this mapping can be used instead of the normal mapping for these characters. +# Note that the Turkic mappings do not maintain canonical equivalence without additional processing. +# See the discussions of case mapping in the Unicode Standard for more information. +# +# Usage: +# A. To do a simple case folding, use the mappings with status C + S. +# B. To do a full case folding, use the mappings with status C + F. +# +# The mappings with status T can be used or omitted depending on the desired case-folding +# behavior. (The default option is to exclude them.) +# +# ================================================================= + +0041; C; 0061; # LATIN CAPITAL LETTER A +0042; C; 0062; # LATIN CAPITAL LETTER B +0043; C; 0063; # LATIN CAPITAL LETTER C +0044; C; 0064; # LATIN CAPITAL LETTER D +0045; C; 0065; # LATIN CAPITAL LETTER E +0046; C; 0066; # LATIN CAPITAL LETTER F +0047; C; 0067; # LATIN CAPITAL LETTER G +0048; C; 0068; # LATIN CAPITAL LETTER H +0049; C; 0069; # LATIN CAPITAL LETTER I +0049; T; 0131; # LATIN CAPITAL LETTER I +004A; C; 006A; # LATIN CAPITAL LETTER J +004B; C; 006B; # LATIN CAPITAL LETTER K +004C; C; 006C; # LATIN CAPITAL LETTER L +004D; C; 006D; # LATIN CAPITAL LETTER M +004E; C; 006E; # LATIN CAPITAL LETTER N +004F; C; 006F; # LATIN CAPITAL LETTER O +0050; C; 0070; # LATIN CAPITAL LETTER P +0051; C; 0071; # LATIN CAPITAL LETTER Q +0052; C; 0072; # LATIN CAPITAL LETTER R +0053; C; 0073; # LATIN CAPITAL LETTER S +0054; C; 0074; # LATIN CAPITAL LETTER T +0055; C; 0075; # LATIN CAPITAL LETTER U +0056; C; 0076; # LATIN CAPITAL LETTER V +0057; C; 0077; # LATIN CAPITAL LETTER W +0058; C; 0078; # LATIN CAPITAL LETTER X +0059; C; 0079; # LATIN CAPITAL LETTER Y +005A; C; 007A; # LATIN CAPITAL LETTER Z +00B5; C; 03BC; # MICRO SIGN +00C0; C; 00E0; # LATIN CAPITAL LETTER A WITH GRAVE +00C1; C; 00E1; # LATIN CAPITAL LETTER A WITH ACUTE +00C2; C; 00E2; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +00C3; C; 00E3; # LATIN CAPITAL LETTER A WITH TILDE +00C4; C; 00E4; # LATIN CAPITAL LETTER A WITH DIAERESIS +00C5; C; 00E5; # LATIN CAPITAL LETTER A WITH RING ABOVE +00C6; C; 00E6; # LATIN CAPITAL LETTER AE +00C7; C; 00E7; # LATIN CAPITAL LETTER C WITH CEDILLA +00C8; C; 00E8; # LATIN CAPITAL LETTER E WITH GRAVE +00C9; C; 00E9; # LATIN CAPITAL LETTER E WITH ACUTE +00CA; C; 00EA; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +00CB; C; 00EB; # LATIN CAPITAL LETTER E WITH DIAERESIS +00CC; C; 00EC; # LATIN CAPITAL LETTER I WITH GRAVE +00CD; C; 00ED; # LATIN CAPITAL LETTER I WITH ACUTE +00CE; C; 00EE; # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +00CF; C; 00EF; # LATIN CAPITAL LETTER I WITH DIAERESIS +00D0; C; 00F0; # LATIN CAPITAL LETTER ETH +00D1; C; 00F1; # LATIN CAPITAL LETTER N WITH TILDE +00D2; C; 00F2; # LATIN CAPITAL LETTER O WITH GRAVE +00D3; C; 00F3; # LATIN CAPITAL LETTER O WITH ACUTE +00D4; C; 00F4; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +00D5; C; 00F5; # LATIN CAPITAL LETTER O WITH TILDE +00D6; C; 00F6; # LATIN CAPITAL LETTER O WITH DIAERESIS +00D8; C; 00F8; # LATIN CAPITAL LETTER O WITH STROKE +00D9; C; 00F9; # LATIN CAPITAL LETTER U WITH GRAVE +00DA; C; 00FA; # LATIN CAPITAL LETTER U WITH ACUTE +00DB; C; 00FB; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +00DC; C; 00FC; # LATIN CAPITAL LETTER U WITH DIAERESIS +00DD; C; 00FD; # LATIN CAPITAL LETTER Y WITH ACUTE +00DE; C; 00FE; # LATIN CAPITAL LETTER THORN +00DF; F; 0073 0073; # LATIN SMALL LETTER SHARP S +0100; C; 0101; # LATIN CAPITAL LETTER A WITH MACRON +0102; C; 0103; # LATIN CAPITAL LETTER A WITH BREVE +0104; C; 0105; # LATIN CAPITAL LETTER A WITH OGONEK +0106; C; 0107; # LATIN CAPITAL LETTER C WITH ACUTE +0108; C; 0109; # LATIN CAPITAL LETTER C WITH CIRCUMFLEX +010A; C; 010B; # LATIN CAPITAL LETTER C WITH DOT ABOVE +010C; C; 010D; # LATIN CAPITAL LETTER C WITH CARON +010E; C; 010F; # LATIN CAPITAL LETTER D WITH CARON +0110; C; 0111; # LATIN CAPITAL LETTER D WITH STROKE +0112; C; 0113; # LATIN CAPITAL LETTER E WITH MACRON +0114; C; 0115; # LATIN CAPITAL LETTER E WITH BREVE +0116; C; 0117; # LATIN CAPITAL LETTER E WITH DOT ABOVE +0118; C; 0119; # LATIN CAPITAL LETTER E WITH OGONEK +011A; C; 011B; # LATIN CAPITAL LETTER E WITH CARON +011C; C; 011D; # LATIN CAPITAL LETTER G WITH CIRCUMFLEX +011E; C; 011F; # LATIN CAPITAL LETTER G WITH BREVE +0120; C; 0121; # LATIN CAPITAL LETTER G WITH DOT ABOVE +0122; C; 0123; # LATIN CAPITAL LETTER G WITH CEDILLA +0124; C; 0125; # LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0126; C; 0127; # LATIN CAPITAL LETTER H WITH STROKE +0128; C; 0129; # LATIN CAPITAL LETTER I WITH TILDE +012A; C; 012B; # LATIN CAPITAL LETTER I WITH MACRON +012C; C; 012D; # LATIN CAPITAL LETTER I WITH BREVE +012E; C; 012F; # LATIN CAPITAL LETTER I WITH OGONEK +0130; F; 0069 0307; # LATIN CAPITAL LETTER I WITH DOT ABOVE +0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE +0132; C; 0133; # LATIN CAPITAL LIGATURE IJ +0134; C; 0135; # LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0136; C; 0137; # LATIN CAPITAL LETTER K WITH CEDILLA +0139; C; 013A; # LATIN CAPITAL LETTER L WITH ACUTE +013B; C; 013C; # LATIN CAPITAL LETTER L WITH CEDILLA +013D; C; 013E; # LATIN CAPITAL LETTER L WITH CARON +013F; C; 0140; # LATIN CAPITAL LETTER L WITH MIDDLE DOT +0141; C; 0142; # LATIN CAPITAL LETTER L WITH STROKE +0143; C; 0144; # LATIN CAPITAL LETTER N WITH ACUTE +0145; C; 0146; # LATIN CAPITAL LETTER N WITH CEDILLA +0147; C; 0148; # LATIN CAPITAL LETTER N WITH CARON +0149; F; 02BC 006E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE +014A; C; 014B; # LATIN CAPITAL LETTER ENG +014C; C; 014D; # LATIN CAPITAL LETTER O WITH MACRON +014E; C; 014F; # LATIN CAPITAL LETTER O WITH BREVE +0150; C; 0151; # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0152; C; 0153; # LATIN CAPITAL LIGATURE OE +0154; C; 0155; # LATIN CAPITAL LETTER R WITH ACUTE +0156; C; 0157; # LATIN CAPITAL LETTER R WITH CEDILLA +0158; C; 0159; # LATIN CAPITAL LETTER R WITH CARON +015A; C; 015B; # LATIN CAPITAL LETTER S WITH ACUTE +015C; C; 015D; # LATIN CAPITAL LETTER S WITH CIRCUMFLEX +015E; C; 015F; # LATIN CAPITAL LETTER S WITH CEDILLA +0160; C; 0161; # LATIN CAPITAL LETTER S WITH CARON +0162; C; 0163; # LATIN CAPITAL LETTER T WITH CEDILLA +0164; C; 0165; # LATIN CAPITAL LETTER T WITH CARON +0166; C; 0167; # LATIN CAPITAL LETTER T WITH STROKE +0168; C; 0169; # LATIN CAPITAL LETTER U WITH TILDE +016A; C; 016B; # LATIN CAPITAL LETTER U WITH MACRON +016C; C; 016D; # LATIN CAPITAL LETTER U WITH BREVE +016E; C; 016F; # LATIN CAPITAL LETTER U WITH RING ABOVE +0170; C; 0171; # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0172; C; 0173; # LATIN CAPITAL LETTER U WITH OGONEK +0174; C; 0175; # LATIN CAPITAL LETTER W WITH CIRCUMFLEX +0176; C; 0177; # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX +0178; C; 00FF; # LATIN CAPITAL LETTER Y WITH DIAERESIS +0179; C; 017A; # LATIN CAPITAL LETTER Z WITH ACUTE +017B; C; 017C; # LATIN CAPITAL LETTER Z WITH DOT ABOVE +017D; C; 017E; # LATIN CAPITAL LETTER Z WITH CARON +017F; C; 0073; # LATIN SMALL LETTER LONG S +0181; C; 0253; # LATIN CAPITAL LETTER B WITH HOOK +0182; C; 0183; # LATIN CAPITAL LETTER B WITH TOPBAR +0184; C; 0185; # LATIN CAPITAL LETTER TONE SIX +0186; C; 0254; # LATIN CAPITAL LETTER OPEN O +0187; C; 0188; # LATIN CAPITAL LETTER C WITH HOOK +0189; C; 0256; # LATIN CAPITAL LETTER AFRICAN D +018A; C; 0257; # LATIN CAPITAL LETTER D WITH HOOK +018B; C; 018C; # LATIN CAPITAL LETTER D WITH TOPBAR +018E; C; 01DD; # LATIN CAPITAL LETTER REVERSED E +018F; C; 0259; # LATIN CAPITAL LETTER SCHWA +0190; C; 025B; # LATIN CAPITAL LETTER OPEN E +0191; C; 0192; # LATIN CAPITAL LETTER F WITH HOOK +0193; C; 0260; # LATIN CAPITAL LETTER G WITH HOOK +0194; C; 0263; # LATIN CAPITAL LETTER GAMMA +0196; C; 0269; # LATIN CAPITAL LETTER IOTA +0197; C; 0268; # LATIN CAPITAL LETTER I WITH STROKE +0198; C; 0199; # LATIN CAPITAL LETTER K WITH HOOK +019C; C; 026F; # LATIN CAPITAL LETTER TURNED M +019D; C; 0272; # LATIN CAPITAL LETTER N WITH LEFT HOOK +019F; C; 0275; # LATIN CAPITAL LETTER O WITH MIDDLE TILDE +01A0; C; 01A1; # LATIN CAPITAL LETTER O WITH HORN +01A2; C; 01A3; # LATIN CAPITAL LETTER OI +01A4; C; 01A5; # LATIN CAPITAL LETTER P WITH HOOK +01A6; C; 0280; # LATIN LETTER YR +01A7; C; 01A8; # LATIN CAPITAL LETTER TONE TWO +01A9; C; 0283; # LATIN CAPITAL LETTER ESH +01AC; C; 01AD; # LATIN CAPITAL LETTER T WITH HOOK +01AE; C; 0288; # LATIN CAPITAL LETTER T WITH RETROFLEX HOOK +01AF; C; 01B0; # LATIN CAPITAL LETTER U WITH HORN +01B1; C; 028A; # LATIN CAPITAL LETTER UPSILON +01B2; C; 028B; # LATIN CAPITAL LETTER V WITH HOOK +01B3; C; 01B4; # LATIN