diff options
Diffstat (limited to 'Build/source/libs/icu-xetex/data/translit')
148 files changed, 7078 insertions, 5812 deletions
diff --git a/Build/source/libs/icu-xetex/data/translit/Any_Accents.txt b/Build/source/libs/icu-xetex/data/translit/Any_Accents.txt index fe26c690476..163307df6d5 100644 --- a/Build/source/libs/icu-xetex/data/translit/Any_Accents.txt +++ b/Build/source/libs/icu-xetex/data/translit/Any_Accents.txt @@ -1,20 +1,15 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Any_Accents.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# :: NFD (NFC) ; - -# to do: make reversible - -# define special conversion characters. -# varients of this could use different characters, or set one or the other to null. - $pre = \< ; $post = \> ; - -# Provide keyboard equivalents for common diacritics used in transliteration - $pre \` $post <> \u0300 ; # COMBINING GRAVE ACCENT $pre \' $post <> \u0301 ; # COMBINING ACUTE ACCENT $pre \^ $post <> \u0302 ; # COMBINING CIRCUMFLEX ACCENT @@ -25,266 +20,34 @@ $pre \* $post <> \u030A ; # COMBINING RING ABOVE $pre \, $post <> \u0327 ; # COMBINING CEDILLA $pre '/' $post <> \u0338 ; # COMBINING LONG SOLIDUS OVERLAY $pre \. $post <> \u0323 ; # COMBINING DOT BELOW - -# Combine common characters - -$pre AE $post <> \u00C6 ; # LATIN CAPITAL LETTER AE -$pre ae $post <> \u00E6 ; # LATIN SMALL LETTER AE -$pre D $post <> \u00D0 ; # LATIN CAPITAL LETTER ETH -$pre d $post <> \u00F0 ; # LATIN SMALL LETTER ETH -$pre O'/' $post <> \u00D8 ; # LATIN CAPITAL LETTER O WITH STROKE -$pre o'/' $post <> \u00F8 ; # LATIN SMALL LETTER O WITH STROKE -$pre TH $post <> \u00DE ; # LATIN CAPITAL LETTER THORN -$pre th $post <> \u00FE ; # LATIN SMALL LETTER THORN -$pre OE $post <> \u0152 ; # LATIN CAPITAL LIGATURE OE -$pre oe $post <> \u0153 ; # LATIN SMALL LIGATURE OE - -$pre ss $post <> \u00DF ; # LATIN SMALL LETTER SHARP S - -$pre NG $post <> \u014A ; # LATIN CAPITAL LETTER ENG -$pre ng $post <> \u014B ; # LATIN SMALL LETTER ENG - -$pre T $post <> \u0398 ; # THETA -$pre t $post <> \u03B8 ; # THETA -$pre SH $post <> \u01A9 ; # LATIN CAPITAL LETTER ESH -$pre sh $post <> \u0283 ; # LATIN SMALL LETTER ESH -$pre ZH $post <> \u01B7 ; # LATIN CAPITAL LETTER EZH -$pre zh $post <> \u0292 ; # LATIN SMALL LETTER EZH - -$pre U $post <> \u01B1 ; # LATIN CAPITAL LETTER UPSILON -$pre u $post <> \u028A ; # LATIN SMALL LETTER UPSILON -$pre A $post <> \u018F ; # LATIN CAPITAL LETTER SCHWA -$pre a $post <> \u0259 ; # LATIN SMALL LETTER SCHWA -$pre O $post <> \u0186 ; # LATIN CAPITAL LETTER OPEN O -$pre o $post <> \u0254 ; # LATIN SMALL LETTER OPEN O -$pre E $post <> \u0190 ; # LATIN CAPITAL LETTER OPEN E -$pre e $post <> \u025B ; # LATIN SMALL LETTER OPEN E - -# three that don't have uppercases - -$pre '?' $post <> \u0294 ; # LATIN LETTER GLOTTAL STOP -$pre i $post <> \u026A ; # LATIN LETTER SMALL CAPITAL I -$pre v $post <> \u028C ; # LATIN SMALL LETTER TURNED V - -# Additional Characters that may be added in the future - -# $pre XXX $post <> \u0306 ; # COMBINING BREVE -# $pre XXX $post <> \u0307 ; # COMBINING DOT ABOVE -# $pre XXX $post <> \u0309 ; # COMBINING HOOK ABOVE -# $pre XXX $post <> \u030B ; # COMBINING DOUBLE ACUTE ACCENT -# $pre XXX $post <> \u030C ; # COMBINING CARON -# $pre XXX $post <> \u030F ; # COMBINING DOUBLE GRAVE ACCENT -# $pre XXX $post <> \u0311 ; # COMBINING INVERTED BREVE -# $pre XXX $post <> \u0313 ; # COMBINING COMMA ABOVE -# $pre XXX $post <> \u0314 ; # COMBINING REVERSED COMMA ABOVE -# $pre XXX $post <> \u031B ; # COMBINING HORN -# $pre XXX $post <> \u0324 ; # COMBINING DIAERESIS BELOW -# $pre XXX $post <> \u0325 ; # COMBINING RING BELOW -# $pre XXX $post <> \u0326 ; # COMBINING COMMA BELOW -# $pre XXX $post <> \u0328 ; # COMBINING OGONEK -# $pre XXX $post <> \u032D ; # COMBINING CIRCUMFLEX ACCENT BELOW -# $pre XXX $post <> \u032E ; # COMBINING BREVE BELOW -# $pre XXX $post <> \u0330 ; # COMBINING TILDE BELOW -# $pre XXX $post <> \u0331 ; # COMBINING MACRON BELOW - -# $pre YYY $post <> \u00AA ; # FEMININE ORDINAL INDICATOR -# $pre YYY $post <> \u00BA ; # MASCULINE ORDINAL INDICATOR -# $pre YYY $post <> \u0110 ; # LATIN CAPITAL LETTER D WITH STROKE -# $pre YYY $post <> \u0111 ; # LATIN SMALL LETTER D WITH STROKE -# $pre YYY $post <> \u0126 ; # LATIN CAPITAL LETTER H WITH STROKE -# $pre YYY $post <> \u0127 ; # LATIN SMALL LETTER H WITH STROKE -# $pre YYY $post <> \u0131 ; # LATIN SMALL LETTER DOTLESS I -# $pre YYY $post <> \u0138 ; # LATIN SMALL LETTER KRA -# $pre YYY $post <> \u013F ; # LATIN CAPITAL LETTER L WITH MIDDLE DOT -# $pre YYY $post <> \u0140 ; # LATIN SMALL LETTER L WITH MIDDLE DOT -# $pre YYY $post <> \u0141 ; # LATIN CAPITAL LETTER L WITH STROKE -# $pre YYY $post <> \u0142 ; # LATIN SMALL LETTER L WITH STROKE -# $pre YYY $post <> \u0149 ; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE -# $pre YYY $post <> \u0166 ; # LATIN CAPITAL LETTER T WITH STROKE -# $pre YYY $post <> \u0167 ; # LATIN SMALL LETTER T WITH STROKE -# $pre YYY $post <> \u017F ; # LATIN SMALL LETTER LONG S -# $pre YYY $post <> \u0180 ; # LATIN SMALL LETTER B WITH STROKE -# $pre YYY $post <> \u0181 ; # LATIN CAPITAL LETTER B WITH HOOK -# $pre YYY $post <> \u0182 ; # LATIN CAPITAL LETTER B WITH TOPBAR -# $pre YYY $post <> \u0183 ; # LATIN SMALL LETTER B WITH TOPBAR -# $pre YYY $post <> \u0184 ; # LATIN CAPITAL LETTER TONE SIX -# $pre YYY $post <> \u0185 ; # LATIN SMALL LETTER TONE SIX -# $pre YYY $post <> \u0187 ; # LATIN CAPITAL LETTER C WITH HOOK -# $pre YYY $post <> \u0188 ; # LATIN SMALL LETTER C WITH HOOK -# $pre YYY $post <> \u0189 ; # LATIN CAPITAL LETTER AFRICAN D -# $pre YYY $post <> \u018A ; # LATIN CAPITAL LETTER D WITH HOOK -# $pre YYY $post <> \u018B ; # LATIN CAPITAL LETTER D WITH TOPBAR -# $pre YYY $post <> \u018C ; # LATIN SMALL LETTER D WITH TOPBAR -# $pre YYY $post <> \u018D ; # LATIN SMALL LETTER TURNED DELTA -# $pre YYY $post <> \u018E ; # LATIN CAPITAL LETTER REVERSED E -# $pre YYY $post <> \u0191 ; # LATIN CAPITAL LETTER F WITH HOOK -# $pre YYY $post <> \u0192 ; # LATIN SMALL LETTER F WITH HOOK -# $pre YYY $post <> \u0193 ; # LATIN CAPITAL LETTER G WITH HOOK -# $pre YYY $post <> \u0194 ; # LATIN CAPITAL LETTER GAMMA -# $pre YYY $post <> \u0195 ; # LATIN SMALL LETTER HV -# $pre YYY $post <> \u0196 ; # LATIN CAPITAL LETTER IOTA -# $pre YYY $post <> \u0197 ; # LATIN CAPITAL LETTER I WITH STROKE -# $pre YYY $post <> \u0198 ; # LATIN CAPITAL LETTER K WITH HOOK -# $pre YYY $post <> \u0199 ; # LATIN SMALL LETTER K WITH HOOK -# $pre YYY $post <> \u019A ; # LATIN SMALL LETTER L WITH BAR -# $pre YYY $post <> \u019B ; # LATIN SMALL LETTER LAMBDA WITH STROKE -# $pre YYY $post <> \u019C ; # LATIN CAPITAL LETTER TURNED M -# $pre YYY $post <> \u019D ; # LATIN CAPITAL LETTER N WITH LEFT HOOK -# $pre YYY $post <> \u019E ; # LATIN SMALL LETTER N WITH LONG RIGHT LEG -# $pre YYY $post <> \u019F ; # LATIN CAPITAL LETTER O WITH MIDDLE TILDE -# $pre YYY $post <> \u01A2 ; # LATIN CAPITAL LETTER OI -# $pre YYY $post <> \u01A3 ; # LATIN SMALL LETTER OI -# $pre YYY $post <> \u01A4 ; # LATIN CAPITAL LETTER P WITH HOOK -# $pre YYY $post <> \u01A5 ; # LATIN SMALL LETTER P WITH HOOK -# $pre YYY $post <> \u01A6 ; # LATIN LETTER YR -# $pre YYY $post <> \u01A7 ; # LATIN CAPITAL LETTER TONE TWO -# $pre YYY $post <> \u01A8 ; # LATIN SMALL LETTER TONE TWO -# $pre YYY $post <> \u01AA ; # LATIN LETTER REVERSED ESH LOOP -# $pre YYY $post <> \u01AB ; # LATIN SMALL LETTER T WITH PALATAL HOOK -# $pre YYY $post <> \u01AC ; # LATIN CAPITAL LETTER T WITH HOOK -# $pre YYY $post <> \u01AD ; # LATIN SMALL LETTER T WITH HOOK -# $pre YYY $post <> \u01AE ; # LATIN CAPITAL LETTER T WITH RETROFLEX HOOK -# $pre YYY $post <> \u01B2 ; # LATIN CAPITAL LETTER V WITH HOOK -# $pre YYY $post <> \u01B3 ; # LATIN CAPITAL LETTER Y WITH HOOK -# $pre YYY $post <> \u01B4 ; # LATIN SMALL LETTER Y WITH HOOK -# $pre YYY $post <> \u01B5 ; # LATIN CAPITAL LETTER Z WITH STROKE -# $pre YYY $post <> \u01B6 ; # LATIN SMALL LETTER Z WITH STROKE -# $pre YYY $post <> \u01B8 ; # LATIN CAPITAL LETTER EZH REVERSED -# $pre YYY $post <> \u01B9 ; # LATIN SMALL LETTER EZH REVERSED -# $pre YYY $post <> \u01BA ; # LATIN SMALL LETTER EZH WITH TAIL -# $pre YYY $post <> \u01BB ; # LATIN LETTER TWO WITH STROKE -# $pre YYY $post <> \u01BC ; # LATIN CAPITAL LETTER TONE FIVE -# $pre YYY $post <> \u01BD ; # LATIN SMALL LETTER TONE FIVE -# $pre YYY $post <> \u01BE ; # LATIN LETTER INVERTED GLOTTAL STOP WITH STROKE -# $pre YYY $post <> \u01BF ; # LATIN LETTER WYNN -# $pre YYY $post <> \u01C0 ; # LATIN LETTER DENTAL CLICK -# $pre YYY $post <> \u01C1 ; # LATIN LETTER LATERAL CLICK -# $pre YYY $post <> \u01C2 ; # LATIN LETTER ALVEOLAR CLICK -# $pre YYY $post <> \u01C3 ; # LATIN LETTER RETROFLEX CLICK -# $pre YYY $post <> \u01C4 ; # LATIN CAPITAL LETTER DZ WITH CARON -# $pre YYY $post <> \u01C5 ; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON -# $pre YYY $post <> \u01C6 ; # LATIN SMALL LETTER DZ WITH CARON -# $pre YYY $post <> \u01C7 ; # LATIN CAPITAL LETTER LJ -# $pre YYY $post <> \u01C8 ; # LATIN CAPITAL LETTER L WITH SMALL LETTER J -# $pre YYY $post <> \u01C9 ; # LATIN SMALL LETTER LJ -# $pre YYY $post <> \u01CA ; # LATIN CAPITAL LETTER NJ -# $pre YYY $post <> \u01CB ; # LATIN CAPITAL LETTER N WITH SMALL LETTER J -# $pre YYY $post <> \u01CC ; # LATIN SMALL LETTER NJ -# $pre YYY $post <> \u01DD ; # LATIN SMALL LETTER TURNED E -# $pre YYY $post <> \u01E4 ; # LATIN CAPITAL LETTER G WITH STROKE -# $pre YYY $post <> \u01E5 ; # LATIN SMALL LETTER G WITH STROKE -# $pre YYY $post <> \u01F1 ; # LATIN CAPITAL LETTER DZ -# $pre YYY $post <> \u01F2 ; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z -# $pre YYY $post <> \u01F3 ; # LATIN SMALL LETTER DZ -# $pre YYY $post <> \u01F6 ; # LATIN CAPITAL LETTER HWAIR -# $pre YYY $post <> \u01F7 ; # LATIN CAPITAL LETTER WYNN -# $pre YYY $post <> \u021C ; # LATIN CAPITAL LETTER YOGH -# $pre YYY $post <> \u021D ; # LATIN SMALL LETTER YOGH -# $pre YYY $post <> \u0222 ; # LATIN CAPITAL LETTER OU -# $pre YYY $post <> \u0223 ; # LATIN SMALL LETTER OU -# $pre YYY $post <> \u0224 ; # LATIN CAPITAL LETTER Z WITH HOOK -# $pre YYY $post <> \u0225 ; # LATIN SMALL LETTER Z WITH HOOK -# $pre YYY $post <> \u0250 ; # LATIN SMALL LETTER TURNED A -# $pre YYY $post <> \u0251 ; # LATIN SMALL LETTER ALPHA -# $pre YYY $post <> \u0252 ; # LATIN SMALL LETTER TURNED ALPHA -# $pre YYY $post <> \u0253 ; # LATIN SMALL LETTER B WITH HOOK -# $pre YYY $post <> \u0255 ; # LATIN SMALL LETTER C WITH CURL -# $pre YYY $post <> \u0256 ; # LATIN SMALL LETTER D WITH TAIL -# $pre YYY $post <> \u0257 ; # LATIN SMALL LETTER D WITH HOOK -# $pre YYY $post <> \u0258 ; # LATIN SMALL LETTER REVERSED E -# $pre YYY $post <> \u025A ; # LATIN SMALL LETTER SCHWA WITH HOOK -# $pre YYY $post <> \u025C ; # LATIN SMALL LETTER REVERSED OPEN E -# $pre YYY $post <> \u025D ; # LATIN SMALL LETTER REVERSED OPEN E WITH HOOK -# $pre YYY $post <> \u025E ; # LATIN SMALL LETTER CLOSED REVERSED OPEN E -# $pre YYY $post <> \u025F ; # LATIN SMALL LETTER DOTLESS J WITH STROKE -# $pre YYY $post <> \u0260 ; # LATIN SMALL LETTER G WITH HOOK -# $pre YYY $post <> \u0261 ; # LATIN SMALL LETTER SCRIPT G -# $pre YYY $post <> \u0262 ; # LATIN LETTER SMALL CAPITAL G -# $pre YYY $post <> \u0263 ; # LATIN SMALL LETTER GAMMA -# $pre YYY $post <> \u0264 ; # LATIN SMALL LETTER RAMS HORN -# $pre YYY $post <> \u0265 ; # LATIN SMALL LETTER TURNED H -# $pre YYY $post <> \u0266 ; # LATIN SMALL LETTER H WITH HOOK -# $pre YYY $post <> \u0267 ; # LATIN SMALL LETTER HENG WITH HOOK -# $pre YYY $post <> \u0268 ; # LATIN SMALL LETTER I WITH STROKE -# $pre YYY $post <> \u0269 ; # LATIN SMALL LETTER IOTA -# $pre YYY $post <> \u026B ; # LATIN SMALL LETTER L WITH MIDDLE TILDE -# $pre YYY $post <> \u026C ; # LATIN SMALL LETTER L WITH BELT -# $pre YYY $post <> \u026D ; # LATIN SMALL LETTER L WITH RETROFLEX HOOK -# $pre YYY $post <> \u026E ; # LATIN SMALL LETTER LEZH -# $pre YYY $post <> \u026F ; # LATIN SMALL LETTER TURNED M -# $pre YYY $post <> \u0270 ; # LATIN SMALL LETTER TURNED M WITH LONG LEG -# $pre YYY $post <> \u0271 ; # LATIN SMALL LETTER M WITH HOOK -# $pre YYY $post <> \u0272 ; # LATIN SMALL LETTER N WITH LEFT HOOK -# $pre YYY $post <> \u0273 ; # LATIN SMALL LETTER N WITH RETROFLEX HOOK -# $pre YYY $post <> \u0274 ; # LATIN LETTER SMALL CAPITAL N -# $pre YYY $post <> \u0275 ; # LATIN SMALL LETTER BARRED O -# $pre YYY $post <> \u0276 ; # LATIN LETTER SMALL CAPITAL OE -# $pre YYY $post <> \u0277 ; # LATIN SMALL LETTER CLOSED OMEGA -# $pre YYY $post <> \u0278 ; # LATIN SMALL LETTER PHI -# $pre YYY $post <> \u0279 ; # LATIN SMALL LETTER TURNED R -# $pre YYY $post <> \u027A ; # LATIN SMALL LETTER TURNED R WITH LONG LEG -# $pre YYY $post <> \u027B ; # LATIN SMALL LETTER TURNED R WITH HOOK -# $pre YYY $post <> \u027C ; # LATIN SMALL LETTER R WITH LONG LEG -# $pre YYY $post <> \u027D ; # LATIN SMALL LETTER R WITH TAIL -# $pre YYY $post <> \u027E ; # LATIN SMALL LETTER R WITH FISHHOOK -# $pre YYY $post <> \u027F ; # LATIN SMALL LETTER REVERSED R WITH FISHHOOK -# $pre YYY $post <> \u0280 ; # LATIN LETTER SMALL CAPITAL R -# $pre YYY $post <> \u0281 ; # LATIN LETTER SMALL CAPITAL INVERTED R -# $pre YYY $post <> \u0282 ; # LATIN SMALL LETTER S WITH HOOK -# $pre YYY $post <> \u0284 ; # LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK -# $pre YYY $post <> \u0285 ; # LATIN SMALL LETTER SQUAT REVERSED ESH -# $pre YYY $post <> \u0286 ; # LATIN SMALL LETTER ESH WITH CURL -# $pre YYY $post <> \u0287 ; # LATIN SMALL LETTER TURNED T -# $pre YYY $post <> \u0288 ; # LATIN SMALL LETTER T WITH RETROFLEX HOOK -# $pre YYY $post <> \u0289 ; # LATIN SMALL LETTER U BAR -# $pre YYY $post <> \u028B ; # LATIN SMALL LETTER V WITH HOOK -# $pre YYY $post <> \u028D ; # LATIN SMALL LETTER TURNED W -# $pre YYY $post <> \u028E ; # LATIN SMALL LETTER TURNED Y -# $pre YYY $post <> \u028F ; # LATIN LETTER SMALL CAPITAL Y -# $pre YYY $post <> \u0290 ; # LATIN SMALL LETTER Z WITH RETROFLEX HOOK -# $pre YYY $post <> \u0291 ; # LATIN SMALL LETTER Z WITH CURL -# $pre YYY $post <> \u0293 ; # LATIN SMALL LETTER EZH WITH CURL -# $pre YYY $post <> \u0294 ; # LATIN LETTER GLOTTAL STOP -# $pre YYY $post <> \u0295 ; # LATIN LETTER PHARYNGEAL VOICED FRICATIVE -# $pre YYY $post <> \u0296 ; # LATIN LETTER INVERTED GLOTTAL STOP -# $pre YYY $post <> \u0297 ; # LATIN LETTER STRETCHED C -# $pre YYY $post <> \u0298 ; # LATIN LETTER BILABIAL CLICK -# $pre YYY $post <> \u0299 ; # LATIN LETTER SMALL CAPITAL B -# $pre YYY $post <> \u029A ; # LATIN SMALL LETTER CLOSED OPEN E -# $pre YYY $post <> \u029B ; # LATIN LETTER SMALL CAPITAL G WITH HOOK -# $pre YYY $post <> \u029C ; # LATIN LETTER SMALL CAPITAL H -# $pre YYY $post <> \u029D ; # LATIN SMALL LETTER J WITH CROSSED-TAIL -# $pre YYY $post <> \u029E ; # LATIN SMALL LETTER TURNED K -# $pre YYY $post <> \u029F ; # LATIN LETTER SMALL CAPITAL L -# $pre YYY $post <> \u02A0 ; # LATIN SMALL LETTER Q WITH HOOK -# $pre YYY $post <> \u02A1 ; # LATIN LETTER GLOTTAL STOP WITH STROKE -# $pre YYY $post <> \u02A2 ; # LATIN LETTER REVERSED GLOTTAL STOP WITH STROKE -# $pre YYY $post <> \u02A3 ; # LATIN SMALL LETTER DZ DIGRAPH -# $pre YYY $post <> \u02A4 ; # LATIN SMALL LETTER DEZH DIGRAPH -# $pre YYY $post <> \u02A5 ; # LATIN SMALL LETTER DZ DIGRAPH WITH CURL -# $pre YYY $post <> \u02A6 ; # LATIN SMALL LETTER TS DIGRAPH -# $pre YYY $post <> \u02A7 ; # LATIN SMALL LETTER TESH DIGRAPH -# $pre YYY $post <> \u02A8 ; # LATIN SMALL LETTER TC DIGRAPH WITH CURL -# $pre YYY $post <> \u02A9 ; # LATIN SMALL LETTER FENG DIGRAPH -# $pre YYY $post <> \u02AA ; # LATIN SMALL LETTER LS DIGRAPH -# $pre YYY $post <> \u02AB ; # LATIN SMALL LETTER LZ DIGRAPH -# $pre YYY $post <> \u02AC ; # LATIN LETTER BILABIAL PERCUSSIVE -# $pre YYY $post <> \u02AD ; # LATIN LETTER BIDENTAL PERCUSSIVE -# $pre YYY $post <> \u02B0 ; # MODIFIER LETTER SMALL H -# $pre YYY $post <> \u02B1 ; # MODIFIER LETTER SMALL H WITH HOOK -# $pre YYY $post <> \u02B2 ; # MODIFIER LETTER SMALL J -# $pre YYY $post <> \u02B3 ; # MODIFIER LETTER SMALL R -# $pre YYY $post <> \u02B4 ; # MODIFIER LETTER SMALL TURNED R -# $pre YYY $post <> \u02B5 ; # MODIFIER LETTER SMALL TURNED R WITH HOOK -# $pre YYY $post <> \u02B6 ; # MODIFIER LETTER SMALL CAPITAL INVERTED R -# $pre YYY $post <> \u02B7 ; # MODIFIER LETTER SMALL W -# $pre YYY $post <> \u02B8 ; # MODIFIER LETTER SMALL Y -# $pre YYY $post <> \u02E0 ; # MODIFIER LETTER SMALL GAMMA -# $pre YYY $post <> \u02E1 ; # MODIFIER LETTER SMALL L -# $pre YYY $post <> \u02E2 ; # MODIFIER LETTER SMALL S -# $pre YYY $post <> \u02E3 ; # MODIFIER LETTER SMALL X -# $pre YYY $post <> \u02E4 ; # MODIFIER LETTER SMALL REVERSED GLOTTAL STOP -# $pre YYY $post <> \u1E9A ; # LATIN SMALL LETTER A WITH RIGHT HALF RING -# $pre YYY $post <> \u207F ; # SUPERSCRIPT LATIN SMALL LETTER N - -:: NFC (NFD) ;
\ No newline at end of file +$pre AE $post <> Æ ; # LATIN CAPITAL LETTER AE +$pre ae $post <> æ ; # LATIN SMALL LETTER AE +$pre D $post <> Ð ; # LATIN CAPITAL LETTER ETH +$pre d $post <> ð ; # LATIN SMALL LETTER ETH +$pre O'/' $post <> Ø ; # LATIN CAPITAL LETTER O WITH STROKE +$pre o'/' $post <> ø ; # LATIN SMALL LETTER O WITH STROKE +$pre TH $post <> Þ ; # LATIN CAPITAL LETTER THORN +$pre th $post <> þ ; # LATIN SMALL LETTER THORN +$pre OE $post <> Œ ; # LATIN CAPITAL LIGATURE OE +$pre oe $post <> œ ; # LATIN SMALL LIGATURE OE +$pre ss $post <> ß ; # LATIN SMALL LETTER SHARP S +$pre NG $post <> Ŋ ; # LATIN CAPITAL LETTER ENG +$pre ng $post <> ŋ ; # LATIN SMALL LETTER ENG +$pre T $post <> Θ ; # THETA +$pre t $post <> θ ; # THETA +$pre SH $post <> Ʃ ; # LATIN CAPITAL LETTER ESH +$pre sh $post <> ʃ ; # LATIN SMALL LETTER ESH +$pre ZH $post <> Ʒ ; # LATIN CAPITAL LETTER EZH +$pre zh $post <> ʒ ; # LATIN SMALL LETTER EZH +$pre U $post <> Ʊ ; # LATIN CAPITAL LETTER UPSILON +$pre u $post <> ʊ ; # LATIN SMALL LETTER UPSILON +$pre A $post <> Ə ; # LATIN CAPITAL LETTER SCHWA +$pre a $post <> ə ; # LATIN SMALL LETTER SCHWA +$pre O $post <> Ɔ ; # LATIN CAPITAL LETTER OPEN O +$pre o $post <> ɔ ; # LATIN SMALL LETTER OPEN O +$pre E $post <> Ɛ ; # LATIN CAPITAL LETTER OPEN E +$pre e $post <> ɛ ; # LATIN SMALL LETTER OPEN E +$pre '?' $post <> ʔ ; # LATIN LETTER GLOTTAL STOP +$pre i $post <> ɪ ; # LATIN LETTER SMALL CAPITAL I +$pre v $post <> ʌ ; # LATIN SMALL LETTER TURNED V +:: NFC (NFD) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Any_Publishing.txt b/Build/source/libs/icu-xetex/data/translit/Any_Publishing.txt index 5e3c36b2144..9f81395ffa2 100644 --- a/Build/source/libs/icu-xetex/data/translit/Any_Publishing.txt +++ b/Build/source/libs/icu-xetex/data/translit/Any_Publishing.txt @@ -1,34 +1,23 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Test case -# "The" "(quick)" ('brown') `fox' ` jumped -- "over?" - -# Variables - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Any_Publishing.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# $single = \' ; $space = ' ' ; $double = \" ; $back = \` ; $tab = '\u0008' ; $makeRight = [[:Z:][:Ps:][:Pi:]$] ; - -# fix UNIX quotes - $back $back > “ ; $back > ‘ ; - -# fix typewriter quotes, by context - $makeRight {$double} <> “ ; $double <> ” ; - $makeRight {$single} <> ‘ ; $single <> ’; - -# fix multiple spaces and hyphens - $space {$space} > ; '--' <> — ; diff --git a/Build/source/libs/icu-xetex/data/translit/Arabic_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Arabic_Latin.txt index 3b8cdcf0cd4..dec58da8f1a 100644 --- a/Build/source/libs/icu-xetex/data/translit/Arabic_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Arabic_Latin.txt @@ -1,146 +1,107 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Generally follows UNGEGN <http://www.eki.ee/wgrs/rom1_ar.pdf> -# Occasionally deviates in the direction of ISO 233 <http://homepage.mac.com/sirbinks/pdf/Arabic.pdf> -# a) where required for disambiguation. -# b) with underdot instead of cedilla for letter like SAD, since -# those are explicitly in Unicode for transliteration. -# c) with extra non-Arabic-language letters, like PEH - -# Does *not* do assimilation of "al", nor hyphenation. -# While it could be done, we need to determine whether a prefix "al" could -# occur other than as the definite article (since no space is used). - -:: [[:Arabic:] [ⁿ\u060C\u061B\u061F\u0640\u064B-\u0655\u0660-\u066C\u06F0-\u06F9\uFDFC]] ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Arabic_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +:: [[:Arabic:] [ⁿ،؛؟ـ\u064B-\u0655٠-٬۰-۹﷼ښ]] ; :: NFKD (NFC); -$disambig = ̱ ; -$disambig2 = ̰ ; -$under = ̣ ; - +$disambig = \u0331 ; +$disambig2 = \u0330 ; +$under = \u0323 ; +$descender = ˌ; $notAbove = [[:^ccc=0:]&[:^ccc=230:]]; - -# non-letters - - ٫ <> '.' $disambig ; # ARABIC DECIMAL SEPARATOR - ٬ <> ',' $disambig ; # ARABIC THOUSANDS SEPARATOR -# ٭ <> ; # ARABIC FIVE POINTED STAR // no need to transliterate - +٫ <> '.' $disambig ; # ARABIC DECIMAL SEPARATOR +٬ <> ',' $disambig ; # ARABIC THOUSANDS SEPARATOR ، <> ',' ; # ARABIC COMMA - ؛ <> ';' ; # ARABIC SEMICOLON - ؟ <> '?' ; # ARABIC QUESTION MARK - ٪ <> '%' ; # ARABIC PERCENT SIGN - - ۰ <> 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO - ۱ <> 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE - ۲ <> 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO - ۳ <> 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE - ۴ <> 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR - ۵ <> 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE - ۶ <> 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX - ۷ <> 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN - ۸ <> 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT - ۹ <> 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE - - ٠ <> 0 ; # ARABIC-INDIC DIGIT ZERO - ١ <> 1 ; # ARABIC-INDIC DIGIT ONE - ٢ <> 2 ; # ARABIC-INDIC DIGIT TWO - ٣ <> 3 ; # ARABIC-INDIC DIGIT THREE - ٤ <> 4 ; # ARABIC-INDIC DIGIT FOUR - ٥ <> 5 ; # ARABIC-INDIC DIGIT FIVE - ٦ <> 6 ; # ARABIC-INDIC DIGIT SIX - ٧ <> 7 ; # ARABIC-INDIC DIGIT SEVEN - ٨ <> 8 ; # ARABIC-INDIC DIGIT EIGHT - ٩ <> 9 ; # ARABIC-INDIC DIGIT NINE - -# letters - -# long vowels - َا<> ā ; # ARABIC FATHA, ARABIC LETTER ALEF - ُو <> ū ; # ARABIC DAMMA, ARABIC LETTER WAW - ِي <> ī ; # ARABIC KASRA, ARABIC LETTER YEH - -# longer items moved here to prevent masking - ث <> t h $disambig ; # ARABIC LETTER THEH - ذ <> d h $disambig ; # ARABIC LETTER THAL - ش <> s h $disambig ; # ARABIC LETTER SHEEN - ص <> s $under ; # ARABIC LETTER SAD - ض <> d $under ; # ARABIC LETTER DAD - ط <> t $under ; # ARABIC LETTER TAH - ظ <> z $under ; # ARABIC LETTER ZAH - غ <> g h $disambig ; # ARABIC LETTER GHAIN - -# WARNING: special case -# <t, umlaut, half-ring below> will be canonically ordered as <t, half-ring below, umlaut> -# so on the return, we have to skip over (but preserve) the half-ring below (or others like it) -# ةٕ < ẗ̹ ; # LATIN SMALL LETTER T, COMBINING RIGHT HALF RING BELOW, COMBINING DIAERESIS - - ة <> t \u0308 ; # ARABIC LETTER TEH MARBUTA - ة | $1 < t ($notAbove+) \u0308 ; # ARABIC LETTER TEH MARBUTA - -# non-Arabic language - ژ <> z h $disambig ; # ARABIC LETTER JEH - ڭ <> n $disambig g ; # ARABIC LETTER NG - ۋ <> v $disambig ; # ARABIC LETTER VE - ی <> y $disambig2 ; # ARABIC LETTER FARSI YEH - -# Arabic language - - ء <> ʾ ; # ARABIC LETTER HAMZA - ا <> a $under; # ARABIC LETTER ALEF - ب <> b ; # ARABIC LETTER BEH - ت <> t ; # ARABIC LETTER TEH - ج <> j ; # ARABIC LETTER JEEM - ح <> h $under ; # ARABIC LETTER HAH - خ <> k h $disambig ; # ARABIC LETTER KHAH - د <> d ; # ARABIC LETTER DAL - ر <> r ; # ARABIC LETTER REH - ز <> z ; # ARABIC LETTER ZAIN - س <> s ; # ARABIC LETTER SEEN - ع <> ʿ ; # ARABIC LETTER AIN - ـ > ; # ARABIC TATWEEL - ف <> f ; # ARABIC LETTER FEH - ق <> q ; # ARABIC LETTER QAF - ك <> k ; # ARABIC LETTER KAF - ل <> l ; # ARABIC LETTER LAM - م <> m ; # ARABIC LETTER MEEM - ن <> n ; # ARABIC LETTER NOON - ه <> h ; # ARABIC LETTER HEH - و <> w ; # ARABIC LETTER WAW - ى <> y $disambig ; # ARABIC LETTER ALEF MAKSURA - ي <> y ; # ARABIC LETTER YEH - ً <> aⁿ ; # ARABIC FATHATAN - ٌ <> uⁿ ; # ARABIC DAMMATAN - ٍ <> iⁿ ; # ARABIC KASRATAN - َ <> a ; # ARABIC FATHA - ُ <> u ; # ARABIC DAMMA - ِ <> i ; # ARABIC KASRA - ّ <> ̃ ; # ARABIC SHADDA - ْ <> ̊ ; # ARABIC SUKUN - -# special combining marks - ٓ <> ̂ ; # ARABIC MADDAH ABOVE - ٔ <> ̉ ; # ARABIC HAMZA ABOVE - ٕ <> ̹ ; # ARABIC HAMZA BELOW - -# Some non-Arabic language (not in UNGEGN) - پ <> p ; # ARABIC LETTER PEH - چ <> c h $disambig ; # ARABIC LETTER TCHEH - ڤ <> v ; # ARABIC LETTER VEH -# ڥ <> v $disambig ; # ARABIC LETTER FEH WITH THREE DOTS BELOW -# ڢ <> f $disambig ; # ARABIC LETTER FEH WITH DOT MOVED BELOW - گ <> g ; # ARABIC LETTER GAF - -# fallbacks +؛ <> ';' ; # ARABIC SEMICOLON +؟ <> '?' ; # ARABIC QUESTION MARK +٪ <> '%' ; # ARABIC PERCENT SIGN +۰ <> 0 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ZERO +۱ <> 1 $disambig ; # EXTENDED ARABIC-INDIC DIGIT ONE +۲ <> 2 $disambig ; # EXTENDED ARABIC-INDIC DIGIT TWO +۳ <> 3 $disambig ; # EXTENDED ARABIC-INDIC DIGIT THREE +۴ <> 4 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FOUR +۵ <> 5 $disambig ; # EXTENDED ARABIC-INDIC DIGIT FIVE +۶ <> 6 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SIX +۷ <> 7 $disambig ; # EXTENDED ARABIC-INDIC DIGIT SEVEN +۸ <> 8 $disambig ; # EXTENDED ARABIC-INDIC DIGIT EIGHT +۹ <> 9 $disambig ; # EXTENDED ARABIC-INDIC DIGIT NINE +٠ <> 0 ; # ARABIC-INDIC DIGIT ZERO +١ <> 1 ; # ARABIC-INDIC DIGIT ONE +٢ <> 2 ; # ARABIC-INDIC DIGIT TWO +٣ <> 3 ; # ARABIC-INDIC DIGIT THREE +٤ <> 4 ; # ARABIC-INDIC DIGIT FOUR +٥ <> 5 ; # ARABIC-INDIC DIGIT FIVE +٦ <> 6 ; # ARABIC-INDIC DIGIT SIX +٧ <> 7 ; # ARABIC-INDIC DIGIT SEVEN +٨ <> 8 ; # ARABIC-INDIC DIGIT EIGHT +٩ <> 9 ; # ARABIC-INDIC DIGIT NINE +\u064Eا<> a\u0304 ; # ARABIC FATHA, ARABIC LETTER ALEF +\u064Fو <> u\u0304 ; # ARABIC DAMMA, ARABIC LETTER WAW +\u0650ي <> i\u0304 ; # ARABIC KASRA, ARABIC LETTER YEH +ث <> t h $disambig ; # ARABIC LETTER THEH +ذ <> d h $disambig ; # ARABIC LETTER THAL +ش <> s h $disambig ; # ARABIC LETTER SHEEN +ص <> s $under ; # ARABIC LETTER SAD +ض <> d $under ; # ARABIC LETTER DAD +ط <> t $under ; # ARABIC LETTER TAH +ظ <> z $under ; # ARABIC LETTER ZAH +غ <> g h $disambig ; # ARABIC LETTER GHAIN +ة <> t \u0308 ; # ARABIC LETTER TEH MARBUTA +ة | $1 < t ($notAbove+) \u0308 ; # ARABIC LETTER TEH MARBUTA +ژ <> z h $disambig ; # ARABIC LETTER JEH +ڭ <> n $disambig g ; # ARABIC LETTER NG +ۋ <> v $disambig ; # ARABIC LETTER VE +ی <> y $disambig2 ; # ARABIC LETTER FARSI YEH +ښ <> s $descender; +ء <> ʾ ; # ARABIC LETTER HAMZA +ا <> a $under; # ARABIC LETTER ALEF +ب <> b ; # ARABIC LETTER BEH +ت <> t ; # ARABIC LETTER TEH +ج <> j ; # ARABIC LETTER JEEM +ح <> h $under ; # ARABIC LETTER HAH +خ <> k h $disambig ; # ARABIC LETTER KHAH +د <> d ; # ARABIC LETTER DAL +ر <> r ; # ARABIC LETTER REH +ز <> z ; # ARABIC LETTER ZAIN +س <> s ; # ARABIC LETTER SEEN +ع <> ʿ ; # ARABIC LETTER AIN +ـ > ; # ARABIC TATWEEL +ف <> f ; # ARABIC LETTER FEH +ق <> q ; # ARABIC LETTER QAF +ك <> k ; # ARABIC LETTER KAF +ل <> l ; # ARABIC LETTER LAM +م <> m ; # ARABIC LETTER MEEM +ن <> n ; # ARABIC LETTER NOON +ه <> h ; # ARABIC LETTER HEH +و <> w ; # ARABIC LETTER WAW +ى <> y $disambig ; # ARABIC LETTER ALEF MAKSURA +ي <> y ; # ARABIC LETTER YEH +\u064B <> aⁿ ; # ARABIC FATHATAN +\u064C <> uⁿ ; # ARABIC DAMMATAN +\u064D <> iⁿ ; # ARABIC KASRATAN +\u064E <> a ; # ARABIC FATHA +\u064F <> u ; # ARABIC DAMMA +\u0650 <> i ; # ARABIC KASRA +\u0651 <> \u0303 ; # ARABIC SHADDA +\u0652 <> \u030A ; # ARABIC SUKUN +\u0653 <> \u0302 ; # ARABIC MADDAH ABOVE +\u0654 <> \u0309 ; # ARABIC HAMZA ABOVE +\u0655 <> \u0339 ; # ARABIC HAMZA BELOW +پ <> p ; # ARABIC LETTER PEH +چ <> c h $disambig ; # ARABIC LETTER TCHEH +ڤ <> v ; # ARABIC LETTER VEH +گ <> g ; # ARABIC LETTER GAF | s < c } [eiy]; | k < c ; | i < e ; | u < o ; | ks < x ; | n < ⁿ; - :: (lower) ; ::NFC (NFD); -:: ( [[:Latin:] [%,.0-9;?\u02BE-\u02BF\u0302-\u0304\u0308-\u030A\u0323\u0330-\u0331\u0339\u037E]] );