CAPITAL LETTER Y WITH HOOK +01B5; C; 01B6; # LATIN CAPITAL LETTER Z WITH STROKE +01B7; C; 0292; # LATIN CAPITAL LETTER EZH +01B8; C; 01B9; # LATIN CAPITAL LETTER EZH REVERSED +01BC; C; 01BD; # LATIN CAPITAL LETTER TONE FIVE +01C4; C; 01C6; # LATIN CAPITAL LETTER DZ WITH CARON +01C5; C; 01C6; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON +01C7; C; 01C9; # LATIN CAPITAL LETTER LJ +01C8; C; 01C9; # LATIN CAPITAL LETTER L WITH SMALL LETTER J +01CA; C; 01CC; # LATIN CAPITAL LETTER NJ +01CB; C; 01CC; # LATIN CAPITAL LETTER N WITH SMALL LETTER J +01CD; C; 01CE; # LATIN CAPITAL LETTER A WITH CARON +01CF; C; 01D0; # LATIN CAPITAL LETTER I WITH CARON +01D1; C; 01D2; # LATIN CAPITAL LETTER O WITH CARON +01D3; C; 01D4; # LATIN CAPITAL LETTER U WITH CARON +01D5; C; 01D6; # LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON +01D7; C; 01D8; # LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE +01D9; C; 01DA; # LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON +01DB; C; 01DC; # LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE +01DE; C; 01DF; # LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON +01E0; C; 01E1; # LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON +01E2; C; 01E3; # LATIN CAPITAL LETTER AE WITH MACRON +01E4; C; 01E5; # LATIN CAPITAL LETTER G WITH STROKE +01E6; C; 01E7; # LATIN CAPITAL LETTER G WITH CARON +01E8; C; 01E9; # LATIN CAPITAL LETTER K WITH CARON +01EA; C; 01EB; # LATIN CAPITAL LETTER O WITH OGONEK +01EC; C; 01ED; # LATIN CAPITAL LETTER O WITH OGONEK AND MACRON +01EE; C; 01EF; # LATIN CAPITAL LETTER EZH WITH CARON +01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON +01F1; C; 01F3; # LATIN CAPITAL LETTER DZ +01F2; C; 01F3; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z +01F4; C; 01F5; # LATIN CAPITAL LETTER G WITH ACUTE +01F6; C; 0195; # LATIN CAPITAL LETTER HWAIR +01F7; C; 01BF; # LATIN CAPITAL LETTER WYNN +01F8; C; 01F9; # LATIN CAPITAL LETTER N WITH GRAVE +01FA; C; 01FB; # LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE +01FC; C; 01FD; # LATIN CAPITAL LETTER AE WITH ACUTE +01FE; C; 01FF; # LATIN CAPITAL LETTER O WITH STROKE AND ACUTE +0200; C; 0201; # LATIN CAPITAL LETTER A WITH DOUBLE GRAVE +0202; C; 0203; # LATIN CAPITAL LETTER A WITH INVERTED BREVE +0204; C; 0205; # LATIN CAPITAL LETTER E WITH DOUBLE GRAVE +0206; C; 0207; # LATIN CAPITAL LETTER E WITH INVERTED BREVE +0208; C; 0209; # LATIN CAPITAL LETTER I WITH DOUBLE GRAVE +020A; C; 020B; # LATIN CAPITAL LETTER I WITH INVERTED BREVE +020C; C; 020D; # LATIN CAPITAL LETTER O WITH DOUBLE GRAVE +020E; C; 020F; # LATIN CAPITAL LETTER O WITH INVERTED BREVE +0210; C; 0211; # LATIN CAPITAL LETTER R WITH DOUBLE GRAVE +0212; C; 0213; # LATIN CAPITAL LETTER R WITH INVERTED BREVE +0214; C; 0215; # LATIN CAPITAL LETTER U WITH DOUBLE GRAVE +0216; C; 0217; # LATIN CAPITAL LETTER U WITH INVERTED BREVE +0218; C; 0219; # LATIN CAPITAL LETTER S WITH COMMA BELOW +021A; C; 021B; # LATIN CAPITAL LETTER T WITH COMMA BELOW +021C; C; 021D; # LATIN CAPITAL LETTER YOGH +021E; C; 021F; # LATIN CAPITAL LETTER H WITH CARON +0220; C; 019E; # LATIN CAPITAL LETTER N WITH LONG RIGHT LEG +0222; C; 0223; # LATIN CAPITAL LETTER OU +0224; C; 0225; # LATIN CAPITAL LETTER Z WITH HOOK +0226; C; 0227; # LATIN CAPITAL LETTER A WITH DOT ABOVE +0228; C; 0229; # LATIN CAPITAL LETTER E WITH CEDILLA +022A; C; 022B; # LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON +022C; C; 022D; # LATIN CAPITAL LETTER O WITH TILDE AND MACRON +022E; C; 022F; # LATIN CAPITAL LETTER O WITH DOT ABOVE +0230; C; 0231; # LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON +0232; C; 0233; # LATIN CAPITAL LETTER Y WITH MACRON +0345; C; 03B9; # COMBINING GREEK YPOGEGRAMMENI +0386; C; 03AC; # GREEK CAPITAL LETTER ALPHA WITH TONOS +0388; C; 03AD; # GREEK CAPITAL LETTER EPSILON WITH TONOS +0389; C; 03AE; # GREEK CAPITAL LETTER ETA WITH TONOS +038A; C; 03AF; # GREEK CAPITAL LETTER IOTA WITH TONOS +038C; C; 03CC; # GREEK CAPITAL LETTER OMICRON WITH TONOS +038E; C; 03CD; # GREEK CAPITAL LETTER UPSILON WITH TONOS +038F; C; 03CE; # GREEK CAPITAL LETTER OMEGA WITH TONOS +0390; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0391; C; 03B1; # GREEK CAPITAL LETTER ALPHA +0392; C; 03B2; # GREEK CAPITAL LETTER BETA +0393; C; 03B3; # GREEK CAPITAL LETTER GAMMA +0394; C; 03B4; # GREEK CAPITAL LETTER DELTA +0395; C; 03B5; # GREEK CAPITAL LETTER EPSILON +0396; C; 03B6; # GREEK CAPITAL LETTER ZETA +0397; C; 03B7; # GREEK CAPITAL LETTER ETA +0398; C; 03B8; # GREEK CAPITAL LETTER THETA +0399; C; 03B9; # GREEK CAPITAL LETTER IOTA +039A; C; 03BA; # GREEK CAPITAL LETTER KAPPA +039B; C; 03BB; # GREEK CAPITAL LETTER LAMDA +039C; C; 03BC; # GREEK CAPITAL LETTER MU +039D; C; 03BD; # GREEK CAPITAL LETTER NU +039E; C; 03BE; # GREEK CAPITAL LETTER XI +039F; C; 03BF; # GREEK CAPITAL LETTER OMICRON +03A0; C; 03C0; # GREEK CAPITAL LETTER PI +03A1; C; 03C1; # GREEK CAPITAL LETTER RHO +03A3; C; 03C3; # GREEK CAPITAL LETTER SIGMA +03A4; C; 03C4; # GREEK CAPITAL LETTER TAU +03A5; C; 03C5; # GREEK CAPITAL LETTER UPSILON +03A6; C; 03C6; # GREEK CAPITAL LETTER PHI +03A7; C; 03C7; # GREEK CAPITAL LETTER CHI +03A8; C; 03C8; # GREEK CAPITAL LETTER PSI +03A9; C; 03C9; # GREEK CAPITAL LETTER OMEGA +03AA; C; 03CA; # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +03AB; C; 03CB; # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +03B0; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +03C2; C; 03C3; # GREEK SMALL LETTER FINAL SIGMA +03D0; C; 03B2; # GREEK BETA SYMBOL +03D1; C; 03B8; # GREEK THETA SYMBOL +03D5; C; 03C6; # GREEK PHI SYMBOL +03D6; C; 03C0; # GREEK PI SYMBOL +03D8; C; 03D9; # GREEK LETTER ARCHAIC KOPPA +03DA; C; 03DB; # GREEK LETTER STIGMA +03DC; C; 03DD; # GREEK LETTER DIGAMMA +03DE; C; 03DF; # GREEK LETTER KOPPA +03E0; C; 03E1; # GREEK LETTER SAMPI +03E2; C; 03E3; # COPTIC CAPITAL LETTER SHEI +03E4; C; 03E5; # COPTIC CAPITAL LETTER FEI +03E6; C; 03E7; # COPTIC CAPITAL LETTER KHEI +03E8; C; 03E9; # COPTIC CAPITAL LETTER HORI +03EA; C; 03EB; # COPTIC CAPITAL LETTER GANGIA +03EC; C; 03ED; # COPTIC CAPITAL LETTER SHIMA +03EE; C; 03EF; # COPTIC CAPITAL LETTER DEI +03F0; C; 03BA; # GREEK KAPPA SYMBOL +03F1; C; 03C1; # GREEK RHO SYMBOL +03F4; C; 03B8; # GREEK CAPITAL THETA SYMBOL +03F5; C; 03B5; # GREEK LUNATE EPSILON SYMBOL +03F7; C; 03F8; # GREEK CAPITAL LETTER SHO +03F9; C; 03F2; # GREEK CAPITAL LUNATE SIGMA SYMBOL +03FA; C; 03FB; # GREEK CAPITAL LETTER SAN +0400; C; 0450; # CYRILLIC CAPITAL LETTER IE WITH GRAVE +0401; C; 0451; # CYRILLIC CAPITAL LETTER IO +0402; C; 0452; # CYRILLIC CAPITAL LETTER DJE +0403; C; 0453; # CYRILLIC CAPITAL LETTER GJE +0404; C; 0454; # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0405; C; 0455; # CYRILLIC CAPITAL LETTER DZE +0406; C; 0456; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0407; C; 0457; # CYRILLIC CAPITAL LETTER YI +0408; C; 0458; # CYRILLIC CAPITAL LETTER JE +0409; C; 0459; # CYRILLIC CAPITAL LETTER LJE +040A; C; 045A; # CYRILLIC CAPITAL LETTER NJE +040B; C; 045B; # CYRILLIC CAPITAL LETTER TSHE +040C; C; 045C; # CYRILLIC CAPITAL LETTER KJE +040D; C; 045D; # CYRILLIC CAPITAL LETTER I WITH GRAVE +040E; C; 045E; # CYRILLIC CAPITAL LETTER SHORT U +040F; C; 045F; # CYRILLIC CAPITAL LETTER DZHE +0410; C; 0430; # CYRILLIC CAPITAL LETTER A +0411; C; 0431; # CYRILLIC CAPITAL LETTER BE +0412; C; 0432; # CYRILLIC CAPITAL LETTER VE +0413; C; 0433; # CYRILLIC CAPITAL LETTER GHE +0414; C; 0434; # CYRILLIC CAPITAL LETTER DE +0415; C; 0435; # CYRILLIC CAPITAL LETTER IE +0416; C; 0436; # CYRILLIC CAPITAL LETTER ZHE +0417; C; 0437; # CYRILLIC CAPITAL LETTER ZE +0418; C; 0438; # CYRILLIC CAPITAL LETTER I +0419; C; 0439; # CYRILLIC CAPITAL LETTER SHORT I +041A; C; 043A; # CYRILLIC CAPITAL LETTER KA +041B; C; 043B; # CYRILLIC CAPITAL LETTER EL +041C; C; 043C; # CYRILLIC CAPITAL LETTER EM +041D; C; 043D; # CYRILLIC CAPITAL LETTER EN +041E; C; 043E; # CYRILLIC CAPITAL LETTER O +041F; C; 043F; # CYRILLIC CAPITAL LETTER PE +0420; C; 0440; # CYRILLIC CAPITAL LETTER ER +0421; C; 0441; # CYRILLIC CAPITAL LETTER ES +0422; C; 0442; # CYRILLIC CAPITAL LETTER TE +0423; C; 0443; # CYRILLIC CAPITAL LETTER U +0424; C; 0444; # CYRILLIC CAPITAL LETTER EF +0425; C; 0445; # CYRILLIC CAPITAL LETTER HA +0426; C; 0446; # CYRILLIC CAPITAL LETTER TSE +0427; C; 0447; # CYRILLIC CAPITAL LETTER CHE +0428; C; 0448; # CYRILLIC CAPITAL LETTER SHA +0429; C; 0449; # CYRILLIC CAPITAL LETTER SHCHA +042A; C; 044A; # CYRILLIC CAPITAL LETTER HARD SIGN +042B; C; 044B; # CYRILLIC CAPITAL LETTER YERU +042C; C; 044C; # CYRILLIC CAPITAL LETTER SOFT SIGN +042D; C; 044D; # CYRILLIC CAPITAL LETTER E +042E; C; 044E; # CYRILLIC CAPITAL LETTER YU +042F; C; 044F; # CYRILLIC CAPITAL LETTER YA +0460; C; 0461; # CYRILLIC CAPITAL LETTER OMEGA +0462; C; 0463; # CYRILLIC CAPITAL LETTER YAT +0464; C; 0465; # CYRILLIC CAPITAL LETTER IOTIFIED E +0466; C; 0467; # CYRILLIC CAPITAL LETTER LITTLE YUS +0468; C; 0469; # CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS +046A; C; 046B; # CYRILLIC CAPITAL LETTER BIG YUS +046C; C; 046D; # CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS +046E; C; 046F; # CYRILLIC CAPITAL LETTER KSI +0470; C; 0471; # CYRILLIC CAPITAL LETTER PSI +0472; C; 0473; # CYRILLIC CAPITAL LETTER FITA +0474; C; 0475; # CYRILLIC CAPITAL LETTER IZHITSA +0476; C; 0477; # CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0478; C; 0479; # CYRILLIC CAPITAL LETTER UK +047A; C; 047B; # CYRILLIC CAPITAL LETTER ROUND OMEGA +047C; C; 047D; # CYRILLIC CAPITAL LETTER OMEGA WITH TITLO +047E; C; 047F; # CYRILLIC CAPITAL LETTER OT +0480; C; 0481; # CYRILLIC CAPITAL LETTER KOPPA +048A; C; 048B; # CYRILLIC CAPITAL LETTER SHORT I WITH TAIL +048C; C; 048D; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN +048E; C; 048F; # CYRILLIC CAPITAL LETTER ER WITH TICK +0490; C; 0491; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0492; C; 0493; # CYRILLIC CAPITAL LETTER GHE WITH STROKE +0494; C; 0495; # CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK +0496; C; 0497; # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER +0498; C; 0499; # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER +049A; C; 049B; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER +049C; C; 049D; # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE +049E; C; 049F; # CYRILLIC CAPITAL LETTER KA WITH STROKE +04A0; C; 04A1; # CYRILLIC CAPITAL LETTER BASHKIR KA +04A2; C; 04A3; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER +04A4; C; 04A5; # CYRILLIC CAPITAL LIGATURE EN GHE +04A6; C; 04A7; # CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK +04A8; C; 04A9; # CYRILLIC CAPITAL LETTER ABKHASIAN HA +04AA; C; 04AB; # CYRILLIC CAPITAL LETTER ES WITH DESCENDER +04AC; C; 04AD; # CYRILLIC CAPITAL LETTER TE WITH DESCENDER +04AE; C; 04AF; # CYRILLIC CAPITAL LETTER STRAIGHT U +04B0; C; 04B1; # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE +04B2; C; 04B3; # CYRILLIC CAPITAL LETTER HA WITH DESCENDER +04B4; C; 04B5; # CYRILLIC CAPITAL LIGATURE TE TSE +04B6; C; 04B7; # CYRILLIC CAPITAL LETTER CHE WITH DESCENDER +04B8; C; 04B9; # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE +04BA; C; 04BB; # CYRILLIC CAPITAL LETTER SHHA +04BC; C; 04BD; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE +04BE; C; 04BF; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER +04C1; C; 04C2; # CYRILLIC CAPITAL LETTER ZHE WITH BREVE +04C3; C; 04C4; # CYRILLIC CAPITAL LETTER KA WITH HOOK +04C5; C; 04C6; # CYRILLIC CAPITAL LETTER EL WITH TAIL +04C7; C; 04C8; # CYRILLIC CAPITAL LETTER EN WITH HOOK +04C9; C; 04CA; # CYRILLIC CAPITAL LETTER EN WITH TAIL +04CB; C; 04CC; # CYRILLIC CAPITAL LETTER KHAKASSIAN CHE +04CD; C; 04CE; # CYRILLIC CAPITAL LETTER EM WITH TAIL +04D0; C; 04D1; # CYRILLIC CAPITAL LETTER A WITH BREVE +04D2; C; 04D3; # CYRILLIC CAPITAL LETTER A WITH DIAERESIS +04D4; C; 04D5; # CYRILLIC CAPITAL LIGATURE A IE +04D6; C; 04D7; # CYRILLIC CAPITAL LETTER IE WITH BREVE +04D8; C; 04D9; # CYRILLIC CAPITAL LETTER SCHWA +04DA; C; 04DB; # CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS +04DC; C; 04DD; # CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS +04DE; C; 04DF; # CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS +04E0; C; 04E1; # CYRILLIC CAPITAL LETTER ABKHASIAN DZE +04E2; C; 04E3; # CYRILLIC CAPITAL LETTER I WITH MACRON +04E4; C; 04E5; # CYRILLIC CAPITAL LETTER I WITH DIAERESIS +04E6; C; 04E7; # CYRILLIC CAPITAL LETTER O WITH DIAERESIS +04E8; C; 04E9; # CYRILLIC CAPITAL LETTER BARRED O +04EA; C; 04EB; # CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS +04EC; C; 04ED; # CYRILLIC CAPITAL LETTER E WITH DIAERESIS +04EE; C; 04EF; # CYRILLIC CAPITAL LETTER U WITH MACRON +04F0; C; 04F1; # CYRILLIC CAPITAL LETTER U WITH DIAERESIS +04F2; C; 04F3; # CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE +04F4; C; 04F5; # CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS +04F8; C; 04F9; # CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS +0500; C; 0501; # CYRILLIC CAPITAL LETTER KOMI DE +0502; C; 0503; # CYRILLIC CAPITAL LETTER KOMI DJE +0504; C; 0505; # CYRILLIC CAPITAL LETTER KOMI ZJE +0506; C; 0507; # CYRILLIC CAPITAL LETTER KOMI DZJE +0508; C; 0509; # CYRILLIC CAPITAL LETTER KOMI LJE +050A; C; 050B; # CYRILLIC CAPITAL LETTER KOMI NJE +050C; C; 050D; # CYRILLIC CAPITAL LETTER KOMI SJE +050E; C; 050F; # CYRILLIC CAPITAL LETTER KOMI TJE +0531; C; 0561; # ARMENIAN CAPITAL LETTER AYB +0532; C; 0562; # ARMENIAN CAPITAL LETTER BEN +0533; C; 0563; # ARMENIAN CAPITAL LETTER GIM +0534; C; 0564; # ARMENIAN CAPITAL LETTER DA +0535; C; 0565; # ARMENIAN CAPITAL LETTER ECH +0536; C; 0566; # ARMENIAN CAPITAL LETTER ZA +0537; C; 0567; # ARMENIAN CAPITAL LETTER EH +0538; C; 0568; # ARMENIAN CAPITAL LETTER ET +0539; C; 0569; # ARMENIAN CAPITAL LETTER TO +053A; C; 056A; # ARMENIAN CAPITAL LETTER ZHE +053B; C; 056B; # ARMENIAN CAPITAL LETTER INI +053C; C; 056C; # ARMENIAN CAPITAL LETTER LIWN +053D; C; 056D; # ARMENIAN CAPITAL LETTER XEH +053E; C; 056E; # ARMENIAN CAPITAL LETTER CA +053F; C; 056F; # ARMENIAN CAPITAL LETTER KEN +0540; C; 0570; # ARMENIAN CAPITAL LETTER HO +0541; C; 0571; # ARMENIAN CAPITAL LETTER JA +0542; C; 0572; # ARMENIAN CAPITAL LETTER GHAD +0543; C; 0573; # ARMENIAN CAPITAL LETTER CHEH +0544; C; 0574; # ARMENIAN CAPITAL LETTER MEN +0545; C; 0575; # ARMENIAN CAPITAL LETTER YI +0546; C; 0576; # ARMENIAN CAPITAL LETTER NOW +0547; C; 0577; # ARMENIAN CAPITAL LETTER SHA +0548; C; 0578; # ARMENIAN CAPITAL LETTER VO +0549; C; 0579; # ARMENIAN CAPITAL LETTER CHA +054A; C; 057A; # ARMENIAN CAPITAL LETTER PEH +054B; C; 057B; # ARMENIAN CAPITAL LETTER JHEH +054C; C; 057C; # ARMENIAN CAPITAL LETTER RA +054D; C; 057D; # ARMENIAN CAPITAL LETTER SEH +054E; C; 057E; # ARMENIAN CAPITAL LETTER VEW +054F; C; 057F; # ARMENIAN CAPITAL LETTER TIWN +0550; C; 0580; # ARMENIAN CAPITAL LETTER REH +0551; C; 0581; # ARMENIAN CAPITAL LETTER CO +0552; C; 0582; # ARMENIAN CAPITAL LETTER YIWN +0553; C; 0583; # ARMENIAN CAPITAL LETTER PIWR +0554; C; 0584; # ARMENIAN CAPITAL LETTER KEH +0555; C; 0585; # ARMENIAN CAPITAL LETTER OH +0556; C; 0586; # ARMENIAN CAPITAL LETTER FEH +0587; F; 0565 0582; # ARMENIAN SMALL LIGATURE ECH YIWN +1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW +1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE +1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW +1E06; C; 1E07; # LATIN CAPITAL LETTER B WITH LINE BELOW +1E08; C; 1E09; # LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE +1E0A; C; 1E0B; # LATIN CAPITAL LETTER D WITH DOT ABOVE +1E0C; C; 1E0D; # LATIN CAPITAL LETTER D WITH DOT BELOW +1E0E; C; 1E0F; # LATIN CAPITAL LETTER D WITH LINE BELOW +1E10; C; 1E11; # LATIN CAPITAL LETTER D WITH CEDILLA +1E12; C; 1E13; # LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW +1E14; C; 1E15; # LATIN CAPITAL LETTER E WITH MACRON AND GRAVE +1E16; C; 1E17; # LATIN CAPITAL LETTER E WITH MACRON AND ACUTE +1E18; C; 1E19; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW +1E1A; C; 1E1B; # LATIN CAPITAL LETTER E WITH TILDE BELOW +1E1C; C; 1E1D; # LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE +1E1E; C; 1E1F; # LATIN CAPITAL LETTER F WITH DOT ABOVE +1E20; C; 1E21; # LATIN CAPITAL LETTER G WITH MACRON +1E22; C; 1E23; # LATIN CAPITAL LETTER H WITH DOT ABOVE +1E24; C; 1E25; # LATIN CAPITAL LETTER H WITH DOT BELOW +1E26; C; 1E27; # LATIN CAPITAL LETTER H WITH DIAERESIS +1E28; C; 1E29; # LATIN CAPITAL LETTER H WITH CEDILLA +1E2A; C; 1E2B; # LATIN CAPITAL LETTER H WITH BREVE BELOW +1E2C; C; 1E2D; # LATIN CAPITAL LETTER I WITH TILDE BELOW +1E2E; C; 1E2F; # LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE +1E30; C; 1E31; # LATIN CAPITAL LETTER K WITH ACUTE +1E32; C; 1E33; # LATIN CAPITAL LETTER K WITH DOT BELOW +1E34; C; 1E35; # LATIN CAPITAL LETTER K WITH LINE BELOW +1E36; C; 1E37; # LATIN CAPITAL LETTER L WITH DOT BELOW +1E38; C; 1E39; # LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON +1E3A; C; 1E3B; # LATIN CAPITAL LETTER L WITH LINE BELOW +1E3C; C; 1E3D; # LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW +1E3E; C; 1E3F; # LATIN CAPITAL LETTER M WITH ACUTE +1E40; C; 1E41; # LATIN CAPITAL LETTER M WITH DOT ABOVE +1E42; C; 1E43; # LATIN CAPITAL LETTER M WITH DOT BELOW +1E44; C; 1E45; # LATIN CAPITAL LETTER N WITH DOT