\ No newline at end of file +:: ( [[:Latin:] [%,.0-9;?ʾ-ʿ\u0302-\u0304\u0308-\u030A\u0323\u0330-\u0331\u0339;ˌ]] ); diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Devanagari.txt new file mode 100644 index 00000000000..737da17925f --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Gujarati.txt new file mode 100644 index 00000000000..07592838159 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Gurmukhi.txt new file mode 100644 index 00000000000..096fc0b2cfc --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_InterIndic.txt index a1229317709..6409a5e82a3 100644 --- a/Build/source/libs/icu-xetex/data/translit/Bengali_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_InterIndic.txt @@ -1,103 +1,101 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Bengali-InterIndic - -\u09C7\u09BE>\uE04B; # VOWEL SIGN O -\u09C7\u09D7>\uE04C; # VOWEL SIGN AU +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +ো>\uE04B; # VOWEL SIGN O +ৌ>\uE04C; # VOWEL SIGN AU \u0981>\uE001; # SIGN CANDRABINDU -\u0982>\uE002; # SIGN ANUSVARA -\u0983>\uE003; # SIGN VISARGA -\u0985>\uE005; # LETTER A -\u0986>\uE006; # LETTER AA -\u0987>\uE007; # LETTER I -\u0988>\uE008; # LETTER II -\u0989>\uE009; # LETTER U -\u098A>\uE00A; # LETTER UU -\u098B>\uE00B; # LETTER VOCALIC R -\u098C>\uE00C; # LETTER VOCALIC L -\u098F>\uE00F; # LETTER E -\u0990>\uE010; # LETTER AI -\u0993>\uE013; # LETTER O -\u0994>\uE014; # LETTER AU -\u0995>\uE015; # LETTER KA -\u0996>\uE016; # LETTER KHA -\u0997>\uE017; # LETTER GA -\u0998>\uE018; # LETTER GHA -\u0999>\uE019; # LETTER NGA -\u099A>\uE01A; # LETTER CA -\u099B>\uE01B; # LETTER CHA -\u099C>\uE01C; # LETTER JA -\u099D>\uE01D; # LETTER JHA -\u099E>\uE01E; # LETTER NYA -\u099F>\uE01F; # LETTER TTA -\u09A0>\uE020; # LETTER TTHA -\u09A1>\uE021; # LETTER DDA -\u09A2>\uE022; # LETTER DDHA -\u09A3>\uE023; # LETTER NNA -\u09A4>\uE024; # LETTER TA -\u09A5>\uE025; # LETTER THA -\u09A6>\uE026; # LETTER DA -\u09A7>\uE027; # LETTER DHA -\u09A8>\uE028; # LETTER NA -\u09AA>\uE02A; # LETTER PA -\u09AB>\uE02B; # LETTER PHA -\u09AC>\uE02C; # LETTER BA -\u09AD>\uE02D; # LETTER BHA -\u09AE>\uE02E; # LETTER MA -\u09AF>\uE02F; # LETTER YA -\u09B0>\uE030; # LETTER RA -\u09B2>\uE032; # LETTER LA -\u09B6>\uE036; # LETTER SHA -\u09B7>\uE037; # LETTER SSA -\u09B8>\uE038; # LETTER SA -\u09B9>\uE039; # LETTER HA +ং>\uE002; # SIGN ANUSVARA +ঃ>\uE003; # SIGN VISARGA +অ>\uE005; # LETTER A +আ>\uE006; # LETTER AA +ই>\uE007; # LETTER I +ঈ>\uE008; # LETTER II +উ>\uE009; # LETTER U +ঊ>\uE00A; # LETTER UU +ঋ>\uE00B; # LETTER VOCALIC R +ঌ>\uE00C; # LETTER VOCALIC L +এ>\uE00F; # LETTER E +ঐ>\uE010; # LETTER AI +ও>\uE013; # LETTER O +ঔ>\uE014; # LETTER AU +ক>\uE015; # LETTER KA +খ>\uE016; # LETTER KHA +গ>\uE017; # LETTER GA +ঘ>\uE018; # LETTER GHA +ঙ>\uE019; # LETTER NGA +চ>\uE01A; # LETTER CA +ছ>\uE01B; # LETTER CHA +জ>\uE01C; # LETTER JA +ঝ>\uE01D; # LETTER JHA +ঞ>\uE01E; # LETTER NYA +ট>\uE01F; # LETTER TTA +ঠ>\uE020; # LETTER TTHA +ড>\uE021; # LETTER DDA +ঢ>\uE022; # LETTER DDHA +ণ>\uE023; # LETTER NNA +ত>\uE024; # LETTER TA +থ>\uE025; # LETTER THA +দ>\uE026; # LETTER DA +ধ>\uE027; # LETTER DHA +ন>\uE028; # LETTER NA +প>\uE02A; # LETTER PA +ফ>\uE02B; # LETTER PHA +ব>\uE02C; # LETTER BA +ভ>\uE02D; # LETTER BHA +ম>\uE02E; # LETTER MA +য>\uE02F; # LETTER YA +র>\uE030; # LETTER RA +ল>\uE032; # LETTER LA +শ>\uE036; # LETTER SHA +ষ>\uE037; # LETTER SSA +স>\uE038; # LETTER SA +হ>\uE039; # LETTER HA \u09BC>\uE03C; # SIGN NUKTA -\u09BD>\uE03D; # SIGN AVAGRAHA -\u09BE>\uE03E; # VOWEL SIGN AA -\u09BF>\uE03F; # VOWEL SIGN I -\u09C0>\uE040; # VOWEL SIGN II +ঽ>\uE03D; # SIGN AVAGRAHA +া>\uE03E; # VOWEL SIGN AA +ি>\uE03F; # VOWEL SIGN I +ী>\uE040; # VOWEL SIGN II \u09C1>\uE041; # VOWEL SIGN U \u09C2>\uE042; # VOWEL SIGN UU \u09C3>\uE043; # VOWEL SIGN VOCALIC R \u09C4>\uE044; # VOWEL SIGN VOCALIC RR -\u09C7>\uE047; # VOWEL SIGN E -\u09C8>\uE048; # VOWEL SIGN AI -\u09CB>\uE04B; -\u09CC>\uE04C; -# +ে>\uE047; # VOWEL SIGN E +ৈ>\uE048; # VOWEL SIGN AI +ো>\uE04B; +ৌ>\uE04C; \u09CD>\uE04D; # SIGN VIRAMA -\u09ce>\ue083; # Khanda-ta -\u09D7>\uE057; # AU LENGTH MARK -# -\u09E0>\uE060; # LETTER VOCALIC RR -\u09E1>\uE061; # LETTER VOCALIC LL +ৎ>\uE083; # Khanda-ta +ৗ>\uE057; # AU LENGTH MARK +ৠ>\uE060; # LETTER VOCALIC RR +ৡ>\uE061; # LETTER VOCALIC LL \u09E2>\uE062; # VOWEL SIGN VOCALIC L \u09E3>\uE063; # VOWEL SIGN VOCALIC LL -\u09E6>\uE066; # DIGIT ZERO -\u09E7>\uE067; # DIGIT ONE -\u09E8>\uE068; # DIGIT TWO -\u09E9>\uE069; # DIGIT THREE -\u09EA>\uE06A; # DIGIT FOUR -\u09EB>\uE06B; # DIGIT FIVE -\u09EC>\uE06C; # DIGIT SIX -\u09ED>\uE06D; # DIGIT SEVEN -\u09EE>\uE06E; # DIGIT EIGHT -\u09EF>\uE06F; # DIGIT NINE -\u09F0>\ue071; # Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL -\u09F1>\ue072; # Bengali-InterIndic: LETTER RA WITH LOWER DIAGONAL -\u09F2>\ue073; # Bengali-InterIndic: RUPEE MARK -\u09F3>\ue074; # Bengali-InterIndic: RUPEE SIGN -\u09F4>\ue075; # Bengali-InterIndic: CURRENCY NUMERATOR ONE -\u09F5>\ue076; # Bengali-InterIndic: CURRENCY NUMERATOR TWO -\u09F6>\ue077; # Bengali-InterIndic: CURRENCY NUMERATOR THREE -\u09F7>\ue078; # Bengali-InterIndic: CURRENCY NUMERATOR FOUR -\u09F8>\ue079; # Bengali-InterIndic: CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\u09F9>\ue07A; # Bengali-InterIndic: CURRENCY DENOMINATOR SIXTEEN -\u09FA>\ue07B; # ISSHAR -\u0964>\ue064; # DANDA -\u0965>\ue065; # DOUBLE DANDA -# :: NFC (NFD) ; -# eof +০>\uE066; # DIGIT ZERO +১>\uE067; # DIGIT ONE +২>\uE068; # DIGIT TWO +৩>\uE069; # DIGIT THREE +৪>\uE06A; # DIGIT FOUR +৫>\uE06B; # DIGIT FIVE +৬>\uE06C; # DIGIT SIX +৭>\uE06D; # DIGIT SEVEN +৮>\uE06E; # DIGIT EIGHT +৯>\uE06F; # DIGIT NINE +ৰ>\uE071; # Bengali-InterIndic: LETTER RA WITH MIDDLE DIAGONAL +ৱ>\uE072; # Bengali-InterIndic: LETTER RA WITH LOWER DIAGONAL +৲>\uE073; # Bengali-InterIndic: RUPEE MARK +৳>\uE074; # Bengali-InterIndic: RUPEE SIGN +৴>\uE075; # Bengali-InterIndic: CURRENCY NUMERATOR ONE +৵>\uE076; # Bengali-InterIndic: CURRENCY NUMERATOR TWO +৶>\uE077; # Bengali-InterIndic: CURRENCY NUMERATOR THREE +৷>\uE078; # Bengali-InterIndic: CURRENCY NUMERATOR FOUR +৸>\uE079; # Bengali-InterIndic: CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +৹>\uE07A; # Bengali-InterIndic: CURRENCY DENOMINATOR SIXTEEN +৺>\uE07B; # ISSHAR +।>\uE064; # DANDA +॥>\uE065; # DOUBLE DANDA diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Kannada.txt new file mode 100644 index 00000000000..1c8ccacd44d --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Latin.txt new file mode 100644 index 00000000000..f67ef4ae547 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Malayalam.txt new file mode 100644 index 00000000000..6865a2924c6 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Oriya.txt new file mode 100644 index 00000000000..88eb0aac9b1 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Tamil.txt new file mode 100644 index 00000000000..d93a2d91efc --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Bengali_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Bengali_Telugu.txt new file mode 100644 index 00000000000..366f50d9f31 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Bengali_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Bengali_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]; +::NFD; +::Bengali-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/CanadianAboriginal_Latin.txt b/Build/source/libs/icu-xetex/data/translit/CanadianAboriginal_Latin.txt new file mode 100644 index 00000000000..29d8cad311c --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/CanadianAboriginal_Latin.txt @@ -0,0 +1,191 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: CanadianAboriginal_Latin.txt +# Generated from CLDR: Thu Jul 20 14:57:44 PDT 2006 +# +šwê <> ᔗ ; +šwî <> ᔛ ; +šwi <> ᔙ ; +šwô <> ᔟ ; +šwo <> ᔝ ; +šwâ <> ᔣ ; +šwa <> ᔡ ; +pwê <> ᐺ ; +pwî <> ᐾ ; +pwi <> ᐼ ; +pwô <> ᑂ ; +pwo <> ᑀ ; +pwâ <> ᑆ ; +pwa <> ᑄ ; +twê <> ᑗ ; +twî <> ᑛ ; +twi <> ᑙ ; +twô <> ᑟ ; +two <> ᑝ ; +twâ <> ᑣ ; +twa <> ᑡ ; +kwê <> ᑴ ; +kwî <> ᑸ ; +kwi <> ᑶ ; +kwô <> ᑼ ; +kwo <> ᑺ ; +kwâ <> ᒀ ; +kwa <> ᑾ ; +cwê <> ᒒ ; +cwî <> ᒖ ; +cwi <> ᒔ ; +cwô <> ᒚ ; +cwo <> ᒘ ; +cwâ <> ᒞ ; +cwa <> ᒜ ; +mwê <> ᒬ ; +mwî <> ᒰ ; +mwi <> ᒮ ; +mwô <> ᒴ ; +mwo <> ᒲ ; +mwâ <> ᒸ ; +mwa <> ᒶ ; +nwê <> ᓉ ; +nwâ <> ᓍ ; +nwa <> ᓋ ; +lwê <> ᓜ ; +lwî <> ᓠ ; +lwi <> ᓞ ; +lwô <> ᓤ ; +lwo <> ᓢ ; +lwâ <> ᓨ ; +lwa <> ᓦ ; +swê <> ᓶ ; +swî <> ᓺ ; +swi <> ᓸ ; +swô <> ᓾ ; +swo <> ᓼ ; +swâ <> ᔂ ; +swa <> ᔀ ; +ywê <> ᔯ ; +ywî <> ᔳ ; +ywi <> ᔱ ; +ywô <> ᔷ ; +ywo <> ᔵ ; +ywâ <> ᔻ ; +ywa <> ᔹ ; +rwâ <> ᕎ ; +hk <> ᕽ ; +thê <> ᖧ ; +thî <> ᖩ ; +thi <> ᖨ ; +thô <> ᖫ ; +tho <> ᖪ ; +thâ <> ᖭ ; +tha <> ᖬ ; +th <> ᖮ ; +šê <> ᔐ ; +šî <> ᔑ ; +ši <> ᔒ ; +šô <> ᔓ ; +šo <> ᔔ ; +šâ <> ᔕ ; +ša <> ᔖ ; +š <> ᔥ ; +wê <> ᐌ ; +wî <> ᐐ ; +wi <> ᐎ ; +wô <> ᐔ ; +wo <> ᐒ ; +wâ <> ᐙ ; +wa <> ᐗ ; +w <> ᐤ ; +pê <> ᐯ ; +pî <> ᐲ ; +pi <> ᐱ ; +pô <> ᐴ ; +po <> ᐳ ; +pâ <> ᐹ ; +pa <> ᐸ ; +p <> ᑉ ; +tê <> ᑌ ; +tî <> ᑏ ; +ti <> ᑎ ; +tô <> ᑑ ; +to <> ᑐ ; +tâ <> ᑖ ; +ta <> ᑕ ; +t <> ᑦ ; +kê <> ᑫ ; +kî <> ᑮ ; +ki <> ᑭ ; +kô <> ᑰ ; +ko <> ᑯ ; +kâ <> ᑳ ; +ka <> ᑲ ; +kw <> ᒄ ; +k <> ᒃ ; +cê <> ᒉ ; +cî <> ᒌ ; +ci <> ᒋ ; +cô <> ᒎ ; +co <> ᒍ ; +câ <> ᒑ ; +ca <> ᒐ ; +c <> ᒡ ; +mê <> ᒣ ; +mî <> ᒦ ; +mi <> ᒥ ; +mô <> ᒨ ; +mo <> ᒧ ; +mâ <> ᒫ ; +ma <> ᒪ ; +m <> ᒻ ; +nê <> ᓀ ; +nî <> ᓃ ; +ni <> ᓂ ; +nô <> ᓅ ; +no <> ᓄ ; +nâ <> ᓈ ; +na <> ᓇ ; +n <> ᓐ ; +lê <> ᓓ ; +lî <> ᓖ ; +li <> ᓕ ; +lô <> ᓘ ; +lo <> ᓗ ; +lâ <> ᓛ ; +la <> ᓚ ; +l <> ᓪ ; +sê <> ᓭ ; +sî <> ᓰ ; +si <> ᓯ ; +sô <> ᓲ ; +so <> ᓱ ; +sâ <> ᓵ ; +sa <> ᓴ ; +s <> ᔅ ; +yê <> ᔦ ; +yî <> ᔩ ; +yi <> ᔨ ; +yô <> ᔫ ; +yo <> ᔪ ; +yâ <> ᔮ ; +ya <> ᔭ ; +y <> ᔾ ; +rê <> ᕂ ; +rî <> ᕇ ; +ri <> ᕆ ; +rô <> ᕉ ; +ro <> ᕈ ; +râ <> ᕌ ; +ra <> ᕋ ; +r <> ᕐ ; +hê <> ᐁ ; +hî <> ᐄ ; +hi <> ᐃ ; +hô <> ᐆ ; +ho <> ᐅ ; +hâ <> ᐋ ; +ha <> ᐊ ; +h <> ᐦ ; +'.' <> ᙮ ; diff --git a/Build/source/libs/icu-xetex/data/translit/Cyrillic_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Cyrillic_Latin.txt index c50e9d6849e..50ec9973e10 100644 --- a/Build/source/libs/icu-xetex/data/translit/Cyrillic_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Cyrillic_Latin.txt @@ -1,21 +1,16 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# TODO: add remaining characters -# Should add variants for Russian-English, Russian-German -# Those can use this as a base, and then remap cases -# like a $hat to ya or ja. - -# :: [\u0000-\u007E \u02B9 \u02BA [:Cyrillic:] [:Latin:] [:nonspacing mark:]] ; -### WARNING, \u0308 must be added to the generated filters, in both directions ### -# MINIMAL FILTER -:: [\u0308\u0102-\u0103\u0114-\u0115\u011E-\u011F\u012C-\u012D\u014E-\u014F\u016C-\u016D\u0306\u0400-\u045F\u0490-\u0495\u0498-\u0499\u04C1-\u04C2\u04D0-\u04DF\u04E2-\u04E7\u04EC-\u04F5\u04F8-\u04F9\u1E1C-\u1E1D\u1EAE-\u1EB7\u1FB0\u1FB8\u1FD0\u1FD8\u1FE0\u1FE8] ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Cyrillic_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +:: [Ққ\u0308Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ\u0306Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ; :: NFD (NFC) ; - -$modprime = \u02B9; -$modprime2 = \u02BA; - +$modprime = ʹ; +$modprime2 = ʺ; $grave = \u0300; $acute = \u0301; $hat = \u0302; @@ -24,68 +19,45 @@ $dot = \u0307 ; $caron = \u030C ; $comma = \u0326 ; $under = \u0331 ; - -# move up so not masked - +$descender = ˌ; я <> a $hat ; # CYRILLIC SMALL LETTER YA Я <> A $hat ; # CYRILLIC CAPITAL LETTER YA - ч <> c $caron ; # CYRILLIC SMALL LETTER CHE Ч <> C $caron; # CYRILLIC CAPITAL LETTER CHE -# ҷ <> XXX ; # CYRILLIC SMALL LETTER CHE WITH DESCENDER -# Ҷ <> XXX ; # CYRILLIC CAPITAL LETTER CHE WITH DESCENDER -# ӌ <> XXX ; # CYRILLIC SMALL LETTER KHAKASSIAN CHE -# Ӌ <> XXX ; # CYRILLIC CAPITAL LETTER KHAKASSIAN CHE -# ҹ <> XXX ; # CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE -# Ҹ <> XXX ; # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE - э <> e $acute; # CYRILLIC SMALL LETTER E Э <> E $acute; # CYRILLIC CAPITAL LETTER E є <> e $hat; # CYRILLIC SMALL LETTER UKRAINIAN IE Є <> E $hat; # CYRILLIC CAPITAL LETTER UKRAINIAN IE - ш <> s $caron ; # CYRILLIC SMALL LETTER SHA Ш <> S $caron ; # CYRILLIC CAPITAL LETTER SHA щ <> s $hat ; # CYRILLIC SMALL LETTER SHCHA Щ <> S $hat; # CYRILLIC CAPITAL LETTER SHCHA - ѕ <> z $hat ; # CYRILLIC SMALL LETTER DZE Ѕ <> Z $hat; # CYRILLIC CAPITAL LETTER DZE -# ӡ <> XXX ; # CYRILLIC SMALL LETTER ABKHASIAN DZE -# Ӡ <> XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN DZE - ю <> u $hat ; # CYRILLIC SMALL LETTER YU Ю <> U $hat ; # CYRILLIC CAPITAL LETTER YU - і <> i $acute; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I І <> I $acute; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I ј <> j $caron; # CYRILLIC SMALL LETTER JE Ј <> J $caron; # CYRILLIC CAPITAL LETTER JE - љ <> l $hat ; # CYRILLIC SMALL LETTER LJE Љ <> L $hat ; # CYRILLIC CAPITAL LETTER LJE њ <> n $hat ; # CYRILLIC SMALL LETTER NJE Њ <> N $hat ; # CYRILLIC CAPITAL LETTER NJE - ћ <> c $acute ; # CYRILLIC SMALL LETTER TSHE Ћ <> C $acute ; # CYRILLIC CAPITAL LETTER TSHE - џ <> d $hat ; # CYRILLIC SMALL LETTER DZHE Џ <> D $hat ; # CYRILLIC CAPITAL LETTER DZHE - -# Normal order - а <> a ; # CYRILLIC SMALL LETTER A А <> A ; # CYRILLIC CAPITAL LETTER A -ә <> \u0259 ; # CYRILLIC SMALL LETTER SCHWA -Ә <> \u018F ; # CYRILLIC CAPITAL LETTER SCHWA -ӕ <> \u00E6 ; # CYRILLIC SMALL LIGATURE A IE -Ӕ <> \u00C6 ; # CYRILLIC CAPITAL LIGATURE A IE +ә <> ə ; # CYRILLIC SMALL LETTER SCHWA +Ә <> Ə ; # CYRILLIC CAPITAL LETTER SCHWA +ӕ <> æ ; # CYRILLIC SMALL LIGATURE A IE +Ӕ <> Æ ; # CYRILLIC CAPITAL LIGATURE A IE б <> b ; # CYRILLIC SMALL LETTER BE Б <> B ; # CYRILLIC CAPITAL LETTER BE в <> v ; # CYRILLIC SMALL LETTER VE В <> V ; # CYRILLIC CAPITAL LETTER VE - ґ <> g $grave ; # CYRILLIC SMALL LETTER GHE WITH UPTURN Ґ <> G $grave ; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN ғ <> g $dot ; # CYRILLIC SMALL LETTER GHE WITH STROKE @@ -94,7 +66,6 @@ $under = \u0331 ; Ҕ <> G $breve; # CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK г <> g ; # CYRILLIC SMALL LETTER GHE Г <> G ; # CYRILLIC CAPITAL LETTER GHE - д <> d; # CYRILLIC SMALL LETTER DE Д <> D; # CYRILLIC CAPITAL LETTER DE ђ <> đ ; # CYRILLIC SMALL LETTER DJE @@ -103,192 +74,48 @@ $under = \u0331 ; Ҙ <> Z $comma ; # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER е <> e ; # CYRILLIC SMALL LETTER IE Е <> E; # CYRILLIC CAPITAL LETTER IE - ж <> z $caron; # CYRILLIC SMALL LETTER ZHE Ж <> Z $caron; # CYRILLIC CAPITAL LETTER ZHE - -# җ <> XXX ; # CYRILLIC SMALL LETTER ZHE WITH DESCENDER -# Җ <> XXX ; # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER - з <> z ; # CYRILLIC SMALL LETTER ZE З <> Z; # CYRILLIC CAPITAL LETTER ZE - -й <> j ; # CYRILLIC SMALL LETTER I -Й <> J ; # CYRILLIC CAPITAL LETTER I +и\u0306 <> j ; # CYRILLIC SMALL LETTER I +И\u0306 <> J ; # CYRILLIC CAPITAL LETTER I и <> i ; # CYRILLIC SMALL LETTER I И <> I ; # CYRILLIC CAPITAL LETTER I - +қ <> k $descender ; # CYRILLIC SMALL LETTER KA WITH DESCENDER +Қ <> K $descender ; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER к <> k ; # CYRILLIC SMALL LETTER KA К <> K; # CYRILLIC CAPITAL LETTER KA - -# қ <> XXX ; # CYRILLIC SMALL LETTER KA WITH DESCENDER -# Қ <> XXX ; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER -# ӄ <> XXX ; # CYRILLIC SMALL LETTER KA WITH HOOK -# Ӄ <> XXX ; # CYRILLIC CAPITAL LETTER KA WITH HOOK -# ҡ <> XXX ; # CYRILLIC SMALL LETTER BASHKIR KA -# Ҡ <> XXX ; # CYRILLIC CAPITAL LETTER BASHKIR KA -# ҟ <> XXX ; # CYRILLIC SMALL LETTER KA WITH STROKE -# Ҟ <> XXX ; # CYRILLIC CAPITAL LETTER KA WITH STROKE -# ҝ <> XXX ; # CYRILLIC SMALL LETTER KA WITH VERTICAL STROKE -# Ҝ <> XXX ; # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE л <> l ; # CYRILLIC SMALL LETTER EL Л <> L; # CYRILLIC CAPITAL LETTER EL - м <> m ; # CYRILLIC SMALL LETTER EM М <> M ; # CYRILLIC CAPITAL LETTER EM н <> n ; # CYRILLIC SMALL LETTER EN Н <> N; # CYRILLIC CAPITAL LETTER EN -# ң <> XXX ; # CYRILLIC SMALL LETTER EN WITH DESCENDER -# Ң <> XXX ; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER -# ӈ <> XXX ; # CYRILLIC SMALL LETTER EN WITH HOOK -# Ӈ <> XXX ; # CYRILLIC CAPITAL LETTER EN WITH HOOK -# ҥ <> XXX ; # CYRILLIC SMALL LIGATURE EN GHE -# Ҥ <> XXX ; # CYRILLIC CAPITAL LIGATURE EN GHE - о <> o ; # CYRILLIC SMALL LETTER O О <> O ; # CYRILLIC CAPITAL LETTER O -# ө <> XXX ; # CYRILLIC SMALL LETTER BARRED O -# Ө <> XXX ; # CYRILLIC CAPITAL LETTER BARRED O п <> p ; # CYRILLIC SMALL LETTER PE П <> P ; # CYRILLIC CAPITAL LETTER PE -# ҧ <> XXX ; # CYRILLIC SMALL LETTER PE WITH MIDDLE HOOK -# Ҧ <> XXX ; # CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK -# ҁ <> XXX ; # CYRILLIC SMALL LETTER KOPPA -# Ҁ <> XXX ; # CYRILLIC CAPITAL LETTER KOPPA р <> r ; # CYRILLIC SMALL LETTER ER Р <> R ; # CYRILLIC CAPITAL LETTER ER -# ҏ <> XXX ; # CYRILLIC SMALL LETTER ER WITH TICK -# Ҏ <> XXX ; # CYRILLIC CAPITAL LETTER ER WITH TICK с <> s ; # CYRILLIC SMALL LETTER ES С <> S ; # CYRILLIC CAPITAL LETTER ES -# ҫ <> XXX ; # CYRILLIC SMALL LETTER ES WITH DESCENDER -# Ҫ <> XXX ; # CYRILLIC CAPITAL LETTER ES WITH DESCENDER т <> t ; # CYRILLIC SMALL LETTER TE Т <> T ; # CYRILLIC CAPITAL LETTER TE -# ҭ <> XXX ; # CYRILLIC SMALL LETTER TE WITH DESCENDER -# Ҭ <> XXX ; # CYRILLIC CAPITAL LETTER TE WITH DESCENDER - у <> u ; # CYRILLIC SMALL LETTER U У <> U ; # CYRILLIC CAPITAL LETTER U -# ү <> XXX ; # CYRILLIC SMALL LETTER STRAIGHT U -# Ү <> XXX ; # CYRILLIC CAPITAL LETTER STRAIGHT U -# ұ <> XXX ; # CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE -# Ұ <> XXX ; # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE -# ѹ <> XXX ; # CYRILLIC SMALL LETTER UK -# Ѹ <> XXX ; # CYRILLIC CAPITAL LETTER UK ф <> f ; # CYRILLIC SMALL LETTER EF Ф <> F ; # CYRILLIC CAPITAL LETTER EF х <> h ; # CYRILLIC SMALL LETTER HA Х <> H; # CYRILLIC CAPITAL LETTER HA -# ҳ <> XXX ; # CYRILLIC SMALL LETTER HA WITH DESCENDER -# Ҳ <> XXX ; # CYRILLIC CAPITAL LETTER HA WITH DESCENDER -# һ <> XXX ; # CYRILLIC SMALL LETTER SHHA -# Һ <> XXX ; # CYRILLIC CAPITAL LETTER SHHA -# ѡ <> XXX ; # CYRILLIC SMALL LETTER OMEGA -# Ѡ <> XXX ; # CYRILLIC CAPITAL LETTER OMEGA -# ѿ <> XXX ; # CYRILLIC SMALL LETTER OT -# Ѿ <> XXX ; # CYRILLIC CAPITAL LETTER OT -# ѽ <> XXX ; # CYRILLIC SMALL LETTER OMEGA WITH TITLO -# Ѽ <> XXX ; # CYRILLIC CAPITAL LETTER OMEGA WITH TITLO -# ѻ <> XXX ; # CYRILLIC SMALL LETTER ROUND OMEGA -# Ѻ <> XXX ; # CYRILLIC CAPITAL LETTER ROUND OMEGA ц <> c ; # CYRILLIC SMALL LETTER TSE Ц <> C; # CYRILLIC CAPITAL LETTER TSE -# ҵ <> XXX ; # CYRILLIC SMALL LIGATURE TE TSE -# Ҵ <> XXX ; # CYRILLIC CAPITAL LIGATURE TE TSE - -# ҽ <> XXX ; # CYRILLIC SMALL LETTER ABKHASIAN CHE -# Ҽ <> XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE -# ҿ <> XXX ; # CYRILLIC SMALL LETTER ABKHASIAN CHE WITH DESCENDER -# Ҿ <> XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER - - Ъ <> $modprime2 $under ; # CYRILLIC CAPITAL LETTER HARD SIGN ъ <> $modprime2 ; # CYRILLIC SMALL LETTER HARD SIGN Ь <> $modprime $under ; # CYRILLIC CAPITAL LETTER SOFT SIGN ь <> $modprime ; # CYRILLIC SMALL LETTER SOFT SIGN - ы <> y ; # CYRILLIC SMALL LETTER YERU Ы <> Y ; # CYRILLIC CAPITAL LETTER YERU - -# ҍ <> XXX ; # CYRILLIC SMALL LETTER SEMISOFT SIGN -# Ҍ <> XXX ; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN -# ѣ <> XXX ; # CYRILLIC SMALL LETTER YAT -# Ѣ <> XXX ; # CYRILLIC CAPITAL LETTER YAT - -# ѥ <> XXX ; # CYRILLIC SMALL LETTER IOTIFIED E -# Ѥ <> XXX ; # CYRILLIC CAPITAL LETTER IOTIFIED E -# ѧ <> XXX ; # CYRILLIC SMALL LETTER LITTLE YUS -# Ѧ <> XXX ; # CYRILLIC CAPITAL LETTER LITTLE YUS -# ѫ <> XXX ; # CYRILLIC SMALL LETTER BIG YUS -# Ѫ <> XXX ; # CYRILLIC CAPITAL LETTER BIG YUS -# ѩ <> XXX ; # CYRILLIC SMALL LETTER IOTIFIED LITTLE YUS -# Ѩ <> XXX ; # CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS -# ѭ <> XXX ; # CYRILLIC SMALL LETTER IOTIFIED BIG YUS -# Ѭ <> XXX ; # CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS -# ѯ <> XXX ; # CYRILLIC SMALL LETTER KSI -# Ѯ <> XXX ; # CYRILLIC CAPITAL LETTER KSI -# ѱ <> XXX ; # CYRILLIC SMALL LETTER PSI -# Ѱ <> XXX ; # CYRILLIC CAPITAL LETTER PSI -# ѳ <> XXX ; # CYRILLIC SMALL LETTER FITA -# Ѳ <> XXX ; # CYRILLIC CAPITAL LETTER FITA -# ѵ <> XXX ; # CYRILLIC SMALL LETTER IZHITSA -# Ѵ <> XXX ; # CYRILLIC CAPITAL LETTER IZHITSA -# ҩ <> XXX ; # CYRILLIC SMALL LETTER ABKHASIAN HA -# Ҩ <> XXX ; # CYRILLIC CAPITAL LETTER ABKHASIAN HA -# Ӏ <> XXX ; # CYRILLIC LETTER PALOCHKA -### ӑ <> XXX ; # CYRILLIC SMALL LETTER A -### Ӑ <> XXX ; # CYRILLIC CAPITAL LETTER A -### ӓ <> XXX ; # CYRILLIC SMALL LETTER A -### Ӓ <> XXX ; # CYRILLIC CAPITAL LETTER A -### ӛ <> XXX ; # CYRILLIC SMALL LETTER SCHWA -### Ӛ <> XXX ; # CYRILLIC CAPITAL LETTER SCHWA -### ѓ <> XXX ; # CYRILLIC SMALL LETTER GHE -### Ѓ <> XXX ; # CYRILLIC CAPITAL LETTER GHE -### ѐ <> XXX ; # CYRILLIC SMALL LETTER IE -### Ѐ <> XXX ; # CYRILLIC CAPITAL LETTER IE -### ё <> XXX ; # CYRILLIC SMALL LETTER IE -### Ё <> XXX ; # CYRILLIC CAPITAL LETTER IE -### ӗ <> XXX ; # CYRILLIC SMALL LETTER IE -### Ӗ <> XXX ; # CYRILLIC CAPITAL LETTER IE -### ӂ <> XXX ; # CYRILLIC SMALL LETTER ZHE -### Ӂ <> XXX ; # CYRILLIC CAPITAL LETTER ZHE -### ӝ <> XXX ; # CYRILLIC SMALL LETTER ZHE -### Ӝ <> XXX ; # CYRILLIC CAPITAL LETTER ZHE -### ӟ <> XXX ; # CYRILLIC SMALL LETTER ZE -### Ӟ <> XXX ; # CYRILLIC CAPITAL LETTER ZE -### ѝ <> XXX ; # CYRILLIC SMALL LETTER I -### Ѝ <> XXX ; # CYRILLIC CAPITAL LETTER I -### ӣ <> XXX ; # CYRILLIC SMALL LETTER I -### Ӣ <> XXX ; # CYRILLIC CAPITAL LETTER I -### ӥ <> XXX ; # CYRILLIC SMALL LETTER I -### Ӥ <> XXX ; # CYRILLIC CAPITAL LETTER I -### ї <> XXX ; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I -### Ї <> XXX ; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I -### ӧ <> XXX ; # CYRILLIC SMALL LETTER O -### Ӧ <> XXX ; # CYRILLIC CAPITAL LETTER O -### ӫ <> XXX ; # CYRILLIC SMALL LETTER BARRED O -### Ӫ <> XXX ; # CYRILLIC CAPITAL LETTER BARRED O -### ќ <> XXX ; # CYRILLIC SMALL LETTER KA -### Ќ <> XXX ; # CYRILLIC CAPITAL LETTER KA -### ӯ <> XXX ; # CYRILLIC SMALL LETTER U -### Ӯ <> XXX ; # CYRILLIC CAPITAL LETTER U -### ў <> XXX ; # CYRILLIC SMALL LETTER U -### Ў <> XXX ; # CYRILLIC CAPITAL LETTER U -### ӱ <> XXX ; # CYRILLIC SMALL LETTER U -### Ӱ <> XXX ; # CYRILLIC CAPITAL LETTER U -### ӳ <> XXX ; # CYRILLIC SMALL LETTER U -### Ӳ <> XXX ; # CYRILLIC CAPITAL LETTER U -### ӵ <> XXX ; # CYRILLIC SMALL LETTER CHE -### Ӵ <> XXX ; # CYRILLIC CAPITAL LETTER CHE -### ӹ <> XXX ; # CYRILLIC SMALL LETTER YERU -### Ӹ <> XXX ; # CYRILLIC CAPITAL LETTER YERU -### ӭ <> XXX ; # CYRILLIC SMALL LETTER E -### Ӭ <> XXX ; # CYRILLIC CAPITAL LETTER E -### ѷ <> XXX ; # CYRILLIC SMALL LETTER IZHITSA -### Ѷ <> XXX ; # CYRILLIC CAPITAL LETTER IZHITSA - -# Completeness $ignore = [[:Mark:]''] * ; | k < q ; | K < Q ; @@ -298,9 +125,5 @@ $ignore = [[:Mark:]''] * ; | KS < [:UppercaseLetter:] $ignore { X ; | Ks < X ; | ks < x ; - :: NFC (NFD) ; -# note: a global filter is more efficient, but MUST include all source chars!! -# :: ([\u0000-\u007E \u02B9 \u02BA [:Cyrillic:] [:Latin:] [:nonspacing mark:]]); -# MINIMAL FILTER: Latin-Cyrillic -:: ( [\u0308A-Za-z\u00C0-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u018F\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0259\u02B9-\u02BA\u0300-\u0302\u0306-\u0307\u030C\u0326\u0331\u0340-\u0341\u0344\u0374\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0400\u0403\u040C-\u040E\u0419\u0439\u0450\u0453\u045C-\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u1E00-\u1E99\u1E9B\u1EA0-\u1EF9\u1F02-\u1F05\u1F0A-\u1F0D\u1F12-\u1F15\u1F1A-\u1F1D\u1F22-\u1F25\u1F2A-\u1F2D\u1F32-\u1F35\u1F3A-\u1F3D\u1F42-\u1F45\u1F4A-\u1F4D\u1F52-\u1F55\u1F5B\u1F5D\u1F62-\u1F65\u1F6A-\u1F6D\u1F70-\u1F7D\u1F82-\u1F85\u1F8A-\u1F8D\u1F92-\u1F95\u1F9A-\u1F9D\u1FA2-\u1FA5\u1FAA-\u1FAD\u1FB0\u1FB2\u1FB4\u1FB8\u1FBA-\u1FBB\u1FC2\u1FC4\u1FC8-\u1FCB\u1FCD-\u1FCE\u1FD0\u1FD2-\u1FD3\u1FD8\u1FDA-\u1FDB\u1FDD-\u1FDE\u1FE0\u1FE2-\u1FE3\u1FE8\u1FEA-\u1FEB\u1FED-\u1FEE\u1FF2\u1FF4\u1FF8-\u1FFB\u212A-\u212B] ) ; +:: ( [ˌ\u0308A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ\u0300-\u0302\u0306-\u0307\u030C\u0326\u0331\u0340-\u0341\u0344ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Bengali.txt new file mode 100644 index 00000000000..cd7151eb110 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Gujarati.txt new file mode 100644 index 00000000000..1eca062537a --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:12 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Gurmukhi.txt new file mode 100644 index 00000000000..beaf87ae4c9 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_InterIndic.txt index 7ff97208984..cd0ecb3c7ee 100644 --- a/Build/source/libs/icu-xetex/data/translit/Devanagari_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_InterIndic.txt @@ -1,119 +1,115 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Devanagari-InterIndic -# :: NFD; -#Rules for Decomposed characters - - - \u0901>\uE001; # SIGN CANDRABINDU - \u0902>\uE002; # SIGN ANUSVARA - \u0903>\uE003; # SIGN VISARGA - \u0904>\uE004; # SIGN SHORT A - \u0905>\uE005; # LETTER A - \u0906>\uE006; # LETTER AA - \u0907>\uE007; # LETTER I - \u0908>\uE008; # LETTER II - \u0909>\uE009; # LETTER U - \u090A>\uE00A; # LETTER UU - \u090B>\uE00B; # LETTER VOCALIC R - \u090C>\uE00C; # LETTER VOCALIC L - \u090D>\uE00D; # LETTER CANDRA E (For representing English sounds) - \u090E>\uE00E; # UNMAPPED LETTER SHORT E(For Southern Scripts) - \u090F>\uE00F; # LETTER E - \u0910>\uE010; # LETTER AI - \u0911>\uE011; # LETTER CANDRA O (For representing English sounds) - \u0912>\uE012; # UNMAPPED LETTER SHORT O (For Southern Scripts) - \u0913>\uE013; # LETTER O - \u0914>\uE014; # LETTER AU - \u0915>\uE015; # LETTER KA - \u0916>\uE016; # LETTER KHA - \u0917>\uE017; # LETTER GA - \u0918>\uE018; # LETTER GHA - \u0919>\uE019; # LETTER NGA - \u091A>\uE01A; # LETTER CA - \u091B>\uE01B; # LETTER CHA - \u091C>\uE01C; # LETTER JA - \u091D>\uE01D; # LETTER JHA - \u091E>\uE01E; # LETTER NYA - \u091F>\uE01F; # LETTER TTA - \u0920>\uE020; # LETTER TTHA - \u0921>\uE021; # LETTER DDA - \u0922>\uE022; # LETTER DDHA - \u0923>\uE023; # LETTER NNA - \u0924>\uE024; # LETTER TA - \u0925>\uE025; # LETTER THA - \u0926>\uE026; # LETTER DA - \u0927>\uE027; # LETTER DHA - \u0928>\uE028; # LETTER NA - \u0929>\uE029; - \u092A>\uE02A; # LETTER PA - \u092B>\uE02B; # LETTER PHA - \u092C>\uE02C; # LETTER BA - \u092D>\uE02D; # LETTER BHA - \u092E>\uE02E; # LETTER MA - \u092F>\uE02F; # LETTER YA - \u0930>\uE030; # LETTER RA - \u0931>\uE031; - \u0932>\uE032; # LETTER LA - \u0933>\uE033; # LETTER LLA - \u0934>\uE034; - - \u0935>\uE035; # LETTER VA - \u0936>\uE036; # LETTER SHA - \u0937>\uE037; # LETTER SSA - \u0938>\uE038; # LETTER SA - \u0939>\uE039; # LETTER HA - \u093C>\uE03C; # SIGN NUKTA - \u093D>\uE03D; # SIGN AVAGRAHA - \u093E>\uE03E; # VOWEL SIGN AA - \u093F>\uE03F; # VOWEL SIGN I - \u0940>\uE040; # VOWEL SIGN II - \u0941>\uE041; # VOWEL SIGN U - \u0942>\uE042; # VOWEL SIGN UU - \u0943>\uE043; # VOWEL SIGN VOCALIC R - \u0944>\uE044; # VOWEL SIGN VOCALIC RR - \u0945>\uE045; # VOWEL SIGN CANDRA E - \u0946>\uE046; # UNMAPPED VOWEL SIGN SHORT E - \u0947>\uE047; # VOWEL SIGN E - \u0948>\uE048; # VOWEL SIGN AI - \u0949>\uE049; # VOWEL SIGN CANDRA O - \u094A>\uE04A; # UNMAPPED VOWEL SIGN SHORT O - \u094B>\uE04B; # VOWEL SIGN O - \u094C>\uE04C; # VOWEL SIGN AU - \u094D>\uE04D; # SIGN VIRAMA - \u0950>\uE050; # OM - \u0951>\uE051; # UNMAPPED STRESS SIGN UDATTA - \u0952>\uE052; # UNMAPPED STRESS SIGN ANUDATTA - \u0953>\uE053; # UNMAPPED GRAVE ACCENT - \u0954>\uE054; # UNMAPPED ACUTE ACCENT - \u0958>\uE058; - \u0959>\uE059; - \u095A>\uE05a; - \u095B>\uE05b; - \u095C>\uE05c; - \u095D>\uE05d; - \u095E>\uE05e; - \u095F>\uE05f; - \u0960>\uE060; # LETTER VOCALIC RR - \u0961>\uE061; # LETTER VOCALIC LL - \u0962>\uE062; # VOWEL SIGN VOCALIC L - \u0963>\uE063; # VOWEL SIGN VOCALIC LL - \u0964>\ue064; # DANDA - \u0965>\ue065; # DOUBLE DANDA - \u0966>\uE066; # DIGIT ZERO - \u0967>\uE067; # DIGIT ONE - \u0968>\uE068; # DIGIT TWO - \u0969>\uE069; # DIGIT THREE - \u096A>\uE06A; # DIGIT FOUR - \u096B>\uE06B; # DIGIT FIVE - \u096C>\uE06C; # DIGIT SIX - \u096D>\uE06D; # DIGIT SEVEN - \u096E>\uE06E; # DIGIT EIGHT - \u096F>\uE06F; # DIGIT NINE - \u0970>\uE070; # Devanagari-InterIndic: ABBREVIATION SIGN - \u097d>\uE082; # Devanagari Glottal Stop - -# :: NFC (NFD) ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +\u0901>\uE001; # SIGN CANDRABINDU +\u0902>\uE002; # SIGN ANUSVARA +ः>\uE003; # SIGN VISARGA +ऄ>\uE004; # SIGN SHORT A +अ>\uE005; # LETTER A +आ>\uE006; # LETTER AA +इ>\uE007; # LETTER I +ई>\uE008; # LETTER II +उ>\uE009; # LETTER U +ऊ>\uE00A; # LETTER UU +ऋ>\uE00B; # LETTER VOCALIC R +ऌ>\uE00C; # LETTER VOCALIC L +ऍ>\uE00D; # LETTER CANDRA E (For representing English sounds) +ऎ>\uE00E; # UNMAPPED LETTER SHORT E(For Southern Scripts) +ए>\uE00F; # LETTER E +ऐ>\uE010; # LETTER AI +ऑ>\uE011; # LETTER CANDRA O (For representing English sounds) +ऒ>\uE012; # UNMAPPED LETTER SHORT O (For Southern Scripts) +ओ>\uE013; # LETTER O +औ>\uE014; # LETTER AU +क>\uE015; # LETTER KA +ख>\uE016; # LETTER KHA +ग>\uE017; # LETTER GA +घ>\uE018; # LETTER GHA +ङ>\uE019; # LETTER NGA +च>\uE01A; # LETTER CA +छ>\uE01B; # LETTER CHA +ज>\uE01C; # LETTER JA +झ>\uE01D; # LETTER JHA +ञ>\uE01E; # LETTER NYA +ट>\uE01F; # LETTER TTA +ठ>\uE020; # LETTER TTHA +ड>\uE021; # LETTER DDA +ढ>\uE022; # LETTER DDHA +ण>\uE023; # LETTER NNA +त>\uE024; # LETTER TA +थ>\uE025; # LETTER THA +द>\uE026; # LETTER DA +ध>\uE027; # LETTER DHA +न>\uE028; # LETTER NA +ऩ>\uE029; +प>\uE02A; # LETTER PA +फ>\uE02B; # LETTER PHA +ब>\uE02C; # LETTER BA +भ>\uE02D; # LETTER BHA +म>\uE02E; # LETTER MA +य>\uE02F; # LETTER YA +र>\uE030; # LETTER RA +ऱ>\uE031; +ल>\uE032; # LETTER LA +ळ>\uE033; # LETTER LLA +ऴ>\uE034; +व>\uE035; # LETTER VA +श>\uE036; # LETTER SHA +ष>\uE037; # LETTER SSA +स>\uE038; # LETTER SA +ह>\uE039; # LETTER HA +\u093C>\uE03C; # SIGN NUKTA +ऽ>\uE03D; # SIGN AVAGRAHA +ा>\uE03E; # VOWEL SIGN AA +ि>\uE03F; # VOWEL SIGN I +ी>\uE040; # VOWEL SIGN II +\u0941>\uE041; # VOWEL SIGN U +\u0942>\uE042; # VOWEL SIGN UU +\u0943>\uE043; # VOWEL SIGN VOCALIC R +\u0944>\uE044; # VOWEL SIGN VOCALIC RR +\u0945>\uE045; # VOWEL SIGN CANDRA E +\u0946>\uE046; # UNMAPPED VOWEL SIGN SHORT E +\u0947>\uE047; # VOWEL SIGN E +\u0948>\uE048; # VOWEL SIGN AI +ॉ>\uE049; # VOWEL SIGN CANDRA O +ॊ>\uE04A; # UNMAPPED VOWEL SIGN SHORT O +ो>\uE04B; # VOWEL SIGN O +ौ>\uE04C; # VOWEL SIGN AU +\u094D>\uE04D; # SIGN VIRAMA +ॐ>\uE050; # OM +\u0951>\uE051; # UNMAPPED STRESS SIGN UDATTA +\u0952>\uE052; # UNMAPPED STRESS SIGN ANUDATTA +\u0953>\uE053; # UNMAPPED GRAVE ACCENT +\u0954>\uE054; # UNMAPPED ACUTE ACCENT +क़>\uE058; +ख़>\uE059; +ग़>\uE05A; +ज़>\uE05B; +ड़>\uE05C; +ढ़>\uE05D; +फ़>\uE05E; +य़>\uE05F; +ॠ>\uE060; # LETTER VOCALIC RR +ॡ>\uE061; # LETTER VOCALIC LL +\u0962>\uE062; # VOWEL SIGN VOCALIC L +\u0963>\uE063; # VOWEL SIGN VOCALIC LL +।>\uE064; # DANDA +॥>\uE065; # DOUBLE DANDA +०>\uE066; # DIGIT ZERO +१>\uE067; # DIGIT ONE +२>\uE068; # DIGIT TWO +३>\uE069; # DIGIT THREE +४>\uE06A; # DIGIT FOUR +५>\uE06B; # DIGIT FIVE +६>\uE06C; # DIGIT SIX +७>\uE06D; # DIGIT SEVEN +८>\uE06E; # DIGIT EIGHT +९>\uE06F; # DIGIT NINE +॰>\uE070; # Devanagari-InterIndic: ABBREVIATION SIGN +ॽ>\uE082; # Devanagari Glottal Stop diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Kannada.txt new file mode 100644 index 00000000000..ca5f280a1e3 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Latin.txt new file mode 100644 index 00000000000..025eed116c1 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Malayalam.txt new file mode 100644 index 00000000000..ba35dbf5495 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Oriya.txt new file mode 100644 index 00000000000..325a05c17ef --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Tamil.txt new file mode 100644 index 00000000000..89203c0e6e7 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Devanagari_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Devanagari_Telugu.txt new file mode 100644 index 00000000000..2f1c686e424 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Devanagari_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Devanagari_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[\u0901-ःऄअ-ह\u093C-\u094Dॐ-\u0954क़-९ॽ]; +::NFD; +::Devanagari-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Fullwidth_Halfwidth.txt b/Build/source/libs/icu-xetex/data/translit/Fullwidth_Halfwidth.txt index e09a13e1fd9..1716a60e557 100644 --- a/Build/source/libs/icu-xetex/data/translit/Fullwidth_Halfwidth.txt +++ b/Build/source/libs/icu-xetex/data/translit/Fullwidth_Halfwidth.txt @@ -1,16 +1,12 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Fullwidth-Halfwidth - -# Mechanically generated from Unicode Character Database -# IDEOGRAPHIC SPACE then added, and -# FULLWIDTH MACRON changed to map to MACRON, not SPACE + COMBINING MACRON - -# multicharacter - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Fullwidth_Halfwidth.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# ガ<>ガ; # to KATAKANA LETTER GA ギ<>ギ; # to KATAKANA LETTER GI グ<>グ; # to KATAKANA LETTER GU @@ -39,9 +35,6 @@ ヴ<>ヴ; # to KATAKANA LETTER VU ヷ<>ヷ; # to KATAKANA LETTER VA ヺ<>ヺ; # to KATAKANA LETTER VO - -# single character - !<>'!'; # from FULLWIDTH EXCLAMATION MARK "<>'\"'; # from FULLWIDTH QUOTATION MARK #<>'#'; # from FULLWIDTH NUMBER SIGN @@ -197,9 +190,9 @@ ロ<>ロ; # to HALFWIDTH KATAKANA LETTER RO ワ<>ワ; # to HALFWIDTH KATAKANA LETTER WA ン<>ン; # to HALFWIDTH KATAKANA LETTER N -゙<>゙; # to HALFWIDTH KATAKANA VOICED SOUND MARK -゚<>゚; # to HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK -ᅠ<>ᅠ; # to HALFWIDTH HANGUL FILLER +\u3099<>゙; # to HALFWIDTH KATAKANA VOICED SOUND MARK +\u309A<>゚; # to HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK +\u1160<>\uFFA0; # to HALFWIDTH HANGUL FILLER ᄀ<>ᄀ; # to HALFWIDTH HANGUL LETTER KIYEOK ᄁ<>ᄁ; # to HALFWIDTH HANGUL LETTER SSANGKIYEOK ᆪ<>ᆪ; # to HALFWIDTH HANGUL LETTER KIYEOK-SIOS @@ -255,17 +248,14 @@ £<>'£'; # from FULLWIDTH POUND SIGN ¬<>'¬'; # from FULLWIDTH NOT SIGN  ̄<>'¯'; # from FULLWIDTH MACRON -' '<>' '; # ideographic space (place this after MACRON) +'\u3000'<>' '; # ideographic space (place this after MACRON) ¦<>'¦'; # from FULLWIDTH BROKEN BAR ¥<>'¥'; # from FULLWIDTH YEN SIGN ₩<>₩; # from FULLWIDTH WON SIGN │<>│; # to HALFWIDTH FORMS LIGHT VERTICAL -'←'<>'←'; # to HALFWIDTH LEFTWARDS ARROW +'<'<>'←'; # to HALFWIDTH LEFTWARDS ARROW ↑<>↑; # to HALFWIDTH UPWARDS ARROW -'→'<>'→'; # to HALFWIDTH RIGHTWARDS ARROW +'>'<>'→'; # to HALFWIDTH RIGHTWARDS ARROW ↓<>↓; # to HALFWIDTH DOWNWARDS ARROW ■<>■; # to HALFWIDTH BLACK SQUARE ○<>○; # to HALFWIDTH WHITE CIRCLE - -# eof - diff --git a/Build/source/libs/icu-xetex/data/translit/Georgian_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Georgian_Latin.txt new file mode 100644 index 00000000000..f493396814f --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Georgian_Latin.txt @@ -0,0 +1,44 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Georgian_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +წ <> tsʼ ; +კ <> kʼ ; +პ <> pʼ ; +ჟ <> zh ; +ტ <> tʼ ; +ღ <> gh ; +ყ <> qʼ ; +შ <> sh ; +ჭ <> chʼ ; +ჩ <> ch ; +ც <> ts ; +ძ <> dz ; +ხ <> kh ; +ჳ <> ŭi ; +ა <> a ; +ბ <> b ; +გ <> g ; +დ <> d ; +ე <> e ; +ვ <> v ; +ზ <> z ; +თ <> t ; +ი <> i ; +ლ <> l ; +მ <> m ; +ნ <> n ; +ო <> o ; +რ <> r ; +ს <> s ; +უ <> u ; +ფ <> p ; +ქ <> k ; +ჯ <> j ; +ჰ <> h ; +ჴ <> q ; diff --git a/Build/source/libs/icu-xetex/data/translit/Greek_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Greek_Latin.txt index 221e5d084e6..d7f0083232e 100644 --- a/Build/source/libs/icu-xetex/data/translit/Greek_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Greek_Latin.txt @@ -1,296 +1,172 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Rules are predicated on running NFD first, and NFC afterwards -# :: [\u0000-\u007F \u0370-\u03FF [:Greek:] [:nonspacing mark:]] ; -# MINIMAL FILTER GENERATED FOR: Greek-Latin -:: [;\u00B5\u00B7\u00C4\u00CB\u00CF\u00D6\u00DC\u00E4\u00EB\u00EF\u00F6\u00FC\u00FF-\u0101\u0112-\u0113\u012A-\u012B\u014C-\u014D\u016A-\u016B\u0178\u01D5-\u01DC\u01DE-\u01E3\u01EC-\u01ED\u022A-\u022D\u0230-\u0233\u0304\u0308\u0313-\u0314\u0342-\u0345\u037A\u037E\u0386-\u038A\u038C\u038E-\u03A1\u03A3-\u03CE\u03D0-\u03D7\u03DB\u03DD\u03DF\u03E1\u03E3\u03E5\u03E7\u03E9\u03EB\u03ED\u03EF-\u03F5\u03F7-\u07FB\u0401\u0407\u0451\u0457\u04D2-\u04D3\u04DA-\u04DF\u04E2-\u04E7\u04EA-\u04F1\u04F4-\u04F5\u04F8-\u04F9\u1E14-\u1E17\u1E20-\u1E21\u1E26-\u1E27\u1E2E-\u1E2F\u1E38-\u1E39\u1E4E-\u1E53\u1E5C-\u1E5D\u1E7A-\u1E7B\u1E84-\u1E85\u1E8C-\u1E8D\u1E97\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC1-\u1FC4\u1FC6-\u1FCC\u1FCF-\u1FD3\u1FD6-\u1FDB\u1FDF-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2126\u03F9] ; - -:: NFD (NFC) ; - -# TEST CASES - -# Ὀλίγοι ἔμφονες πολλῶν ἀφρόνων φοβερώτεροι — Πλάτωνος -# ᾂ ᾒ ᾢ ᾃ ᾓ ᾣ -# ᾳ ῃ ῳ ὃ ὄ -# ὠς ὡς ὢς ὣς -# Ὠς Ὡς Ὢς Ὣς -# ὨΣ ὩΣ ὪΣ ὫΣ -# Ạ, ạ, Ẹ, ẹ, Ọ, ọ - -# Useful variables - -$lower = [[:latin:][:greek:] & [:Ll:]]; -$glower = [[:greek:] & [:Ll:]]; -$upper = [[:latin:][:greek:] & [:Lu:]] ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Greek_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +:: [;µ·ÄËÏÖÜäëïöüÿ-āĒ-ēĪ-īŌ-ōŪ-ūŸǕ-ǜǞ-ǣǬ-ǭȪ-ȭȰ-ȳ\u0304\u0308\u0313-\u0314\u0342-\u0345ͺ;Ά-ΊΌΎ-ΡΣ-ώϐ-ϗϛϝϟϡϣϥϧϩϫϭϯ-ϵϷ-\u07FBЁЇёїӒ-ӓӚ-ӟӢ-ӧӪ-ӱӴ-ӵӸ-ӹḔ-ḗḠ-ḡḦ-ḧḮ-ḯḸ-ḹṎ-ṓṜ-ṝṺ-ṻẄ-ẅẌ-ẍẗἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼι῁-ῄῆ-ῌ῏-ΐῖ-Ί῟-Ῥῲ-ῴῶ-ῼΩϹ] ; +:: NFD (NFC) ; +$lower = [[:latin:][:greek:] & [:Ll:]]; +$glower = [[:greek:] & [:Ll:]]; +$upper = [[:latin:][:greek:] & [:Lu:]] ; $accent = [:M:] ; - -# NOTE: restrict to just the Greek & Latin accents that we care about -# TODO: broaden out once interation is fixed $accentMinus = [ [\u0300-\u0345] & [:M:] - [\u0338]] ; - $macron = \u0304 ; $ddot = \u0308 ; $ddotmac = [$ddot$macron]; - -$lcgvowel = [αεηιουω] ; -$ucgvowel = [ΑΕΗΙΟΥΩ] ; -$gvowel = [$lcgvowel $ucgvowel] ; -$lcgvowelC = [$lcgvowel $accent] ; - +$lcgvowel = [αεηιουω] ; +$ucgvowel = [ΑΕΗΙΟΥΩ] ; +$gvowel = [$lcgvowel $ucgvowel] ; +$lcgvowelC = [$lcgvowel $accent] ; $evowel = [aeiouyAEIOUY]; $evowel2 = [iuyIUY]; -$vowel = [ $evowel $gvowel] ; - -$gammaLike = [ΓΚΞΧγκξχϰ] ; -$egammaLike = [GKXCgkxc] ; -$smooth = ̓ ; -$rough = ̔ ; -$iotasub = ͅ ; - +$vowel = [ $evowel $gvowel] ; +$gammaLike = [ΓΚΞΧγκξχϰ] ; +$egammaLike = [GKXCgkxc] ; +$smooth = \u0313 ; +$rough = \u0314 ; +$iotasub = \u0345 ; $evowel_i = [$evowel-[iI]] ; $evowel2_i = [uyUY]; - $underbar = \u0331; - $afterLetter = [:L:] [[:M:]\']* ; $beforeLetter = [[:M:]\']* [:L:] ; -$beforeLower = $accent * $lower ; - +$beforeLower = $accent * $lower ; $notLetter = [^[:L:][:M:]] ; -$under = ̱; - -# Fix punctuation -# preserve original +$under = \u0331; \: <> \: $under ; \? <> \? $under ; - \; <> \? ; · <> \: ; - -# CIRCUMFLEX: convert greek circumflex to normal one. Could use tilde or inverted breve - -\u0342 <> \u0302 ; - -# IOTA: convert iota subscript to iota -# first make previous alpha long! - +\u0342 <> \u0302 ; $accent_minus = [[$accent]-[$iotasub$macron]]; - -Α } $accent_minus * $iotasub > | Α $macron ; -α } $accent_minus * $iotasub > | α $macron ; - -# now convert to uppercase if after uppercase, ow to lowercase - -$upper $accent * { $iotasub > I ; -$iotasub > i ; - +Α } $accent_minus * $iotasub > | Α $macron ; +α } $accent_minus * $iotasub > | α $macron ; +$upper $accent * { $iotasub > I ; +$iotasub > i ; | $1 $iotasub < ($evowel $macron $accentMinus *) i ; | $1 $iotasub < ($evowel $macron $accentMinus *) I ; - -# BREATHING - -# Convert rough breathing to h, and move before letters. - -# Make A ` x = > H a x - - Α ($macron?) $rough } $beforeLower > H | α $1; - Ε $rough } $beforeLower > H | ε; - Η $rough } $beforeLower > H | η ; - Ι ($ddot?) $rough } $beforeLower > H | ι $1; - Ο $rough } $beforeLower > H | ο ; - Υ $rough } $beforeLower > H | υ ; - Ω ($ddot?) $rough } $beforeLower > H | ω $1; - -# Make A x ` = > H a x - -Α ($glower $macron?) $rough > H | α $1 ; -Ε ($glower) $rough > H | ε $1 ; -Η ($glower) $rough > H | η $1 ; -Ι ($glower $ddot?) $rough > H | ι $1 ; -Ο ($glower) $rough > H | ο $1 ; -Υ ($glower) $rough > H | υ $1 ; -Ω ($glower $ddot?) $rough > H | ω $1 ; - -#Otherwise, make x ` into h x and X ` into H X - -($lcgvowel + $ddotmac? ) $rough > h | $1 ; -($gvowel + $ddotmac? ) $rough > H | $1 ; - -# Go backwards with H - +Α ($macron?) $rough } $beforeLower > H | α $1; +Ε $rough } $beforeLower > H | ε; +Η $rough } $beforeLower > H | η ; +Ι ($ddot?) $rough } $beforeLower > H | ι $1; +Ο $rough } $beforeLower > H | ο ; +Υ $rough } $beforeLower > H | υ ; +Ω ($ddot?) $rough } $beforeLower > H | ω $1; +Α ($glower $macron?) $rough > H | α $1 ; +Ε ($glower) $rough > H | ε $1 ; +Η ($glower) $rough > H | η $1 ; +Ι ($glower $ddot?) $rough > H | ι $1 ; +Ο ($glower) $rough > H | ο $1 ; +Υ ($glower) $rough > H | υ $1 ; +Ω ($glower $ddot?) $rough > H | ω $1 ; +($lcgvowel + $ddotmac? ) $rough > h | $1 ; +($gvowel + $ddotmac? ) $rough > H | $1 ; | $1 $rough < h ($evowel $macron $ddot? $evowel2_i $macron?) ; | $1 $rough < h ($evowel $ddot? $evowel2 $macron?) ; | $1 $rough < h ($evowel $macron? $ddot?) ; - | $1 $rough < H ([AEIOUY] $macron $ddot? $evowel2_i $macron?) ; | $1 $rough < H ([AEIOUY] $ddot? $evowel2 $macron?) ; | $1 $rough < H ([AEIOUY] $macron? $ddot?) ; - -# titlecase, have to fix individually -# in the future, we should add &uppercase() to make this easier - | A $1 $rough < H a ($macron $ddot? $evowel2_i $macron?) ; | E $1 $rough < H e ($macron $ddot? $evowel2_i $macron?) ; | I $1 $rough < H i ($macron $ddot? $evowel2_i $macron?) ; | O $1 $rough < H o ($macron $ddot? $evowel2_i $macron?) ; | U $1 $rough < H u ($macron $ddot? $evowel2_i $macron?) ; | Y $1 $rough < H y ($macron $ddot? $evowel2_i $macron?) ; - | A $1 $rough < H a ($ddot? $evowel2 $macron?) ; | E $1 $rough < H e ($ddot? $evowel2 $macron?) ; | I $1 $rough < H i ($ddot? $evowel2 $macron?) ; | O $1 $rough < H o ($ddot? $evowel2 $macron?) ; | U $1 $rough < H u ($ddot? $evowel2 $macron?) ; | Y $1 $rough < H y ($ddot? $evowel2 $macron?) ; - | A $1 $rough < H a ($macron? $ddot? ) ; | E $1 $rough < H e ($macron? $ddot? ) ; | I $1 $rough < H i ($macron? $ddot? ) ; | O $1 $rough < H o ($macron? $ddot? ) ; | U $1 $rough < H u ($macron? $ddot? ) ; | Y $1 $rough < H y ($macron? $ddot? ) ; - -# Now do smooth - -#delete smooth breathing for Latin -$smooth > ; - -# insert in Greek -# the assumption is that all Marks are on letters. - - | $1 $smooth < $notLetter { ([rR]) } [^hH$smooth$rough] ; - | $1 $smooth < $notLetter { ($evowel $macron? $evowel2 $macron?) } [^$smooth$rough] ; - | $1 $smooth < $notLetter { ($evowel $macron?) } [^$evowel2$smooth$rough] ; - -# TODO: preserve smooth/rough breathing if not -# on initial vowel sequence - -# need to have these up here so the rules don't mask - -# remove now superfluous macron when returning - -Α < A $macron ; -α < a $macron ; - +$smooth > ; +| $1 $smooth < $notLetter { ([rR]) } [^hH$smooth$rough] ; +| $1 $smooth < $notLetter { ($evowel $macron? $evowel2 $macron?) } [^$smooth$rough] ; +| $1 $smooth < $notLetter { ($evowel $macron?) } [^$evowel2$smooth$rough] ; +Α < A $macron ; +α < a $macron ; η <> e $macron ; Η <> E $macron ; - -φ <> ph ; -Ψ } $beforeLower <> Ps ; -Ψ <> PS ; - -Φ } $beforeLower <> Ph ; +φ <> ph ; +Ψ } $beforeLower <> Ps ; +Ψ <> PS ; +Φ } $beforeLower <> Ph ; Φ <> PH ; -ψ <> ps ; - +ψ <> ps ; ω <> o $macron ; Ω <> O $macron; - -# NORMAL - -α <> a ; -Α <> A ; - -β <> b ; -Β <> B ; - -γ } $gammaLike <> n } $egammaLike ; -γ <> g ; -Γ } $gammaLike <> N } $egammaLike ; -Γ <> G ; - -δ <> d ; -Δ <> D ; - -ε <> e ; -Ε <> E ; - -ζ <> z ; -Ζ <> Z ; - -θ <> th ; -Θ } $beforeLower <> Th ; -Θ <> TH ; - -ι <> i ; -Ι <> I ; - +α <> a ; +Α <> A ; +β <> b ; +Β <> B ; +γ } $gammaLike <> n } $egammaLike ; +γ <> g ; +Γ } $gammaLike <> N } $egammaLike ; +Γ <> G ; +δ <> d ; +Δ <> D ; +ε <> e ; +Ε <> E ; +ζ <> z ; +Ζ <> Z ; +θ <> th ; +Θ } $beforeLower <> Th ; +Θ <> TH ; +ι <> i ; +Ι <> I ; κ <> k ; -Κ <> K ; - -λ <> l ; -Λ <> L ; - -μ <> m ; -Μ <> M ; - -ν } $gammaLike > n\' ; -ν <> n ; -Ν } $gammaLike <> N\' ; -Ν <> N ; - -ξ <> x ; -Ξ <> X ; - -ο <> o ; -Ο <> O ; - -π <> p ; -Π <> P ; - -ρ $rough <> rh; -Ρ $rough } $beforeLower <> Rh ; -Ρ $rough <> RH ; -ρ <> r ; -Ρ <> R ; - -# insert separator before things that turn into s - -[Pp] { } [ςσΣϷϸϺϻ] > \' ; - -# special S variants - -Ϸ <> Š ; # Ϸ GREEK CAPITAL LETTER SHO Uppercase_Letter Grek - L -ϸ <> š ; #ϸ GREEK SMALL LETTER SHO Lowercase_Letter Grek - L -Ϻ <> Ŝ ; # Ϻ GREEK CAPITAL LETTER SAN Uppercase_Letter Grek - L -ϻ <> ŝ ; # ϻ GREEK SMALL LETTER SAN Lowercase_Letter Grek - L - -# underbar means exception - -# before a letter, initial +Κ <> K ; +λ <> l ; +Λ <> L ; +μ <> m ; +Μ <> M ; +ν } $gammaLike > n\' ; +ν <> n ; +Ν } $gammaLike <> N\' ; +Ν <> N ; +ξ <> x ; +Ξ <> X ; +ο <> o ; +Ο <> O ; +π <> p ; +Π <> P ; +ρ $rough <> rh; +Ρ $rough } $beforeLower <> Rh ; +Ρ $rough <> RH ; +ρ <> r ; +Ρ <> R ; +[Pp] { } [ςσΣϷϸϺϻ] > \' ; +Ϸ <> S\u030C ; # Ϸ GREEK CAPITAL LETTER SHO Uppercase_Letter Grek - L +ϸ <> s\u030C ; #ϸ GREEK SMALL LETTER SHO Lowercase_Letter Grek - L +Ϻ <> S\u0302 ; # Ϻ GREEK CAPITAL LETTER SAN Uppercase_Letter Grek - L +ϻ <> s\u0302 ; # ϻ GREEK SMALL LETTER SAN Lowercase_Letter Grek - L ς } $beforeLetter <> s $underbar } $beforeLetter; σ } $beforeLetter <> s } $beforeLetter; - -# otherwise, after a letter = final $afterLetter { σ <> $afterLetter { s $underbar; $afterLetter { ς <> $afterLetter { s ; - -# otherwise (isolated) = initial ς <> s $underbar; σ <> s ; - -# [Pp] { Σ <> \'S ; -Σ <> S ; - -τ <> t ; -Τ <> T ; - -$vowel {υ } <> u ; -υ <> y ; -$vowel { Υ <> U ; -Υ <> Y ; - -χ <> ch ; -Χ } $beforeLower <> Ch ; -Χ <> CH ; - -# Completeness for ASCII - +Σ <> S ; +τ <> t ; +Τ <> T ; +$vowel {υ } <> u ; +υ <> y ; +$vowel { Υ <> U ; +Υ <> Y ; +χ <> ch ; +Χ } $beforeLower <> Ch ; +Χ <> CH ; $ignore = [[:Mark:]''] * ; - | k < c ; | ph < f ; | i < j ; @@ -307,20 +183,15 @@ $ignore = [[:Mark:]''] * ; | B < W } $vowel ; | U < V ; | U < W ; - $rough } $ignore [:UppercaseLetter:] > H ; $ignore [:UppercaseLetter:] { $rough > H ; $rough < H ; $rough <> h ; - -# Completeness for Greek - ϐ > | β ; ϑ > | θ ; ϒ > | Υ ; ϕ > | φ ; ϖ > | π ; - ϰ > | κ ; ϱ > | ρ ; ϲ > | σ ; @@ -328,18 +199,9 @@ $rough <> h ; ϳ > j ; ϴ > | Θ ; ϵ > | ε ; - µ > | μ ; - - ͺ > i; - -# delete any trailing ' marks used for roundtripping - - < [Ππ] { \' } [Ss] ; - < [Νν] { \' } $egammaLike ; - +ͺ > i; +< [Ππ] { \' } [Ss] ; +< [Νν] { \' } $egammaLike ; ::NFC (NFD) ; -# ([\u0000-\u007F [:Latin:] [:Greek:] [:nonspacing mark:]]) ; -# ([\u0000-\u007F \u00B7 [:Latin:] [:nonspacing mark:]]) ; -# MINIMAL FILTER GENERATED FOR: Latin-Greek BACKWARD -:: ( [':?A-Za-z\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0300-\u0337\u0339-\u0345\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AA-\u03B0\u03CA-\u03CE\u03D3-\u03D4\u0400-\u0401\u0403\u0407\u040C-\u040E\u0419\u0439\u0450-\u0451\u0453\u0457\u045C-\u045E\u0476-\u0477\u04C1-\u04C2\u04D0-\u04D3\u04D6-\u04D7\u04DA-\u04DF\u04E2-\u04E7\u04EA-\u04F5\u04F8-\u04F9\u1E00-\u1E99\u1E9B\u1EA0-\u1EF9\u1F00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FC1-\u1FC4\u1FC6-\u1FD3\u1FD6-\u1FDB\u1FDD-\u1FEE\u1FF2-\u1FF4\u1FF6-\u1FFC\u212A-\u212B] ) ; +:: ( [':?A-Za-zÀ-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳ\u0300-\u0337\u0339-\u0345΅-ΆΈ-ΊΌΎ-ΐΪ-ΰϊ-ώϓ-ϔЀ-ЁЃЇЌ-ЎЙйѐ-ёѓїќ-ўѶ-ѷӁ-ӂӐ-ӓӖ-ӗӚ-ӟӢ-ӧӪ-ӵӸ-ӹḀ-ẙẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼ῁-ῄῆ-ΐῖ-Ί῝-΅ῲ-ῴῶ-ῼK-Å] ) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Greek_Latin_UNGEGN.txt b/Build/source/libs/icu-xetex/data/translit/Greek_Latin_UNGEGN.txt index f14bc236cef..b56efb4505a 100644 --- a/Build/source/libs/icu-xetex/data/translit/Greek_Latin_UNGEGN.txt +++ b/Build/source/libs/icu-xetex/data/translit/Greek_Latin_UNGEGN.txt @@ -1,211 +1,131 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- -# For modern Greek, based on UNGEGN rules. - -# Rules are predicated on running NFD first, and NFC afterwards -# MINIMAL FILTER GENERATED FOR: Greek-Latin/UNGEGN -# WARNING: need to add accents to both filters ### -# :: [́̄̆̈;µ·ÀÂÈÊÌÎÒÔÙÛàâèêìîòôùûĈ-ĉĜ-ĝĤ-ĥĴ-ĵŜ-ŝŴ-ŷǛ-ǜǸ-ǹ̀̂̓-̔̀͂-̓ͅͺ;Ά-ΊΌΎ-ΡΣ-ώϐ-ϖϰ-ϵЀЍѐѝḔ-ḕṐ-ṑẀ-ẁẐ-ẑẤ-ậẰ-ằẾ-ệỐ-ộỜ-ờỪ-ừỲ-ỳἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼι῁-ῄῆ-῍῏-ΐῖ-Ί῝῟-῭ῲ-ῴῶ-ῼΩ\u03F7-\u07FB\u03F9] ; - -:: [[[:Greek:][:Mn:][:Me:]] [\:-;?\u00B7\u037E\u0387]] ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Greek_Latin_UNGEGN.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +:: [[[:Greek:][:Mn:][:Me:]] [\:-;?