ABOVE +1E46; C; 1E47; # LATIN CAPITAL LETTER N WITH DOT BELOW +1E48; C; 1E49; # LATIN CAPITAL LETTER N WITH LINE BELOW +1E4A; C; 1E4B; # LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW +1E4C; C; 1E4D; # LATIN CAPITAL LETTER O WITH TILDE AND ACUTE +1E4E; C; 1E4F; # LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS +1E50; C; 1E51; # LATIN CAPITAL LETTER O WITH MACRON AND GRAVE +1E52; C; 1E53; # LATIN CAPITAL LETTER O WITH MACRON AND ACUTE +1E54; C; 1E55; # LATIN CAPITAL LETTER P WITH ACUTE +1E56; C; 1E57; # LATIN CAPITAL LETTER P WITH DOT ABOVE +1E58; C; 1E59; # LATIN CAPITAL LETTER R WITH DOT ABOVE +1E5A; C; 1E5B; # LATIN CAPITAL LETTER R WITH DOT BELOW +1E5C; C; 1E5D; # LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON +1E5E; C; 1E5F; # LATIN CAPITAL LETTER R WITH LINE BELOW +1E60; C; 1E61; # LATIN CAPITAL LETTER S WITH DOT ABOVE +1E62; C; 1E63; # LATIN CAPITAL LETTER S WITH DOT BELOW +1E64; C; 1E65; # LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE +1E66; C; 1E67; # LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE +1E68; C; 1E69; # LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE +1E6A; C; 1E6B; # LATIN CAPITAL LETTER T WITH DOT ABOVE +1E6C; C; 1E6D; # LATIN CAPITAL LETTER T WITH DOT BELOW +1E6E; C; 1E6F; # LATIN CAPITAL LETTER T WITH LINE BELOW +1E70; C; 1E71; # LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW +1E72; C; 1E73; # LATIN CAPITAL LETTER U WITH DIAERESIS BELOW +1E74; C; 1E75; # LATIN CAPITAL LETTER U WITH TILDE BELOW +1E76; C; 1E77; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW +1E78; C; 1E79; # LATIN CAPITAL LETTER U WITH TILDE AND ACUTE +1E7A; C; 1E7B; # LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS +1E7C; C; 1E7D; # LATIN CAPITAL LETTER V WITH TILDE +1E7E; C; 1E7F; # LATIN CAPITAL LETTER V WITH DOT BELOW +1E80; C; 1E81; # LATIN CAPITAL LETTER W WITH GRAVE +1E82; C; 1E83; # LATIN CAPITAL LETTER W WITH ACUTE +1E84; C; 1E85; # LATIN CAPITAL LETTER W WITH DIAERESIS +1E86; C; 1E87; # LATIN CAPITAL LETTER W WITH DOT ABOVE +1E88; C; 1E89; # LATIN CAPITAL LETTER W WITH DOT BELOW +1E8A; C; 1E8B; # LATIN CAPITAL LETTER X WITH DOT ABOVE +1E8C; C; 1E8D; # LATIN CAPITAL LETTER X WITH DIAERESIS +1E8E; C; 1E8F; # LATIN CAPITAL LETTER Y WITH DOT ABOVE +1E90; C; 1E91; # LATIN CAPITAL LETTER Z WITH CIRCUMFLEX +1E92; C; 1E93; # LATIN CAPITAL LETTER Z WITH DOT BELOW +1E94; C; 1E95; # LATIN CAPITAL LETTER Z WITH LINE BELOW +1E96; F; 0068 0331; # LATIN SMALL LETTER H WITH LINE BELOW +1E97; F; 0074 0308; # LATIN SMALL LETTER T WITH DIAERESIS +1E98; F; 0077 030A; # LATIN SMALL LETTER W WITH RING ABOVE +1E99; F; 0079 030A; # LATIN SMALL LETTER Y WITH RING ABOVE +1E9A; F; 0061 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING +1E9B; C; 1E61; # LATIN SMALL LETTER LONG S WITH DOT ABOVE +1EA0; C; 1EA1; # LATIN CAPITAL LETTER A WITH DOT BELOW +1EA2; C; 1EA3; # LATIN CAPITAL LETTER A WITH HOOK ABOVE +1EA4; C; 1EA5; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE +1EA6; C; 1EA7; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE +1EA8; C; 1EA9; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +1EAA; C; 1EAB; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE +1EAC; C; 1EAD; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW +1EAE; C; 1EAF; # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE +1EB0; C; 1EB1; # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE +1EB2; C; 1EB3; # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE +1EB4; C; 1EB5; # LATIN CAPITAL LETTER A WITH BREVE AND TILDE +1EB6; C; 1EB7; # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW +1EB8; C; 1EB9; # LATIN CAPITAL LETTER E WITH DOT BELOW +1EBA; C; 1EBB; # LATIN CAPITAL LETTER E WITH HOOK ABOVE +1EBC; C; 1EBD; # LATIN CAPITAL LETTER E WITH TILDE +1EBE; C; 1EBF; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE +1EC0; C; 1EC1; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE +1EC2; C; 1EC3; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +1EC4; C; 1EC5; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE +1EC6; C; 1EC7; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW +1EC8; C; 1EC9; # LATIN CAPITAL LETTER I WITH HOOK ABOVE +1ECA; C; 1ECB; # LATIN CAPITAL LETTER I WITH DOT BELOW +1ECC; C; 1ECD; # LATIN CAPITAL LETTER O WITH DOT BELOW +1ECE; C; 1ECF; # LATIN CAPITAL LETTER O WITH HOOK ABOVE +1ED0; C; 1ED1; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED2; C; 1ED3; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED4; C; 1ED5; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED6; C; 1ED7; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +1ED8; C; 1ED9; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +1EDA; C; 1EDB; # LATIN CAPITAL LETTER O WITH HORN AND ACUTE +1EDC; C; 1EDD; # LATIN CAPITAL LETTER O WITH HORN AND GRAVE +1EDE; C; 1EDF; # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE +1EE0; C; 1EE1; # LATIN CAPITAL LETTER O WITH HORN AND TILDE +1EE2; C; 1EE3; # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW +1EE4; C; 1EE5; # LATIN CAPITAL LETTER U WITH DOT BELOW +1EE6; C; 1EE7; # LATIN CAPITAL LETTER U WITH HOOK ABOVE +1EE8; C; 1EE9; # LATIN CAPITAL LETTER U WITH HORN AND ACUTE +1EEA; C; 1EEB; # LATIN CAPITAL LETTER U WITH HORN AND GRAVE +1EEC; C; 1EED; # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE +1EEE; C; 1EEF; # LATIN CAPITAL LETTER U WITH HORN AND TILDE +1EF0; C; 1EF1; # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW +1EF2; C; 1EF3; # LATIN CAPITAL LETTER Y WITH GRAVE +1EF4; C; 1EF5; # LATIN CAPITAL LETTER Y WITH DOT BELOW +1EF6; C; 1EF7; # LATIN CAPITAL LETTER Y WITH HOOK ABOVE +1EF8; C; 1EF9; # LATIN CAPITAL LETTER Y WITH TILDE +1F08; C; 1F00; # GREEK CAPITAL LETTER ALPHA WITH PSILI +1F09; C; 1F01; # GREEK CAPITAL LETTER ALPHA WITH DASIA +1F0A; C; 1F02; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA +1F0B; C; 1F03; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA +1F0C; C; 1F04; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA +1F0D; C; 1F05; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA +1F0E; C; 1F06; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI +1F0F; C; 1F07; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI +1F18; C; 1F10; # GREEK CAPITAL LETTER EPSILON WITH PSILI +1F19; C; 1F11; # GREEK CAPITAL LETTER EPSILON WITH DASIA +1F1A; C; 1F12; # GREEK CAPITAL LETTER EPSILON WITH PSILI AND VARIA +1F1B; C; 1F13; # GREEK CAPITAL LETTER EPSILON WITH DASIA AND VARIA +1F1C; C; 1F14; # GREEK CAPITAL LETTER EPSILON WITH PSILI AND OXIA +1F1D; C; 1F15; # GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F28; C; 1F20; # GREEK CAPITAL LETTER ETA WITH PSILI +1F29; C; 1F21; # GREEK CAPITAL LETTER ETA WITH DASIA +1F2A; C; 1F22; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA +1F2B; C; 1F23; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA +1F2C; C; 1F24; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA +1F2D; C; 1F25; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA +1F2E; C; 1F26; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI +1F2F; C; 1F27; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI +1F38; C; 1F30; # GREEK CAPITAL LETTER IOTA WITH PSILI +1F39; C; 1F31; # GREEK CAPITAL LETTER IOTA WITH DASIA +1F3A; C; 1F32; # GREEK CAPITAL LETTER IOTA WITH PSILI AND VARIA +1F3B; C; 1F33; # GREEK CAPITAL LETTER IOTA WITH DASIA AND VARIA +1F3C; C; 1F34; # GREEK CAPITAL LETTER IOTA WITH PSILI AND OXIA +1F3D; C; 1F35; # GREEK CAPITAL LETTER IOTA WITH DASIA AND OXIA +1F3E; C; 1F36; # GREEK CAPITAL LETTER IOTA WITH PSILI AND PERISPOMENI +1F3F; C; 1F37; # GREEK CAPITAL LETTER IOTA WITH DASIA AND PERISPOMENI +1F48; C; 1F40; # GREEK CAPITAL LETTER OMICRON WITH PSILI +1F49; C; 1F41; # GREEK CAPITAL LETTER OMICRON WITH DASIA +1F4A; C; 1F42; # GREEK CAPITAL LETTER OMICRON WITH PSILI AND VARIA +1F4B; C; 1F43; # GREEK CAPITAL LETTER OMICRON WITH DASIA AND VARIA +1F4C; C; 1F44; # GREEK CAPITAL LETTER OMICRON WITH PSILI AND OXIA +1F4D; C; 1F45; # GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F50; F; 03C5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI +1F52; F; 03C5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA +1F54; F; 03C5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA +1F56; F; 03C5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI +1F59; C; 1F51; # GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B; C; 1F53; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D; C; 1F55; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F; C; 1F57; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F68; C; 1F60; # GREEK CAPITAL LETTER OMEGA WITH PSILI +1F69; C; 