·;·]] ; ::NFD (NFC) ; - -# Useful variables - $lower = [[:latin:][:greek:] & [:Ll:]] ; $upper = [[:latin:][:greek:] & [:Lu:]] ; $accent = [[:Mn:][:Me:]] ; - -$macron = ̄ ; -$ddot = ̈ ; - +$macron = \u0304 ; +$ddot = \u0308 ; $lcgvowel = [αεηιουω] ; $ucgvowel = [ΑΕΗΙΟΥΩ] ; $gvowel = [$lcgvowel $ucgvowel] ; $lcgvowelC = [$lcgvowel $accent] ; - $evowel = [aeiouyAEIOUY]; $vowel = [ $evowel $gvowel] ; - $beforeLower = $accent * $lower ; - $gammaLike = [ΓΚΞΧγκξχϰ] ; $egammaLike = [GKXCgkxc] ; -$smooth = ̓ ; -$rough = ̔ ; -$iotasub = ͅ ; - +$smooth = \u0313 ; +$rough = \u0314 ; +$iotasub = \u0345 ; $softener = [βΒγΓδΔζΖλΛμΜνΝρΡ$gvowel] ; - -$under = ̱; - -$caron = ̌; - +$under = \u0331; +$caron = \u030C; $afterLetter = [:L:] [\'$accent]* ; $beforeLetter = [\'$accent]* [:L:] ; - -# Fix punctuation - -# preserve orginal \: <> \: $under ; \? <> \? $under ; - \; <> \? ; · <> \: ; - -# Fix any ancient characters that creep in - -͂ > ́ ; -̂ > ́ ; -̀ > ́ ; +\u0342 > \u0301 ; +\u0302 > \u0301 ; +\u0300 > \u0301 ; $smooth > ; $rough > ; $iotasub > ; ͺ > ; - -# need to have these up here so the rules don't mask - η <> i $under ; Η <> I $under ; - Ψ } $beforeLower <> Ps ; Ψ <> PS ; ψ <> ps ; - ω <> o $under ; Ω <> O $under; - -# at begining or end of word, convert mp to b - [^[:L:]$accent] { μπ > b ; μπ } [^[:L:]$accent] > b ; [^[:L:]$accent] { [Μμ][Ππ] > B ; [Μμ][Ππ] } [^[:L:]$accent] > B ; - μπ < b ; Μπ < B } $beforeLower ; ΜΠ < B ; - -# handle diphthongs ending with upsilon - ου <> ou ; ΟΥ <> OU ; Ου <> Ou ; οΥ <> oU ; - $fmaker = [aeiAEI] $under ? ; $shiftForwardVowels = [[:Mn:]-[\u0308]]; # note: a diaeresis keeps the items separate - $fmaker { υ ( $shiftForwardVowels )* } $softener > $1 v $under ; υ $1 < ( $shiftForwardVowels )* v $under ; - $fmaker { υ ( $shiftForwardVowels )* } > $1 f $under; υ $1 < ( $shiftForwardVowels )* f $under ; - $fmaker { Υ } $softener <> V $under ; $fmaker { Υ <> U $under ; - υ <> y ; Υ <> Y ; - -# NORMAL - α <> a ; Α <> A ; - β <> v ; Β <> V ; - γ } $gammaLike <> n } $egammaLike ; γ <> g ; Γ } $gammaLike <> N } $egammaLike ; Γ <> G ; - δ <> d ; Δ <> D ; - ε <> e ; Ε <> E ; - ζ <> z ; Ζ <> Z ; - θ <> th ; Θ } $beforeLower <> Th ; Θ <> TH ; - ι <> i ; Ι <> I ; - κ <> k ; Κ <> K ; - λ <> l ; Λ <> L ; - μ <> m ; Μ <> M ; - ν } $gammaLike > n\' ; ν <> n ; Ν } $gammaLike <> N\' ; Ν <> N ; - ξ <> x ; Ξ <> X ; - ο <> o ; Ο <> O ; - π <> p ; Π <> P ; - ρ <> r ; Ρ <> R ; - -# insert separator before things that turn into s -[Pp] { } [ςσΣϷϸϺϻ] > \' ; - -# special S variants - -Ϸ <> Š ; # Ϸ GREEK CAPITAL LETTER SHO Uppercase_Letter Grek - L -ϸ <> š ; #ϸ GREEK SMALL LETTER SHO Lowercase_Letter Grek - L -Ϻ <> Ŝ ; # Ϻ GREEK CAPITAL LETTER SAN Uppercase_Letter Grek - L -ϻ <> ŝ ; # ϻ GREEK SMALL LETTER SAN Lowercase_Letter Grek - L - -# Caron means exception - -# before a letter, initial +[Pp] { } [ςσΣϷϸϺϻ] > \' ; +Ϸ <> S\u030C ; # Ϸ GREEK CAPITAL LETTER SHO Uppercase_Letter Grek - L +ϸ <> s\u030C ; #ϸ GREEK SMALL LETTER SHO Lowercase_Letter Grek - L +Ϻ <> S\u0302 ; # Ϻ GREEK CAPITAL LETTER SAN Uppercase_Letter Grek - L +ϻ <> s\u0302 ; # ϻ GREEK SMALL LETTER SAN Lowercase_Letter Grek - L ς } $beforeLetter <> s $under } $beforeLetter; σ } $beforeLetter <> s } $beforeLetter; - -# otherwise, after a letter = final $afterLetter { σ <> $afterLetter { s $under; $afterLetter { ς <> $afterLetter { s ; - -# otherwise (isolated) = initial ς <> s $under; σ <> s ; - -# [Pp] { Σ <> \'S ; Σ <> S ; - τ <> t ; Τ <> T ; - φ <> f ; Φ <> F ; - χ <> ch ; Χ } $beforeLower <> Ch ; Χ <> CH ; - -# Completeness for ASCII - -# $ignore = [[:Mark:]''] * ; - | ch < h ; | k < c ; | i < j ; @@ -214,7 +134,6 @@ $afterLetter { ς <> $afterLetter { s ; | b < w } $vowel ; | y < u ; | y < w ; - | Ch < H ; | K < C ; | I < J ; @@ -223,15 +142,11 @@ $afterLetter { ς <> $afterLetter { s ; | B < U } $vowel ; | Y < W ; | Y < U ; - -# Completeness for Greek - ϐ > | β ; ϑ > | θ ; ϒ > | Υ ; ϕ > | φ ; ϖ > | π ; - ϰ > | κ ; ϱ > | ρ ; ϲ > | σ ; @@ -240,13 +155,7 @@ $afterLetter { ς <> $afterLetter { s ; ϴ > | Θ ; ϵ > | ε ; µ > | μ ; - -# delete any trailing ' marks used for roundtripping - - < [Ππ] { \' } [Ss] ; - < [Νν] { \' } $egammaLike ; - +< [Ππ] { \' } [Ss] ; +< [Νν] { \' } $egammaLike ; ::NFC (NFD) ; - -# MINIMAL FILTER GENERATED FOR: Latin-Greek/UNGEGN BACKWARD :: ([[[:Latin:][:Mn:][:Me:]] ['\:?]]) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Bengali.txt new file mode 100644 index 00000000000..20dba90b8c5 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Devanagari.txt new file mode 100644 index 00000000000..614612a4d06 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Gurmukhi.txt new file mode 100644 index 00000000000..797dada1834 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_InterIndic.txt index 2053427608a..935e72da00d 100644 --- a/Build/source/libs/icu-xetex/data/translit/Gujarati_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_InterIndic.txt @@ -1,91 +1,91 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Gujarati-InterIndic -#:: NFD (NFC) ; -\u0a81>\ue001; # SIGN CANDRABINDU -\u0a82>\ue002; # SIGN ANUSVARA -\u0a83>\ue003; # SIGN VISARGA -\u0a85>\ue005; # LETTER A -\u0a86>\ue006; # LETTER AA -\u0a87>\ue007; # LETTER I -\u0a88>\ue008; # LETTER II -\u0a89>\ue009; # LETTER U -\u0a8a>\ue00a; # LETTER UU -\u0a8b>\ue00b; # LETTER VOCALIC R -\u0a8c>\ue00c; # LETTER VOCALLIC L -\u0a8d>\ue00d; # VOWEL CANDRA E -\u0a8f>\ue00f; # LETTER E -\u0a90>\ue010; # LETTER AI -\u0a91>\ue011; # VOWEL CANDRA O -\u0a93>\ue013; # LETTER O -\u0a94>\ue014; # LETTER AU -\u0a95>\ue015; # LETTER KA -\u0a96>\ue016; # LETTER KHA -\u0a97>\ue017; # LETTER GA -\u0a98>\ue018; # LETTER GHA -\u0a99>\ue019; # LETTER NGA -\u0a9a>\ue01a; # LETTER CA -\u0a9b>\ue01b; # LETTER CHA -\u0a9c>\ue01c; # LETTER JA -\u0a9d>\ue01d; # LETTER JHA -\u0a9e>\ue01e; # LETTER NYA -\u0a9f>\ue01f; # LETTER TTA -\u0aa0>\ue020; # LETTER TTHA -\u0aa1>\ue021; # LETTER DDA -\u0aa2>\ue022; # LETTER DDHA -\u0aa3>\ue023; # LETTER NNA -\u0aa4>\ue024; # LETTER TA -\u0aa5>\ue025; # LETTER THA -\u0aa6>\ue026; # LETTER DA -\u0aa7>\ue027; # LETTER DHA -\u0aa8>\ue028; # LETTER NA -\u0aaa>\ue02a; # LETTER PA -\u0aab>\ue02b; # LETTER PHA -\u0aac>\ue02c; # LETTER BA -\u0aad>\ue02d; # LETTER BHA -\u0aae>\ue02e; # LETTER MA -\u0aaf>\ue02f; # LETTER YA -\u0ab0>\ue030; # LETTER RA -\u0ab2>\ue032; # LETTER LA -\u0ab3>\ue033; # LETTER LLA -\u0ab5>\ue035; # LETTER VA -\u0ab6>\ue036; # LETTER SHA -\u0ab7>\ue037; # LETTER SSA -\u0ab8>\ue038; # LETTER SA -\u0ab9>\ue039; # LETTER HA -\u0abc>\ue03c; # SIGN NUKTA -\u0abd>\ue03d; # SIGN AVAGRAHA -\u0abe>\ue03e; # VOWEL SIGN AA -\u0abf>\ue03f; # VOWEL SIGN I -\u0ac0>\ue040; # VOWEL SIGN II -\u0ac1>\ue041; # VOWEL SIGN U -\u0ac2>\ue042; # VOWEL SIGN UU -\u0ac3>\ue043; # VOWEL SIGN VOCALIC R -\u0ac4>\ue044; # VOWEL SIGN VOCALIC RR -\u0ac5>\ue045; # VOWEL SIGN CANDRA E -\u0ac7>\ue047; # VOWEL SIGN E -\u0ac8>\ue048; # VOWEL SIGN AI -\u0ac9>\ue049; # VOWEL SIGN CANDRA O -\u0acb>\ue04b; # VOWEL SIGN O -\u0acc>\ue04c; # VOWEL SIGN AU -\u0acd>\ue04d; # SIGN VIRAMA -\u0ad0>\ue050; # OM -\u0ae0>\ue060; # LETTER VOCALIC RR -\u0ae1>\ue061; # LETTER VOCALIC LL -\u0ae6>\ue066; # DIGIT ZERO -\u0ae7>\ue067; # DIGIT ONE -\u0ae8>\ue068; # DIGIT TWO -\u0ae9>\ue069; # DIGIT THREE -\u0aea>\ue06a; # DIGIT FOUR -\u0aeb>\ue06b; # DIGIT FIVE -\u0aec>\ue06c; # DIGIT SIX -\u0aed>\ue06d; # DIGIT SEVEN -\u0aee>\ue06e; # DIGIT EIGHT -\u0aef>\ue06f; # DIGIT NINE -\u0964>\ue064; # DANDA -\u0965>\ue065; # DOUBLE DANDA -# :: NFC (NFD) ; -# eof +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +\u0A81>\uE001; # SIGN CANDRABINDU +\u0A82>\uE002; # SIGN ANUSVARA +ઃ>\uE003; # SIGN VISARGA +અ>\uE005; # LETTER A +આ>\uE006; # LETTER AA +ઇ>\uE007; # LETTER I +ઈ>\uE008; # LETTER II +ઉ>\uE009; # LETTER U +ઊ>\uE00A; # LETTER UU +ઋ>\uE00B; # LETTER VOCALIC R +ઌ>\uE00C; # LETTER VOCALLIC L +ઍ>\uE00D; # VOWEL CANDRA E +એ>\uE00F; # LETTER E +ઐ>\uE010; # LETTER AI +ઑ>\uE011; # VOWEL CANDRA O +ઓ>\uE013; # LETTER O +ઔ>\uE014; # LETTER AU +ક>\uE015; # LETTER KA +ખ>\uE016; # LETTER KHA +ગ>\uE017; # LETTER GA +ઘ>\uE018; # LETTER GHA +ઙ>\uE019; # LETTER NGA +ચ>\uE01A; # LETTER CA +છ>\uE01B; # LETTER CHA +જ>\uE01C; # LETTER JA +ઝ>\uE01D; # LETTER JHA +ઞ>\uE01E; # LETTER NYA +ટ>\uE01F; # LETTER TTA +ઠ>\uE020; # LETTER TTHA +ડ>\uE021; # LETTER DDA +ઢ>\uE022; # LETTER DDHA +ણ>\uE023; # LETTER NNA +ત>\uE024; # LETTER TA +થ>\uE025; # LETTER THA +દ>\uE026; # LETTER DA +ધ>\uE027; # LETTER DHA +ન>\uE028; # LETTER NA +પ>\uE02A; # LETTER PA +ફ>\uE02B; # LETTER PHA +બ>\uE02C; # LETTER BA +ભ>\uE02D; # LETTER BHA +મ>\uE02E; # LETTER MA +ય>\uE02F; # LETTER YA +ર>\uE030; # LETTER RA +લ>\uE032; # LETTER LA +ળ>\uE033; # LETTER LLA +વ>\uE035; # LETTER VA +શ>\uE036; # LETTER SHA +ષ>\uE037; # LETTER SSA +સ>\uE038; # LETTER SA +હ>\uE039; # LETTER HA +\u0ABC>\uE03C; # SIGN NUKTA +ઽ>\uE03D; # SIGN AVAGRAHA +ા>\uE03E; # VOWEL SIGN AA +િ>\uE03F; # VOWEL SIGN I +ી>\uE040; # VOWEL SIGN II +\u0AC1>\uE041; # VOWEL SIGN U +\u0AC2>\uE042; # VOWEL SIGN UU +\u0AC3>\uE043; # VOWEL SIGN VOCALIC R +\u0AC4>\uE044; # VOWEL SIGN VOCALIC RR +\u0AC5>\uE045; # VOWEL SIGN CANDRA E +\u0AC7>\uE047; # VOWEL SIGN E +\u0AC8>\uE048; # VOWEL SIGN AI +ૉ>\uE049; # VOWEL SIGN CANDRA O +ો>\uE04B; # VOWEL SIGN O +ૌ>\uE04C; # VOWEL SIGN AU +\u0ACD>\uE04D; # SIGN VIRAMA +ૐ>\uE050; # OM +ૠ>\uE060; # LETTER VOCALIC RR +ૡ>\uE061; # LETTER VOCALIC LL +૦>\uE066; # DIGIT ZERO +૧>\uE067; # DIGIT ONE +૨>\uE068; # DIGIT TWO +૩>\uE069; # DIGIT THREE +૪>\uE06A; # DIGIT FOUR +૫>\uE06B; # DIGIT FIVE +૬>\uE06C; # DIGIT SIX +૭>\uE06D; # DIGIT SEVEN +૮>\uE06E; # DIGIT EIGHT +૯>\uE06F; # DIGIT NINE +।>\uE064; # DANDA +॥>\uE065; # DOUBLE DANDA diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Kannada.txt new file mode 100644 index 00000000000..9a248b46fb9 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Latin.txt new file mode 100644 index 00000000000..7cd61715179 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Malayalam.txt new file mode 100644 index 00000000000..dfdd45c19fc --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Oriya.txt new file mode 100644 index 00000000000..fe95e2a8963 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Tamil.txt new file mode 100644 index 00000000000..0597c1818f2 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gujarati_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Gujarati_Telugu.txt new file mode 100644 index 00000000000..49710607c23 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gujarati_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gujarati_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A81-ઃઅ-ઍએ-ઑઓ-નપ-રલ-ળવ-હ\u0ABC-\u0AC5\u0AC7-ૉો-\u0ACDૐૠૡ૦-૯]; +::NFD; +::Gujarati-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Bengali.txt new file mode 100644 index 00000000000..692921b3753 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Devanagari.txt new file mode 100644 index 00000000000..aaf764b61e4 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Gujarati.txt new file mode 100644 index 00000000000..c96bcd2f58d --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:13 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_InterIndic.txt index 2c93789836b..b6cbf1fb0da 100644 --- a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_InterIndic.txt @@ -1,68 +1,63 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Gurmukhi-InterIndic -#:: NFD (NFC) ; - -#\u0A16\u0A3C>\uE059; # LETTER KHHA -#\u0A17\u0A3C>\uE05A; # LETTER GHHA -#\u0A1C\u0A3C>\uE05B; # LETTER ZA -#\u0A38\u0A3C>\uE036; # LETTER SHA -#\u0A32\u0A3C>\uE033; # LETTER LLA -#\u0A2B\u0A3C>\uE05E; # LETTER FA -\u0A01>\ue001; # SIGN CHANDRABINDU +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +\u0A01>\uE001; # SIGN CHANDRABINDU \u0A02>\uE002; # SIGN BINDI -\u0A05>\uE005; # LETTER A -\u0A06>\uE006; # LETTER AA -\u0A07>\uE007; # LETTER I -\u0A08>\uE008; # LETTER II -\u0A09>\uE009; # LETTER U -\u0A0A>\uE00A; # LETTER UU -\u0A0C>\uE032; # FALLBACK : VOCALLIC LA -\u0A0F>\uE00F; # LETTER EE -\u0A10>\uE010; # LETTER AI -\u0A13>\uE013; # LETTER OO -\u0A14>\uE014; # LETTER AU -\u0A15>\uE015; # LETTER KA -\u0A16>\uE016; # LETTER KHA -\u0A17>\uE017; # LETTER GA -\u0A18>\uE018; # LETTER GHA -\u0A19>\uE019; # LETTER NGA -\u0A1A>\uE01A; # LETTER CA -\u0A1B>\uE01B; # LETTER CHA -\u0A1C>\uE01C; # LETTER JA -\u0A1D>\uE01D; # LETTER JHA -\u0A1E>\uE01E; # LETTER NYA -\u0A1F>\uE01F; # LETTER TTA -\u0A20>\uE020; # LETTER TTHA -\u0A21>\uE021; # LETTER DDA -\u0A22>\uE022; # LETTER DDHA -\u0A23>\uE023; # LETTER NNA -\u0A24>\uE024; # LETTER TA -\u0A25>\uE025; # LETTER THA -\u0A26>\uE026; # LETTER DA -\u0A27>\uE027; # LETTER DHA -\u0A28>\uE028; # LETTER NA -\u0A2A>\uE02A; # LETTER PA -\u0A2B>\uE02B; # LETTER PHA -\u0A2C>\uE02C; # LETTER BA -\u0A2D>\uE02D; # LETTER BHA -\u0A2E>\uE02E; # LETTER MA -\u0A2F>\uE02F; # LETTER YA -\u0A30>\uE030; # LETTER RA -\u0A32>\uE032; # LETTER LA -\u0a33>\uE033; # FALLBACK -\u0A35>\uE035; # LETTER VA -\u0a36>\ue036; -\u0A38\0a3c>\ue036; # FALLBACK -\u0A38>\uE038; # LETTER SA -\u0A39>\uE039; # LETTER HA +ਅ>\uE005; # LETTER A +ਆ>\uE006; # LETTER AA +ਇ>\uE007; # LETTER I +ਈ>\uE008; # LETTER II +ਉ>\uE009; # LETTER U +ਊ>\uE00A; # LETTER UU +\u0A0C>\uE032; # FALLBACK : VOCALLIC LA +ਏ>\uE00F; # LETTER EE +ਐ>\uE010; # LETTER AI +ਓ>\uE013; # LETTER OO +ਔ>\uE014; # LETTER AU +ਕ>\uE015; # LETTER KA +ਖ>\uE016; # LETTER KHA +ਗ>\uE017; # LETTER GA +ਘ>\uE018; # LETTER GHA +ਙ>\uE019; # LETTER NGA +ਚ>\uE01A; # LETTER CA +ਛ>\uE01B; # LETTER CHA +ਜ>\uE01C; # LETTER JA +ਝ>\uE01D; # LETTER JHA +ਞ>\uE01E; # LETTER NYA +ਟ>\uE01F; # LETTER TTA +ਠ>\uE020; # LETTER TTHA +ਡ>\uE021; # LETTER DDA +ਢ>\uE022; # LETTER DDHA +ਣ>\uE023; # LETTER NNA +ਤ>\uE024; # LETTER TA +ਥ>\uE025; # LETTER THA +ਦ>\uE026; # LETTER DA +ਧ>\uE027; # LETTER DHA +ਨ>\uE028; # LETTER NA +ਪ>\uE02A; # LETTER PA +ਫ>\uE02B; # LETTER PHA +ਬ>\uE02C; # LETTER BA +ਭ>\uE02D; # LETTER BHA +ਮ>\uE02E; # LETTER MA +ਯ>\uE02F; # LETTER YA +ਰ>\uE030; # LETTER RA +ਲ>\uE032; # LETTER LA +ਲ਼>\uE033; # FALLBACK +ਵ>\uE035; # LETTER VA +ਸ਼>\uE036; +ਸ\0a3c>\uE036; # FALLBACK +ਸ>\uE038; # LETTER SA +ਹ>\uE039; # LETTER HA \u0A3C>\uE03C; # SIGN NUKTA -\u0A3E>\uE03E; # VOWEL SIGN AA -\u0A3F>\uE03F; # VOWEL SIGN I -\u0A40>\uE040; # VOWEL SIGN II +ਾ>\uE03E; # VOWEL SIGN AA +ਿ>\uE03F; # VOWEL SIGN I +ੀ>\uE040; # VOWEL SIGN II \u0A41>\uE041; # VOWEL SIGN U \u0A42>\uE042; # VOWEL SIGN UU \u0A47>\uE047; # VOWEL SIGN EE @@ -70,26 +65,21 @@ \u0A4B>\uE04B; # VOWEL SIGN OO \u0A4C>\uE04C; # VOWEL SIGN AU \u0A4D>\uE04D; # SIGN VIRAMA - -\u0A5C>\uE05C; # LETTER RRA - -\u0A66>\uE066; # DIGIT ZERO -\u0A67>\uE067; # DIGIT ONE -\u0A68>\uE068; # DIGIT TWO -\u0A69>\uE069; # DIGIT THREE -\u0A6A>\uE06A; # DIGIT FOUR -\u0A6B>\uE06B; # DIGIT FIVE -\u0A6C>\uE06C; # DIGIT SIX -\u0A6D>\uE06D; # DIGIT SEVEN -\u0A6E>\uE06E; # DIGIT EIGHT -\u0A6F>\uE06F; # DIGIT NINE +ੜ>\uE05C; # LETTER RRA +੦>\uE066; # DIGIT ZERO +੧>\uE067; # DIGIT ONE +੨>\uE068; # DIGIT TWO +੩>\uE069; # DIGIT THREE +੪>\uE06A; # DIGIT FOUR +੫>\uE06B; # DIGIT FIVE +੬>\uE06C; # DIGIT SIX +੭>\uE06D; # DIGIT SEVEN +੮>\uE06E; # DIGIT EIGHT +੯>\uE06F; # DIGIT NINE \u0A70>\uE07C; # TIPPI \u0A71>\uE07D; # ADDAK -\u0A72>\uE07E; # IRI -\u0A73>\uE07F; # URA -\u0A74>\uE080; # EK ONKAR -\u0964>\ue064; # DANDA -\u0965>\ue065; # DOUBLE DANDA -# :: NFC (NFD) ; -# eof - +ੲ>\uE07E; # IRI +ੳ>\uE07F; # URA +ੴ>\uE080; # EK ONKAR +।>\uE064; # DANDA +॥>\uE065; # DOUBLE DANDA diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Kannada.txt new file mode 100644 index 00000000000..a0f2c379b5e --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Latin.txt new file mode 100644 index 00000000000..fa1fd0ba13c --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Malayalam.txt new file mode 100644 index 00000000000..becc7f01001 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Oriya.txt new file mode 100644 index 00000000000..4855f87c2c7 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Tamil.txt new file mode 100644 index 00000000000..4cc00109695 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Telugu.txt new file mode 100644 index 00000000000..1e2e3e1ed1a --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Gurmukhi_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Gurmukhi_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:14 PDT 2006 +# +::[।-॥\u0A01\u0A02ਅ-ਊਏ-ਐਓ-ਨਪ-ਰਲ-ਲ਼ਵ-ਸ਼ਸ-ਹ\u0A3Cਾ-\u0A42\u0A47-\u0A48\u0A4B-\u0A4Dਖ਼-ੜਫ਼੦-ੴ]; +::NFD; +::Gurmukhi-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Han_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Han_Latin.txt index 665609710e9..96b06acbe77 100644 --- a/Build/source/libs/icu-xetex/data/translit/Han_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Han_Latin.txt @@ -1,14 +1,13 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Warning: does not do round-trip mapping!! - -# Convert CJK characters +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Han_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# ::Han-Spacedhan(); - -# Start RAW data for converting CJK characters [吖呵錒锕阿]>ā; 嗄>á; 啊>a; @@ -754,7 +753,7 @@ [㜛㯎㶧嫩嫰]>nèn; [㴰䏻嬣能薴]>néng; 㲌>nèng; -㕶>ng̀; +㕶>ng\u0300; 妮>nī; [㞾㪒㹸䘦䘽䛏䝚倪坭埿婗尼屔怩泥淣狋猊秜籾臡蚭蜺觬貎跜輗郳霓鯓鯢鲵麑齯]>ní; [㣇㵫䕥䦵䧇䭲䰯伱伲你儗儞孴抳拟擬旎柅狔禰苨薿鈮鉨铌隬馜]>nǐ; @@ -1408,33 +1407,3 @@ [㸲䎰䝫䞰昨椊琢秨稓筰葃鈼]>zuó; [㝾佐咗唨左毑繓]>zuǒ; [㑅㘀㘴㛗㭮䋏䔘作侳做唑坐夎岝岞座怍柞祚糳胙葄袏酢阼]>zuò; -# End RAW data for converting CJK characters - -# fallbacks - -## | yi < i; -## | wu < u; -## | bi < b; -## | ci < c; -## | di < d; -## | fu < f; -## | gu < g; -## | he < h; -## | ji < j; -## | ku < k; -## | li < l; -## | mi < m; -## | pi < p; -## | qi < q; -## | l < r; -## | si < s; -## | ti < t; -## | f < v; -## | wa < w; -## | xi < x; -## | yi < y; -## | zi < z; - -# filter out the half-width hangul -# :: [^\uFFBE-\uFFEE] fullwidth-halfwidth (); -## :: (lower) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Han_Spacedhan.txt b/Build/source/libs/icu-xetex/data/translit/Han_Spacedhan.txt index 85607b58e72..e3681bb78bf 100644 --- a/Build/source/libs/icu-xetex/data/translit/Han_Spacedhan.txt +++ b/Build/source/libs/icu-xetex/data/translit/Han_Spacedhan.txt @@ -1,24 +1,17 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Only intended for internal use +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Han_Spacedhan.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# :: fullwidth-halfwidth; - 。 > '.'; - $terminalPunct = [\.\,\:\;\?\!.,:?!。、;[:Pe:][:Pf:]]; $initialPunct = [:Ps:][:Pi:]; - -# add space between any Han or terminal punctuation and letters, and -# between letters and Han or initial punct - [[:Ideographic:] $terminalPunct] {} [:Letter:] > ' ' ; [:Letter:] [:Mark:]* {} [[:Ideographic:] $initialPunct] > ' ' ; - -# remove spacing between ideographs and other letters - - < [:Ideographic:] { ' ' } [:Letter:] ; - < [:Letter:] [:Mark:]* { ' ' } [:Ideographic:] ; - +< [:Ideographic:] { ' ' } [:Letter:] ; +< [:Letter:] [:Mark:]* { ' ' } [:Ideographic:] ; diff --git a/Build/source/libs/icu-xetex/data/translit/Hangul_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Hangul_Latin.txt new file mode 100644 index 00000000000..9d5208c0842 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Hangul_Latin.txt @@ -0,0 +1,13 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Hangul_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# +::['ᄀ-하-ᅵᆨ-ᇂㄱ-ㄿㅁ-ㅃㅅ-ㅣ㈀-㈜㉠-㉻가-힣'ᄀ-ᆵᄆ-ᄈᄉ-하-ᅦᅧ-ᅬᅭ-ᅲᅳ-ᅵ]; +::NFKD; +::ConjoiningJamo-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Hebrew_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Hebrew_Latin.txt index 810d8a7f8fc..40c63cadf07 100644 --- a/Build/source/libs/icu-xetex/data/translit/Hebrew_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Hebrew_Latin.txt @@ -1,40 +1,20 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Transliteration table for Hebrew -# Based on the UNGEGN table at: -# http://www.eki.ee/wgrs/rom1_he.pdf +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Hebrew_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 # -# Exceptions: -# - Accents are added to disambiguate letters -# - Combinations of dagesh, shin/sin dot that produce different -# letters are not yet encoded. -# -# To test, open: -# http://oss.software.ibm.com/cgi-bin/icu/tr -# Click Edit, paste in this file, Save As hebrew-latin/XXX -# (where XXX is a username) -# Now go back to the main window, and try it out. -# Use hebrew-latin/XXX for Output 1, and (Inverse) for Output 2 -# Paste in hebrew text in Input, and hit Transliterate. -# -# For more information, see" -# http://icu.sourceforge.net/userguide/Transform.html - -:: [[:Hebrew:] [:^ccc=0:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2\u2135-\u2138̄\u05BF] - [\u05BD]] ; +:: [[:Hebrew:] [:^ccc=0:] [\u05B0-\u05B9\u05BB-\u05BC\u05C1-\u05C2ℵ-ℸ\u0304\u05BF] - [\u05BD]] ; :: nfkd (nfc) ; $letterAfter = [:M:]* [:L:] ; - -# move longer items here to avoid masking - -ח <> ẖ ; -צ <> ẕ } $letterAfter; -ץ <> ẕ ; -ש <> ş ; -ת <> ţ ; - +ח <> h\u0331 ; +צ <> z\u0331 } $letterAfter; +ץ <> z\u0331 ; +ש <> s\u0327 ; +ת <> t\u0327 ; א <> ʼ ; ב <> b ; ג <> g ; @@ -48,7 +28,7 @@ $letterAfter = [:M:]* [:L:] ; ך <> k ; ל <> l ; מ <> m } $letterAfter; -ם <> m ; +ם <> m ; נ <> n } $letterAfter; ן <> n ; ס <> s ; @@ -57,53 +37,37 @@ $letterAfter = [:M:]* [:L:] ; ף <> p ; ק <> q ; ר <> r ; - - װ > | וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV - ױ > | וי; # HEBREW LIGATURE YIDDISH VAV YOD - ײ > | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD - - -ּ <> ̇ ; # dagesh just goes to overdot for now -ׁ <> ̌ ; # shin dot -> sh -ׂ <> ̂ ; # sin dot -> s - -# points +װ > | וו; # HEBREW LIGATURE YIDDISH DOUBLE VAV +ױ > | וי; # HEBREW LIGATURE YIDDISH VAV YOD +ײ > | יי ; # HEBREW LIGATURE YIDDISH DOUBLE YOD +\u05BC <> \u0307 ; # dagesh just goes to overdot for now +\u05C1 <> \u030C ; # shin dot -> sh +\u05C2 <> \u0302 ; # sin dot -> s $above = [^[:ccc=0:][:ccc=230:]]*; - -ֲ > à ; -ֲ $1< a ($above) ̀; - -ָ > á ; -ָ $1 < a ($above) ́; - -ֱ > è ; -ֱ $1 < e ($above) ̀; - -ֵ > é ; -ֵ $1 < e ($above) ́; - -ְ > e ̆ ; -ְ $1 < e ($above) ̆; - -ֹ > ò ; -ֹ $1 < o ($above) ̀; - -ִ <> i ; -ֻ <> u ; -ַ <> a ; -ֶ <> e ; -ֳ <> o ; - -\u05BF <> ̄ ; - -# fallbacks +\u05B2 > à ; +\u05B2 $1< a ($above) \u0300; +\u05B8 > á ; +\u05B8 $1 < a ($above) \u0301; +\u05B1 > è ; +\u05B1 $1 < e ($above) \u0300; +\u05B5 > é ; +\u05B5 $1 < e ($above) \u0301; +\u05B0 > e \u0306 ; +\u05B0 $1 < e ($above) \u0306; +\u05B9 > ò ; +\u05B9 $1 < o ($above) \u0300; +\u05B4 <> i ; +\u05BB <> u ; +\u05B7 <> a ; +\u05B6 <> e ; +\u05B3 <> o ; +\u05BF <> \u0304 ; ק < c ; פ < f } $letterAfter; ף < f ; ז < j ; ו < v ; כס < x ; - :: (lower); :: nfc (nfd) ; -:: ([[:Latin:] [:^ccc=0:] [\u02BB-\u02BC\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 ̄ ]]);
\ No newline at end of file +:: ([[:Latin:] [:^ccc=0:] [ʻ-ʼ\u0300-\u0302\u0307\u030C\u0327\u0331\u0340-\u0341 \u0304 ]]); diff --git a/Build/source/libs/icu-xetex/data/translit/Hiragana_Katakana.txt b/Build/source/libs/icu-xetex/data/translit/Hiragana_Katakana.txt index 78a97165311..28adf455a9a 100644 --- a/Build/source/libs/icu-xetex/data/translit/Hiragana_Katakana.txt +++ b/Build/source/libs/icu-xetex/data/translit/Hiragana_Katakana.txt @@ -1,55 +1,18 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# note: a global filter is more efficient, but MUST include all source chars -:: [\u0000-\u007E \u3001\u3002 \u3099-\u309C \u30A1-\u30FC \uFF61-\uFF9Fー[:Hiragana:] [:Katakana:] [:nonspacing mark:]] ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Hiragana_Katakana.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# +:: [\u0000-\u007E 、。 \u3099-゜ ァ-ー 。-゚ー[:Hiragana:] [:Katakana:] [:nonspacing mark:]] ; :: NFKC (); - -# Hiragana-Katakana - -# This is largely a one-to-one mapping, but it has a -# few kinks: - -# 1. The Katakana va/vi/ve/vo (30F7-30FA) have no -# Hiragana equivalents. We use Hiragana wa/wi/we/wo -# (308F-3092) with a voicing mark (3099), which is -# semantically equivalent. However, this is a non- -# roundtripping transformation. - -# 2. The Katakana small ka/ke (30F5,30F6) have no -# Hiragana equiavlents. We convert them to normal -# Hiragana ka/ke (304B,3051). This is a one-way -# information-losing transformation and precludes -# round-tripping of 30F5 and 30F6. - -# 3. The combining marks 3099-309C are in the Hiragana -# block, but they apply to Katakana as well, so we -# leave them untouched. - -# 4. The Katakana prolonged sound mark 30FC doubles the -# preceding vowel. This is a one-way information- -# losing transformation from Katakana to Hiragana. - -# 5. The Katakana middle dot separates words in foreign -# expressions; we leave this unmodified. - -# The above points preclude successful round-trip -# transformations of arbitrary input text. However, -# they provide naturalistic results that should conform -# to user expectations. - - -# Combining equivalents va/vi/ve/vo -わ゙ <> ヷ; -ゐ゙ <> ヸ; -ゑ゙ <> ヹ; -を゙ <> ヺ; - -# One-to-one mappings, main block -# 3041:3094 <> 30A1:30F4 -# 309D,E <> 30FD,E +わ\u3099 <> ヷ; +ゐ\u3099 <> ヸ; +ゑ\u3099 <> ヹ; +を\u3099 <> ヺ; ぁ <> ァ; あ <> ア; ぃ <> ィ; @@ -136,72 +99,37 @@ ゔ <> ヴ; ゝ <> ヽ; ゞ <> ヾ; - -# One-way Katakana-Hiragana xform of small K ka/ke to -# normal H ka/ke. か < ヵ; け < ヶ; - -# Katakana followed by a prolonged sound mark 30FC has -# its final vowel doubled. This is a Katakana-Hiragana -# one-way information-losing transformation. We -# include the small Katakana (e.g., small A 3041) and -# do not distinguish them from their large -# counterparts. It doesn't make sense to double a -# small counterpart vowel as a small Hiragana vowel, so -# we don't do so. In natural text this should never -# occur anyway. If a 30FC is seen without a preceding -# vowel sound (e.g., after n 30F3) we do not change it. - -### $long = ー; - -# The following categories are Hiragana, not Katakana -# as might be expected, since by the time we get to the -# 30FC, the preceding character will have already been -# transformed to Hiragana. - -# {The following mechanically generated from the -# Unicode 3.0 data:} - $xa = [ \ ぁ あ か が さ ざ \ た だ な は ば ぱ \ ま ゃ や ら ゎ わ \ ]; - $xi = [ \ ぃ い き ぎ し じ \ ち ぢ に ひ び ぴ \ み り ゐ \ ]; - $xu = [ \ ぅ う く ぐ す ず \ っ つ づ ぬ ふ ぶ \ ぷ む ゅ ゆ る ゔ \ ]; - $xe = [ \ ぇ え け げ せ ぜ \ て で ね へ べ ぺ \ め れ ゑ \ ]; - $xo = [ \ ぉ お こ ご そ ぞ \ と ど の ほ ぼ ぽ \ も ょ よ ろ を \ ]; - あ < $xa {ー}; い < $xi {ー}; う < $xu {ー}; え < $xe {ー}; お < $xo {ー}; - :: (NFKC) ; - -# note: a global filter is more efficient, but MUST include all source chars!! -:: ([\u0000-\u007E \u3001\u3002 \u3099-\u309C \u30A1-\u30FC \uFF61-\uFF9Fー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]); - -# eof +:: ([\u0000-\u007E 、。 \u3099-゜ ァ-ー 。-゚ー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]); diff --git a/Build/source/libs/icu-xetex/data/translit/Hiragana_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Hiragana_Latin.txt index ed0688173c1..36b9c1fac57 100644 --- a/Build/source/libs/icu-xetex/data/translit/Hiragana_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Hiragana_Latin.txt @@ -1,14 +1,16 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -:: [\u3041-\u3094\u3099\u309D-\u309E\u30AC\u30AE\u30B0\u30B2\u30B4\u30B6\u30B8\u30BA\u30BC\u30BE\u30C0\u30C2\u30C5\u30C7\u30C9\u30D0\u30D3\u30D6\u30D9\u30DC\u30F4\u30F7-\u30FA\u30FE] ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Hiragana_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# +:: [ぁ-ゔ\u3099ゝ-ゞガギグゲゴザジズゼゾダヂヅデドバビブベボヴヷ-ヺヾ] ; :: NFD ; - :: Hiragana-Katakana; :: Katakana-Latin; - :: NFC ; :: (Lower) ; -:: ([',.A-Za-z~\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0304\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1FB1\u1FB9\u1FD1\u1FD9\u1FE1\u1FE9\u212A-\u212B]) ; +:: ([',.A-Za-z~À-ÖØ-öø-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳ\u0304Ӣ-ӣӮ-ӯḀ-ẙẠ-ỹᾱᾹῑῙῡῩK-Å]) ; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Bengali.txt index 929e4140eef..50db709d329 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Bengali.