1F61; # GREEK CAPITAL LETTER OMEGA WITH DASIA +1F6A; C; 1F62; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA +1F6B; C; 1F63; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA +1F6C; C; 1F64; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA +1F6D; C; 1F65; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA +1F6E; C; 1F66; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI +1F6F; C; 1F67; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI +1F80; F; 1F00 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI +1F81; F; 1F01 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI +1F82; F; 1F02 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1F83; F; 1F03 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1F84; F; 1F04 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1F85; F; 1F05 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1F86; F; 1F06 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1F87; F; 1F07 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F88; F; 1F00 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI +1F88; S; 1F80; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI +1F89; F; 1F01 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI +1F89; S; 1F81; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI +1F8A; F; 1F02 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F8A; S; 1F82; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F8B; F; 1F03 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F8B; S; 1F83; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F8C; F; 1F04 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F8C; S; 1F84; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F8D; F; 1F05 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F8D; S; 1F85; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F8E; F; 1F06 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F8E; S; 1F86; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F8F; F; 1F07 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F8F; S; 1F87; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F90; F; 1F20 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI +1F91; F; 1F21 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI +1F92; F; 1F22 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1F93; F; 1F23 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1F94; F; 1F24 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1F95; F; 1F25 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1F96; F; 1F26 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1F97; F; 1F27 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F98; F; 1F20 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI +1F98; S; 1F90; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI +1F99; F; 1F21 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI +1F99; S; 1F91; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI +1F9A; F; 1F22 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F9A; S; 1F92; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F9B; F; 1F23 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F9B; S; 1F93; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F9C; F; 1F24 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F9C; S; 1F94; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F9D; F; 1F25 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F9D; S; 1F95; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F9E; F; 1F26 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F9E; S; 1F96; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F9F; F; 1F27 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F9F; S; 1F97; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FA0; F; 1F60 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI +1FA1; F; 1F61 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI +1FA2; F; 1F62 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1FA3; F; 1F63 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1FA4; F; 1F64 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1FA5; F; 1F65 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1FA6; F; 1F66 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1FA7; F; 1F67 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1FA8; F; 1F60 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI +1FA8; S; 1FA0; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI +1FA9; F; 1F61 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI +1FA9; S; 1FA1; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI +1FAA; F; 1F62 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1FAA; S; 1FA2; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1FAB; F; 1F63 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1FAB; S; 1FA3; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1FAC; F; 1F64 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1FAC; S; 1FA4; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1FAD; F; 1F65 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1FAD; S; 1FA5; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1FAE; F; 1F66 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1FAE; S; 1FA6; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1FAF; F; 1F67 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FAF; S; 1FA7; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FB2; F; 1F70 03B9; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI +1FB3; F; 03B1 03B9; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI +1FB4; F; 03AC 03B9; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6; F; 03B1 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI +1FB7; F; 03B1 0342 03B9; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI +1FB8; C; 1FB0; # GREEK CAPITAL LETTER ALPHA WITH VRACHY +1FB9; C; 1FB1; # GREEK CAPITAL LETTER ALPHA WITH MACRON +1FBA; C; 1F70; # GREEK CAPITAL LETTER ALPHA WITH VARIA +1FBB; C; 1F71; # GREEK CAPITAL LETTER ALPHA WITH OXIA +1FBC; F; 03B1 03B9; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBC; S; 1FB3; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBE; C; 03B9; # GREEK PROSGEGRAMMENI +1FC2; F; 1F74 03B9; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI +1FC3; F; 03B7 03B9; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI +1FC4; F; 03AE 03B9; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6; F; 03B7 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI +1FC7; F; 03B7 0342 03B9; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI +1FC8; C; 1F72; # GREEK CAPITAL LETTER EPSILON WITH VARIA +1FC9; C; 1F73; # GREEK CAPITAL LETTER EPSILON WITH OXIA +1FCA; C; 1F74; # GREEK CAPITAL LETTER ETA WITH VARIA +1FCB; C; 1F75; # GREEK CAPITAL LETTER ETA WITH OXIA +1FCC; F; 03B7 03B9; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA +1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI +1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI +1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY +1FD9; C; 1FD1; # GREEK CAPITAL LETTER IOTA WITH MACRON +1FDA; C; 1F76; # GREEK CAPITAL LETTER IOTA WITH VARIA +1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA +1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA +1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA +1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI +1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI +1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI +1FE8; C; 1FE0; # GREEK CAPITAL LETTER UPSILON WITH VRACHY +1FE9; C; 1FE1; # GREEK CAPITAL LETTER UPSILON WITH MACRON +1FEA; C; 1F7A; # GREEK CAPITAL LETTER UPSILON WITH VARIA +1FEB; C; 1F7B; # GREEK CAPITAL LETTER UPSILON WITH OXIA +1FEC; C; 1FE5; # GREEK CAPITAL LETTER RHO WITH DASIA +1FF2; F; 1F7C 03B9; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI +1FF3; F; 03C9 03B9; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI +1FF4; F; 03CE 03B9; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6; F; 03C9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI +1FF7; F; 03C9 0342 03B9; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI +1FF8; C; 1F78; # GREEK CAPITAL LETTER OMICRON WITH VARIA +1FF9; C; 1F79; # GREEK CAPITAL LETTER OMICRON WITH OXIA +1FFA; C; 1F7C; # GREEK CAPITAL LETTER OMEGA WITH VARIA +1FFB; C; 1F7D; # GREEK CAPITAL LETTER OMEGA WITH OXIA +1FFC; F; 03C9 03B9; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +1FFC; S; 1FF3; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +2126; C; 03C9; # OHM SIGN +212A; C; 006B; # KELVIN SIGN +212B; C; 00E5; # ANGSTROM SIGN +2160; C; 2170; # ROMAN NUMERAL ONE +2161; C; 2171; # ROMAN NUMERAL TWO +2162; C; 2172; # ROMAN NUMERAL THREE +2163; C; 2173; # ROMAN NUMERAL FOUR +2164; C; 2174; # ROMAN NUMERAL FIVE +2165; C; 2175; # ROMAN NUMERAL SIX +2166; C; 2176; # ROMAN NUMERAL SEVEN +2167; C; 2177; # ROMAN NUMERAL EIGHT +2168; C; 2178; # ROMAN NUMERAL NINE +2169; C; 2179; # ROMAN NUMERAL TEN +216A; C; 217A; # ROMAN NUMERAL ELEVEN +216B; C; 217B; # ROMAN NUMERAL TWELVE +216C; C; 217C; # ROMAN NUMERAL FIFTY +216D; C; 217D; # ROMAN NUMERAL ONE HUNDRED +216E; C; 217E; # ROMAN NUMERAL FIVE HUNDRED +216F; C; 217F; # ROMAN NUMERAL ONE THOUSAND +24B6; C; 24D0; # CIRCLED LATIN CAPITAL LETTER A +24B7; C; 24D1; # CIRCLED LATIN CAPITAL LETTER B +24B8; C; 24D2; # CIRCLED LATIN CAPITAL LETTER C +24B9; C; 24D3; # CIRCLED LATIN CAPITAL LETTER D +24BA; C; 24D4; # CIRCLED LATIN CAPITAL LETTER E +24BB; C; 24D5; # CIRCLED LATIN CAPITAL LETTER F +24BC; C; 24D6; # CIRCLED LATIN CAPITAL LETTER G +24BD; C; 24D7; # CIRCLED LATIN CAPITAL LETTER H +24BE; C; 24D8; # CIRCLED LATIN CAPITAL LETTER I +24BF; C; 24D9; # CIRCLED LATIN CAPITAL LETTER J +24C0; C; 24DA; # CIRCLED LATIN CAPITAL LETTER K +24C1; C; 24DB; # CIRCLED LATIN CAPITAL LETTER L +24C2; C; 24DC; # CIRCLED LATIN CAPITAL LETTER M +24C3; C; 24DD; # CIRCLED LATIN CAPITAL LETTER N +24C4; C; 24DE; # CIRCLED LATIN CAPITAL LETTER O +24C5; C; 24DF; # CIRCLED LATIN CAPITAL LETTER P +24C6; C; 24E0; # CIRCLED LATIN CAPITAL LETTER Q +24C7; C; 24E1; # CIRCLED LATIN CAPITAL LETTER R +24C8; C; 24E2; # CIRCLED LATIN CAPITAL LETTER S +24C9; C; 24E3; # CIRCLED LATIN CAPITAL LETTER T +24CA; C; 24E4; # CIRCLED LATIN CAPITAL LETTER U +24CB; C; 24E5; # CIRCLED LATIN CAPITAL LETTER V +24CC; C; 24E6; # CIRCLED LATIN CAPITAL LETTER W +24CD; C; 24E7; # CIRCLED LATIN CAPITAL LETTER X +24CE; C; 24E8; # CIRCLED LATIN CAPITAL LETTER Y +24CF; C; 24E9; # CIRCLED LATIN CAPITAL LETTER Z +FB00; F; 0066 0066; # LATIN SMALL LIGATURE FF +FB01; F; 0066 0069; # LATIN SMALL LIGATURE FI +FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL +FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI +FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL +FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T +FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST +FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW +FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH +FB15; F; 0574 056B; # ARMENIAN SMALL LIGATURE MEN INI +FB16; F; 057E 0576; # ARMENIAN SMALL LIGATURE VEW NOW +FB17; F; 0574 056D; # ARMENIAN SMALL LIGATURE MEN XEH +FF21; C; FF41; # FULLWIDTH LATIN CAPITAL LETTER A +FF22; C; FF42; # FULLWIDTH LATIN CAPITAL LETTER B +FF23; C; FF43; # FULLWIDTH LATIN CAPITAL LETTER C +FF24; C; FF44; # FULLWIDTH LATIN CAPITAL LETTER D +FF25; C; FF45; # FULLWIDTH LATIN CAPITAL LETTER E +FF26; C; FF46; # FULLWIDTH LATIN CAPITAL LETTER F +FF27; C; FF47; # FULLWIDTH LATIN CAPITAL LETTER G +FF28; C; FF48; # FULLWIDTH LATIN CAPITAL LETTER H +FF29; C; FF49; # FULLWIDTH LATIN CAPITAL LETTER I +FF2A; C; FF4A; # FULLWIDTH LATIN CAPITAL LETTER J +FF2B; C; FF4B; # FULLWIDTH LATIN CAPITAL LETTER K +FF2C; C; FF4C; # FULLWIDTH LATIN CAPITAL LETTER L +FF2D; C; FF4D; # FULLWIDTH LATIN CAPITAL LETTER M +FF2E; C; FF4E; # FULLWIDTH LATIN CAPITAL LETTER N +FF2F; C; FF4F; # FULLWIDTH LATIN CAPITAL LETTER O +FF30; C; FF50; # FULLWIDTH LATIN CAPITAL LETTER P +FF31; C; FF51; # FULLWIDTH LATIN CAPITAL LETTER Q +FF32; C; FF52; # FULLWIDTH LATIN CAPITAL LETTER R +FF33; C; FF53; # FULLWIDTH LATIN CAPITAL LETTER S +FF34; C; FF54; # FULLWIDTH LATIN CAPITAL LETTER T +FF35; C; FF55; # FULLWIDTH LATIN CAPITAL LETTER U +FF36; C; FF56; # FULLWIDTH LATIN CAPITAL LETTER V +FF37; C; FF57; # FULLWIDTH LATIN CAPITAL LETTER W +FF38; C; FF58; # FULLWIDTH LATIN CAPITAL LETTER X +FF39; C; FF59; # FULLWIDTH LATIN CAPITAL LETTER Y +FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z +10400; C; 10428; # DESERET CAPITAL LETTER LONG I +10401; C; 10429; # DESERET CAPITAL LETTER LONG E +10402; C; 1042A; # DESERET CAPITAL LETTER LONG A +10403; C; 1042B; # DESERET CAPITAL LETTER LONG AH +10404; C; 1042C; # DESERET CAPITAL LETTER LONG O +10405; C; 1042D; # DESERET CAPITAL LETTER LONG OO +10406; C; 1042E; # DESERET CAPITAL LETTER SHORT I +10407; C; 1042F; # DESERET CAPITAL LETTER SHORT E +10408; C; 10430; # DESERET CAPITAL LETTER SHORT A +10409; C; 10431; # DESERET CAPITAL LETTER SHORT AH +1040A; C; 10432; # DESERET CAPITAL LETTER SHORT O +1040B; C; 10433; # DESERET CAPITAL LETTER SHORT OO +1040C; C; 10434; # DESERET CAPITAL LETTER AY +1040D; C; 10435; # DESERET CAPITAL LETTER OW +1040E; C; 10436; # DESERET CAPITAL LETTER WU +1040F; C; 10437; # DESERET CAPITAL LETTER YEE +10410; C; 10438; # DESERET CAPITAL LETTER H +10411; C; 10439; # DESERET CAPITAL LETTER PEE +10412; C; 1043A; # DESERET CAPITAL LETTER BEE +10413; C; 1043B; # DESERET CAPITAL LETTER TEE +10414; C; 1043C; # DESERET CAPITAL LETTER DEE +10415; C; 1043D; # DESERET CAPITAL LETTER CHEE +10416; C; 1043E; # DESERET CAPITAL LETTER JEE +10417; C; 1043F; # DESERET CAPITAL LETTER KAY +10418; C; 10440; # DESERET CAPITAL LETTER GAY +10419; C; 10441; # DESERET CAPITAL LETTER EF +1041A; C; 10442; # DESERET CAPITAL LETTER VEE +1041B; C; 10443; # DESERET CAPITAL LETTER ETH +1041C; C; 10444; # DESERET CAPITAL LETTER THEE +1041D; C; 10445; # DESERET CAPITAL LETTER ES +1041E; C; 10446; # DESERET CAPITAL LETTER ZEE +1041F; C; 10447; # DESERET CAPITAL LETTER ESH +10420; C; 10448; # DESERET CAPITAL LETTER ZHEE +10421; C; 10449; # DESERET CAPITAL LETTER ER +10422; C; 1044A; # DESERET CAPITAL LETTER EL +10423; C; 1044B; # DESERET CAPITAL LETTER EM +10424; C; 1044C; # DESERET CAPITAL LETTER EN +10425; C; 1044D; # DESERET CAPITAL LETTER ENG +10426; C; 1044E; # DESERET CAPITAL LETTER OI +10427; C; 1044F; # DESERET CAPITAL LETTER EW diff --git a/fc-case/Makefile.am b/fc-case/Makefile.am new file mode 100644 index 0000000..e00508b --- /dev/null +++ b/fc-case/Makefile.am @@ -0,0 +1,52 @@ +# +# $Id $ +# +# Copyright © 2003 Keith Packard +# +# Permission to use, copy, modify, distribute, and sell this software and its +# documentation for any purpose is hereby granted without fee, provided that +# the above copyright notice appear in all copies and that both that +# copyright notice and this permission notice appear in supporting +# documentation, and that the name of Keith Packard not be used in +# advertising or publicity pertaining to distribution of the software without +# specific, written prior permission. Keith Packard makes no +# representations about the suitability of this software for any purpose. It +# is provided "as is" without express or implied warranty. +# +# KEITH PACKARD DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, +# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO +# EVENT SHALL KEITH PACKARD BE LIABLE FOR ANY SPECIAL, INDIRECT OR +# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, +# DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER +# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR +# PERFORMANCE OF THIS SOFTWARE. +# + +INCLUDES=-I${top_srcdir}/src -I${top_srcdir} $(FREETYPE_CFLAGS) $(WARN_CFLAGS) + +TMPL=fccase.tmpl.h +STMPL=${top_srcdir}/fc-case/${TMPL} +TARG=fccase.h + +noinst_PROGRAMS=fc-case + +noinst_HEADERS=$(TARG) + +noinst_MANS=fc-case.man + +fc_case_SRCS= \ + fc-case.c \ + fccaseint.h \ + fccaseread.c + +CASEFOLDING=CaseFolding.txt +SCASEFOLDING=${top_srcdir}/fc-case/CaseFolding.txt + +EXTRA_DIST=$(TMPL) $(CASEFOLDING) + +$(TARG): $(STMPL) fc-case $(SCASEFOLDING) + rm -f $(TARG) + ./fc-case $(SCASEFOLDING) < $(STMPL) > $(TARG) + +CLEANFILES=$(TARG) + diff --git a/fc-case/fc-case.c b/fc-case/fc-case.c new file mode 100644 index 0000000..588ccf3 --- /dev/null +++ b/fc-case/fc-case.c @@ -0,0 +1,363 @@ +/* + * $Id$ + * + * Copyright © 2004 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that + * copyright notice and this permission notice appear in supporting + * documentation, and that the name of Keith Packard not be used in + * advertising or publicity pertaining to distribution of the software without + * specific, written prior permission. Keith Packard makes no + * representations about the suitability of this software for any purpose. It + * is provided "as is" without express or implied warranty. + * + * KEITH PACKARD DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL KEITH PACKARD BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THIS SOFTWARE. + */ + +#include "fcint.h" +#include + +#define MAX_OUT 32 +#define MAX_LINE 8192 + +typedef enum _caseFoldClass { CaseFoldCommon, CaseFoldFull, CaseFoldSimple, CaseFoldTurkic } CaseFoldClass; + +typedef struct _caseFoldClassMap { + char *name; + CaseFoldClass class; +} CaseFoldClassMap; + +static CaseFoldClassMap