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Bengali.txt @@ -1,149 +1,138 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Bengali -#:: NFD (NFC) ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# \uE001>\u0981; # SIGN CANDRABINDU -\uE002>\u0982; # SIGN ANUSVARA -\uE003>\u0983; # SIGN VISARGA -\uE004>\u0985; # FALLBACK TO LETTER A -\uE005>\u0985; # LETTER A -\uE006>\u0986; # LETTER AA -\uE007>\u0987; # LETTER I -\uE008>\u0988; # LETTER II -\uE009>\u0989; # LETTER U -\uE00A>\u098A; # LETTER UU -\uE00B>\u098B; # LETTER VOCALIC R -\uE00C>\u098C; # LETTER VOCALIC L -\uE00D>\u098F; # FALLBACK -\uE00E>\u098F; # FALLBACK -\uE00F>\u098F; # LETTER E -\uE010>\u0990; # LETTER AI -\uE011>\u0993; # FALLBACK -\uE012>\u0993; # FALLBACK -\uE013>\u0993; # LETTER O -\uE014>\u0994; # LETTER AU -\uE015>\u0995; # LETTER KA -\uE016>\u0996; # LETTER KHA -\uE017>\u0997; # LETTER GA -\uE018>\u0998; # LETTER GHA -\uE019>\u0999; # LETTER NGA -\uE01A>\u099A; # LETTER CA -\uE01B>\u099B; # LETTER CHA -\uE01C>\u099C; # LETTER JA -\uE01D>\u099D; # LETTER JHA -\uE01E>\u099E; # LETTER NYA -\uE01F>\u099F; # LETTER TTA -\uE020>\u09A0; # LETTER TTHA -\uE021>\u09A1; # LETTER DDA -\uE022>\u09A2; # LETTER DDHA -\uE023>\u09A3; # LETTER NNA -\uE024>\u09A4; # LETTER TA -\uE025>\u09A5; # LETTER THA -\uE026>\u09A6; # LETTER DA -\uE027>\u09A7; # LETTER DHA -\uE028>\u09A8; # LETTER NA -\uE029>\u09A8\u09BC; # REMAP (indicExceptions.txt): \u09a9>\u09a8 = LETTER NNNA>LETTER NA -\uE02A>\u09AA; # LETTER PA -\uE02B>\u09AB; # LETTER PHA -\uE02C>\u09AC; # LETTER BA -\uE02D>\u09AD; # LETTER BHA -\uE02E>\u09AE; # LETTER MA -\uE02F>\u09AF; # LETTER YA -\uE030>\u09B0; # LETTER RA -\uE031>\u09B0\u09BC; # FALLBACK to RA -\uE032>\u09B2; # LETTER LA -\uE033>\u09B2; # REMAP (indicExceptions.txt): \u09b3>\u09b2 = LETTER LLA>LETTER LA -\uE034>\u09B2; # REMAP (indicExceptions.txt): \u09b4>\u09b2 = LETTER LLLA>LETTER LA -\uE035>\u09AC; # REMAP (indicExceptions.txt): \u09b5>\u09ac = LETTER VA>LETTER BA -\uE036>\u09B6; # LETTER SHA -\uE037>\u09B7; # LETTER SSA -\uE038>\u09B8; # LETTER SA -\uE039>\u09B9; # LETTER HA +\uE002>ং; # SIGN ANUSVARA +\uE003>ঃ; # SIGN VISARGA +\uE004>অ; # FALLBACK TO LETTER A +\uE005>অ; # LETTER A +\uE006>আ; # LETTER AA +\uE007>ই; # LETTER I +\uE008>ঈ; # LETTER II +\uE009>উ; # LETTER U +\uE00A>ঊ; # LETTER UU +\uE00B>ঋ; # LETTER VOCALIC R +\uE00C>ঌ; # LETTER VOCALIC L +\uE00D>এ; # FALLBACK +\uE00E>এ; # FALLBACK +\uE00F>এ; # LETTER E +\uE010>ঐ; # LETTER AI +\uE011>ও; # FALLBACK +\uE012>ও; # FALLBACK +\uE013>ও; # LETTER O +\uE014>ঔ; # LETTER AU +\uE015>ক; # LETTER KA +\uE016>খ; # LETTER KHA +\uE017>গ; # LETTER GA +\uE018>ঘ; # LETTER GHA +\uE019>ঙ; # LETTER NGA +\uE01A>চ; # LETTER CA +\uE01B>ছ; # LETTER CHA +\uE01C>জ; # LETTER JA +\uE01D>ঝ; # LETTER JHA +\uE01E>ঞ; # LETTER NYA +\uE01F>ট; # LETTER TTA +\uE020>ঠ; # LETTER TTHA +\uE021>ড; # LETTER DDA +\uE022>ঢ; # LETTER DDHA +\uE023>ণ; # LETTER NNA +\uE024>ত; # LETTER TA +\uE025>থ; # LETTER THA +\uE026>দ; # LETTER DA +\uE027>ধ; # LETTER DHA +\uE028>ন; # LETTER NA +\uE029>ন\u09BC; # REMAP (indicExceptions.txt): \u09A9>ন = LETTER NNNA>LETTER NA +\uE02A>প; # LETTER PA +\uE02B>ফ; # LETTER PHA +\uE02C>ব; # LETTER BA +\uE02D>ভ; # LETTER BHA +\uE02E>ম; # LETTER MA +\uE02F>য; # LETTER YA +\uE030>র; # LETTER RA +\uE031>র\u09BC; # FALLBACK to RA +\uE032>ল; # LETTER LA +\uE033>ল; # REMAP (indicExceptions.txt): \u09B3>ল = LETTER LLA>LETTER LA +\uE034>ল; # REMAP (indicExceptions.txt): \u09B4>ল = LETTER LLLA>LETTER LA +\uE035>ব; # REMAP (indicExceptions.txt): \u09B5>ব = LETTER VA>LETTER BA +\uE036>শ; # LETTER SHA +\uE037>ষ; # LETTER SSA +\uE038>স; # LETTER SA +\uE039>হ; # LETTER HA \uE03C>\u09BC; # SIGN NUKTA -\uE03D>\u09bd; # SIGN AVAGRAHA -\uE03E>\u09BE; # VOWEL SIGN AA -\uE03F>\u09BF; # VOWEL SIGN I -\uE040>\u09C0; # VOWEL SIGN II +\uE03D>ঽ; # SIGN AVAGRAHA +\uE03E>া; # VOWEL SIGN AA +\uE03F>ি; # VOWEL SIGN I +\uE040>ী; # VOWEL SIGN II \uE041>\u09C1; # VOWEL SIGN U \uE042>\u09C2; # VOWEL SIGN UU \uE043>\u09C3; # VOWEL SIGN VOCALIC R \uE044>\u09C4; # VOWEL SIGN VOCALIC RR -\uE045>\u09C7; # REMAP (indicExceptions.txt): \u09c5>\u09c7 = VOWEL SIGN CANDRA E>VOWEL SIGN E -\uE046>\u09C7; # FALLBACK -\uE047>\u09C7; # VOWEL SIGN E -\uE048>\u09C8; # VOWEL SIGN AI -\uE049>\u09C7\u09BE; # REMAP (indicExceptions.txt): \u09c9>\u09cb = VOWEL SIGN CANDRA O>VOWEL SIGN O -\uE04A>\u09C7\u09BE; # FALLBACK -\uE04B>\u09C7\u09BE; # VOWEL SIGN O -\uE04C>\u09C7\u09D7; # VOWEL SIGN AU +\uE045>ে; # REMAP (indicExceptions.txt): \u09C5>ে = VOWEL SIGN CANDRA E>VOWEL SIGN E +\uE046>ে; # FALLBACK +\uE047>ে; # VOWEL SIGN E +\uE048>ৈ; # VOWEL SIGN AI +\uE049>ো; # REMAP (indicExceptions.txt): \u09C9>ো = VOWEL SIGN CANDRA O>VOWEL SIGN O +\uE04A>ো; # FALLBACK +\uE04B>ো; # VOWEL SIGN O +\uE04C>ৌ; # VOWEL SIGN AU \uE04D>\u09CD; # SIGN VIRAMA -\uE050>\u0993\u0982; # InterIndic-Bengali: OM -\ue051>; -\ue052>; -\ue053>; -\ue054>; +\uE050>ওং; # InterIndic-Bengali: OM +\uE051>; +\uE052>; +\uE053>; +\uE054>; \uE055>; # LENGTH MARK -\uE056>\u09C8; # REMAP (indicExceptions.txt): \u09d6>\u09c8 = AI LENGTH MARK>VOWEL SIGN AI -\uE057>\u09D7; # AU LENGTH MARK -\uE058>\u0995\u09BC; # FALLBACK -\uE059>\u0996\u09BC; # REMAP (indicExceptions.txt): \u09d9>\u0996 = LETTER KHHA>LETTER KHA -\uE05A>\u0997\u09BC; # REMAP (indicExceptions.txt): \u09da>\u0997 = LETTER GHHA>LETTER GA -\uE05B>\u099C\u09BC; # REMAP (indicExceptions.txt): \u09db>\u099c = LETTER ZA>LETTER JA -\uE05C>\u09A1\u09BC; # FALLBACK -\uE05D>\u09A2\u09BC; # LETTER RHA -\uE05E>\u09AB\u09BC; # REMAP (indicExceptions.txt): \u09de>\u09ab = LETTER FA>LETTER PHA -\uE05F>\u09AF\u09BC; # LETTER YYA -\uE060>\u09E0; # LETTER VOCALIC RR -\uE061>\u09E1; # LETTER VOCALIC LL +\uE056>ৈ; # REMAP (indicExceptions.txt): \u09D6>ৈ = AI LENGTH MARK>VOWEL SIGN AI +\uE057>ৗ; # AU LENGTH MARK +\uE058>ক\u09BC; # FALLBACK +\uE059>খ\u09BC; # REMAP (indicExceptions.txt): \u09D9>খ = LETTER KHHA>LETTER KHA +\uE05A>গ\u09BC; # REMAP (indicExceptions.txt): \u09DA>গ = LETTER GHHA>LETTER GA +\uE05B>জ\u09BC; # REMAP (indicExceptions.txt): \u09DB>জ = LETTER ZA>LETTER JA +\uE05C>ড\u09BC; # FALLBACK +\uE05D>ঢ\u09BC; # LETTER RHA +\uE05E>ফ\u09BC; # REMAP (indicExceptions.txt): \u09DE>ফ = LETTER FA>LETTER PHA +\uE05F>য\u09BC; # LETTER YYA +\uE060>ৠ; # LETTER VOCALIC RR +\uE061>ৡ; # LETTER VOCALIC LL \uE062>\u09E2; # VOWEL SIGN VOCALIC L \uE063>\u09E3; # VOWEL SIGN VOCALIC LL -\uE064>\u0964; # DANDA -\uE065>\u0965; # DOUBLE DANDA -\uE066>\u09E6; # DIGIT ZERO -\uE067>\u09E7; # DIGIT ONE -\uE068>\u09E8; # DIGIT TWO -\uE069>\u09E9; # DIGIT THREE -\uE06A>\u09EA; # DIGIT FOUR -\uE06B>\u09EB; # DIGIT FIVE -\uE06C>\u09EC; # DIGIT SIX -\uE06D>\u09ED; # DIGIT SEVEN -\uE06E>\u09EE; # DIGIT EIGHT -\uE06F>\u09EF; # DIGIT NINE -\ue070>; # ABBREVIATION SIGN -\ue071>\u09F0; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u09F1; # LETTER RA WITH LOWER DIAGONAL -\ue073>\u09F2; # RUPEE MARK -\ue074>\u09F3; # RUPEE SIGN -\ue075>\u09F4; # CURRENCY NUMERATOR ONE -\ue076>\u09F5; # CURRENCY NUMERATOR TWO -\ue077>\u09F6; # CURRENCY NUMERATOR THREE -\ue078>\u09F7; # CURRENCY NUMERATOR FOUR -\ue079>\u09F8; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>\u09F9; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>\u09FA; # ISSHAR +\uE064>।; # DANDA +\uE065>॥; # DOUBLE DANDA +\uE066>০; # DIGIT ZERO +\uE067>১; # DIGIT ONE +\uE068>২; # DIGIT TWO +\uE069>৩; # DIGIT THREE +\uE06A>৪; # DIGIT FOUR +\uE06B>৫; # DIGIT FIVE +\uE06C>৬; # DIGIT SIX +\uE06D>৭; # DIGIT SEVEN +\uE06E>৮; # DIGIT EIGHT +\uE06F>৯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ৰ; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ৱ; # LETTER RA WITH LOWER DIAGONAL +\uE073>৲; # RUPEE MARK +\uE074>৳; # RUPEE SIGN +\uE075>৴; # CURRENCY NUMERATOR ONE +\uE076>৵; # CURRENCY NUMERATOR TWO +\uE077>৶; # CURRENCY NUMERATOR THREE +\uE078>৷; # CURRENCY NUMERATOR FOUR +\uE079>৸; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>৹; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>৺; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u09AC; # FALLBACK FOR ORIYA LETTER WA +\uE081>ব; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u09ce; # Khanda-ta -0 > \u09E6; # FALLBACK FOR TAMIL -1 > \u09E7; - - - - - - - - - - - -# :: NFC (NFD) ; -# eof +\uE083>ৎ; # Khanda-ta +0 > ০; # FALLBACK FOR TAMIL +1 > ১; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Devanagari.txt index 47b74da08d7..d04e7ec8119 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Devanagari.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Devanagari.txt @@ -1,159 +1,150 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Devanagari -#:: NFD (NFC) ; -#Rules for Decomposed characters - \ue028\ue03c > \u0929; #\ue029 - \ue030\ue03c > \u0931; #\ue031 - \ue033\ue03c > \u0934; #\ue034 - \ue015\ue03c > \u0958; #\ue058 LETTER QA (For Urdu) - \ue016\ue03c > \u0959; #\ue059 LETTER KHHA (For Urdu) - \ue017\ue03c > \u095a; #\ue05a LETTER GHHA (For Urdu) - \ue01c\ue03c > \u095b; #\ue05b LETTER ZA (For Urdu) - \ue021\ue03c > \u095c; #\ue05c LETTER DDDHA (pronounced RRA) - \ue022\ue03c > \u095d; #\ue05d LETTER RHA (pronounced RRHA) - \ue02b\ue03c > \u095e; #\ue05e LETTER FA - \ue02f\ue03c > \u095f; #\ue05f LETTER YYA - - #Decomposed compatibility transliterations - \ue012\ue057>\u0914; # FALLBACK FOR TAMIL AU - 0 > \u0966; # FALLBACK FOR TAMIL - 1 > \u0967; - - \ue055>; # FALLBACK BLOW AWAY KANNADA AND TELUGU LENGTH MARK - \ue056>; # FALLBACK BLOW AWAY KANNADA AND TELUGU AI LENGTH MARK - \ue057>; # FALLBACK BLOW AWAY TAMIL AU LENGTH MARK - - \ue001 > \u0901; # SIGN CANDRABINDU - \ue002 > \u0902; # SIGN ANUSVARA - \ue003 > \u0903; # SIGN VISARGA - \ue004 > \u0904; # SIGN SHORT A - \ue005 > \u0905; # LETTER A - \ue006 > \u0906; # LETTER AA - \ue007 > \u0907; # LETTER I - \ue008 > \u0908; # LETTER II - \ue009 > \u0909; # LETTER U - \ue00a > \u090a; # LETTER UU - \ue00b > \u090b; # LETTER VOCALIC R - \ue00c > \u090c; # LETTER VOCALIC L - \ue00d > \u090d; # LETTER CANDRA E (For representing English sounds) - \ue00e > \u090e; # LETTER SHORT E(For Southern Scripts) - \ue00f > \u090f; # LETTER E - \ue010 > \u0910; # LETTER AI - \ue011 > \u0911; # LETTER CANDRA O (For representing English sounds) - \ue012 > \u0912; # LETTER SHORT O (For Southern Scripts) - \ue013 > \u0913; # LETTER O - \ue014 > \u0914; # LETTER AU - \ue015 > \u0915; # LETTER KA - \ue016 > \u0916; # LETTER KHA - \ue017 > \u0917; # LETTER GA - \ue018 > \u0918; # LETTER GHA - \ue019 > \u0919; # LETTER NGA - \ue01a > \u091a; # LETTER CA - \ue01b > \u091b; # LETTER CHA - \ue01c > \u091c; # LETTER JA - \ue01d > \u091d; # LETTER JHA - \ue01e > \u091e; # LETTER NYA - \ue01f > \u091f; # LETTER TTA - \ue020 > \u0920; # LETTER TTHA - \ue021 > \u0921; # LETTER DDA - \ue022 > \u0922; # LETTER DDHA - \ue023 > \u0923; # LETTER NNA - \ue024 > \u0924; # LETTER TA - \ue025 > \u0925; # LETTER THA - \ue026 > \u0926; # LETTER DA - \ue027 > \u0927; # LETTER DHA - \ue028 > \u0928; # LETTER NA - \ue029 > \u0929; # LETTER NNNA - \ue02a > \u092a; # LETTER PA - \ue02b > \u092b; # LETTER PHA - \ue02c > \u092c; # LETTER BA - \ue02d > \u092d; # LETTER BHA - \ue02e > \u092e; # LETTER MA - \ue02f > \u092f; # LETTER YA - \ue030 > \u0930; # LETTER RA - \ue031 > \u0931; # LETTER RRA (Eyelash RA for Southern scripts) - #\ue031 > \u0930; - \ue032 > \u0932; # LETTER LA - \ue033 > \u0933; # LETTER LLA - \ue034 > \u0934; # LETTER LLLA (LLLA for Southern scripts) - #\ue034 > \u0933; - \ue035 > \u0935; # LETTER VA - \ue036 > \u0936; # LETTER SHA - \ue037 > \u0937; # LETTER SSA - \ue038 > \u0938; # LETTER SA - \ue039 > \u0939; # LETTER HA - \ue03c > \u093c; # SIGN NUKTA - \ue03d > \u093d; # SIGN AVAGRAHA - \ue03e > \u093e; # VOWEL SIGN AA - \ue03f > \u093f; # VOWEL SIGN I - \ue040 > \u0940; # VOWEL SIGN II - \ue041 > \u0941; # VOWEL SIGN U - \ue042 > \u0942; # VOWEL SIGN UU - \ue043 > \u0943; # VOWEL SIGN VOCALIC R - \ue044 > \u0944; # VOWEL SIGN VOCALIC RR - \ue045 > \u0945; # VOWEL SIGN CANDRA E - \ue046 > \u0946; # VOWEL SIGN SHORT E - \ue047 > \u0947; # VOWEL SIGN E - \ue048 > \u0948; # VOWEL SIGN AI - \ue049 > \u0949; # VOWEL SIGN CANDRA O - \ue04a > \u094a; # VOWEL SIGN SHORT O - \ue04b > \u094b; # VOWEL SIGN O - \ue04c > \u094c; # VOWEL SIGN AU - \ue04d > \u094d; # SIGN VIRAMA - \ue050 > \u0950; # OM - \ue051 > \u0951; # STRESS SIGN UDATTA - \ue052 > \u0952; # STRESS SIGN ANUDATTA - \ue053 > \u0953; # GRAVE ACCENT - \ue054 > \u0954; # ACUTE ACCENT - \ue058 > \u0958; # LETTER QA (For Urdu) - \ue059 > \u0959; # LETTER KHHA (For Urdu) - \ue05a > \u095a; # LETTER GHHA (For Urdu) - \ue05b > \u095b; # LETTER ZA (For Urdu) - \ue05c > \u095c; # LETTER DDDHA (pronounced RRA) - \ue05d > \u095d; # LETTER RHA (pronounced RRHA) - \ue05e > \u095e; # LETTER FA - \ue05f > \u095f; # LETTER YYA - \ue060 > \u0960; # LETTER VOCALIC RR - \ue061 > \u0961; # LETTER VOCALIC LL - \ue062 > \u0962; # VOWEL SIGN VOCALIC L - \ue063 > \u0963; # VOWEL SIGN VOCALIC LL - \ue064 > \u0964; # DANDA - \ue065 > \u0965; # DOUBLE DANDA - \ue066 > \u0966; # DIGIT ZERO - \ue067 > \u0967; # DIGIT ONE - \ue068 > \u0968; # DIGIT TWO - \ue069 > \u0969; # DIGIT THREE - \ue06a > \u096a; # DIGIT FOUR - \ue06b > \u096b; # DIGIT FIVE - \ue06c > \u096c; # DIGIT SIX - \ue06d > \u096d; # DIGIT SEVEN - \ue06e > \u096e; # DIGIT EIGHT - \ue06f > \u096f; # DIGIT NINE - - \ue070>\u0970; # ABBREVIATION SIGN - \ue071>\u0930; # LETTER RA WITH MIDDLE DIAGONAL - \ue072>\u0930; # LETTER RA WITH LOWER DIAGONAL - \ue073>; # RUPEE MARK - \ue074>\u0930\u0942; # RUPEE SIGN - \ue075>; # CURRENCY NUMERATOR ONE - \ue076>; # CURRENCY NUMERATOR TWO - \ue077>; # CURRENCY NUMERATOR THREE - \ue078>; # CURRENCY NUMERATOR FOUR - \ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR - \ue07A>; # CURRENCY DENOMINATOR SIXTEEN - \ue07B>; # ISSHAR - \uE07C>; # TIPPI - \uE07D>; # ADDAK - \uE07E>; # IRI - \uE07F>; # URA - \uE080>; # EK ONKAR - \uE081>\u0935; # FALLBACK FOR ORIYA LETTER WA - \uE082>\u097d; # Devanagari Glottal Sign - \uE083>\u0924\u094d; # Bengali Khanda-ta -# \u0970 # UNMAPPED Devanagari-InterIndic: ABBREVIATION SIGN -# :: NFC; -# eof +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# +\uE028\uE03C > ऩ; #\uE029 +\uE030\uE03C > ऱ; #\uE031 +\uE033\uE03C > ऴ; #\uE034 +\uE015\uE03C > क़; #\uE058 LETTER QA (For Urdu) +\uE016\uE03C > ख़; #\uE059 LETTER KHHA (For Urdu) +\uE017\uE03C > ग़; #\uE05A LETTER GHHA (For Urdu) +\uE01C\uE03C > ज़; #\uE05B LETTER ZA (For Urdu) +\uE021\uE03C > ड़; #\uE05C LETTER DDDHA (pronounced RRA) +\uE022\uE03C > ढ़; #\uE05D LETTER RHA (pronounced RRHA) +\uE02B\uE03C > फ़; #\uE05E LETTER FA +\uE02F\uE03C > य़; #\uE05F LETTER YYA +\uE012\uE057>औ; # FALLBACK FOR TAMIL AU +0 > ०; # FALLBACK FOR TAMIL +1 > १; +\uE055>; # FALLBACK BLOW AWAY KANNADA AND TELUGU LENGTH MARK +\uE056>; # FALLBACK BLOW AWAY KANNADA AND TELUGU AI LENGTH MARK +\uE057>; # FALLBACK BLOW AWAY TAMIL AU LENGTH MARK +\uE001 > \u0901; # SIGN CANDRABINDU +\uE002 > \u0902; # SIGN ANUSVARA +\uE003 > ः; # SIGN VISARGA +\uE004 > ऄ; # SIGN SHORT A +\uE005 > अ; # LETTER A +\uE006 > आ; # LETTER AA +\uE007 > इ; # LETTER I +\uE008 > ई; # LETTER II +\uE009 > उ; # LETTER U +\uE00A > ऊ; # LETTER UU +\uE00B > ऋ; # LETTER VOCALIC R +\uE00C > ऌ; # LETTER VOCALIC L +\uE00D > ऍ; # LETTER CANDRA E (For representing English sounds) +\uE00E > ऎ; # LETTER SHORT E(For Southern Scripts) +\uE00F > ए; # LETTER E +\uE010 > ऐ; # LETTER AI +\uE011 > ऑ; # LETTER CANDRA O (For representing English sounds) +\uE012 > ऒ; # LETTER SHORT O (For Southern Scripts) +\uE013 > ओ; # LETTER O +\uE014 > औ; # LETTER AU +\uE015 > क; # LETTER KA +\uE016 > ख; # LETTER KHA +\uE017 > ग; # LETTER GA +\uE018 > घ; # LETTER GHA +\uE019 > ङ; # LETTER NGA +\uE01A > च; # LETTER CA +\uE01B > छ; # LETTER CHA +\uE01C > ज; # LETTER JA +\uE01D > झ; # LETTER JHA +\uE01E > ञ; # LETTER NYA +\uE01F > ट; # LETTER TTA +\uE020 > ठ; # LETTER TTHA +\uE021 > ड; # LETTER DDA +\uE022 > ढ; # LETTER DDHA +\uE023 > ण; # LETTER NNA +\uE024 > त; # LETTER TA +\uE025 > थ; # LETTER THA +\uE026 > द; # LETTER DA +\uE027 > ध; # LETTER DHA +\uE028 > न; # LETTER NA +\uE029 > ऩ; # LETTER NNNA +\uE02A > प; # LETTER PA +\uE02B > फ; # LETTER PHA +\uE02C > ब; # LETTER BA +\uE02D > भ; # LETTER BHA +\uE02E > म; # LETTER MA +\uE02F > य; # LETTER YA +\uE030 > र; # LETTER RA +\uE031 > ऱ; # LETTER RRA (Eyelash RA for Southern scripts) +\uE032 > ल; # LETTER LA +\uE033 > ळ; # LETTER LLA +\uE034 > ऴ; # LETTER LLLA (LLLA for Southern scripts) +\uE035 > व; # LETTER VA +\uE036 > श; # LETTER SHA +\uE037 > ष; # LETTER SSA +\uE038 > स; # LETTER SA +\uE039 > ह; # LETTER HA +\uE03C > \u093C; # SIGN NUKTA +\uE03D > ऽ; # SIGN AVAGRAHA +\uE03E > ा; # VOWEL SIGN AA +\uE03F > ि; # VOWEL SIGN I +\uE040 > ी; # VOWEL SIGN II +\uE041 > \u0941; # VOWEL SIGN U +\uE042 > \u0942; # VOWEL SIGN UU +\uE043 > \u0943; # VOWEL SIGN VOCALIC R +\uE044 > \u0944; # VOWEL SIGN VOCALIC RR +\uE045 > \u0945; # VOWEL SIGN CANDRA E +\uE046 > \u0946; # VOWEL SIGN SHORT E +\uE047 > \u0947; # VOWEL SIGN E +\uE048 > \u0948; # VOWEL SIGN AI +\uE049 > ॉ; # VOWEL SIGN CANDRA O +\uE04A > ॊ; # VOWEL SIGN SHORT O +\uE04B > ो; # VOWEL SIGN O +\uE04C > ौ; # VOWEL SIGN AU +\uE04D > \u094D; # SIGN VIRAMA +\uE050 > ॐ; # OM +\uE051 > \u0951; # STRESS SIGN UDATTA +\uE052 > \u0952; # STRESS SIGN ANUDATTA +\uE053 > \u0953; # GRAVE ACCENT +\uE054 > \u0954; # ACUTE ACCENT +\uE058 > क़; # LETTER QA (For Urdu) +\uE059 > ख़; # LETTER KHHA (For Urdu) +\uE05A > ग़; # LETTER GHHA (For Urdu) +\uE05B > ज़; # LETTER ZA (For Urdu) +\uE05C > ड़; # LETTER DDDHA (pronounced RRA) +\uE05D > ढ़; # LETTER RHA (pronounced RRHA) +\uE05E > फ़; # LETTER FA +\uE05F > य़; # LETTER YYA +\uE060 > ॠ; # LETTER VOCALIC RR +\uE061 > ॡ; # LETTER VOCALIC LL +\uE062 > \u0962; # VOWEL SIGN VOCALIC L +\uE063 > \u0963; # VOWEL SIGN VOCALIC LL +\uE064 > ।; # DANDA +\uE065 > ॥; # DOUBLE DANDA +\uE066 > ०; # DIGIT ZERO +\uE067 > १; # DIGIT ONE +\uE068 > २; # DIGIT TWO +\uE069 > ३; # DIGIT THREE +\uE06A > ४; # DIGIT FOUR +\uE06B > ५; # DIGIT FIVE +\uE06C > ६; # DIGIT SIX +\uE06D > ७; # DIGIT SEVEN +\uE06E > ८; # DIGIT EIGHT +\uE06F > ९; # DIGIT NINE +\uE070>॰; # ABBREVIATION SIGN +\uE071>र; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>र; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>र\u0942; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR +\uE07C>; # TIPPI +\uE07D>; # ADDAK +\uE07E>; # IRI +\uE07F>; # URA +\uE080>; # EK ONKAR +\uE081>व; # FALLBACK FOR ORIYA LETTER WA +\uE082>ॽ; # Devanagari Glottal Sign +\uE083>त\u094D; # Bengali Khanda-ta diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Gujarati.txt index 277e3dff44d..14063c22219 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Gujarati.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Gujarati.txt @@ -1,140 +1,138 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Gujarati -#:: NFD (NFC) ; -\ue001>\u0a81; # SIGN CANDRABINDU -\ue002>\u0a82; # SIGN ANUSVARA -\ue003>\u0a83; # SIGN VISARGA -\uE004>\u0a85; # FALLBACK TO LETTER A -\ue005>\u0a85; # LETTER A -\ue006>\u0a86; # LETTER AA -\ue007>\u0a87; # LETTER I -\ue008>\u0a88; # LETTER II -\ue009>\u0a89; # LETTER U -\ue00a>\u0a8a; # LETTER UU -\ue00b>\u0a8b; # LETTER VOCALIC R -\ue00c>\u0a8c; # LETTER VOCALIC L -\ue00d>\u0a8d; # GUJARATI VOWEL CANDRA E -\ue00e>\u0a8f; # FALLBACK -\ue00f>\u0a8f; # InterIndic-Gujarati: LETTER EE (\u0a8f = LETTER E) -\ue010>\u0a90; # LETTER AI -\ue011>\u0a91; # FALLBACK -\ue012>\u0a93; # FALLBACK -\ue013>\u0a93; # UNMAPPED InterIndic-Gujarati: LETTER OO (\u0a93 = LETTER O) -\ue014>\u0a94; # LETTER AU -\ue015>\u0a95; # LETTER KA -\ue016>\u0a96; # LETTER KHA -\ue017>\u0a97; # LETTER GA -\ue018>\u0a98; # LETTER GHA -\ue019>\u0a99; # LETTER NGA -\ue01a>\u0a9a; # LETTER CA -\ue01b>\u0a9b; # LETTER CHA -\ue01c>\u0a9c; # LETTER JA -\ue01d>\u0a9d; # LETTER JHA -\ue01e>\u0a9e; # LETTER NYA -\ue01f>\u0a9f; # LETTER TTA -\ue020>\u0aa0; # LETTER TTHA -\ue021>\u0aa1; # LETTER DDA -\ue022>\u0aa2; # LETTER DDHA -\ue023>\u0aa3; # LETTER NNA -\ue024>\u0aa4; # LETTER TA -\ue025>\u0aa5; # LETTER THA -\ue026>\u0aa6; # LETTER DA -\ue027>\u0aa7; # LETTER DHA -\ue028>\u0aa8; # LETTER NA -\ue029>\u0aa8\u0abc; # FALLBACK to NA+NUKTA -\ue02a>\u0aaa; # LETTER PA -\ue02b>\u0aab; # LETTER PHA -\ue02c>\u0aac; # LETTER BA -\ue02d>\u0aad; # LETTER BHA -\ue02e>\u0aae; # LETTER MA -\ue02f>\u0aaf; # LETTER YA -\ue030>\u0ab0; # LETTER RA -\ue031>\u0ab0\u0abc; # FALLBACK -\ue032>\u0ab2; # LETTER LA -\ue033>\u0ab3; # LETTER LLA -\ue034>\u0ab3\u0abc; # LETTER LLLA>LETTER LLA+NUKTA -\ue035>\u0ab5; # LETTER VA -\ue036>\u0ab6; # LETTER SHA -\ue037>\u0ab7; # LETTER SSA -\ue038>\u0ab8; # LETTER SA -\ue039>\u0ab9; # LETTER HA -\ue03c>\u0abc; # SIGN NUKTA -\ue03d>\u0abd; # SIGN AVAGRAHA -\ue03e>\u0abe; # VOWEL SIGN AA -\ue03f>\u0abf; # VOWEL SIGN I -\ue040>\u0ac0; # VOWEL SIGN II -\ue041>\u0ac1; # VOWEL SIGN U -\ue042>\u0ac2; # VOWEL SIGN UU -\ue043>\u0ac3; # VOWEL SIGN VOCALIC R -\ue044>\u0ac4; # VOWEL SIGN VOCALIC RR -\ue045>\u0ac5; # VOWEL SIGN CANDRA E -\ue046>\u0ac7; # FALLBACK -\ue047>\u0ac7; # InterIndic-Gujarati: VOWEL SIGN EE (\u0ac7 = VOWEL SIGN E) -\ue048>\u0ac8; # VOWEL SIGN AI -\ue049>\u0ac9; # VOWEL SIGN CANDRA O -\ue04a>\u0acb; # FALLBACK -\ue04b>\u0acb; # UNMAPPED InterIndic-Gujarati: VOWEL SIGN OO (\u0acb = VOWEL SIGN O) -\ue04c>\u0acc; # VOWEL SIGN AU -\ue04d>\u0acd; # SIGN VIRAMA -\ue050>\u0ad0; # OM -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>; # UNMAPPED InterIndic-Gujarati: LENGTH MARK -\ue056>\u0ac8; # REMAP (indicExceptions.txt): \u0ad6>\u0ac8 = AI LENGTH MARK>VOWEL SIGN AI -\ue057>\u0acc; # REMAP (indicExceptions.txt): \u0ad7>\u0acc = AU LENGTH MARK>VOWEL SIGN AU -\ue058>\u0a95\u0abc; # FALLBACK -\ue059>\u0a96\u0abc; # REMAP (indicExceptions.txt): \u0ad9>\u0a96\u0abc = LETTER KHHA>LETTER KHA.SIGN NUKTA -\ue05a>\u0a97\u0abc; # REMAP (indicExceptions.txt): \u0ada>\u0a97\u0abc = LETTER GHHA>LETTER GA.SIGN NUKTA -\ue05b>\u0a9c\u0abc; # REMAP (indicExceptions.txt): \u0adb>\u0a9c\u0abc = LETTER ZA>LETTER JA.SIGN NUKTA -\ue05c>\u0aa1\u0abc; # FALLBACK -\ue05d>\u0aa2\u0abc; # REMAP (indicExceptions.txt): \u0add>\u0aa2\u0abc = LETTER RHA>LETTER DDHA.SIGN NUKTA -\ue05e>\u0aab\u0abc; # REMAP (indicExceptions.txt): \u0ade>\u0aab\u0abc = LETTER FA>LETTER PHA.SIGN NUKTA -\ue05f>\u0aaf\u0abc; # REMAP (indicExceptions.txt): \u0adf>\u0aaf\u0abc = LETTER YYA>LETTER YA.SIGN NUKTA -\ue060>\u0ae0; # LETTER VOCALIC RR -\ue061>\u0ae1; # LETTER VOCALIC LL -\ue062>\u0abf\u0abc; # REMAP (indicExceptions.txt): \u0ae2>\u0abf\u0abc = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA -\ue063>\u0ac0\u0abc; # REMAP (indicExceptions.txt): \u0ae3>\u0ac0\u0abc = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA -\uE064>\u0964; # DANDA -\uE065>\u0965; # DOUBLE DANDA -\ue066>\u0ae6; # DIGIT ZERO -\ue067>\u0ae7; # DIGIT ONE -\ue068>\u0ae8; # DIGIT TWO -\ue069>\u0ae9; # DIGIT THREE -\ue06a>\u0aea; # DIGIT FOUR -\ue06b>\u0aeb; # DIGIT FIVE -\ue06c>\u0aec; # DIGIT SIX -\ue06d>\u0aed; # DIGIT SEVEN -\ue06e>\u0aee; # DIGIT EIGHT -\ue06f>\u0aef; # DIGIT NINE -\ue070>; # ABBREVIATION SIGN -\ue071>\u0ab0; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0ab0; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>; # ISSHAR +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\uE001>\u0A81; # SIGN CANDRABINDU +\uE002>\u0A82; # SIGN ANUSVARA +\uE003>ઃ; # SIGN VISARGA +\uE004>અ; # FALLBACK TO LETTER A +\uE005>અ; # LETTER A +\uE006>આ; # LETTER AA +\uE007>ઇ; # LETTER I +\uE008>ઈ; # LETTER II +\uE009>ઉ; # LETTER U +\uE00A>ઊ; # LETTER UU +\uE00B>ઋ; # LETTER VOCALIC R +\uE00C>ઌ; # LETTER VOCALIC L +\uE00D>ઍ; # GUJARATI VOWEL CANDRA E +\uE00E>એ; # FALLBACK +\uE00F>એ; # InterIndic-Gujarati: LETTER EE (એ = LETTER E) +\uE010>ઐ; # LETTER AI +\uE011>ઑ; # FALLBACK +\uE012>ઓ; # FALLBACK +\uE013>ઓ; # UNMAPPED InterIndic-Gujarati: LETTER OO (ઓ = LETTER O) +\uE014>ઔ; # LETTER AU +\uE015>ક; # LETTER KA +\uE016>ખ; # LETTER KHA +\uE017>ગ; # LETTER GA +\uE018>ઘ; # LETTER GHA +\uE019>ઙ; # LETTER NGA +\uE01A>ચ; # LETTER CA +\uE01B>છ; # LETTER CHA +\uE01C>જ; # LETTER JA +\uE01D>ઝ; # LETTER JHA +\uE01E>ઞ; # LETTER NYA +\uE01F>ટ; # LETTER TTA +\uE020>ઠ; # LETTER TTHA +\uE021>ડ; # LETTER DDA +\uE022>ઢ; # LETTER DDHA +\uE023>ણ; # LETTER NNA +\uE024>ત; # LETTER TA +\uE025>થ; # LETTER THA +\uE026>દ; # LETTER DA +\uE027>ધ; # LETTER DHA +\uE028>ન; # LETTER NA +\uE029>ન\u0ABC; # FALLBACK to NA+NUKTA +\uE02A>પ; # LETTER PA +\uE02B>ફ; # LETTER PHA +\uE02C>બ; # LETTER BA +\uE02D>ભ; # LETTER BHA +\uE02E>મ; # LETTER MA +\uE02F>ય; # LETTER YA +\uE030>ર; # LETTER RA +\uE031>ર\u0ABC; # FALLBACK +\uE032>લ; # LETTER LA +\uE033>ળ; # LETTER LLA +\uE034>ળ\u0ABC; # LETTER LLLA>LETTER LLA+NUKTA +\uE035>વ; # LETTER VA +\uE036>શ; # LETTER SHA +\uE037>ષ; # LETTER SSA +\uE038>સ; # LETTER SA +\uE039>હ; # LETTER HA +\uE03C>\u0ABC; # SIGN NUKTA +\uE03D>ઽ; # SIGN AVAGRAHA +\uE03E>ા; # VOWEL SIGN AA +\uE03F>િ; # VOWEL SIGN I +\uE040>ી; # VOWEL SIGN II +\uE041>\u0AC1; # VOWEL SIGN U +\uE042>\u0AC2; # VOWEL SIGN UU +\uE043>\u0AC3; # VOWEL SIGN VOCALIC R +\uE044>\u0AC4; # VOWEL SIGN VOCALIC RR +\uE045>\u0AC5; # VOWEL SIGN CANDRA E +\uE046>\u0AC7; # FALLBACK +\uE047>\u0AC7; # InterIndic-Gujarati: VOWEL SIGN EE (\u0AC7 = VOWEL SIGN E) +\uE048>\u0AC8; # VOWEL SIGN AI +\uE049>ૉ; # VOWEL SIGN CANDRA O +\uE04A>ો; # FALLBACK +\uE04B>ો; # UNMAPPED InterIndic-Gujarati: VOWEL SIGN OO (ો = VOWEL SIGN O) +\uE04C>ૌ; # VOWEL SIGN AU +\uE04D>\u0ACD; # SIGN VIRAMA +\uE050>ૐ; # OM +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>; # UNMAPPED InterIndic-Gujarati: LENGTH MARK +\uE056>\u0AC8; # REMAP (indicExceptions.txt): \u0AD6>\u0AC8 = AI LENGTH MARK>VOWEL SIGN AI +\uE057>ૌ; # REMAP (indicExceptions.txt): \u0AD7>ૌ = AU LENGTH MARK>VOWEL SIGN AU +\uE058>ક\u0ABC; # FALLBACK +\uE059>ખ\u0ABC; # REMAP (indicExceptions.txt): \u0AD9>ખ\u0ABC = LETTER KHHA>LETTER KHA.SIGN NUKTA +\uE05A>ગ\u0ABC; # REMAP (indicExceptions.txt): \u0ADA>ગ\u0ABC = LETTER GHHA>LETTER GA.SIGN NUKTA +\uE05B>જ\u0ABC; # REMAP (indicExceptions.txt): \u0ADB>જ\u0ABC = LETTER ZA>LETTER JA.SIGN NUKTA +\uE05C>ડ\u0ABC; # FALLBACK +\uE05D>ઢ\u0ABC; # REMAP (indicExceptions.txt): \u0ADD>ઢ\u0ABC = LETTER RHA>LETTER DDHA.SIGN NUKTA +\uE05E>ફ\u0ABC; # REMAP (indicExceptions.txt): \u0ADE>ફ\u0ABC = LETTER FA>LETTER PHA.SIGN NUKTA +\uE05F>ય\u0ABC; # REMAP (indicExceptions.txt): \u0ADF>ય\u0ABC = LETTER YYA>LETTER YA.SIGN NUKTA +\uE060>ૠ; # LETTER VOCALIC RR +\uE061>ૡ; # LETTER VOCALIC LL +\uE062>િ\u0ABC; # REMAP (indicExceptions.txt): \u0AE2>િ\u0ABC = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA +\uE063>ી\u0ABC; # REMAP (indicExceptions.txt): \u0AE3>ી\u0ABC = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA +\uE064>।