caseFoldClassMap[] = { + { "C", CaseFoldCommon }, + { "F", CaseFoldFull }, + { "S", CaseFoldSimple }, + { "T", CaseFoldTurkic }, + { 0, 0 } +}; + +typedef struct _caseFoldRaw { + FcChar32 upper; + CaseFoldClass class; + int nout; + FcChar32 lower[MAX_OUT]; +} CaseFoldRaw; + +static void +panic (char *reason) +{ + fprintf (stderr, "fc-case: panic %s\n", reason); + exit (1); +} + +int maxExpand; +static FcCaseFold *folds; +int nfolds; + +static FcCaseFold * +addFold (void) +{ + if (folds) + folds = realloc (folds, (nfolds + 1) * sizeof (FcCaseFold)); + else + folds = malloc (sizeof (FcCaseFold)); + if (!folds) + panic ("out of memory"); + return &folds[nfolds++]; +} + +static int +ucs4_to_utf8 (FcChar32 ucs4, + FcChar8 dest[FC_UTF8_MAX_LEN]) +{ + int bits; + FcChar8 *d = dest; + + if (ucs4 < 0x80) { *d++= ucs4; bits= -6; } + else if (ucs4 < 0x800) { *d++= ((ucs4 >> 6) & 0x1F) | 0xC0; bits= 0; } + else if (ucs4 < 0x10000) { *d++= ((ucs4 >> 12) & 0x0F) | 0xE0; bits= 6; } + else if (ucs4 < 0x200000) { *d++= ((ucs4 >> 18) & 0x07) | 0xF0; bits= 12; } + else if (ucs4 < 0x4000000) { *d++= ((ucs4 >> 24) & 0x03) | 0xF8; bits= 18; } + else if (ucs4 < 0x80000000) { *d++= ((ucs4 >> 30) & 0x01) | 0xFC; bits= 24; } + else return 0; + + for ( ; bits >= 0; bits-= 6) { + *d++= ((ucs4 >> bits) & 0x3F) | 0x80; + } + return d - dest; +} + +static int +utf8_size (FcChar32 ucs4) +{ + FcChar8 utf8[FC_UTF8_MAX_LEN]; + return ucs4_to_utf8 (ucs4, utf8 ); +} + +static FcChar8 *foldChars; +int nfoldChars; +int maxFoldChars; +FcChar32 minFoldChar; +FcChar32 maxFoldChar; + +static void +addChar (FcChar32 c) +{ + FcChar8 utf8[FC_UTF8_MAX_LEN]; + int len; + int i; + + len = ucs4_to_utf8 (c, utf8); + if (foldChars) + foldChars = realloc (foldChars, (nfoldChars + len) * sizeof (FcChar8)); + else + foldChars = malloc (sizeof (FcChar8) * len); + if (!foldChars) + panic ("out of memory"); + for (i = 0; i < len; i++) + foldChars[nfoldChars + i] = utf8[i]; + nfoldChars += len; +} + +static int +foldExtends (FcCaseFold *fold, CaseFoldRaw *raw) +{ + switch (fold->method) { + case FC_CASE_FOLD_RANGE: + if ((short) (raw->lower[0] - raw->upper) != fold->offset) + return 0; + if (raw->upper != fold->upper + fold->count) + return 0; + return 1; + case FC_CASE_FOLD_EVEN_ODD: + if ((short) (raw->lower[0] - raw->upper) != 1) + return 0; + if (raw->upper != fold->upper + fold->count + 1) + return 0; + return 1; + case FC_CASE_FOLD_FULL: + break; + } + return 0; +} + +static char * +case_fold_method_name (FcChar16 method) +{ + switch (method) { + case FC_CASE_FOLD_RANGE: return "FC_CASE_FOLD_RANGE,"; + case FC_CASE_FOLD_EVEN_ODD: return "FC_CASE_FOLD_EVEN_ODD,"; + case FC_CASE_FOLD_FULL: return "FC_CASE_FOLD_FULL,"; + default: return "unknown"; + } +} + +static void +dump (void) +{ + int i; + + printf ( "#define FC_NUM_CASE_FOLD %d\n", nfolds); + printf ( "#define FC_NUM_CASE_FOLD_CHARS %d\n", nfoldChars); + printf ( "#define FC_MAX_CASE_FOLD_CHARS %d\n", maxFoldChars); + printf ( "#define FC_MAX_CASE_FOLD_EXPAND %d\n", maxExpand); + printf ( "#define FC_MIN_FOLD_CHAR 0x%08x\n", minFoldChar); + printf ( "#define FC_MAX_FOLD_CHAR 0x%08x\n", maxFoldChar); + printf ( "\n"); + + /* + * Dump out ranges + */ + printf ("static const FcCaseFold fcCaseFold[FC_NUM_CASE_FOLD] = {\n"); + for (i = 0; i < nfolds; i++) + { + printf (" { 0x%08x, %-22s 0x%04x, %6d },\n", + folds[i].upper, case_fold_method_name (folds[i].method), + folds[i].count, folds[i].offset); + } + printf ("};\n\n"); + + /* + * Dump out "other" values + */ + + printf ("static const FcChar8 fcCaseFoldChars[FC_NUM_CASE_FOLD_CHARS] = {\n"); + for (i = 0; i < nfoldChars; i++) + { + printf ("0x%02x", foldChars[i]); + if (i != nfoldChars - 1) + { + if ((i & 0xf) == 0xf) + printf (",\n"); + else + printf (","); + } + } + printf ("\n};\n"); +} + +/* + * Read the standard Unicode CaseFolding.txt file + */ +#define SEP "; \t\n" + +static int +parseRaw (char *line, CaseFoldRaw *raw) +{ + char *tok, *end; + int i; + + if (!isxdigit (line[0])) + return 0; + /* + * Get upper case value + */ + tok = strtok (line, SEP); + if (!tok || tok[0] == '#') + return 0; + raw->upper = strtol (tok, &end, 16); + if (end == tok) + return 0; + /* + * Get class + */ + tok = strtok (NULL, SEP); + if (!tok || tok[0] == '#') + return 0; + for (i = 0; caseFoldClassMap[i].name; i++) + if (!strcmp (tok, caseFoldClassMap[i].name)) + { + raw->class = caseFoldClassMap[i].class; + break; + } + if (!caseFoldClassMap[i].name) + return 0; + + /* + * Get list of result characters + */ + for (i = 0; i < MAX_OUT; i++) + { + tok = strtok (NULL, SEP); + if (!tok || tok[0] == '#') + break; + raw->lower[i] = strtol (tok, &end, 16); + if (end == tok) + break; + } + if (i == 0) + return 0; + raw->nout = i; + return 1; +} + +static int +caseFoldReadRaw (FILE *in, CaseFoldRaw *raw) +{ + char line[MAX_LINE]; + + for (;;) + { + if (!fgets (line, sizeof (line) - 1, in)) + return 0; + if (parseRaw (line, raw)) + return 1; + } +} + +int +main (int argc, char **argv) +{ + FcCaseFold *fold = 0; + CaseFoldRaw raw; + int i; + FILE *caseFile; + char line[MAX_LINE]; + int expand; + + if (argc != 2) + panic ("usage: fc-case CaseFolding.txt"); + caseFile = fopen (argv[1], "r"); + if (!caseFile) + panic ("can't open case folding file"); + + while (caseFoldReadRaw (caseFile, &raw)) + { + if (!minFoldChar) + minFoldChar = raw.upper; + maxFoldChar = raw.upper; + switch (raw.class) { + case CaseFoldCommon: + case CaseFoldFull: + if (raw.nout == 1) + { + if (fold && foldExtends (fold, &raw)) + fold->count = raw.upper - fold->upper + 1; + else + { + fold = addFold (); + fold->upper = raw.upper; + fold->offset = raw.lower[0] - raw.upper; + if (fold->offset == 1) + fold->method = FC_CASE_FOLD_EVEN_ODD; + else + fold->method = FC_CASE_FOLD_RANGE; + fold->count = 1; + } + expand = utf8_size (raw.lower[0]) - utf8_size(raw.upper); + } + else + { + fold = addFold (); + fold->upper = raw.upper; + fold->method = FC_CASE_FOLD_FULL; + fold->offset = nfoldChars; + for (i = 0; i < raw.nout; i++) + addChar (raw.lower[i]); + fold->count = nfoldChars - fold->offset; + if (fold->count > maxFoldChars) + maxFoldChars = fold->count; + expand = fold->count - utf8_size (raw.upper); + } + if (expand > maxExpand) + maxExpand = expand; + break; + case CaseFoldSimple: + break; + case CaseFoldTurkic: + break; + } + } + /* + * Scan the input until the marker is found + */ + + while (fgets (line, sizeof (line), stdin)) + { + if (!strncmp (line, "@@@", 3)) + break; + fputs (line, stdout); + } + + /* + * Dump these tables + */ + dump (); + + /* + * And flush out the rest of the input file + */ + + while (fgets (line, sizeof (line), stdin)) + fputs (line, stdout); + + fflush (stdout); + exit (ferror (stdout)); +} diff --git a/fc-case/fccase.tmpl.h b/fc-case/fccase.tmpl.h new file mode 100644 index 0000000..24222d2 --- /dev/null +++ b/fc-case/fccase.tmpl.h @@ -0,0 +1,25 @@ +/* + * $Id$ + * + * Copyright © 2003 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that + * copyright notice and this permission notice appear in supporting + * documentation, and that the name of Keith Packard not be used in + * advertising or publicity pertaining to distribution of the software without + * specific, written prior permission. Keith Packard makes no + * representations about the suitability of this software for any purpose. It + * is provided "as is" without express or implied warranty. + * + * KEITH PACKARD DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL KEITH PACKARD BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THIS SOFTWARE. + */ + +@@@ diff --git a/fonts.conf.in b/fonts.conf.in index 446c0a0..712cdda 100644 --- a/fonts.conf.in +++ b/fonts.conf.in @@ -73,8 +73,9 @@ --> Bitstream Vera Serif - Times Times New Roman + Thorndale AMT + Times Nimbus Roman No9 L Luxi Serif Kochi Mincho @@ -92,6 +93,7 @@ Helvetica Arial Verdana + Albany AMT Nimbus Sans L Luxi Sans Kochi Gothic @@ -111,6 +113,7 @@ Courier New Andale Mono Luxi Mono + Cumberland AMT Nimbus Mono L NSimSun FreeMono @@ -134,6 +137,48 @@ + + + Times + + Nimbus Roman No9 L + + + + Helvetica + + Nimbus Sans L + + + + Courier + + Nimbus Mono L + + + + + + Times New Roman + Thorndale AMT + + Arial + Albany AMT + + Courier New + Cumberland AMT + conf.d local.conf - - - Times - Times New Roman - - - Helvetica - Arial - - - Courier - Courier New - - @@ -238,8 +267,9 @@ Bitstream Vera Serif Times New Roman - Nimbus Roman No9 L + Thorndale AMT Luxi Serif + Nimbus Roman No9 L Times Frank Ruehl Kochi Mincho @@ -254,9 +284,10 @@ Bitstream Vera Sans Verdana - Nimbus Sans L - Luxi Sans Arial + Albany AMT + Luxi