; # DANDA +\uE065>॥; # DOUBLE DANDA +\uE066>૦; # DIGIT ZERO +\uE067>૧; # DIGIT ONE +\uE068>૨; # DIGIT TWO +\uE069>૩; # DIGIT THREE +\uE06A>૪; # DIGIT FOUR +\uE06B>૫; # DIGIT FIVE +\uE06C>૬; # DIGIT SIX +\uE06D>૭; # DIGIT SEVEN +\uE06E>૮; # DIGIT EIGHT +\uE06F>૯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ર; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ર; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u0ab5; # FALLBACK FOR ORIYA LETTER WA +\uE081>વ; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0aa4\u0acd; # Bengali Khanda-ta -0 > \u0ae6; # FALLBACK FOR TAMIL -1 > \u0ae7; - -#\ue080>; # UNMAPPED InterIndic-Gujarati: ISSHAR -# :: NFC (NFD) ; -# eof +\uE083>ત\u0ACD; # Bengali Khanda-ta +0 > ૦; # FALLBACK FOR TAMIL +1 > ૧; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Gurmukhi.txt index 686e30118fd..81c35314cc3 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Gurmukhi.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Gurmukhi.txt @@ -1,149 +1,142 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Gurmukhi -#:: NFD (NFC) ; -$vowel = [\u0A05-\u0A14 \u0A3e-\u0A4D]; -$consonant = [\u0A15-\u0A39]; - -\ue001>\u0a01; # SIGN CHANDRABINDU -#rules for BINDI - -# Anusvara is equivalent to BINDI when preceeded by a vowel -$vowel{\ue002>\u0a02; # SIGN ANUSVARA (\u0a02 = SIGN BINDI) -# else is equivalent to TIPPI -$consonant{\ue002>\u0a70; # SIGN TIPPI -\ue002>\u0a02; - -\ue003>; # FALLBACK BLOW AWAY SIGN VISARGA -\uE004>\u0a05; # FALLBACK TO LETTER A -\ue005>\u0a05; # LETTER A -\ue006>\u0a06; # LETTER AA -\ue007>\u0a07; # LETTER I -\ue008>\u0a08; # LETTER II -\ue009>\u0a09; # LETTER U -\ue00a>\u0a0a; # LETTER UU -\ue00b>\u0a30\u0a3f; # REMAP (indicExceptions.txt): \u0a0b>\u0a30\u0a3f = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I -\ue00c>\u0a33; # FALLBACK -\ue00d>\u0a0f; # FALLBACK -\ue00e>\u0a0f; # FALLBACK -\ue00f>\u0a0f; # LETTER EE -\ue010>\u0a10; # LETTER AI -\ue011>\u0a13; # FALLBACK -\ue012>\u0a13; # FALLBACK -\ue013>\u0a13; # LETTER OO -\ue014>\u0a14; # LETTER AU -\ue015>\u0a15; # LETTER KA -\ue016>\u0a16; # LETTER KHA -\ue017>\u0a17; # LETTER GA -\ue018>\u0a18; # LETTER GHA -\ue019>\u0a19; # LETTER NGA -\ue01a>\u0a1a; # LETTER CA -\ue01b>\u0a1b; # LETTER CHA -\ue01c>\u0a1c; # LETTER JA -\ue01d>\u0a1d; # LETTER JHA -\ue01e>\u0a1e; # LETTER NYA -\ue01f>\u0a1f; # LETTER TTA -\ue020>\u0a20; # LETTER TTHA -\ue021>\u0a21; # LETTER DDA -\ue022>\u0a22; # LETTER DDHA -\ue023>\u0a23; # LETTER NNA -\ue024>\u0a24; # LETTER TA -\ue025>\u0a25; # LETTER THA -\ue026>\u0a26; # LETTER DA -\ue027>\u0a27; # LETTER DHA -\ue028>\u0a28; # LETTER NA -\ue029>\u0a28\u0a3c; # REMAP (indicExceptions.txt): \u0a29>\u0a28 = LETTER NNNA>LETTER NA -\ue02a>\u0a2a; # LETTER PA -\ue02b>\u0a2b; # LETTER PHA -\ue02c>\u0a2c; # LETTER BA -\ue02d>\u0a2d; # LETTER BHA -\ue02e>\u0a2e; # LETTER MA -\ue02f>\u0a2f; # LETTER YA -\ue030>\u0a30; # LETTER RA -\ue031>\u0a30\u0a3c; # FALLBACK LETTER RA+NUKTA -\ue032>\u0a32; # LETTER LA -\ue033>\u0a32; # LETTER LLA -\ue034>\u0a33; # REMAP (indicExceptions.txt): \u0a34>\u0a33 = LETTER LLLA>LETTER LLA -\ue035>\u0a35; # LETTER VA -\ue036>\u0a36; # LETTER SHA -\ue037>\u0a36; # REMAP (indicExceptions.txt): \u0a37>\u0a36 = LETTER SSA>LETTER SHA -\ue038>\u0a38; # LETTER SA -\ue039>\u0a39; # LETTER HA -\ue03c>\u0a3c; # SIGN NUKTA -\ue03d>; # FALLBACK BLOW AWAY SIGN AVAGRAHA -\ue03e>\u0a3e; # VOWEL SIGN AA -\ue03f>\u0a3f; # VOWEL SIGN I -\ue040>\u0a40; # VOWEL SIGN II -\ue041>\u0a41; # VOWEL SIGN U -\ue042>\u0a42; # VOWEL SIGN UU -\ue043>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC R -\ue044>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC RR -\ue045>\u0a48; # REMAP (indicExceptions.txt): \u0a45>\u0a48 = VOWEL SIGN CANDRA E>VOWEL SIGN AI -\ue046>\u0a47; # FALLABCK -\ue047>\u0a47; # VOWEL SIGN EE -\ue048>\u0a48; # VOWEL SIGN AI -\ue049>\u0a4c; # REMAP (indicExceptions.txt): \u0a49>\u0a4c = VOWEL SIGN CANDRA O>VOWEL SIGN AU -\ue04a>\u0a4b; # FALLBACK -\ue04b>\u0a4b; # VOWEL SIGN OO -\ue04c>\u0a4c; # VOWEL SIGN AU -\ue04d>\u0a4d; # SIGN VIRAMA -\ue050>\u0a0f\u0a02; # FALLBACK to OO+BINDI : OM -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>; # FALLBACK BLOW AWAY LENGTH MARK -\ue056>\u0a48; # REMAP (indicExceptions.txt): \u0a56>\u0a48 = AI LENGTH MARK>VOWEL SIGN AI -\ue057>\u0a4c; # REMAP (indicExceptions.txt): \u0a57>\u0a4c = AU LENGTH MARK>VOWEL SIGN AU -\ue058>\u0a15\u0a3c; # FALLBACK RA+ NUKTA -\ue059>\u0a59; # LETTER KHHA -\ue05a>\u0a5a; # LETTER GHHA -\ue05b>\u0a5b; # LETTER ZA -\ue05c>\u0a5c; # LETTER RRA -\ue05d>\u0a22\u0a3c; # REMAP (indicExceptions.txt): \u0a5d>\u0a22\u0a3c = LETTER RHA>LETTER DDHA.SIGN NUKTA -\ue05e>\u0a5e; # LETTER FA -\ue05f>\u0a2f\u0a3c; # REMAP (indicExceptions.txt): \u0a5f>\u0a2f = LETTER YYA>LETTER YA -\ue060>\u0a30\u0a3f; # REMAP (indicExceptions.txt): \u0a60>\u0a30\u0a3f = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I -\ue061>\u0a32\u0a3c; # -\ue062>\u0a3f\u0a3c; # REMAP (indicExceptions.txt): \u0a62>\u0a3f\u0a3c = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA -\ue063>\u0a40\u0a3c; # REMAP (indicExceptions.txt): \u0a63>\u0a40\u0a3c = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA -\uE064>\u0964; # DANDA -\uE065>\u0965; # DOUBLE DANDA -\ue066>\u0a66; # DIGIT ZERO -\ue067>\u0a67; # DIGIT ONE -\ue068>\u0a68; # DIGIT TWO -\ue069>\u0a69; # DIGIT THREE -\ue06a>\u0a6a; # DIGIT FOUR -\ue06b>\u0a6b; # DIGIT FIVE -\ue06c>\u0a6c; # DIGIT SIX -\ue06d>\u0a6d; # DIGIT SEVEN -\ue06e>\u0a6e; # DIGIT EIGHT -\ue06f>\u0a6f; # DIGIT NINE -\ue070>; # ABBREVIATION SIGN -\ue071>\u0a30; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0a30; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>; # ISSHAR -\uE07C>\u0a70; # TIPPI -\uE07D>\u0a71; # ADDAK -\uE07E>\u0a72; # IRI -\uE07F>\u0a73; # URA -\uE080>\u0a74; # EK ONKAR -\uE081>\u0a35; # FALLBACK FOR ORIYA LETTER WA +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +$vowel = [ਅ-ਔ ਾ-\u0A4D]; +$consonant = [ਕ-ਹ]; +\uE001>\u0A01; # SIGN CHANDRABINDU +$vowel{\uE002>\u0A02; # SIGN ANUSVARA (\u0A02 = SIGN BINDI) +$consonant{\uE002>\u0A70; # SIGN TIPPI +\uE002>\u0A02; +\uE003>; # FALLBACK BLOW AWAY SIGN VISARGA +\uE004>ਅ; # FALLBACK TO LETTER A +\uE005>ਅ; # LETTER A +\uE006>ਆ; # LETTER AA +\uE007>ਇ; # LETTER I +\uE008>ਈ; # LETTER II +\uE009>ਉ; # LETTER U +\uE00A>ਊ; # LETTER UU +\uE00B>ਰਿ; # REMAP (indicExceptions.txt): \u0A0B>ਰਿ = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I +\uE00C>ਲ਼; # FALLBACK +\uE00D>ਏ; # FALLBACK +\uE00E>ਏ; # FALLBACK +\uE00F>ਏ; # LETTER EE +\uE010>ਐ; # LETTER AI +\uE011>ਓ; # FALLBACK +\uE012>ਓ; # FALLBACK +\uE013>ਓ; # LETTER OO +\uE014>ਔ; # LETTER AU +\uE015>ਕ; # LETTER KA +\uE016>ਖ; # LETTER KHA +\uE017>ਗ; # LETTER GA +\uE018>ਘ; # LETTER GHA +\uE019>ਙ; # LETTER NGA +\uE01A>ਚ; # LETTER CA +\uE01B>ਛ; # LETTER CHA +\uE01C>ਜ; # LETTER JA +\uE01D>ਝ; # LETTER JHA +\uE01E>ਞ; # LETTER NYA +\uE01F>ਟ; # LETTER TTA +\uE020>ਠ; # LETTER TTHA +\uE021>ਡ; # LETTER DDA +\uE022>ਢ; # LETTER DDHA +\uE023>ਣ; # LETTER NNA +\uE024>ਤ; # LETTER TA +\uE025>ਥ; # LETTER THA +\uE026>ਦ; # LETTER DA +\uE027>ਧ; # LETTER DHA +\uE028>ਨ; # LETTER NA +\uE029>ਨ\u0A3C; # REMAP (indicExceptions.txt): \u0A29>ਨ = LETTER NNNA>LETTER NA +\uE02A>ਪ; # LETTER PA +\uE02B>ਫ; # LETTER PHA +\uE02C>ਬ; # LETTER BA +\uE02D>ਭ; # LETTER BHA +\uE02E>ਮ; # LETTER MA +\uE02F>ਯ; # LETTER YA +\uE030>ਰ; # LETTER RA +\uE031>ਰ\u0A3C; # FALLBACK LETTER RA+NUKTA +\uE032>ਲ; # LETTER LA +\uE033>ਲ; # LETTER LLA +\uE034>ਲ਼; # REMAP (indicExceptions.txt): \u0A34>ਲ਼ = LETTER LLLA>LETTER LLA +\uE035>ਵ; # LETTER VA +\uE036>ਸ਼; # LETTER SHA +\uE037>ਸ਼; # REMAP (indicExceptions.txt): \u0A37>ਸ਼ = LETTER SSA>LETTER SHA +\uE038>ਸ; # LETTER SA +\uE039>ਹ; # LETTER HA +\uE03C>\u0A3C; # SIGN NUKTA +\uE03D>; # FALLBACK BLOW AWAY SIGN AVAGRAHA +\uE03E>ਾ; # VOWEL SIGN AA +\uE03F>ਿ; # VOWEL SIGN I +\uE040>ੀ; # VOWEL SIGN II +\uE041>\u0A41; # VOWEL SIGN U +\uE042>\u0A42; # VOWEL SIGN UU +\uE043>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC R +\uE044>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC RR +\uE045>\u0A48; # REMAP (indicExceptions.txt): \u0A45>\u0A48 = VOWEL SIGN CANDRA E>VOWEL SIGN AI +\uE046>\u0A47; # FALLABCK +\uE047>\u0A47; # VOWEL SIGN EE +\uE048>\u0A48; # VOWEL SIGN AI +\uE049>\u0A4C; # REMAP (indicExceptions.txt): \u0A49>\u0A4C = VOWEL SIGN CANDRA O>VOWEL SIGN AU +\uE04A>\u0A4B; # FALLBACK +\uE04B>\u0A4B; # VOWEL SIGN OO +\uE04C>\u0A4C; # VOWEL SIGN AU +\uE04D>\u0A4D; # SIGN VIRAMA +\uE050>ਏ\u0A02; # FALLBACK to OO+BINDI : OM +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>; # FALLBACK BLOW AWAY LENGTH MARK +\uE056>\u0A48; # REMAP (indicExceptions.txt): \u0A56>\u0A48 = AI LENGTH MARK>VOWEL SIGN AI +\uE057>\u0A4C; # REMAP (indicExceptions.txt): \u0A57>\u0A4C = AU LENGTH MARK>VOWEL SIGN AU +\uE058>ਕ\u0A3C; # FALLBACK RA+ NUKTA +\uE059>ਖ਼; # LETTER KHHA +\uE05A>ਗ਼; # LETTER GHHA +\uE05B>ਜ਼; # LETTER ZA +\uE05C>ੜ; # LETTER RRA +\uE05D>ਢ\u0A3C; # REMAP (indicExceptions.txt): \u0A5D>ਢ\u0A3C = LETTER RHA>LETTER DDHA.SIGN NUKTA +\uE05E>ਫ਼; # LETTER FA +\uE05F>ਯ\u0A3C; # REMAP (indicExceptions.txt): \u0A5F>ਯ = LETTER YYA>LETTER YA +\uE060>ਰਿ; # REMAP (indicExceptions.txt): \u0A60>ਰਿ = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I +\uE061>ਲ\u0A3C; # +\uE062>ਿ\u0A3C; # REMAP (indicExceptions.txt): \u0A62>ਿ\u0A3C = VOWEL SIGN VOCALIC L>VOWEL SIGN I.SIGN NUKTA +\uE063>ੀ\u0A3C; # REMAP (indicExceptions.txt): \u0A63>ੀ\u0A3C = VOWEL SIGN VOCALIC LL>VOWEL SIGN II.SIGN NUKTA +\uE064>।; # DANDA +\uE065>॥; # DOUBLE DANDA +\uE066>੦; # DIGIT ZERO +\uE067>੧; # DIGIT ONE +\uE068>੨; # DIGIT TWO +\uE069>੩; # DIGIT THREE +\uE06A>੪; # DIGIT FOUR +\uE06B>੫; # DIGIT FIVE +\uE06C>੬; # DIGIT SIX +\uE06D>੭; # DIGIT SEVEN +\uE06E>੮; # DIGIT EIGHT +\uE06F>੯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ਰ; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ਰ; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR +\uE07C>\u0A70; # TIPPI +\uE07D>\u0A71; # ADDAK +\uE07E>ੲ; # IRI +\uE07F>ੳ; # URA +\uE080>ੴ; # EK ONKAR +\uE081>ਵ; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0a24\u0a4d; # Bengali Khanda-ta - -0 > \u0a66; # FALLBACK FOR TAMIL -1 > \u0a67; -# :: NFC (NFD) ; -# eof +\uE083>ਤ\u0A4D; # Bengali Khanda-ta +0 > ੦; # FALLBACK FOR TAMIL +1 > ੧; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Kannada.txt index 9ed3619c735..92a8d141d1f 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Kannada.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Kannada.txt @@ -1,143 +1,140 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Kannada -#:: NFD (NFC) ; -\ue033\ue03c>\u0cde; # LETTER FA -\ue001>\u0c82; # REMAP (indicExceptions.txt): \u0c81>\u0c82 = SIGN CANDRABINDU>SIGN ANUSVARA -\ue002>\u0c82; # SIGN ANUSVARA -\ue003>\u0c83; # SIGN VISARGA -\uE004>\u0c85; # FALLBACK TO LETTER A -\ue005>\u0c85; # LETTER A -\ue006>\u0c86; # LETTER AA -\ue007>\u0c87; # LETTER I -\ue008>\u0c88; # LETTER II -\ue009>\u0c89; # LETTER U -\ue00a>\u0c8a; # LETTER UU -\ue00b>\u0c8b; # LETTER VOCALIC R -\ue00c>\u0c8c; # LETTER VOCALIC L -\ue00d>\u0c8e; # LETTER E -\ue00e>\u0c8e; # FALLBACK -\ue00f>\u0c8f; # LETTER EE -\ue010>\u0c90; # LETTER AI -\ue011>\u0c92; # FALLBACK -\ue012>\u0c92; # LETTER O -\ue013>\u0c93; # LETTER OO -\ue014>\u0c94; # LETTER AU -\ue015>\u0c95; # LETTER KA -\ue016>\u0c96; # LETTER KHA -\ue017>\u0c97; # LETTER GA -\ue018>\u0c98; # LETTER GHA -\ue019>\u0c99; # LETTER NGA -\ue01a>\u0c9a; # LETTER CA -\ue01b>\u0c9b; # LETTER CHA -\ue01c>\u0c9c; # LETTER JA -\ue01d>\u0c9d; # LETTER JHA -\ue01e>\u0c9e; # LETTER NYA -\ue01f>\u0c9f; # LETTER TTA -\ue020>\u0ca0; # LETTER TTHA -\ue021>\u0ca1; # LETTER DDA -\ue022>\u0ca2; # LETTER DDHA -\ue023>\u0ca3; # LETTER NNA -\ue024>\u0ca4; # LETTER TA -\ue025>\u0ca5; # LETTER THA -\ue026>\u0ca6; # LETTER DA -\ue027>\u0ca7; # LETTER DHA -\ue028>\u0ca8; # LETTER NA -\ue029>\u0ca8; # REMAP (indicExceptions.txt): \u0ca9>\u0ca8 = LETTER NNNA>LETTER NA -\ue02a>\u0caa; # LETTER PA -\ue02b>\u0cab; # LETTER PHA -\ue02c>\u0cac; # LETTER BA -\ue02d>\u0cad; # LETTER BHA -\ue02e>\u0cae; # LETTER MA -\ue02f>\u0caf; # LETTER YA -\ue030\ue03c>\u0cb1; -\ue030>\u0cb0; # LETTER RA -\ue031>\u0cb1; # LETTER RRA -\ue032>\u0cb2; # LETTER LA -\ue033>\u0cb3; # LETTER LLA -\ue034>\u0cde; # REMAP (indicExceptions.txt): \u0cb4>\u0cb3 = LETTER LLLA>LETTER LLA -\ue035>\u0cb5; # LETTER VA -\ue036>\u0cb6; # LETTER SHA -\ue037>\u0cb7; # LETTER SSA -\ue038>\u0cb8; # LETTER SA -\ue039>\u0cb9; # LETTER HA - -\ue03c>\u0cbc; # NUKTA -\ue03d>\u0cbd; # AVAGRAHA - -\ue03e>\u0cbe; # VOWEL SIGN AA -\ue03f>\u0cbf; # VOWEL SIGN I -\ue040>\u0cc0; # VOWEL SIGN II -\ue041>\u0cc1; # VOWEL SIGN U -\ue042>\u0cc2; # VOWEL SIGN UU -\ue043>\u0cc3; # VOWEL SIGN VOCALIC R -\ue044>\u0cc4; # VOWEL SIGN VOCALIC RR -\ue045>\u0cc6; # REMAP (indicExceptions.txt): \u0cc5>\u0cc6 = VOWEL SIGN CANDRA E>VOWEL SIGN E -\ue046>\u0cc6; # VOWEL SIGN E -\ue047>\u0cc7; # VOWEL SIGN EE -\ue048>\u0cc8; # VOWEL SIGN AI -\ue049>\u0cca; # REMAP (indicExceptions.txt): \u0cc9>\u0cca = VOWEL SIGN CANDRA O>VOWEL SIGN O -\ue04a>\u0cca; # VOWEL SIGN O -\ue04b>\u0ccb; # VOWEL SIGN OO -\ue04c>\u0ccc; # VOWEL SIGN AU -\ue04d>\u0ccd; # SIGN VIRAMA -\ue050>\u0c93\u0c82; # REMAP (indicExceptions.txt): \u0cd0>\u0c93\u0c82 = OM>LETTER OO.SIGN ANUSVARA -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>\u0cd5; # LENGTH MARK -\ue056>\u0cd6; # AI LENGTH MARK -\ue057>\u0ccc; # REMAP (indicExceptions.txt): \u0cd7>\u0ccc = AU LENGTH MARK>VOWEL SIGN AU -\ue058>\u0c95; # FALLBACK -\ue059>\u0c96; # REMAP (indicExceptions.txt): \u0cd9>\u0c96 = LETTER KHHA>LETTER KHA -\ue05a>\u0c97; # REMAP (indicExceptions.txt): \u0cda>\u0c97 = LETTER GHHA>LETTER GA -\ue05b>\u0c9c; # REMAP (indicExceptions.txt): \u0cdb>\u0c9c = LETTER ZA>LETTER JA -\ue05c>\u0ca2; # FALLBACK -\ue05d>\u0ca2; # REMAP (indicExceptions.txt): \u0cdd>\u0ca2 = LETTER RHA>LETTER DDHA -\ue05e>\u0cde; # LETTER FA -\ue05f>\u0caf; # REMAP (indicExceptions.txt): \u0cdf>\u0caf = LETTER YYA>LETTER YA -\ue060>\u0ce0; # LETTER VOCALIC RR -\ue061>\u0ce1; # LETTER VOCALIC LL -\ue062>\u0cbf; # REMAP (indicExceptions.txt): \u0ce2>\u0cbf = VOWEL SIGN VOCALIC L>VOWEL SIGN I -\ue063>\u0cc0; # REMAP (indicExceptions.txt): \u0ce3>\u0cc0 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II -\ue064>'.' ; # FALLBACK FOR DANDA -\ue065>'.' ; # FALLBACK FOR DOUBLE DANDA -\ue066>\u0ce6; # DIGIT ZERO -\ue067>\u0ce7; # DIGIT ONE -\ue068>\u0ce8; # DIGIT TWO -\ue069>\u0ce9; # DIGIT THREE -\ue06a>\u0cea; # DIGIT FOUR -\ue06b>\u0ceb; # DIGIT FIVE -\ue06c>\u0cec; # DIGIT SIX -\ue06d>\u0ced; # DIGIT SEVEN -\ue06e>\u0cee; # DIGIT EIGHT -\ue06f>\u0cef; # DIGIT NINE -\ue070>; # ABBREVIATION SIGN -\ue071>\u0cb0; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0cb0; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>; # ISSHAR +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\uE033\uE03C>ೞ; # LETTER FA +\uE001>ಂ; # REMAP (indicExceptions.txt): \u0C81>ಂ = SIGN CANDRABINDU>SIGN ANUSVARA +\uE002>ಂ; # SIGN ANUSVARA +\uE003>ಃ; # SIGN VISARGA +\uE004>ಅ; # FALLBACK TO LETTER A +\uE005>ಅ; # LETTER A +\uE006>ಆ; # LETTER AA +\uE007>ಇ; # LETTER I +\uE008>ಈ; # LETTER II +\uE009>ಉ; # LETTER U +\uE00A>ಊ; # LETTER UU +\uE00B>ಋ; # LETTER VOCALIC R +\uE00C>ಌ; # LETTER VOCALIC L +\uE00D>ಎ; # LETTER E +\uE00E>ಎ; # FALLBACK +\uE00F>ಏ; # LETTER EE +\uE010>ಐ; # LETTER AI +\uE011>ಒ; # FALLBACK +\uE012>ಒ; # LETTER O +\uE013>ಓ; # LETTER OO +\uE014>ಔ; # LETTER AU +\uE015>ಕ; # LETTER KA +\uE016>ಖ; # LETTER KHA +\uE017>ಗ; # LETTER GA +\uE018>ಘ; # LETTER GHA +\uE019>ಙ; # LETTER NGA +\uE01A>ಚ; # LETTER CA +\uE01B>ಛ; # LETTER CHA +\uE01C>ಜ; # LETTER JA +\uE01D>ಝ; # LETTER JHA +\uE01E>ಞ; # LETTER NYA +\uE01F>ಟ; # LETTER TTA +\uE020>ಠ; # LETTER TTHA +\uE021>ಡ; # LETTER DDA +\uE022>ಢ; # LETTER DDHA +\uE023>ಣ; # LETTER NNA +\uE024>ತ; # LETTER TA +\uE025>ಥ; # LETTER THA +\uE026>ದ; # LETTER DA +\uE027>ಧ; # LETTER DHA +\uE028>ನ; # LETTER NA +\uE029>ನ; # REMAP (indicExceptions.txt): \u0CA9>ನ = LETTER NNNA>LETTER NA +\uE02A>ಪ; # LETTER PA +\uE02B>ಫ; # LETTER PHA +\uE02C>ಬ; # LETTER BA +\uE02D>ಭ; # LETTER BHA +\uE02E>ಮ; # LETTER MA +\uE02F>ಯ; # LETTER YA +\uE030\uE03C>ಱ; +\uE030>ರ; # LETTER RA +\uE031>ಱ; # LETTER RRA +\uE032>ಲ; # LETTER LA +\uE033>ಳ; # LETTER LLA +\uE034>ೞ; # REMAP (indicExceptions.txt): \u0CB4>ಳ = LETTER LLLA>LETTER LLA +\uE035>ವ; # LETTER VA +\uE036>ಶ; # LETTER SHA +\uE037>ಷ; # LETTER SSA +\uE038>ಸ; # LETTER SA +\uE039>ಹ; # LETTER HA +\uE03C>\u0CBC; # NUKTA +\uE03D>ಽ; # AVAGRAHA +\uE03E>ಾ; # VOWEL SIGN AA +\uE03F>\u0CBF; # VOWEL SIGN I +\uE040>ೀ; # VOWEL SIGN II +\uE041>ು; # VOWEL SIGN U +\uE042>ೂ; # VOWEL SIGN UU +\uE043>ೃ; # VOWEL SIGN VOCALIC R +\uE044>ೄ; # VOWEL SIGN VOCALIC RR +\uE045>\u0CC6; # REMAP (indicExceptions.txt): \u0CC5>\u0CC6 = VOWEL SIGN CANDRA E>VOWEL SIGN E +\uE046>\u0CC6; # VOWEL SIGN E +\uE047>ೇ; # VOWEL SIGN EE +\uE048>ೈ; # VOWEL SIGN AI +\uE049>ೊ; # REMAP (indicExceptions.txt): \u0CC9>ೊ = VOWEL SIGN CANDRA O>VOWEL SIGN O +\uE04A>ೊ; # VOWEL SIGN O +\uE04B>ೋ; # VOWEL SIGN OO +\uE04C>\u0CCC; # VOWEL SIGN AU +\uE04D>\u0CCD; # SIGN VIRAMA +\uE050>ಓಂ; # REMAP (indicExceptions.txt): \u0CD0>ಓಂ = OM>LETTER OO.SIGN ANUSVARA +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>ೕ; # LENGTH MARK +\uE056>ೖ; # AI LENGTH MARK +\uE057>\u0CCC; # REMAP (indicExceptions.txt): \u0CD7>\u0CCC = AU LENGTH MARK>VOWEL SIGN AU +\uE058>ಕ; # FALLBACK +\uE059>ಖ; # REMAP (indicExceptions.txt): \u0CD9>ಖ = LETTER KHHA>LETTER KHA +\uE05A>ಗ; # REMAP (indicExceptions.txt): \u0CDA>ಗ = LETTER GHHA>LETTER GA +\uE05B>ಜ; # REMAP (indicExceptions.txt): \u0CDB>ಜ = LETTER ZA>LETTER JA +\uE05C>ಢ; # FALLBACK +\uE05D>ಢ; # REMAP (indicExceptions.txt): \u0CDD>ಢ = LETTER RHA>LETTER DDHA +\uE05E>ೞ; # LETTER FA +\uE05F>ಯ; # REMAP (indicExceptions.txt): \u0CDF>ಯ = LETTER YYA>LETTER YA +\uE060>ೠ; # LETTER VOCALIC RR +\uE061>ೡ; # LETTER VOCALIC LL +\uE062>\u0CBF; # REMAP (indicExceptions.txt): \u0CE2>\u0CBF = VOWEL SIGN VOCALIC L>VOWEL SIGN I +\uE063>ೀ; # REMAP (indicExceptions.txt): \u0CE3>ೀ = VOWEL SIGN VOCALIC LL>VOWEL SIGN II +\uE064>'.' ; # FALLBACK FOR DANDA +\uE065>'.' ; # FALLBACK FOR DOUBLE DANDA +\uE066>೦; # DIGIT ZERO +\uE067>೧; # DIGIT ONE +\uE068>೨; # DIGIT TWO +\uE069>೩; # DIGIT THREE +\uE06A>೪; # DIGIT FOUR +\uE06B>೫; # DIGIT FIVE +\uE06C>೬; # DIGIT SIX +\uE06D>೭; # DIGIT SEVEN +\uE06E>೮; # DIGIT EIGHT +\uE06F>೯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ರ; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ರ; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u0cb5; # FALLBACK FOR ORIYA LETTER WA +\uE081>ವ; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0ca4\u0ccd; # Bengali Khanda-ta -0 > \u0ce6; # FALLBACK FOR TAMIL -1 > \u0ce7; - -# :: NFC (NFD) ; -# eof +\uE083>ತ\u0CCD; # Bengali Khanda-ta +0 > ೦; # FALLBACK FOR TAMIL +1 > ೧; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Latin.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Latin.txt index a6552801f74..b78872c9c3d 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Latin.txt @@ -1,535 +1,462 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Latin - #\u0e00 reserved - #consonants - $chandrabindu=\ue001; - $anusvara=\ue002; - $visarga=\ue003; - #\u0e004 reserved - # w<vowel> represents the stand-alone form - $wa=\ue005; - $waa=\ue006; - $wi=\ue007; - $wii=\ue008; - $wu=\ue009; - $wuu=\ue00a; - $wr=\ue00b; - $wl=\ue00c; - $wce=\ue00d; # LETTER CANDRA E - $wse=\ue00e; # LETTER SHORT E - $we=\ue00f; # \u090f LETTER E - $wai=\ue010; - $wco=\ue011; # LETTER CANDRA O - $wso=\ue012; # LETTER SHORT O - $wo=\ue013; # \u0913 LETTER O - $wau=\ue014; - $ka=\ue015; - $kha=\ue016; - $ga=\ue017; - $gha=\ue018; - $nga=\ue019; - $ca=\ue01a; - $cha=\ue01b; - $ja=\ue01c; - $jha=\ue01d; - $nya=\ue01e; - $tta=\ue01f; - $ttha=\ue020; - $dda=\ue021; - $ddha=\ue022; - $nna=\ue023; - $ta=\ue024; - $tha=\ue025; - $da=\ue026; - $dha=\ue027; - $na=\ue028; - $ena=\ue029; #compatibility - $pa=\ue02a; - $pha=\ue02b; - $ba=\ue02c; - $bha=\ue02d; - $ma=\ue02e; - $ya=\ue02f; - $ra=\ue030; - $vva=\ue081; - $rra=\ue031; - $la=\ue032; - $lla=\ue033; - $ela=\ue034; #compatibility - $va=\ue035; - $sha=\ue036; - $ssa=\ue037; - $sa=\ue038; - $ha=\ue039; -#\u093a Reserved -#\u093b Reserved - $nukta=\ue03c; - $avagraha=\ue03d; # SIGN AVAGRAHA - # <vowel> represents the dependent form - $aa=\ue03e; - $i=\ue03f; - $ii=\ue040; - $u=\ue041; - $uu=\ue042; - $rh=\ue043; - $lh=\ue044; - $ce=\ue045; #VOWEL SIGN CANDRA E - $se=\ue046; #VOWEL SIGN SHORT E - $e=\ue047; - $ai=\ue048; - $co=\ue049; # VOWEL SIGN CANDRA O - $so=\ue04a; # VOWEL SIGN SHORT O - $o=\ue04b; # \u094b - $au=\ue04c; - $virama=\ue04d; -# \u094e Reserved -# \u094f Reserved - $om=\ue050; # OM - \ue051>; # UNMAPPED STRESS SIGN UDATTA - \ue052>; # UNMAPPED STRESS SIGN ANUDATTA - \ue053>; # UNMAPPED GRAVE ACCENT - \ue054>; # UNMAPPED ACUTE ACCENT - $lm = \ue055;# Telugu Length Mark - $ailm=\ue056;# AI Length Mark - $aulm=\ue057;# AU Length Mark - #urdu compatibity forms - $uka=\ue058; - $ukha=\ue059; - $ugha=\ue05a; - $ujha=\ue05b; - $uddha=\ue05c; - $udha=\ue05d; - $ufa=\ue05e; - $uya=\ue05f; - $wrr=\ue060; - $wll=\ue061; - $rrh=\ue062; - $llh=\ue063; - $danda=\ue064; - $doubleDanda=\ue065; - $zero=\ue066; # DIGIT ZERO - $one=\ue067; # DIGIT ONE - $two=\ue068; # DIGIT TWO - $three=\ue069; # DIGIT THREE - $four=\ue06a; # DIGIT FOUR - $five=\ue06b; # DIGIT FIVE - $six=\ue06c; # DIGIT SIX - $seven=\ue06d; # DIGIT SEVEN - $eight=\ue06e; # DIGIT EIGHT - $nine=\ue06f; # DIGIT NINE - - # Glottal stop - $dgs=\ue082; - #Khanda-ta - $kta=\ue083; -# \u0970>; # UNMAPPED ABBREVIATION SIGN - $depVowelAbove=[\ue03e-\ue040\ue045-\ue04c]; - $depVowelBelow=[\ue041-\ue044]; - # $x was originally called '&'; $z was '%' - $x=[$aa$ai$au$ii$i$uu$u$rrh$rh$lh$llh$e$o$se$ce$so$co]; - $z=[bcdfghjklmnpqrstvwxyz]; - $vowels=[aeiour\u0304\u0325\u0306]; - $forceIndependentMatra = [^[[:L:][\u0300-\u034c]]]; - ###################################################################### - # convert from Native letters to Latin letters - ###################################################################### - #transliterations for anusvara - $anusvara} [$ka$kha$ga$gha$nga] > n\u0307; - $anusvara} [$ca$cha$ja$jha$nya] > n\u0304; - $anusvara} [$tta$ttha$dda$ddha$nna] > n\u0323; - $anusvara} [$ta$tha$da$dha$na] > n; - $anusvara} [$pa$pha$ba$bha$ma] > m; - $anusvara} [$ya$ra$lla$la$va$ssa$sha$sa$ha] > n; - $anusvara> m\u0307; - - # Urdu compatibility - $ya$nukta}$x > y\u0307; - $ya$nukta$virama > y\u0307; - $ya$nukta > y\u0307a; - - $la$nukta }$x > l\u0331; - $la$nukta$virama > l\u0331; - $la$nukta > l\u0331a; - - $na$nukta }$x > n\u0331; - $na$nukta$virama > n\u0331; - $na$nukta > n\u0331a; - - $ena }$x > n\u0331; - $ena$virama > n\u0331; - $ena > n\u0331a; - $uka > qa; - $ka$nukta }$x > q; - $ka$nukta$virama > q; - $ka$nukta > qa; - $kha$nukta }$x > k\u0331h\u0331; - $kha$nukta$virama > k\u0331h\u0331; - $kha$nukta > k\u0331h\u0331a; - $ukha$virama > k\u0331h\u0331; - $ukha > k\u0331h\u0331a; - $ugha > g\u0307a; - $ga$nukta }$x > g\u0307; - $ga$nukta$virama > g\u0307; - $ga$nukta > g\u0307a; - - $ujha > za; - $ja$nukta }$x > z; - $ja$nukta$virama > z; - $ja$nukta > za; - $ddha$nukta}$x > r\u0323h; - $ddha$nukta$virama > r\u0323h; - $ddha$nukta > r\u0323ha; - - $uddha}$x > r\u0323; - $uddha$virama > r\u0323; - $uddha > r\u0323a; - - $udha > r\u0323a; - $dda$nukta}$x > r\u0323; - $dda$nukta$virama > r\u0323; - $dda$nukta > r\u0323a; - $pha$nukta }$x > f; - $pha$nukta$virama > f; - $pha$nukta > fa; - $ufa }$x > f; - $ufa$virama > f; - $ufa > fa; - - $ra$nukta}$x > r\u0331; - $ra$nukta$virama > r\u0331; - $ra$nukta > r\u0331a; - $lla$nukta}$x > l\u0331; - $lla$nukta$virama > l\u0331; - $lla$nukta > l\u0331a; - - $ela}$x > l\u0331; - $ela$virama > l\u0331; - $ela > l\u0331a; - - $uya}$x > y\u0307; - $uya$virama > y\u0307; - $uya > y\u0307a; - - - # normal consonants - $ka$virama}$ha>k''; - $ka}$x>k; - $ka$virama>k; - $ka>ka; - $kha}$x>kh; - $kha$virama>kh; - $kha>kha; - $ga$virama}$ha>g''; - $ga}$x>g; - $ga$virama>g; - $ga>ga; - - $gha}$x>gh; - $gha$virama>gh; - $gha>gha; - - $nga}$x>n\u0307; - $nga$virama>n\u0307; - $nga>n\u0307a; - $ca$virama}$ha>c''; - $ca}$x>c; - $ca$virama>c; - $ca>ca; - - $cha}$x>ch; - $cha$virama>ch; - $cha>cha; - $ja$virama}$ha>j''; - $ja}$x>j; - $ja$virama>j; - $ja>ja; - - $jha}$x>jh; - $jha$virama>jh; - $jha>jha; - - $nya }$x>n\u0303; - $nya$virama>n\u0303; - $nya > n\u0303a; - - - $tta$virama}$ha>t\u0323''; - $tta}$x>t\u0323; - $tta$virama>t\u0323; - $tta>t\u0323a; - - $ttha}$x>t\u0323h; - $ttha$virama>t\u0323h; - $ttha>t\u0323ha; - $dda}$x$ha>d\u0323''; - $dda}$x>d\u0323; - $dda$virama>d\u0323; - $dda>d\u0323a; - - $ddha}$x>d\u0323h; - $ddha$virama>d\u0323h; - $ddha>d\u0323ha; - - $nna}$x>n\u0323; - $nna$virama>n\u0323; - $nna>n\u0323a; - - - $ta$virama}$ha>t''; - $ta$virama}$ttha>t''; - $ta$virama}$tta>t''; - $ta$virama}$tha>t''; - $ta}$x>t; - $ta$virama>t; - $ta>ta; - $tha}$x>th; - $tha$virama>th; - $tha>tha; - - $da$virama}$ha>d''; - $da$virama}$ddha>d''; - $da$virama}$dda>d''; - $da$virama}$dha>d''; - $da}$x>d; - $da$virama>d; - $da>da; - $dha}$x>dh; - $dha$virama>dh; - $dha>dha; - $na$virama}$ga>n''; - $na$virama}$ya>n''; - $na}$x>n; - $na$virama>n; - $na>na; - - - $pa$virama}$ha>p''; - $pa}$x>p; - $pa$virama>p; - $pa>pa; - $pha}$x>ph; - $pha$virama>ph; - $pha>pha; - $ba$virama}$ha>b''; - $ba}$x>b; - $ba$virama>b; - $ba>ba; - - $bha}$x>bh; - $bha$virama>bh; - $bha>bha; - - $ma$virama}$ma>m''; - $ma}$x>m; - $ma$virama>m; - $ma>ma; - - $ya}$x>y; - $ya$virama>y; - $ya>ya; - $ra$virama}$ha>r''; - $ra}$x>r; - $ra$virama>r; - $ra>ra; - $vva$virama}$ha>w\u0307''; - $vva}$x>w\u0307; - $vva$virama>w\u0307; - $vva>w\u0307a; - $rra$virama}$ha>r\u0331''; - $rra}$x>r\u0331; - $rra$virama>r\u0331; - $rra>r\u0331a; - $la$virama}$ha>l''; - $la}$x>l; - $la$virama>l; - $la>la; - $lla$virama}$ha>l\u0323''; - $lla}$x>l\u0323; - $lla$virama>l\u0323; - $lla>l\u0323a; - $va}$x>v; - $va$virama>v; - $va>va; - $sa$virama}$ha>s''; - $sa$virama}$sha>s''; - $sa$virama}$ssa>s''; - $sa$virama}$sa>s''; - $sa}$x>s; - $sa$virama>s; - - #for gurmukhi - $sa$nukta}$x>s\u0301; - $sa$nukta$virama>s\u0301; - $sa$nukta>s\u0301a; - $sa>sa; - - $sha}$x>s\u0301; - $sha$virama>s\u0301; - $sha>s\u0301a; - - $ssa}$x>s\u0323; - $ssa$virama>s\u0323; - $ssa>s\u0323a; - $ha}$x>h; - $ha$virama>h; - $ha>ha; - - # dependent vowels (should never occur except following consonants) - $forceIndependentMatra{$aa > \u0314a\u0304; - $forceIndependentMatra{$ai > \u0314ai; - $forceIndependentMatra{$au > \u0314au; - $forceIndependentMatra{$ii > \u0314i\u0304; - $forceIndependentMatra{$i > \u0314i; - $forceIndependentMatra{$uu > \u0314u\u0304; - $forceIndependentMatra{$u > \u0314u; - $forceIndependentMatra{$rrh > \u0314r\u0325\u0304; - $forceIndependentMatra{$rh > \u0314r\u0325; - $forceIndependentMatra{$llh > \u0314l\u0325\u0304; - $forceIndependentMatra{$lh > \u0314l\u0325; - $forceIndependentMatra{$e > \u0314e\u0304; - $forceIndependentMatra{$o > \u0314o\u0304; - #extra vowels - $forceIndependentMatra{$ce > \u0314e\u0306; - $forceIndependentMatra{$co > \u0314o\u0306; - $forceIndependentMatra{$se > \u0314e; - $forceIndependentMatra{$so > \u0314o; - $forceIndependentMatra{$nukta >; # Nukta cannot appear independently or as first character - $forceIndependentMatra{$virama >; # Virama cannot appear independently or as first character - $aa > a\u0304; - $ai > ai; - $au > au; - $ii > i\u0304; - $i > i; - $uu > u\u0304; - $u > u; - $rrh > r\u0325\u0304; - $rh > r\u0325; - $llh > l\u0325\u0304; - $lh > l\u0325; - $e > e\u0304; - $o > o\u0304; - #extra vowels - $ce > e\u0306; - $co > o\u0306; - $se > e; - $so > o; - #dependent vowels when following independent vowels. Generally Illegal only for roundtripping - $waa} $x > a\u0304\u0314; - $wai} $x > ai\u0314; - $wau} $x > au\u0314; - $wii} $x > i\u0304\u0314; - $wi } $x > i\u0314; - $wuu} $x > u\u0304\u0314; - $wu } $x > u\u0314; - $wrr} $x > r\u0325\u0304\u0314; - $wr } $x > r\u0325\u0314; - $wll} $x > l\u0325\u0304\u0314; - $wl } $x > l\u0325\u0314; - $we } $x > e\u0304\u0314; - $wo } $x > o\u0304\u0314; - $wa } $x > a\u0314; - #extra vowels - $wce} $x > e\u0306\u0314; - $wco} $x > o\u0306\u0314; - $wse} $x > e\u0314; - $wso} $x > o\u0314; - $om} $x > ''om\u0314; - - # independent vowels when preceeded by vowels - $vowels{$waa > ''a\u0304; - $vowels{$wai > ''ai; - $vowels{$wau > ''au; - $vowels{$wii > ''i\u0304; - $vowels{$wi > ''i; - $vowels{$wuu > ''u\u0304; - $vowels{$wu > ''u; - $vowels{$wrr > ''r\u0325\u0304; - $vowels{$wr > ''r\u0325; - $vowels{$wll > ''l\u0325\u0304; - $vowels{$wl > ''l\u0325; - $vowels{$we > ''e\u0304; - $vowels{$wo > ''o\u0304; - $vowels{$wa > ''a; - #extra vowels - $vowels{$wce > ''e\u0306; - $vowels{$wco > ''o\u0306; - $vowels{$wse > ''e; - $vowels{$wso > ''o; - - # independent vowels (otherwise) - $waa > a\u0304; - $wai > ai; - $wau > au; - $wii > i\u0304; - $wi > i; - $wuu > u\u0304; - $wu > u; - $wrr > r\u0325\u0304; - $wr > r\u0325; - $wll > l\u0325\u0304; - $wl > l\u0325; - $we > e\u0304; - $wo > o\u0304; - $wa > a; - #extra vowels - $wce > e\u0306; - $wco > o\u0306; - $wse > e; - $wso > o; - $om > ''om; - - #stress marks - $avagraha > \u0315; - $chandrabindu$anusvara>\u0303; - $chandrabindu > m\u0310; - $visarga>h\u0323; - #numbers - $zero > 0; - $one > 1; - $two > 2; - $three > 3; - $four > 4; - $five > 5; - $six > 6; - $seven > 7; - $eight > 8; - $nine > 9; - $lm >; - $ailm >; - $aulm >; - - $dgs>\u0294; - $kta>t\u0331; - $danda>'.'; - $doubleDanda>'.'; - - \ue070>; # ABBREVIATION SIGN - # LETTER RA WITH MIDDLE DIAGONAL - \ue071}$x>ra; - \ue071$virama>r; - \ue071>ra; - # LETTER RA WITH LOWER DIAGONAL - \ue072}$x>ra; - \ue072$virama>r; - \ue072>ra; - - \ue073>; # RUPEE MARK - \ue074>; # RUPEE SIGN - \ue075>; # CURRENCY NUMERATOR ONE - \ue076>; # CURRENCY NUMERATOR TWO - \ue077>; # CURRENCY NUMERATOR THREE - \ue078>; # CURRENCY NUMERATOR FOUR - \ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR - \ue07A>; # CURRENCY DENOMINATOR SIXTEEN - \ue07B>; # ISSHAR - \uE07C>; # TIPPI - \uE07D>; # ADDAK - \uE07E>; # IRI - \uE07F>; # URA - \uE080>; # EK ONKAR - \uE004>; # DEVANAGARI VOWEL SIGN SHORT A - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +$chandrabindu=\uE001; +$anusvara=\uE002; +$visarga=\uE003; +$wa=\uE005; +$waa=\uE006; +$wi=\uE007; +$wii=\uE008; +$wu=\uE009; +$wuu=\uE00A; +$wr=\uE00B; +$wl=\uE00C; +$wce=\uE00D; # LETTER CANDRA E +$wse=\uE00E; # LETTER SHORT E +$we=\uE00F; # ए LETTER E +$wai=\uE010; +$wco=\uE011; # LETTER CANDRA O +$wso=\uE012; # LETTER SHORT O +$wo=\uE013; # ओ LETTER O +$wau=\uE014; +$ka=\uE015; +$kha=\uE016; +$ga=\uE017; +$gha=\uE018; +$nga=\uE019; +$ca=\uE01A; +$cha=\uE01B; +$ja=\uE01C; +$jha=\uE01D; +$nya=\uE01E; +$tta=\uE01F; +$ttha=\uE020; +$dda=\uE021; +$ddha=\uE022; +$nna=\uE023; +$ta=\uE024; +$tha=\uE025; +$da=\uE026; +$dha=\uE027; +$na=\uE028; +$ena=\uE029; #compatibility +$pa=\uE02A; +$pha=\uE02B; +$ba=\uE02C; +$bha=\uE02D; +$ma=\uE02E; +$ya=\uE02F; +$ra=\uE030; +$vva=\uE081; +$rra=\uE031; +$la=\uE032; +$lla=\uE033; +$ela=\uE034; #compatibility +$va=\uE035; +$sha=\uE036; +$ssa=\uE037; +$sa=\uE038; +$ha=\uE039; +$nukta=\uE03C; +$avagraha=\uE03D; # SIGN AVAGRAHA +$aa=\uE03E; +$i=\uE03F; +$ii=\uE040; +$u=\uE041; +$uu=\uE042; +$rh=\uE043; +$lh=\uE044; +$ce=\uE045; #VOWEL SIGN CANDRA E +$se=\uE046; #VOWEL SIGN SHORT E +$e=\uE047; +$ai=\uE048; +$co=\uE049; # VOWEL SIGN CANDRA O +$so=\uE04A; # VOWEL SIGN SHORT O +$o=\uE04B; # ो +$au=\uE04C; +$virama=\uE04D; +$om=\uE050; # OM +\uE051>; # UNMAPPED STRESS SIGN UDATTA +\uE052>; # UNMAPPED STRESS SIGN ANUDATTA +\uE053>; # UNMAPPED GRAVE ACCENT +\uE054>; # UNMAPPED ACUTE ACCENT +$lm = \uE055;# Telugu Length Mark +$ailm=\uE056;# AI Length Mark +$aulm=\uE057;# AU Length Mark +$uka=\uE058; +$ukha=\uE059; +$ugha=\uE05A; +$ujha=\uE05B; +$uddha=\uE05C; +$udha=\uE05D; +$ufa=\uE05E; +$uya=\uE05F; +$wrr=\uE060; +$wll=\uE061; +$rrh=\uE062; +$llh=\uE063; +$danda=\uE064; +$doubleDanda=\uE065; +$zero=\uE066; # DIGIT ZERO +$one=\uE067; # DIGIT ONE +$two=\uE068; # DIGIT TWO +$three=\uE069; # DIGIT THREE +$four=\uE06A; # DIGIT FOUR +$five=\uE06B; # DIGIT FIVE +$six=\uE06C; # DIGIT SIX +$seven=\uE06D; # DIGIT SEVEN +$eight=\uE06E; # DIGIT EIGHT +$nine=\uE06F; # DIGIT NINE +$dgs=\uE082; +$kta=\uE083; +$depVowelAbove=[\uE03E-\uE040\uE045-\uE04C]; +$depVowelBelow=[\uE041-\uE044]; +$x=[$aa$ai$au$ii$i$uu$u$rrh$rh$lh$llh$e$o$se$ce$so$co]; +$z=[bcdfghjklmnpqrstvwxyz]; +$vowels=[aeiour\u0304\u0325\u0306]; +$forceIndependentMatra = [^[[:L:][\u0300-\u034C]]]; +$anusvara} [$ka$kha$ga$gha$nga] > n\u0307; +$anusvara} [$ca$cha$ja$jha$nya] > n\u0304; +$anusvara} [$tta$ttha$dda$ddha$nna] > n\u0323; +$anusvara} [$ta$tha$da$dha$na] > n; +$anusvara} [$pa$pha$ba$bha$ma] > m; +$anusvara} [$ya$ra$lla$la$va$ssa$sha$sa$ha] > n; +$anusvara> m\u0307; +$ya$nukta}$x > y\u0307; +$ya$nukta$virama > y\u0307; +$ya$nukta > y\u0307a; +$la$nukta }$x > l\u0331; +$la$nukta$virama > l\u0331; +$la$nukta > l\u0331a; +$na$nukta }$x > n\u0331; +$na$nukta$virama > n\u0331; +$na$nukta > n\u0331a; +$ena }$x > n\u0331; +$ena$virama > n\u0331; +$ena > n\u0331a; +$uka > qa; +$ka$nukta }$x > q; +$ka$nukta$virama > q; +$ka$nukta > qa; +$kha$nukta }$x > k\u0331h\u0331; +$kha$nukta$virama > k\u0331h\u0331; +$kha$nukta > k\u0331h\u0331a; +$ukha$virama > k\u0331h\u0331; +$ukha > k\u0331h\u0331a; +$ugha > g\u0307a; +$ga$nukta }$x > g\u0307; +$ga$nukta$virama > g\u0307; +$ga$nukta > g\u0307a; +$ujha > za; +$ja$nukta }$x > z; +$ja$nukta$virama > z; +$ja$nukta > za; +$ddha$nukta}$x > r\u0323h; +$ddha$nukta$virama > r\u0323h; +$ddha$nukta > r\u0323ha; +$uddha}$x > r\u0323; +$uddha$virama > r\u0323; +$uddha > r\u0323a; +$udha > r\u0323a; +$dda$nukta}$x > r\u0323; +$dda$nukta$virama > r\u0323; +$dda$nukta > r\u0323a; +$pha$nukta }$x > f; +$pha$nukta$virama > f; +$pha$nukta > fa; +$ufa }$x > f; +$ufa$virama > f; +$ufa > fa; +$ra$nukta}$x > r\u0331; +$ra$nukta$virama > r\u0331; +$ra$nukta > r\u0331a; +$lla$nukta}$x > l\u0331; +$lla$nukta$virama > l\u0331; +$lla$nukta > l\u0331a; +$ela}$x > l\u0331; +$ela$virama > l\u0331; +$ela > l\u0331a; +$uya}$x > y\u0307; +$uya$virama > y\u0307; +$uya > y\u0307a; +$ka$virama}$ha>k''; +$ka}$x>k; +$ka$virama>k; +$ka>ka; +$kha}$x>kh; +$kha$virama>kh; +$kha>kha; +$ga$virama}$ha>g''; +$ga}$x>g; +$ga$virama>g; +$ga>ga; +$gha}$x>gh; +$gha$virama>gh; +$gha>gha; +$nga}$x>n\u0307; +$nga$virama>n\u0307; +$nga>n\u0307a; +$ca$virama}$ha>c''; +$ca}$x>c; +$ca$virama>c; +$ca>ca; +$cha}$x>ch; +$cha$virama>ch; +$cha>cha; +$ja$virama}$ha>j''; +$ja}$x>j; +$ja$virama>j; +$ja>ja; +$jha}$x>jh; +$jha$virama>jh; +$jha>jha; +$nya }$x>n\u0303; +$nya$virama>n\u0303; +$nya > n\u0303a; +$tta$virama}$ha>t\u0323''; +$tta}$x>t\u0323; +$tta$virama>t\u0323; +$tta>t\u0323a; +$ttha}$x>t\u0323h; +$ttha$virama>t\u0323h; +$ttha>t\u0323ha; +$dda}$x$ha>d\u0323''; +$dda}$x>d\u0323; +$dda$virama>d\u0323; +$dda>d\u0323a; +$ddha}$x>d\u0323h; +$ddha$virama>d\u0323h; +$ddha>d\u0323ha; +$nna}$x>n\u0323; +$nna$virama>n\u0323; +$nna>n\u0323a; +$ta$virama}$ha>t''; +$ta$virama}$ttha>t''; +$ta$virama}$tta>t''; +$ta$virama}$tha>t''; +$ta}$x>t; +$ta$virama>t; +$ta>ta; +$tha}$x>th; +$tha$virama>th; +$tha>tha; +$da$virama}$ha>d''; +$da$virama}$ddha>d''; +$da$virama}$dda>d''; +$da$virama}$dha>d''; +$da}$x>d; +$da$virama>d; +$da>da; +$dha}$x>dh; +$dha$virama>dh; +$dha>dha; +$na$virama}$ga>n''; +$na$virama}$ya>n''; +$na}$x>n; +$na$virama>n; +$na>na; +$pa$virama}$ha>p''; +$pa}$x>p; +$pa$virama>p; +$pa>pa; +$pha}$x>ph; +$pha$virama>ph; +$pha>pha; +$ba$virama}$ha>b''; +$ba}$x>b; +$ba$virama>b; +$ba>ba; +$bha}$x>bh; +$bha$virama>bh; +$bha>bha; +$ma$virama}$ma>m''; +$ma}$x>m; +$ma$virama>m; +$ma>ma; +$ya}$x>y; +$ya$virama>y; +$ya>ya; +$ra$virama}$ha>r''; +$ra}$x>r; +$ra$virama>r; +$ra>ra; +$vva$virama}$ha>w\u0307''; +$vva}$x>w\u0307; +$vva$virama>w\u0307; +$vva>w\u0307a; +$rra$virama}$ha>r\u0331''; +$rra}$x>r\u0331; +$rra$virama>r\u0331; +$rra>r\u0331a; +$la$virama}$ha>l''; +$la}$x>l; +$la$virama>l; +$la>la; +$lla$virama}$ha>l\u0323''; +$lla}$x>l\u0323; +$lla$virama>l\u0323; +$lla>l\u0323a; +$va}$x>v; +$va$virama>v; +$va>va; +$sa$virama}$ha>s''; +$sa$virama}$sha>s''; +$sa$virama}$ssa>s''; +$sa$virama}$sa>s''; +$sa}$x>s; +$sa$virama>s; +$sa$nukta}$x>s\u0301; +$sa$nukta$virama>s\u0301; +$sa$nukta>s\u0301a; +$sa>sa; +$sha}$x>s\u0301; +$sha$virama>s\u0301; +$sha>s\u0301a; +$ssa}$x>s\u0323; +$ssa$virama>s\u0323; +$ssa>s\u0323a; +$ha}$x>h; +$ha$virama>h; +$ha>ha; +$forceIndependentMatra{$aa > \u0314a\u0304; +$forceIndependentMatra{$ai > \u0314ai; +$forceIndependentMatra{$au > \u0314au; +$forceIndependentMatra{$ii > \u0314i\u0304; +$forceIndependentMatra{$i > \u0314i; +$forceIndependentMatra{$uu > \u0314u\u0304; +$forceIndependentMatra{$u > \u0314u; +$forceIndependentMatra{$rrh > \u0314r\u0325\u0304; +$forceIndependentMatra{$rh > \u0314r\u0325; +$forceIndependentMatra{$llh > \u0314l\u0325\u0304; +$forceIndependentMatra{$lh > \u0314l\u0325; +$forceIndependentMatra{$e > \u0314e\u0304; +$forceIndependentMatra{$o > \u0314o\u0304; +$forceIndependentMatra{$ce > \u0314e\u0306; +$forceIndependentMatra{$co > \u0314o\u0306; +$forceIndependentMatra{$se > \u0314e; +$forceIndependentMatra{$so > \u0314o; +$forceIndependentMatra{$nukta >; # Nukta cannot appear independently or as first character +$forceIndependentMatra{$virama >; # Virama cannot appear independently or as first character +$aa > a\u0304; +$ai > ai; +$au > au; +$ii > i\u0304; +$i > i; +$uu > u\u0304; +$u > u; +$rrh > r\u0325\u0304; +$rh > r\u0325; +$llh > l\u0325\u0304; +$lh > l\u0325; +$e > e\u0304; +$o > o\u0304; +$ce > e\u0306; +$co > o\u0306; +$se > e; +$so > o; +$waa} $x > a\u0304\u0314; +$wai} $x > ai\u0314; +$wau} $x > au\u0314; +$wii} $x > i\u0304\u0314; +$wi } $x > i\u0314; +$wuu} $x > u\u0304\u0314; +$wu } $x > u\u0314; +$wrr} $x > r\u0325\u0304\u0314; +$wr } $x > r\u0325\u0314; +$wll} $x > l\u0325\u0304\u0314; +$wl } $x > l\u0325\u0314; +$we } $x > e\u0304\u0314; +$wo } $x > o\u0304\u0314; +$wa } $x > a\u0314; +$wce} $x > e\u0306\u0314; +$wco} $x > o\u0306\u0314; +$wse} $x > e\u0314; +$wso} $x > o\u0314; +$om} $x > ''om\u0314; +$vowels{$waa > ''a\u0304; +$vowels{$wai > ''ai; +$vowels{$wau > ''au; +$vowels{$wii > ''i\u0304; +$vowels{$wi > ''i; +$vowels{$wuu > ''u\u0304; +$vowels{$wu > ''u; +$vowels{$wrr > ''r\u0325\u0304; +$vowels{$wr > ''r\u0325; +$vowels{$wll > ''l\u0325\u0304; +$vowels{$wl > ''l\u0325; +$vowels{$we > ''e\u0304; +$vowels{$wo > ''o\u0304; +$vowels{$wa > ''a; +$vowels{$wce > ''e\u0306; +$vowels{$wco > ''o\u0306; +$vowels{$wse > ''e; +$vowels{$wso > ''o; +$waa > a\u0304; +$wai > ai; +$wau > au; +$wii > i\u0304; +$wi > i; +$wuu > u\u0304; +$wu > u; +$wrr > r\u0325\u0304; +$wr > r\u0325; +$wll > l\u0325\u0304; +$wl > l\u0325; +$we > e\u0304; +$wo > o\u0304; +$wa > a; +$wce > e\u0306; +$wco > o\u0306; +$wse > e; +$wso > o; +$om > ''om; +$avagraha > \u0315; +$chandrabindu$anusvara>\u0303; +$chandrabindu > m\u0310; +$visarga>h\u0323; +$zero > 0; +$one > 1; +$two > 2; +$three > 3; +$four > 4; +$five > 5; +$six > 6; +$seven > 7; +$eight > 8; +$nine > 9; +$lm >; +$ailm >; +$aulm >; +$dgs>ʔ; +$kta>t\u0331; +$danda>'.'; +$doubleDanda>'.'; +\uE070>; # ABBREVIATION SIGN +\uE071}$x>ra; +\uE071$virama>r; +\uE071>ra; +\uE072}$x>ra; +\uE072$virama>r; +\uE072>ra; +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR +\uE07C>; # TIPPI +\uE07D>; # ADDAK +\uE07E>; # IRI +\uE07F>; # URA +\uE080>; # EK ONKAR +\uE004>; # DEVANAGARI VOWEL SIGN SHORT A diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Malayalam.txt index cea620b5fa4..0557a7e7ab7 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Malayalam.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Malayalam.txt @@ -1,143 +1,140 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Malayalam -#:: NFD (NFC) ; -\ue001>\u0d02; # REMAP (indicExceptions.txt): \u0d01>\u0d02 = SIGN CANDRABINDU>SIGN ANUSVARA -\ue002>\u0d02; # SIGN ANUSVARA -\ue003>\u0d03; # SIGN VISARGA -\uE004>\u0d05; # FALLBACK TO LETTER A -\ue005>\u0d05; # LETTER A -\ue006>\u0d06; # LETTER AA -\ue007>\u0d07; # LETTER I -\ue008>\u0d08; # LETTER II -\ue009>\u0d09; # LETTER U -\ue00a>\u0d0a; # LETTER UU -\ue00b>\u0d0b; # LETTER VOCALIC R -\ue00c>\u0d0c; # LETTER VOCALIC L -\ue00d>\u0d0e; # FALLLBACK LETTER E -\ue00e>\u0d0e; # LETTER E -\ue00f>\u0d0f; # LETTER EE -\ue010>\u0d10; # LETTER AI -\ue011>\u0d12; # FALLBACK TO O -\ue012>\u0d12; # LETTER O -\ue013>\u0d13; # LETTER OO -\ue014>\u0d14; # LETTER AU -\ue015>\u0d15; # LETTER KA -\ue016>\u0d16; # LETTER KHA -\ue017>\u0d17; # LETTER GA -\ue018>\u0d18; # LETTER GHA -\ue019>\u0d19; # LETTER NGA -\ue01a>\u0d1a; # LETTER CA -\ue01b>\u0d1b; # LETTER CHA -\ue01c>\u0d1c; # LETTER JA -\ue01d>\u0d1d; # LETTER JHA -\ue01e>\u0d1e; # LETTER NYA -\ue01f>\u0d1f; # LETTER TTA -\ue020>\u0d20; # LETTER TTHA -\ue021>\u0d21; # LETTER DDA -\ue022>\u0d22; # LETTER DDHA -\ue023>\u0d23; # LETTER NNA -\ue024>\u0d24; # LETTER TA -\ue025>\u0d25; # LETTER THA -\ue026>\u0d26; # LETTER DA -\ue027>\u0d27; # LETTER DHA -\ue028>\u0d28; # LETTER NA -\ue029>\u0d28; # REMAP (indicExceptions.txt): \u0d29>\u0d28 = LETTER NNNA>LETTER NA -\ue02a>\u0d2a; # LETTER PA -\ue02b>\u0d2b; # LETTER PHA -\ue02c>\u0d2c; # LETTER BA -\ue02d>\u0d2d; # LETTER BHA -\ue02e>\u0d2e; # LETTER MA -\ue02f>\u0d2f; # LETTER YA -\ue030\ue03c>\u0d31; -\ue030>\u0d30; # LETTER RA -\ue031>\u0d31; # LETTER RRA -\ue032>\u0d32; # LETTER LA -\ue033\ue03c>\u0d34; -\ue033>\u0d33; # LETTER LLA -\ue034>\u0d34; # LETTER LLLA -\ue035>\u0d35; # LETTER VA -\ue036>\u0d36; # LETTER SHA -\ue037>\u0d37; # LETTER SSA -\ue038>\u0d38; # LETTER SA -\ue039>\u0d39; # LETTER HA - -\ue03c>; # FALLBACK BLOW AWAY NUKTA -\ue03d>; # FALLBACK BLOW AWAY AVAGRAHA - -\ue03e>\u0d3e; # VOWEL SIGN AA -\ue03f>\u0d3f; # VOWEL SIGN I -\ue040>\u0d40; # VOWEL SIGN II -\ue041>\u0d41; # VOWEL SIGN U -\ue042>\u0d42; # VOWEL SIGN UU -\ue043>\u0d43; # VOWEL SIGN VOCALIC R -\ue044>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC RR -\ue045>\u0d3e; # REMAP (indicExceptions.txt): \u0d45>\u0d3e = VOWEL SIGN CANDRA E>VOWEL SIGN AA -\ue046>\u0d46; # VOWEL SIGN E -\ue047>\u0d47; # VOWEL SIGN EE -\ue048>\u0d48; # VOWEL SIGN AI -\ue049>\u0d4b; # REMAP (indicExceptions.txt): \u0d49>\u0d4b = VOWEL SIGN CANDRA O>VOWEL SIGN OO -\ue04a>\u0d4a; # VOWEL SIGN O -\ue04b>\u0d4b; # VOWEL SIGN OO -\ue04c>\u0d4c; # VOWEL SIGN AU -\ue04d>\u0d4d; # SIGN VIRAMA -\ue050>\u0d13\u0d02; # UNMAPPED InterIndic-Malayalam: OM -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>; # FALLBACK BLOW AWAY LENGTH MARK -\ue056>\u0d48; # REMAP (indicExceptions.txt): \u0d56>\u0d48 = AI LENGTH MARK>VOWEL SIGN AI -\ue057>\u0d57; # AU LENGTH MARK -\ue058>\u0d15; # FALLBACK -\ue059>\u0d16; # REMAP (indicExceptions.txt): \u0d59>\u0d16 = LETTER KHHA>LETTER KHA -\ue05a>\u0d17; # REMAP (indicExceptions.txt): \u0d5a>\u0d17 = LETTER GHHA>LETTER GA -\ue05b>\u0d1c; # REMAP (indicExceptions.txt): \u0d5b>\u0d1c = LETTER ZA>LETTER JA -\ue05d>\u0d22; # REMAP (indicExceptions.txt): \u0d5d>\u0d22 = LETTER RHA>LETTER DDHA -\ue05c>\u0d21; # FALLBACK -\ue05e>\u0d2b; # REMAP (indicExceptions.txt): \u0d5e>\u0d2b = LETTER FA>LETTER PHA -\ue05f>\u0d2f; # REMAP (indicExceptions.txt): \u0d5f>\u0d2f = LETTER YYA>LETTER YA -\ue060>\u0d60; # LETTER VOCALIC RR -\ue061>\u0d61; # LETTER VOCALIC LL -\ue062>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC L -\ue063>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC LL -\ue064>'.' ; # FALLBACK FOR DANDA -\ue065>'.' ; # FALLBACK FOR DOUBLE DANDA -\ue066>\u0d66; # DIGIT ZERO -\ue067>\u0d67; # DIGIT ONE -\ue068>\u0d68; # DIGIT TWO -\ue069>\u0d69; # DIGIT THREE -\ue06a>\u0d6a; # DIGIT FOUR -\ue06b>\u0d6b; # DIGIT FIVE -\ue06c>\u0d6c; # DIGIT SIX -\ue06d>\u0d6d; # DIGIT SEVEN -\ue06e>\u0d6e; # DIGIT EIGHT -\ue06f>\u0d6f; # DIGIT NINE -\ue070>; # ABBREVIATION SIGN -\ue071>\u0d30; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0d30; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>; # ISSHAR +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\uE001>ം; # REMAP (indicExceptions.txt): \u0D01>ം = SIGN CANDRABINDU>SIGN ANUSVARA +\uE002>ം; # SIGN ANUSVARA +\uE003>ഃ; # SIGN VISARGA +\uE004>അ; # FALLBACK TO LETTER A +\uE005>അ; # LETTER A +\uE006>ആ; # LETTER AA +\uE007>ഇ; # LETTER I +\uE008>ഈ; # LETTER II +\uE009>ഉ; # LETTER U +\uE00A>ഊ; # LETTER UU +\uE00B>ഋ; # LETTER VOCALIC R +\uE00C>ഌ; # LETTER VOCALIC L +\uE00D>എ; # FALLLBACK LETTER E +\uE00E>എ; # LETTER E +\uE00F>ഏ; # LETTER EE +\uE010>ഐ; # LETTER AI +\uE011>ഒ; # FALLBACK TO O +\uE012>ഒ; # LETTER O +\uE013>ഓ; # LETTER OO +\uE014>ഔ; # LETTER AU +\uE015>ക; # LETTER KA +\uE016>ഖ; # LETTER KHA +\uE017>ഗ; # LETTER GA +\uE018>ഘ; # LETTER GHA +\uE019>ങ; # LETTER NGA +\uE01A>ച; # LETTER CA +\uE01B>ഛ; # LETTER CHA +\uE01C>ജ; # LETTER JA +\uE01D>ഝ; # LETTER JHA +\uE01E>ഞ; # LETTER NYA +\uE01F>ട; # LETTER TTA +\uE020>ഠ; # LETTER TTHA +\uE021>ഡ; # LETTER DDA +\uE022>ഢ; # LETTER DDHA +\uE023>ണ; # LETTER NNA +\uE024>ത; # LETTER TA +\uE025>ഥ; # LETTER THA +\uE026>ദ; # LETTER DA +\uE027>ധ; # LETTER DHA +\uE028>ന; # LETTER NA +\uE029>ന; # REMAP (indicExceptions.txt): \u0D29>ന = LETTER NNNA>LETTER NA +\uE02A>പ; # LETTER PA +\uE02B>ഫ; # LETTER PHA +\uE02C>ബ; # LETTER BA +\uE02D>ഭ; # LETTER BHA +\uE02E>മ; # LETTER MA +\uE02F>യ; # LETTER YA +\uE030\uE03C>റ; +\uE030>ര; # LETTER RA +\uE031>റ; # LETTER RRA +\uE032>ല; # LETTER LA +\uE033\uE03C>ഴ; +\uE033>ള; # LETTER LLA +\uE034>ഴ; # LETTER LLLA +\uE035>വ; # LETTER VA +\uE036>ശ; # LETTER SHA +\uE037>ഷ; # LETTER SSA +\uE038>സ; # LETTER SA +\uE039>ഹ; # LETTER HA +\uE03C>; # FALLBACK BLOW AWAY NUKTA +\uE03D>; # FALLBACK BLOW AWAY AVAGRAHA +\uE03E>ാ; # VOWEL SIGN AA +\uE03F>ി; # VOWEL SIGN I +\uE040>ീ; # VOWEL SIGN II +\uE041>\u0D41; # VOWEL SIGN U +\uE042>\u0D42; # VOWEL SIGN UU +\uE043>\u0D43; # VOWEL SIGN VOCALIC R +\uE044>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC RR +\uE045>ാ; # REMAP (indicExceptions.txt): \u0D45>ാ = VOWEL SIGN CANDRA E>VOWEL SIGN AA +\uE046>െ; # VOWEL SIGN E +\uE047>േ; # VOWEL SIGN EE +\uE048>ൈ; # VOWEL SIGN AI +\uE049>ോ; # REMAP (indicExceptions.txt): \u0D49>ോ = VOWEL SIGN CANDRA O>VOWEL SIGN OO +\uE04A>ൊ; # VOWEL SIGN O +\uE04B>ോ; # VOWEL SIGN OO +\uE04C>ൌ; # VOWEL SIGN AU +\uE04D>\u0D4D; # SIGN VIRAMA +\uE050>ഓം; # UNMAPPED InterIndic-Malayalam: OM +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>; # FALLBACK BLOW AWAY LENGTH MARK +\uE056>ൈ; # REMAP (indicExceptions.txt): \u0D56>ൈ = AI LENGTH MARK>VOWEL SIGN AI +\uE057>ൗ; # AU LENGTH MARK +\uE058>ക; # FALLBACK +\uE059>ഖ; # REMAP (indicExceptions.txt): \u0D59>ഖ = LETTER KHHA>LETTER KHA +\uE05A>ഗ; # REMAP (indicExceptions.txt): \u0D5A>ഗ = LETTER GHHA>LETTER GA +\uE05B>ജ; # REMAP (indicExceptions.txt): \u0D5B>ജ = LETTER ZA>LETTER JA +\uE05D>ഢ; # REMAP (indicExceptions.txt): \u0D5D>ഢ = LETTER RHA>LETTER DDHA +\uE05C>ഡ; # FALLBACK +\uE05E>ഫ; # REMAP (indicExceptions.txt): \u0D5E>ഫ = LETTER FA>LETTER PHA +\uE05F>യ; # REMAP (indicExceptions.txt): \u0D5F>യ = LETTER YYA>LETTER YA +\uE060>ൠ; # LETTER VOCALIC RR +\uE061>ൡ; # LETTER VOCALIC LL +\uE062>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC L +\uE063>; # FALLBACK BLOW AWAY VOWEL SIGN VOCALIC LL +\uE064>'.' ; # FALLBACK FOR DANDA +\uE065>'.' ; # FALLBACK FOR DOUBLE DANDA +\uE066>൦; # DIGIT ZERO +\uE067>൧; # DIGIT ONE +\uE068>൨; # DIGIT TWO +\uE069>൩; # DIGIT THREE +\uE06A>൪; # DIGIT FOUR +\uE06B>൫; # DIGIT FIVE +\uE06C>൬; # DIGIT SIX +\uE06D>൭; # DIGIT SEVEN +\uE06E>൮; # DIGIT EIGHT +\uE06F>൯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ര; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ര; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u0d35; # FALLBACK FOR ORIYA LETTER WA +\uE081>വ; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0d24\u0d4d; # Bengali Khanda-ta -0 > \u0d66; # FALLBACK FOR TAMIL -1 > \u0d67; - -# :: NFC (NFD) ; -# eof +\uE083>ത\u0D4D; # Bengali Khanda-ta +0 > ൦; # FALLBACK FOR TAMIL +1 > ൧; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Oriya.txt index 50f4509c3b0..0fd8f0f2f7c 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Oriya.