Sans + Nimbus Sans L Helvetica Nachlieli Kochi Gothic @@ -273,8 +304,10 @@ Bitstream Vera Sans Mono Andale Mono Courier New + Cumberland AMT Luxi Mono Nimbus Mono L + Courier Miriam Mono Kochi Gothic AR PL KaitiM GB diff --git a/src/fcint.h b/src/fcint.h index 106a38b..4dca3c5 100644 --- a/src/fcint.h +++ b/src/fcint.h @@ -231,6 +231,37 @@ typedef struct _FcGlyphName { FcChar8 name[1]; /* name extends beyond struct */ } FcGlyphName; +/* + * To perform case-insensitive string comparisons, a table + * is used which holds three different kinds of folding data. + * + * The first is a range of upper case values mapping to a range + * of their lower case equivalents. Within each range, the offset + * between upper and lower case is constant. + * + * The second is a range of upper case values which are interleaved + * with their lower case equivalents. + * + * The third is a set of raw unicode values mapping to a list + * of unicode values for comparison purposes. This allows conversion + * of ß to "ss" so that SS, ss and ß all match. A separate array + * holds the list of unicode values for each entry. + * + * These are packed into a single table. Using a binary search, + * the appropriate entry can be located. + */ + +#define FC_CASE_FOLD_RANGE 0 +#define FC_CASE_FOLD_EVEN_ODD 1 +#define FC_CASE_FOLD_FULL 2 + +typedef struct _FcCaseFold { + FcChar32 upper; + FcChar16 method : 2; + FcChar16 count : 14; + short offset; /* lower - upper for RANGE, table id for FULL */ +} FcCaseFold; + #define FC_MAX_FILE_LEN 4096 /* @@ -746,4 +777,7 @@ FcStrUsesHome (const FcChar8 *s); FcChar8 * FcStrLastSlash (const FcChar8 *path); +FcChar32 +FcStrHashIgnoreCase (const FcChar8 *s); + #endif /* _FC_INT_H_ */ diff --git a/src/fclist.c b/src/fclist.c index 6730f20..aaa9061 100644 --- a/src/fclist.c +++ b/src/fclist.c @@ -219,20 +219,6 @@ FcListPatternMatchAny (const FcPattern *p, return FcTrue; } -static FcChar32 -FcListStringHash (const FcChar8 *s) -{ - FcChar32 h = 0; - FcChar8 c; - - while ((c = *s++)) - { - c = FcToLower (c); - h = ((h << 3) ^ (h >> 3)) ^ c; - } - return h; -} - static FcChar32 FcListMatrixHash (const FcMatrix *m) { @@ -255,7 +241,7 @@ FcListValueHash (FcValue v) case FcTypeDouble: return (FcChar32) (int) v.u.d; case FcTypeString: - return FcListStringHash (v.u.s); + return FcStrHashIgnoreCase (v.u.s); case FcTypeBool: return (FcChar32) v.u.b; case FcTypeMatrix: diff --git a/src/fcstr.c b/src/fcstr.c index 06315e6..61f1897 100644 --- a/src/fcstr.c +++ b/src/fcstr.c @@ -63,16 +63,147 @@ FcStrFree (FcChar8 *s) free (s); } + +#include "../fc-case/fccase.h" + +#define FcCaseFoldUpperCount(cf) \ + ((cf)->method == FC_CASE_FOLD_FULL ? 1 : (cf)->count) + +#define FC_STR_CANON_BUF_LEN 1024 + +typedef struct _FcCaseWalker { + const FcChar8 *read; + const FcChar8 *src; + int len; + FcChar8 utf8[FC_MAX_CASE_FOLD_CHARS + 1]; +} FcCaseWalker; + +static void +FcStrCaseWalkerInit (const FcChar8 *src, FcCaseWalker *w) +{ + w->src = src; + w->read = 0; + w->len = strlen (src); +} + +static FcChar8 +FcStrCaseWalkerLong (FcCaseWalker *w, FcChar8 r) +{ + FcChar32 ucs4; + int slen; + + slen = FcUtf8ToUcs4 (w->src - 1, &ucs4, w->len); + if (slen <= 0) + return r; + if (FC_MIN_FOLD_CHAR <= ucs4 && ucs4 <= FC_MAX_FOLD_CHAR) + { + int min = 0; + int max = FC_NUM_CASE_FOLD; + + while (min <= max) + { + int mid = (min + max) >> 1; + FcChar32 low = fcCaseFold[mid].upper; + FcChar32 high = low + FcCaseFoldUpperCount (&fcCaseFold[mid]); + + if (high <= ucs4) + min = mid + 1; + else if (ucs4 < low) + max = mid - 1; + else + { + const FcCaseFold *fold = &fcCaseFold[mid]; + int dlen; + + switch (fold->method) { + case FC_CASE_FOLD_EVEN_ODD: + if ((ucs4 & 1) != (fold->upper & 1)) + return r; + /* fall through ... */ + default: + dlen = FcUcs4ToUtf8 (ucs4 + fold->offset, w->utf8); + break; + case FC_CASE_FOLD_FULL: + dlen = fold->count; + memcpy (w->utf8, fcCaseFoldChars + fold->offset, dlen); + break; + } + + /* consume rest of src utf-8 bytes */ + w->src += slen - 1; + w->len -= slen - 1; + + /* read from temp buffer */ + w->utf8[dlen] = '\0'; + w->read = w->utf8; + return *w->read++; + } + } + } + return r; +} + +static FcChar8 +FcStrCaseWalkerNext (FcCaseWalker *w) +{ + FcChar8 r; + + if (w->read) + { + if ((r = *w->read++)) + return r; + w->read = 0; + } + r = *w->src++; + --w->len; + + if ((r & 0xc0) == 0xc0) + return FcStrCaseWalkerLong (w, r); + if ('A' <= r && r <= 'Z') + r = r - 'A' + 'a'; + return r; +} + +static FcChar8 +FcStrCaseWalkerNextIgnoreBlanks (FcCaseWalker *w) +{ + FcChar8 r; + + if (w->read) + { + if ((r = *w->read++)) + return r; + w->read = 0; + } + do + { + r = *w->src++; + --w->len; + } while (r == ' '); + + if ((r & 0xc0) == 0xc0) + return FcStrCaseWalkerLong (w, r); + if ('A' <= r && r <= 'Z') + r = r - 'A' + 'a'; + return r; +} + int FcStrCmpIgnoreCase (const FcChar8 *s1, const FcChar8 *s2) { - FcChar8 c1, c2; + FcCaseWalker w1, w2; + FcChar8 c1, c2; + + if (s1 == s2) return 0; + + FcStrCaseWalkerInit (s1, &w1); + FcStrCaseWalkerInit (s2, &w2); for (;;) { - c1 = *s1++; - c2 = *s2++; - if (!c1 || (c1 != c2 && (c1 = FcToLower(c1)) != (c2 = FcToLower(c2)))) + c1 = FcStrCaseWalkerNext (&w1); + c2 = FcStrCaseWalkerNext (&w2); + if (!c1 || (c1 != c2)) break; } return (int) c1 - (int) c2; @@ -81,17 +212,19 @@ FcStrCmpIgnoreCase (const FcChar8 *s1, const FcChar8 *s2) int FcStrCmpIgnoreBlanksAndCase (const FcChar8 *s1, const FcChar8 *s2) { - FcChar8 c1, c2; + FcCaseWalker w1, w2; + FcChar8 c1, c2; + + if (s1 == s2) return 0; + + FcStrCaseWalkerInit (s1, &w1); + FcStrCaseWalkerInit (s2, &w2); for (;;) { - do - c1 = *s1++; - while (c1 == ' '); - do - c2 = *s2++; - while (c2 == ' '); - if (!c1 || (c1 != c2 && (c1 = FcToLower(c1)) != (c2 = FcToLower(c2)))) + c1 = FcStrCaseWalkerNextIgnoreBlanks (&w1); + c2 = FcStrCaseWalkerNextIgnoreBlanks (&w2); + if (!c1 || (c1 != c2)) break; } return (int) c1 - (int) c2; @@ -114,6 +247,23 @@ FcStrCmp (const FcChar8 *s1, const FcChar8 *s2) return (int) c1 - (int) c2; } +/* + * Return a hash value for a string + */ + +FcChar32 +FcStrHashIgnoreCase (const FcChar8 *s) +{ + FcChar32 h = 0; + FcCaseWalker w; + FcChar8 c; + + FcStrCaseWalkerInit (s, &w); + while ((c = FcStrCaseWalkerNext (&w))) + h = ((h << 3) ^ (h >> 3)) ^ c; + return h; +} + /* * Is the head of s1 equal to s2? */ @@ -121,17 +271,17 @@ FcStrCmp (const FcChar8 *s1, const FcChar8 *s2) static FcBool FcStrIsAtIgnoreBlanksAndCase (const FcChar8 *s1, const FcChar8 *s2) { - FcChar8 c1, c2; + FcCaseWalker w1, w2; + FcChar8 c1, c2; + + FcStrCaseWalkerInit (s1, &w1); + FcStrCaseWalkerInit (s2, &w2); for (;;) { - do - c1 = *s1++; - while (c1 == ' '); - do - c2 = *s2++; - while (c2 == ' '); - if (!c1 || (c1 != c2 && (c1 = FcToLower(c1)) != (c2 = FcToLower(c2)))) + c1 = FcStrCaseWalkerNextIgnoreBlanks (&w1); + c2 = FcStrCaseWalkerNextIgnoreBlanks (&w2); + if (!c1 || (c1 != c2)) break; } return c1 == c2 || !c2; @@ -160,13 +310,17 @@ FcStrContainsIgnoreBlanksAndCase (const FcChar8 *s1, const FcChar8 *s2) static FcBool FcStrIsAtIgnoreCase (const FcChar8 *s1, const FcChar8 *s2) { - FcChar8 c1, c2; + FcCaseWalker w1, w2; + FcChar8 c1, c2; + + FcStrCaseWalkerInit (s1, &w1); + FcStrCaseWalkerInit (s2, &w2); for (;;) { - c1 = *s1++; - c2 = *s2++; - if (!c1 || (c1 != c2 && (c1 = FcToLower(c1)) != (c2 = FcToLower(c2)))) + c1 = FcStrCaseWalkerNext (&w1); + c2 = FcStrCaseWalkerNext (&w2); + if (!c1 || (c1 != c2)) break; } return c1 == c2 || !c2; @@ -191,52 +345,45 @@ FcStrContainsIgnoreCase (const FcChar8 *s1, const FcChar8 *s2) const FcChar8 * FcStrStrIgnoreCase (const FcChar8 *s1, const FcChar8 *s2) { - FcChar8 c1, c2; - const FcChar8 * p = s1; - const FcChar8 * b = s2; + FcCaseWalker w1, w2; + FcChar8 c1, c2; + const FcChar8 *cur; if (!s1 || !s2) return 0; if (s1 == s2) return s1; - -again: - c2 = *s2++; - c2 = FcToLower (c2); - - if (!c2) - return 0; - - for (;;) + + FcStrCaseWalkerInit (s1, &w1); + FcStrCaseWalkerInit (s2, &w2); + + c2 = FcStrCaseWalkerNext (&w2); + + for (;;) { - p = s1; - c1 = *s1++; - if (!c1 || (c1 = FcToLower (c1)) == c2) + cur = w1.src; + c1 = FcStrCaseWalkerNext (&w1); + if (!c1) break; - } + if (c1 == c2) + { + FcCaseWalker w1t = w1; + FcCaseWalker w2t = w2; + FcChar8 c1t, c2t; - if (c1 != c2) - return 0; + for (;;) + { + c1t = FcStrCaseWalkerNext (&w1t); + c2t = FcStrCaseWalkerNext (&w2t); - for (;;) - { - c1 = *s1; - c2 = *s2; - if (c1 && c2 && (c1 = FcToLower (c1)) != (c2 = FcToLower (c2))) - { - s1 = p + 1; - s2 = b; - goto again; + if (!c2t) + return cur; + if (c2t != c1t) + break; + } } - if (!c2) - return p; - if (!c1) - return 0; - ++ s1; - ++ s2; } - return 0; } -- 2.39.5