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Oriya.txt @@ -1,139 +1,138 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Oriya -#:: NFD (NFC) ; -\ue001>\u0b01; # SIGN CANDRABINDU -\ue002>\u0b02; # SIGN ANUSVARA -\ue003>\u0b03; # SIGN VISARGA -\uE004>\u0b05; # FALLBACK TO LETTER A -\ue005>\u0b05; # LETTER A -\ue006>\u0b06; # LETTER AA -\ue007>\u0b07; # LETTER I -\ue008>\u0b08; # LETTER II -\ue009>\u0b09; # LETTER U -\ue00a>\u0b0a; # LETTER UU -\ue00b>\u0b0b; # LETTER VOCALIC R -\ue00c>\u0b0c; # LETTER VOCALIC L -\ue00d>\u0b0f; # FALLBACK -\ue00e>\u0b0f; # FALLBACK -\ue00f>\u0b0f; # LETTER E -\ue010>\u0b10; # LETTER AI -\ue011>\u0b13; # FALLBACK -\ue012>\u0b13; # FALLBACK -\ue013>\u0b13; # FALLBACK LETTER OO (\u0b13 = LETTER O) -\ue014>\u0b14; # LETTER AU -\ue015>\u0b15; # LETTER KA -\ue016>\u0b16; # LETTER KHA -\ue017>\u0b17; # LETTER GA -\ue018>\u0b18; # LETTER GHA -\ue019>\u0b19; # LETTER NGA -\ue01a>\u0b1a; # LETTER CA -\ue01b>\u0b1b; # LETTER CHA -\ue01c>\u0b1c; # LETTER JA -\ue01d>\u0b1d; # LETTER JHA -\ue01e>\u0b1e; # LETTER NYA -\ue01f>\u0b1f; # LETTER TTA -\ue020>\u0b20; # LETTER TTHA -\ue021>\u0b21; # LETTER DDA -\ue022>\u0b22; # LETTER DDHA -\ue023>\u0b23; # LETTER NNA -\ue024>\u0b24; # LETTER TA -\ue025>\u0b25; # LETTER THA -\ue026>\u0b26; # LETTER DA -\ue027>\u0b27; # LETTER DHA -\ue028>\u0b28; # LETTER NA -\ue029>\u0b28\u0b3c; # FALLBACK \u0b29>\u0b28 = LETTER NNNA>LETTER NA -\ue02a>\u0b2a; # LETTER PA -\ue02b>\u0b2b; # LETTER PHA -\ue02c>\u0b2c; # LETTER BA -\ue02d>\u0b2d; # LETTER BHA -\ue02e>\u0b2e; # LETTER MA -\ue02f>\u0b2f; # LETTER YA -\ue030>\u0b30; # LETTER RA -\ue031>\u0b5c; # LETTER RRA -\ue032>\u0b32; # LETTER LA -\ue033>\u0b33; # LETTER LLA -\ue034>\u0b33\u0b3c; # FALLBACK LETTER LLLA>LETTER LLA -\ue035>\u0b35; # LETTER VA -\ue036>\u0b36; # LETTER SHA -\ue037>\u0b37; # LETTER SSA -\ue038>\u0b38; # LETTER SA -\ue039>\u0b39; # LETTER HA -\ue03c>\u0b3c; # SIGN NUKTA -\ue03d>\u0b3d; # SIGN AVAGRAHA -\ue03e>\u0b3e; # VOWEL SIGN AA -\ue03f>\u0b3f; # VOWEL SIGN I -\ue040>\u0b40; # VOWEL SIGN II -\ue041>\u0b41; # VOWEL SIGN U -\ue042>\u0b42; # VOWEL SIGN UU -\ue043>\u0b43; # VOWEL SIGN VOCALIC R -\ue044>\u0b43\u0b3c; # FALLBACK \u0b44>\u0b43\u0b3c = VOWEL SIGN VOCALIC RR>VOWEL SIGN VOCALIC R.SIGN NUKTA -\ue045>\u0b47; # FALLBACK -\ue046>\u0b47; # FALLBACK -\ue047>\u0b47; # VOWEL SIGN E -\ue048>\u0b48; # VOWEL SIGN AI -\ue049>\u0b4b; # FALLBACK -\ue04a>\u0b4b; # FALLBACK -\ue04b>\u0b4b; # VOWEL SIGN E -\ue04c>\u0b4c; # VOWEL SIGN AU -\ue04d>\u0b4d; # SIGN VIRAMA -\ue050>\u0b13\u0b01; # FALLBACK \u0b50>\u0b13\u0b01 = OM>LETTER O.SIGN CANDRABINDU -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>; # UNMAPPED InterIndic-Oriya: LENGTH MARK -\ue056>\u0b56; # AI LENGTH MARK -\ue057>\u0b57; # AU LENGTH MARK -\ue059>\u0b16\u0b3c; # FALLBACK \u0b59>\u0b16\u0b3c = LETTER KHHA>LETTER KHA.SIGN NUKTA -\ue058>\u0b15\u0b3c; # FALLBACK -\ue05a>\u0b17\u0b3c; # FALLBACK \u0b5a>\u0b17\u0b3c = LETTER GHHA>LETTER GA.SIGN NUKTA -\ue05b>\u0b1c\u0b3c; # FALLBACK \u0b5b>\u0b1c\u0b3c = LETTER ZA>LETTER JA.SIGN NUKTA -\ue05c>\u0b21\u0b3c; # FALLBACK -\ue05d>\u0b5d; # LETTER RHA -\ue05e>\u0b2b\u0b3c; # FALLBACK \u0b5e>\u0b2b\u0b3c = LETTER FA>LETTER PHA.SIGN NUKTA -\ue05f>\u0b5f; # LETTER YYA -\ue060>\u0b60; # LETTER VOCALIC RR -\ue061>\u0b61; # LETTER VOCALIC LL -\ue062>\u0b56\u0b3c; # FALLBACK \u0b62>\u0b56\u0b3c = VOWEL SIGN VOCALIC L>AI LENGTH MARK.SIGN NUKTA -\ue063>\u0b57\u0b3c; # FALLBACK \u0b63>\u0b57\u0b3c = VOWEL SIGN VOCALIC LL>AU LENGTH MARK.SIGN NUKTA -\uE064>\u0964; # DANDA -\uE065>\u0965; # DOUBLE DANDA -\ue066>\u0b66; # DIGIT ZERO -\ue067>\u0b67; # DIGIT ONE -\ue068>\u0b68; # DIGIT TWO -\ue069>\u0b69; # DIGIT THREE -\ue06a>\u0b6a; # DIGIT FOUR -\ue06b>\u0b6b; # DIGIT FIVE -\ue06c>\u0b6c; # DIGIT SIX -\ue06d>\u0b6d; # DIGIT SEVEN -\ue06e>\u0b6e; # DIGIT EIGHT -\ue06f>\u0b6f; # DIGIT NINE -\ue070>; # ABBREVIATION SIGN -\ue071>\u0b30; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0b30; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>\u0B70; # ISSHAR +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\uE001>\u0B01; # SIGN CANDRABINDU +\uE002>ଂ; # SIGN ANUSVARA +\uE003>ଃ; # SIGN VISARGA +\uE004>ଅ; # FALLBACK TO LETTER A +\uE005>ଅ; # LETTER A +\uE006>ଆ; # LETTER AA +\uE007>ଇ; # LETTER I +\uE008>ଈ; # LETTER II +\uE009>ଉ; # LETTER U +\uE00A>ଊ; # LETTER UU +\uE00B>ଋ; # LETTER VOCALIC R +\uE00C>ଌ; # LETTER VOCALIC L +\uE00D>ଏ; # FALLBACK +\uE00E>ଏ; # FALLBACK +\uE00F>ଏ; # LETTER E +\uE010>ଐ; # LETTER AI +\uE011>ଓ; # FALLBACK +\uE012>ଓ; # FALLBACK +\uE013>ଓ; # FALLBACK LETTER OO (ଓ = LETTER O) +\uE014>ଔ; # LETTER AU +\uE015>କ; # LETTER KA +\uE016>ଖ; # LETTER KHA +\uE017>ଗ; # LETTER GA +\uE018>ଘ; # LETTER GHA +\uE019>ଙ; # LETTER NGA +\uE01A>ଚ; # LETTER CA +\uE01B>ଛ; # LETTER CHA +\uE01C>ଜ; # LETTER JA +\uE01D>ଝ; # LETTER JHA +\uE01E>ଞ; # LETTER NYA +\uE01F>ଟ; # LETTER TTA +\uE020>ଠ; # LETTER TTHA +\uE021>ଡ; # LETTER DDA +\uE022>ଢ; # LETTER DDHA +\uE023>ଣ; # LETTER NNA +\uE024>ତ; # LETTER TA +\uE025>ଥ; # LETTER THA +\uE026>ଦ; # LETTER DA +\uE027>ଧ; # LETTER DHA +\uE028>ନ; # LETTER NA +\uE029>ନ\u0B3C; # FALLBACK \u0B29>ନ = LETTER NNNA>LETTER NA +\uE02A>ପ; # LETTER PA +\uE02B>ଫ; # LETTER PHA +\uE02C>ବ; # LETTER BA +\uE02D>ଭ; # LETTER BHA +\uE02E>ମ; # LETTER MA +\uE02F>ଯ; # LETTER YA +\uE030>ର; # LETTER RA +\uE031>ଡ଼; # LETTER RRA +\uE032>ଲ; # LETTER LA +\uE033>ଳ; # LETTER LLA +\uE034>ଳ\u0B3C; # FALLBACK LETTER LLLA>LETTER LLA +\uE035>ଵ; # LETTER VA +\uE036>ଶ; # LETTER SHA +\uE037>ଷ; # LETTER SSA +\uE038>ସ; # LETTER SA +\uE039>ହ; # LETTER HA +\uE03C>\u0B3C; # SIGN NUKTA +\uE03D>ଽ; # SIGN AVAGRAHA +\uE03E>ା; # VOWEL SIGN AA +\uE03F>\u0B3F; # VOWEL SIGN I +\uE040>ୀ; # VOWEL SIGN II +\uE041>\u0B41; # VOWEL SIGN U +\uE042>\u0B42; # VOWEL SIGN UU +\uE043>\u0B43; # VOWEL SIGN VOCALIC R +\uE044>\u0B43\u0B3C; # FALLBACK \u0B44>\u0B43\u0B3C = VOWEL SIGN VOCALIC RR>VOWEL SIGN VOCALIC R.SIGN NUKTA +\uE045>େ; # FALLBACK +\uE046>େ; # FALLBACK +\uE047>େ; # VOWEL SIGN E +\uE048>ୈ; # VOWEL SIGN AI +\uE049>ୋ; # FALLBACK +\uE04A>ୋ; # FALLBACK +\uE04B>ୋ; # VOWEL SIGN E +\uE04C>ୌ; # VOWEL SIGN AU +\uE04D>\u0B4D; # SIGN VIRAMA +\uE050>ଓ\u0B01; # FALLBACK \u0B50>ଓ\u0B01 = OM>LETTER O.SIGN CANDRABINDU +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>; # UNMAPPED InterIndic-Oriya: LENGTH MARK +\uE056>\u0B56; # AI LENGTH MARK +\uE057>ୗ; # AU LENGTH MARK +\uE059>ଖ\u0B3C; # FALLBACK \u0B59>ଖ\u0B3C = LETTER KHHA>LETTER KHA.SIGN NUKTA +\uE058>କ\u0B3C; # FALLBACK +\uE05A>ଗ\u0B3C; # FALLBACK \u0B5A>ଗ\u0B3C = LETTER GHHA>LETTER GA.SIGN NUKTA +\uE05B>ଜ\u0B3C; # FALLBACK \u0B5B>ଜ\u0B3C = LETTER ZA>LETTER JA.SIGN NUKTA +\uE05C>ଡ\u0B3C; # FALLBACK +\uE05D>ଢ଼; # LETTER RHA +\uE05E>ଫ\u0B3C; # FALLBACK \u0B5E>ଫ\u0B3C = LETTER FA>LETTER PHA.SIGN NUKTA +\uE05F>ୟ; # LETTER YYA +\uE060>ୠ; # LETTER VOCALIC RR +\uE061>ୡ; # LETTER VOCALIC LL +\uE062>\u0B56\u0B3C; # FALLBACK \u0B62>\u0B56\u0B3C = VOWEL SIGN VOCALIC L>AI LENGTH MARK.SIGN NUKTA +\uE063>ୗ\u0B3C; # FALLBACK \u0B63>ୗ\u0B3C = VOWEL SIGN VOCALIC LL>AU LENGTH MARK.SIGN NUKTA +\uE064>।; # DANDA +\uE065>॥; # DOUBLE DANDA +\uE066>୦; # DIGIT ZERO +\uE067>୧; # DIGIT ONE +\uE068>୨; # DIGIT TWO +\uE069>୩; # DIGIT THREE +\uE06A>୪; # DIGIT FOUR +\uE06B>୫; # DIGIT FIVE +\uE06C>୬; # DIGIT SIX +\uE06D>୭; # DIGIT SEVEN +\uE06E>୮; # DIGIT EIGHT +\uE06F>୯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ର; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ର; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>୰; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u0B71; # LETTER WA +\uE081>ୱ; # LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0b24\u0b4d; # Bengali Khanda-ta -0 > \u0b66; # FALLBACK FOR TAMIL -1 > \u0b67; - -# :: NFC (NFD) ; -# eof +\uE083>ତ\u0B4D; # Bengali Khanda-ta +0 > ୦; # FALLBACK FOR TAMIL +1 > ୧; diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Tamil.txt index 9b39037b546..6a08581567c 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Tamil.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Tamil.txt @@ -1,153 +1,145 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Tamil -#:: NFD (NFC) ; -\ue001>\u0b82; # FALLBACK SIGN CANDRABINDU -\ue002>\u0b82; # SIGN ANUSVARA -\ue003>\u0b83; # SIGN VISARGA -\uE004>\u0b85; # FALLBACK TO LETTER A -\ue005>\u0b85; # LETTER A -\ue006>\u0b86; # LETTER AA -\ue007>\u0b87; # LETTER I -\ue008>\u0b88; # LETTER II -\ue009>\u0b89; # LETTER U -\ue00a>\u0b8a; # LETTER UU -\ue00b>\u0bb0\u0bbf; # REMAP (indicExceptions.txt): \u0b8b>\u0bb0\u0bbf = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I -\ue00c>\u0bb2; # FALLBACK LETTER LA -\ue00d>\u0b8f; # FALLBACK -\ue00e>\u0b8e; # LETTER E -\ue00f>\u0b8f; # LETTER EE -\ue010>\u0b90; # LETTER AI -\ue011>\u0b92; # FALLBACK -\ue012>\u0b92; # LETTER O -\ue013>\u0b93; # LETTER OO -\ue014>\u0b94; # LETTER AU -\ue015>\u0b95; # LETTER KA -\ue016>\u0b95; # REMAP (indicExceptions.txt): \u0b96>\u0b95 = LETTER KHA>LETTER KA -\ue017>\u0b95; # REMAP (indicExceptions.txt): \u0b97>\u0b95 = LETTER GA>LETTER KA -\ue018>\u0b95; # REMAP (indicExceptions.txt): \u0b98>\u0b95 = LETTER GHA>LETTER KA -\ue019>\u0b99; # LETTER NGA -\ue01a>\u0b9a; # LETTER CA -\ue01b>\u0b9a; # REMAP (indicExceptions.txt): \u0b9b>\u0b9a = LETTER CHA>LETTER CA -\ue01c>\u0b9c; # LETTER JA -\ue01d>\u0b9a; # REMAP (indicExceptions.txt): \u0b9d>\u0b9a = LETTER JHA>LETTER CA -\ue01e>\u0b9e; # LETTER NYA -\ue01f>\u0b9f; # LETTER TTA -\ue020>\u0b9f; # REMAP (indicExceptions.txt): \u0ba0>\u0b9f = LETTER TTHA>LETTER TTA -\ue021>\u0b9f; # REMAP (indicExceptions.txt): \u0ba1>\u0b9f = LETTER DDA>LETTER TTA -\ue022>\u0b9f; # REMAP (indicExceptions.txt): \u0ba2>\u0b9f = LETTER DDHA>LETTER TTA -\ue023>\u0ba3; # LETTER NNA -\ue024>\u0ba4; # LETTER TA -\ue025>\u0ba4; # REMAP (indicExceptions.txt): \u0ba5>\u0ba4 = LETTER THA>LETTER TA -\ue026>\u0ba4; # REMAP (indicExceptions.txt): \u0ba6>\u0ba4 = LETTER DA>LETTER TA -\ue027>\u0ba4; # REMAP (indicExceptions.txt): \u0ba7>\u0ba4 = LETTER DHA>LETTER TA -\ue028\ue03c>\u0ba9; -\ue028>\u0ba8; # LETTER NA -\ue029>\u0ba9; # LETTER NNNA -\ue02a>\u0baa; # LETTER PA -\ue02b>\u0baa; # REMAP (indicExceptions.txt): \u0bab>\u0baa = LETTER PHA>LETTER PA -\ue02c>\u0baa; # REMAP (indicExceptions.txt): \u0bac>\u0baa = LETTER BA>LETTER PA -\ue02d>\u0baa; # REMAP (indicExceptions.txt): \u0bad>\u0baa = LETTER BHA>LETTER PA -\ue02e>\u0bae; # LETTER MA -\ue02f>\u0baf; # LETTER YA -\ue030\ue03c>\u0bb1; -\ue030>\u0bb0; # LETTER RA -\ue031>\u0bb1; # LETTER RRA -\ue032>\u0bb2; # LETTER LA -\ue033\ue03c>\u0bb4; -\ue033>\u0bb3; # LETTER LLA -\ue034>\u0bb4; # LETTER LLLA -\ue035>\u0bb5; # LETTER VA -\ue036>\u0bb6; # REMAP (indicExceptions.txt): \u0bb6>\u0bb7 = LETTER SHA>LETTER SSA -\ue037>\u0bb7; # LETTER SSA -\ue038>\u0bb8; # LETTER SA -\ue039>\u0bb9; # LETTER HA - -\ue03c>; # FALLBACK BLOW AWAY NUKTA -\ue03d>; # FALLBACK BLOW AWAY AVAGRAHA - -\ue03e>\u0bbe; # VOWEL SIGN AA -\ue03f>\u0bbf; # VOWEL SIGN I -\ue040>\u0bc0; # VOWEL SIGN II -\ue041>\u0bc1; # VOWEL SIGN U -\ue042>\u0bc2; # VOWEL SIGN UU -\ue043>\u0bcd\u0bb0\u0bbf; # REMAP (indicExceptions.txt): \u0bc3>\u0bcd\u0bb0\u0bbf = VOWEL SIGN VOCALIC R>SIGN VIRAMA.LETTER RA.VOWEL SIGN I -\ue044>\u0bcd\u0bb0\u0bbf; # REMAP (indicExceptions.txt): \u0bc4>\u0bcd\u0bb0\u0bbf = VOWEL SIGN VOCALIC RR>SIGN VIRAMA.LETTER RA.VOWEL SIGN I -\ue045>\u0bbe; # REMAP (indicExceptions.txt): \u0bc5>\u0bbe = VOWEL SIGN CANDRA E>VOWEL SIGN AA -\ue046>\u0bc6; # VOWEL SIGN E -\ue047>\u0bc7; # VOWEL SIGN EE -\ue048>\u0bc8; # VOWEL SIGN AI -\ue049>\u0bbe; # REMAP (indicExceptions.txt): \u0bc9>\u0bbe = VOWEL SIGN CANDRA O>VOWEL SIGN AA -\ue04a>\u0bca; # VOWEL SIGN O -\ue04b>\u0bcb; # VOWEL SIGN OO -\ue04c>\u0bcc; # VOWEL SIGN AU -\ue04d>\u0bcd; # SIGN VIRAMA -\ue050>\u0b93\u0bae\u0bcd; # REMAP (indicExceptions.txt): \u0bd0>\u0b93\u0bae\u0bcd = OM>LETTER OO.LETTER MA.SIGN VIRAMA -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>; # UNMAPPED InterIndic-Tamil: LENGTH MARK -\ue056>\u0bc8; # REMAP (indicExceptions.txt): \u0bd6>\u0bc8 = AI LENGTH MARK>VOWEL SIGN AI -\ue057>\u0bd7; # AU LENGTH MARK -\ue058>\u0b95; # FALLBACK -\ue059>\u0b95; # REMAP (indicExceptions.txt): \u0bd9>\u0b95 = LETTER KHHA>LETTER KA -\ue05a>\u0b95; # REMAP (indicExceptions.txt): \u0bda>\u0b95 = LETTER GHHA>LETTER KA -\ue05b>\u0b9c; # REMAP (indicExceptions.txt): \u0bdb>\u0b9c = LETTER ZA>LETTER JA -\ue05c>\u0ba4; # FALLBACK -\ue05d>\u0b9f; # REMAP (indicExceptions.txt): \u0bdd>\u0b9f = LETTER RHA>LETTER TTA -\ue05e>\u0baa; # REMAP (indicExceptions.txt): \u0bde>\u0baa = LETTER FA>LETTER PA -\ue05f>\u0baf; # REMAP (indicExceptions.txt): \u0bdf>\u0baf = LETTER YYA>LETTER YA -\ue060>\u0bb0\u0bbf; # REMAP (indicExceptions.txt): \u0be0>\u0bb0\u0bbf = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I -\ue061>\u0bb3; # FALLBACK LETTER LLA -\ue062>\u0bbf; # FALLBACK VOWEL SIGN VOCALIC L -\ue063>\u0bc0; # FALLBACK VOWEL SIGN VOCALIC LL -\ue064>'.' ; # FALLBACK FOR DANDA -\ue065>'.' ; # FALLBACK FOR DOUBLE DANDA - -\ue066>\u0030; # FALLBACK DIGIT ZERO - -\ue067\ue066\ue066\ue066>\u0bF2; -\ue067\ue066\ue066>\u0bf1; -\ue067\ue066>\u0bF0; - -\ue067>\u0be7; # DIGIT ONE -\ue068>\u0be8; # DIGIT TWO -\ue069>\u0be9; # DIGIT THREE -\ue06a>\u0bea; # DIGIT FOUR -\ue06b>\u0beb; # DIGIT FIVE -\ue06c>\u0bec; # DIGIT SIX -\ue06d>\u0bed; # DIGIT SEVEN -\ue06e>\u0bee; # DIGIT EIGHT -\ue06f>\u0bef; # DIGIT NINE - -\ue070>; # ABBREVIATION SIGN -\ue071>\u0bc0; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0bc0; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>; # ISSHAR +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\uE001>\u0B82; # FALLBACK SIGN CANDRABINDU +\uE002>\u0B82; # SIGN ANUSVARA +\uE003>ஃ; # SIGN VISARGA +\uE004>அ; # FALLBACK TO LETTER A +\uE005>அ; # LETTER A +\uE006>ஆ; # LETTER AA +\uE007>இ; # LETTER I +\uE008>ஈ; # LETTER II +\uE009>உ; # LETTER U +\uE00A>ஊ; # LETTER UU +\uE00B>ரி; # REMAP (indicExceptions.txt): \u0B8B>ரி = LETTER VOCALIC R>LETTER RA.VOWEL SIGN I +\uE00C>ல; # FALLBACK LETTER LA +\uE00D>ஏ; # FALLBACK +\uE00E>எ; # LETTER E +\uE00F>ஏ; # LETTER EE +\uE010>ஐ; # LETTER AI +\uE011>ஒ; # FALLBACK +\uE012>ஒ; # LETTER O +\uE013>ஓ; # LETTER OO +\uE014>ஔ; # LETTER AU +\uE015>க; # LETTER KA +\uE016>க; # REMAP (indicExceptions.txt): \u0B96>க = LETTER KHA>LETTER KA +\uE017>க; # REMAP (indicExceptions.txt): \u0B97>க = LETTER GA>LETTER KA +\uE018>க; # REMAP (indicExceptions.txt): \u0B98>க = LETTER GHA>LETTER KA +\uE019>ங; # LETTER NGA +\uE01A>ச; # LETTER CA +\uE01B>ச; # REMAP (indicExceptions.txt): \u0B9B>ச = LETTER CHA>LETTER CA +\uE01C>ஜ; # LETTER JA +\uE01D>ச; # REMAP (indicExceptions.txt): \u0B9D>ச = LETTER JHA>LETTER CA +\uE01E>ஞ; # LETTER NYA +\uE01F>ட; # LETTER TTA +\uE020>ட; # REMAP (indicExceptions.txt): \u0BA0>ட = LETTER TTHA>LETTER TTA +\uE021>ட; # REMAP (indicExceptions.txt): \u0BA1>ட = LETTER DDA>LETTER TTA +\uE022>ட; # REMAP (indicExceptions.txt): \u0BA2>ட = LETTER DDHA>LETTER TTA +\uE023>ண; # LETTER NNA +\uE024>த; # LETTER TA +\uE025>த; # REMAP (indicExceptions.txt): \u0BA5>த = LETTER THA>LETTER TA +\uE026>த; # REMAP (indicExceptions.txt): \u0BA6>த = LETTER DA>LETTER TA +\uE027>த; # REMAP (indicExceptions.txt): \u0BA7>த = LETTER DHA>LETTER TA +\uE028\uE03C>ன; +\uE028>ந; # LETTER NA +\uE029>ன; # LETTER NNNA +\uE02A>ப; # LETTER PA +\uE02B>ப; # REMAP (indicExceptions.txt): \u0BAB>ப = LETTER PHA>LETTER PA +\uE02C>ப; # REMAP (indicExceptions.txt): \u0BAC>ப = LETTER BA>LETTER PA +\uE02D>ப; # REMAP (indicExceptions.txt): \u0BAD>ப = LETTER BHA>LETTER PA +\uE02E>ம; # LETTER MA +\uE02F>ய; # LETTER YA +\uE030\uE03C>ற; +\uE030>ர; # LETTER RA +\uE031>ற; # LETTER RRA +\uE032>ல; # LETTER LA +\uE033\uE03C>ழ; +\uE033>ள; # LETTER LLA +\uE034>ழ; # LETTER LLLA +\uE035>வ; # LETTER VA +\uE036>ஶ; # REMAP (indicExceptions.txt): ஶ>ஷ = LETTER SHA>LETTER SSA +\uE037>ஷ; # LETTER SSA +\uE038>ஸ; # LETTER SA +\uE039>ஹ; # LETTER HA +\uE03C>; # FALLBACK BLOW AWAY NUKTA +\uE03D>; # FALLBACK BLOW AWAY AVAGRAHA +\uE03E>ா; # VOWEL SIGN AA +\uE03F>ி; # VOWEL SIGN I +\uE040>\u0BC0; # VOWEL SIGN II +\uE041>ு; # VOWEL SIGN U +\uE042>ூ; # VOWEL SIGN UU +\uE043>\u0BCDரி; # REMAP (indicExceptions.txt): \u0BC3>\u0BCDரி = VOWEL SIGN VOCALIC R>SIGN VIRAMA.LETTER RA.VOWEL SIGN I +\uE044>\u0BCDரி; # REMAP (indicExceptions.txt): \u0BC4>\u0BCDரி = VOWEL SIGN VOCALIC RR>SIGN VIRAMA.LETTER RA.VOWEL SIGN I +\uE045>ா; # REMAP (indicExceptions.txt): \u0BC5>ா = VOWEL SIGN CANDRA E>VOWEL SIGN AA +\uE046>ெ; # VOWEL SIGN E +\uE047>ே; # VOWEL SIGN EE +\uE048>ை; # VOWEL SIGN AI +\uE049>ா; # REMAP (indicExceptions.txt): \u0BC9>ா = VOWEL SIGN CANDRA O>VOWEL SIGN AA +\uE04A>ொ; # VOWEL SIGN O +\uE04B>ோ; # VOWEL SIGN OO +\uE04C>ௌ; # VOWEL SIGN AU +\uE04D>\u0BCD; # SIGN VIRAMA +\uE050>ஓம\u0BCD; # REMAP (indicExceptions.txt): \u0BD0>ஓம\u0BCD = OM>LETTER OO.LETTER MA.SIGN VIRAMA +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>; # UNMAPPED InterIndic-Tamil: LENGTH MARK +\uE056>ை; # REMAP (indicExceptions.txt): \u0BD6>ை = AI LENGTH MARK>VOWEL SIGN AI +\uE057>ௗ; # AU LENGTH MARK +\uE058>க; # FALLBACK +\uE059>க; # REMAP (indicExceptions.txt): \u0BD9>க = LETTER KHHA>LETTER KA +\uE05A>க; # REMAP (indicExceptions.txt): \u0BDA>க = LETTER GHHA>LETTER KA +\uE05B>ஜ; # REMAP (indicExceptions.txt): \u0BDB>ஜ = LETTER ZA>LETTER JA +\uE05C>த; # FALLBACK +\uE05D>ட; # REMAP (indicExceptions.txt): \u0BDD>ட = LETTER RHA>LETTER TTA +\uE05E>ப; # REMAP (indicExceptions.txt): \u0BDE>ப = LETTER FA>LETTER PA +\uE05F>ய; # REMAP (indicExceptions.txt): \u0BDF>ய = LETTER YYA>LETTER YA +\uE060>ரி; # REMAP (indicExceptions.txt): \u0BE0>ரி = LETTER VOCALIC RR>LETTER RA.VOWEL SIGN I +\uE061>ள; # FALLBACK LETTER LLA +\uE062>ி; # FALLBACK VOWEL SIGN VOCALIC L +\uE063>\u0BC0; # FALLBACK VOWEL SIGN VOCALIC LL +\uE064>'.' ; # FALLBACK FOR DANDA +\uE065>'.' ; # FALLBACK FOR DOUBLE DANDA +\uE066>\u0030; # FALLBACK DIGIT ZERO +\uE067\uE066\uE066\uE066>௲; +\uE067\uE066\uE066>௱; +\uE067\uE066>௰; +\uE067>௧; # DIGIT ONE +\uE068>௨; # DIGIT TWO +\uE069>௩; # DIGIT THREE +\uE06A>௪; # DIGIT FOUR +\uE06B>௫; # DIGIT FIVE +\uE06C>௬; # DIGIT SIX +\uE06D>௭; # DIGIT SEVEN +\uE06E>௮; # DIGIT EIGHT +\uE06F>௯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>\u0BC0; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>\u0BC0; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u0bb5; # FALLBACK FOR ORIYA LETTER WA +\uE081>வ; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0ba4\u0bcd; # Bengali Khanda-ta - -1000 >\u0BF2; # NUMBER ONE THOUSAND -100 >\u0BF1; # NUMBER ONE HUNDRED -10 >\u0BF0; # NUMBER TEN - -# :: NFC (NFD) ; -# eof +\uE083>த\u0BCD; # Bengali Khanda-ta +1000 >௲; # NUMBER ONE THOUSAND +100 >௱; # NUMBER ONE HUNDRED +10 >௰; # NUMBER TEN diff --git a/Build/source/libs/icu-xetex/data/translit/InterIndic_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/InterIndic_Telugu.txt index 943a23a1e5f..3819b011eaa 100644 --- a/Build/source/libs/icu-xetex/data/translit/InterIndic_Telugu.txt +++ b/Build/source/libs/icu-xetex/data/translit/InterIndic_Telugu.txt @@ -1,143 +1,139 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Telugu -#:: NFD (NFC) ; -\ue001>\u0c01; # SIGN CANDRABINDU -\ue002>\u0c02; # SIGN ANUSVARA -\ue003>\u0c03; # SIGN VISARGA -\uE004>\u0c05; # FALLBACK TO LETTER A -\ue005>\u0c05; # LETTER A -\ue006>\u0c06; # LETTER AA -\ue007>\u0c07; # LETTER I -\ue008>\u0c08; # LETTER II -\ue009>\u0c09; # LETTER U -\ue00a>\u0c0a; # LETTER UU -\ue00b>\u0c0b; # LETTER VOCALIC R -\ue00c>\u0c0c; # LETTER VOCALIC L -\ue00d>\u0c0E; # FALLBACK MAPPING -\ue00e>\u0c0E; # LETTER E -\ue00f>\u0c0f; # LETTER EE -\ue010>\u0c10; # LETTER AI -\ue011>\u0c12; # FALBACK MAPPING -\ue012>\u0c12; # LETTER O -\ue013>\u0c13; # LETTER OO -\ue014>\u0c14; # LETTER AU -\ue015>\u0c15; # LETTER KA -\ue016>\u0c16; # LETTER KHA -\ue017>\u0c17; # LETTER GA -\ue018>\u0c18; # LETTER GHA -\ue019>\u0c19; # LETTER NGA -\ue01a>\u0c1a; # LETTER CA -\ue01b>\u0c1b; # LETTER CHA -\ue01c>\u0c1c; # LETTER JA -\ue01d>\u0c1d; # LETTER JHA -\ue01e>\u0c1e; # LETTER NYA -\ue01f>\u0c1f; # LETTER TTA -\ue020>\u0c20; # LETTER TTHA -\ue021>\u0c21; # LETTER DDA -\ue022>\u0c22; # LETTER DDHA -\ue023>\u0c23; # LETTER NNA -\ue024>\u0c24; # LETTER TA -\ue025>\u0c25; # LETTER THA -\ue026>\u0c26; # LETTER DA -\ue027>\u0c27; # LETTER DHA -\ue028>\u0c28; # LETTER NA -\ue029>\u0c28; # REMAP (indicExceptions.txt): \u0c29>\u0c28 = LETTER NNNA>LETTER NA -\ue02a>\u0c2a; # LETTER PA -\ue02b>\u0c2b; # LETTER PHA -\ue02c>\u0c2c; # LETTER BA -\ue02d>\u0c2d; # LETTER BHA -\ue02e>\u0c2e; # LETTER MA -\ue02f>\u0c2f; # LETTER YA -\ue030\ue03c>\u0c31; -\ue030>\u0c30; # LETTER RA -\ue031>\u0c31; # LETTER RRA -\ue032>\u0c32; # LETTER LA -\ue033>\u0c33; # LETTER LLA -\ue034>\u0c33; # REMAP (indicExceptions.txt): \u0c34>\u0c33 = LETTER LLLA>LETTER LLA -\ue035>\u0c35; # LETTER VA -\ue036>\u0c36; # LETTER SHA -\ue037>\u0c37; # LETTER SSA -\ue038>\u0c38; # LETTER SA -\ue039>\u0c39; # LETTER HA - -\ue03c>; # FALLBACK BLOW AWAY NUKTA -\ue03d>; # FALLBACK BLOW AWAY AVAGRAHA - -\ue03e>\u0c3e; # VOWEL SIGN AA -\ue03f>\u0c3f; # VOWEL SIGN I -\ue040>\u0c40; # VOWEL SIGN II -\ue041>\u0c41; # VOWEL SIGN U -\ue042>\u0c42; # VOWEL SIGN UU -\ue043>\u0c43; # VOWEL SIGN VOCALIC R -\ue044>\u0c44; # VOWEL SIGN VOCALIC RR -\ue045>\u0c46; # VOWEL SIGN CANDRA E>VOWEL SIGN E -\ue046>\u0c46; # VOWEL SIGN E -\ue047>\u0c47; # VOWEL SIGN EE -\ue048>\u0c48; # VOWEL SIGN AI -\ue049>\u0c4a; # REMAP (indicExceptions.txt): \u0c49>\u0c4a = VOWEL SIGN CANDRA O>VOWEL SIGN O -\ue04a>\u0c4a; # VOWEL SIGN O -\ue04b>\u0c4b; # VOWEL SIGN OO -\ue04c>\u0c4c; # VOWEL SIGN AU -\ue04d>\u0c4d; # SIGN VIRAMA -\ue050>\u0c13\u0c02; # REMAP (indicExceptions.txt): \u0c50>\u0c13\u0c02 = OM>LETTER OO.SIGN ANUSVARA -\ue051>; -\ue052>; -\ue053>; -\ue054>; -\ue055>\u0c55; # LENGTH MARK -\ue056>\u0c56; # AI LENGTH MARK -\ue057>\u0c4c; # REMAP (indicExceptions.txt): \u0c57>\u0c4c = AU LENGTH MARK>VOWEL SIGN AU -\ue058>\u0c15; # REMAP -\ue059>\u0c16; # REMAP (indicExceptions.txt): \u0c59>\u0c16 = LETTER KHHA>LETTER KHA -\ue05a>\u0c17; # REMAP (indicExceptions.txt): \u0c5a>\u0c17 = LETTER GHHA>LETTER GA -\ue05b>\u0c1c; # REMAP (indicExceptions.txt): \u0c5b>\u0c1c = LETTER ZA>LETTER JA -\ue05c>\u0c22; # REMAP -\ue05d>\u0c22; # REMAP (indicExceptions.txt): \u0c5d>\u0c22 = LETTER RHA>LETTER DDHA -\ue05e>\u0c2b; # REMAP (indicExceptions.txt): \u0c5e>\u0c2b = LETTER FA>LETTER PHA -\ue05f>\u0c2f; # REMAP (indicExceptions.txt): \u0c5f>\u0c2f = LETTER YYA>LETTER YA -\ue060>\u0c60; # LETTER VOCALIC RR -\ue061>\u0c61; # LETTER VOCALIC LL -\ue062>\u0c3f; # REMAP (indicExceptions.txt): \u0c62>\u0c3f = VOWEL SIGN VOCALIC L>VOWEL SIGN I -\ue063>\u0c40; # REMAP (indicExceptions.txt): \u0c63>\u0c40 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II -\ue064>'.' ; # FALLBACK FOR DANDA -\ue065>'.' ; # FALLBACK FOR DOUBLE DANDA -\ue066>\u0c66; # DIGIT ZERO -\ue067>\u0c67; # DIGIT ONE -\ue068>\u0c68; # DIGIT TWO -\ue069>\u0c69; # DIGIT THREE -\ue06a>\u0c6a; # DIGIT FOUR -\ue06b>\u0c6b; # DIGIT FIVE -\ue06c>\u0c6c; # DIGIT SIX -\ue06d>\u0c6d; # DIGIT SEVEN -\ue06e>\u0c6e; # DIGIT EIGHT -\ue06f>\u0c6f; # DIGIT NINE - -\ue070>; # ABBREVIATION SIGN -\ue071>\u0c30; # LETTER RA WITH MIDDLE DIAGONAL -\ue072>\u0c30; # LETTER RA WITH LOWER DIAGONAL -\ue073>; # RUPEE MARK -\ue074>; # RUPEE SIGN -\ue075>; # CURRENCY NUMERATOR ONE -\ue076>; # CURRENCY NUMERATOR TWO -\ue077>; # CURRENCY NUMERATOR THREE -\ue078>; # CURRENCY NUMERATOR FOUR -\ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR -\ue07A>; # CURRENCY DENOMINATOR SIXTEEN -\ue07B>; # ISSHAR +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\uE001>ఁ; # SIGN CANDRABINDU +\uE002>ం; # SIGN ANUSVARA +\uE003>ః; # SIGN VISARGA +\uE004>అ; # FALLBACK TO LETTER A +\uE005>అ; # LETTER A +\uE006>ఆ; # LETTER AA +\uE007>ఇ; # LETTER I +\uE008>ఈ; # LETTER II +\uE009>ఉ; # LETTER U +\uE00A>ఊ; # LETTER UU +\uE00B>ఋ; # LETTER VOCALIC R +\uE00C>ఌ; # LETTER VOCALIC L +\uE00D>ఎ; # FALLBACK MAPPING +\uE00E>ఎ; # LETTER E +\uE00F>ఏ; # LETTER EE +\uE010>ఐ; # LETTER AI +\uE011>ఒ; # FALBACK MAPPING +\uE012>ఒ; # LETTER O +\uE013>ఓ; # LETTER OO +\uE014>ఔ; # LETTER AU +\uE015>క; # LETTER KA +\uE016>ఖ; # LETTER KHA +\uE017>గ; # LETTER GA +\uE018>ఘ; # LETTER GHA +\uE019>ఙ; # LETTER NGA +\uE01A>చ; # LETTER CA +\uE01B>ఛ; # LETTER CHA +\uE01C>జ; # LETTER JA +\uE01D>ఝ; # LETTER JHA +\uE01E>ఞ; # LETTER NYA +\uE01F>ట; # LETTER TTA +\uE020>ఠ; # LETTER TTHA +\uE021>డ; # LETTER DDA +\uE022>ఢ; # LETTER DDHA +\uE023>ణ; # LETTER NNA +\uE024>త; # LETTER TA +\uE025>థ; # LETTER THA +\uE026>ద; # LETTER DA +\uE027>ధ; # LETTER DHA +\uE028>న; # LETTER NA +\uE029>న; # REMAP (indicExceptions.txt): \u0C29>న = LETTER NNNA>LETTER NA +\uE02A>ప; # LETTER PA +\uE02B>ఫ; # LETTER PHA +\uE02C>బ; # LETTER BA +\uE02D>భ; # LETTER BHA +\uE02E>మ; # LETTER MA +\uE02F>య; # LETTER YA +\uE030\uE03C>ఱ; +\uE030>ర; # LETTER RA +\uE031>ఱ; # LETTER RRA +\uE032>ల; # LETTER LA +\uE033>ళ; # LETTER LLA +\uE034>ళ; # REMAP (indicExceptions.txt): \u0C34>ళ = LETTER LLLA>LETTER LLA +\uE035>వ; # LETTER VA +\uE036>శ; # LETTER SHA +\uE037>ష; # LETTER SSA +\uE038>స; # LETTER SA +\uE039>హ; # LETTER HA +\uE03C>; # FALLBACK BLOW AWAY NUKTA +\uE03D>; # FALLBACK BLOW AWAY AVAGRAHA +\uE03E>\u0C3E; # VOWEL SIGN AA +\uE03F>\u0C3F; # VOWEL SIGN I +\uE040>\u0C40; # VOWEL SIGN II +\uE041>ు; # VOWEL SIGN U +\uE042>ూ; # VOWEL SIGN UU +\uE043>ృ; # VOWEL SIGN VOCALIC R +\uE044>ౄ; # VOWEL SIGN VOCALIC RR +\uE045>\u0C46; # VOWEL SIGN CANDRA E>VOWEL SIGN E +\uE046>\u0C46; # VOWEL SIGN E +\uE047>\u0C47; # VOWEL SIGN EE +\uE048>\u0C48; # VOWEL SIGN AI +\uE049>\u0C4A; # REMAP (indicExceptions.txt): \u0C49>\u0C4A = VOWEL SIGN CANDRA O>VOWEL SIGN O +\uE04A>\u0C4A; # VOWEL SIGN O +\uE04B>\u0C4B; # VOWEL SIGN OO +\uE04C>\u0C4C; # VOWEL SIGN AU +\uE04D>\u0C4D; # SIGN VIRAMA +\uE050>ఓం; # REMAP (indicExceptions.txt): \u0C50>ఓం = OM>LETTER OO.SIGN ANUSVARA +\uE051>; +\uE052>; +\uE053>; +\uE054>; +\uE055>\u0C55; # LENGTH MARK +\uE056>\u0C56; # AI LENGTH MARK +\uE057>\u0C4C; # REMAP (indicExceptions.txt): \u0C57>\u0C4C = AU LENGTH MARK>VOWEL SIGN AU +\uE058>క; # REMAP +\uE059>ఖ; # REMAP (indicExceptions.txt): \u0C59>ఖ = LETTER KHHA>LETTER KHA +\uE05A>గ; # REMAP (indicExceptions.txt): \u0C5A>గ = LETTER GHHA>LETTER GA +\uE05B>జ; # REMAP (indicExceptions.txt): \u0C5B>జ = LETTER ZA>LETTER JA +\uE05C>ఢ; # REMAP +\uE05D>ఢ; # REMAP (indicExceptions.txt): \u0C5D>ఢ = LETTER RHA>LETTER DDHA +\uE05E>ఫ; # REMAP (indicExceptions.txt): \u0C5E>ఫ = LETTER FA>LETTER PHA +\uE05F>య; # REMAP (indicExceptions.txt): \u0C5F>య = LETTER YYA>LETTER YA +\uE060>ౠ; # LETTER VOCALIC RR +\uE061>ౡ; # LETTER VOCALIC LL +\uE062>\u0C3F; # REMAP (indicExceptions.txt): \u0C62>\u0C3F = VOWEL SIGN VOCALIC L>VOWEL SIGN I +\uE063>\u0C40; # REMAP (indicExceptions.txt): \u0C63>\u0C40 = VOWEL SIGN VOCALIC LL>VOWEL SIGN II +\uE064>'.' ; # FALLBACK FOR DANDA +\uE065>'.' ; # FALLBACK FOR DOUBLE DANDA +\uE066>౦; # DIGIT ZERO +\uE067>౧; # DIGIT ONE +\uE068>౨; # DIGIT TWO +\uE069>౩; # DIGIT THREE +\uE06A>౪; # DIGIT FOUR +\uE06B>౫; # DIGIT FIVE +\uE06C>౬; # DIGIT SIX +\uE06D>౭; # DIGIT SEVEN +\uE06E>౮; # DIGIT EIGHT +\uE06F>౯; # DIGIT NINE +\uE070>; # ABBREVIATION SIGN +\uE071>ర; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>ర; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR \uE07C>; # TIPPI \uE07D>; # ADDAK \uE07E>; # IRI \uE07F>; # URA \uE080>; # EK ONKAR -\uE081>\u0c35; # FALLBACK FOR ORIYA LETTER WA +\uE081>వ; # FALLBACK FOR ORIYA LETTER WA \uE082>; # Devanagari Glottal Stop -\uE083>\u0c24\u0c4d; # Bengali Khanda-ta -0 > \u0c66; # FALLBACK FOR TAMIL -1 > \u0c67; - -# :: NFC (NFD) ; -# eof +\uE083>త\u0C4D; # Bengali Khanda-ta +0 > ౦; # FALLBACK FOR TAMIL +1 > ౧; diff --git a/Build/source/libs/icu-xetex/data/translit/Jamo_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Jamo_Latin.txt new file mode 100644 index 00000000000..c0dfd589634 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Jamo_Latin.txt @@ -0,0 +1,13 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Jamo_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::['ᄀ-하-ᅵᆨ-ᇂ가-힣]; +::NFD; +::ConjoiningJamo-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Bengali.txt new file mode 100644 index 00000000000..11e38a72108 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Devanagari.txt new file mode 100644 index 00000000000..04053e28d97 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Gujarati.txt new file mode 100644 index 00000000000..6baf8dc7f83 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Gurmukhi.txt new file mode 100644 index 00000000000..61edf3e65fd --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_InterIndic.txt index bc42c7caeac..198e955d430 100644 --- a/Build/source/libs/icu-xetex/data/translit/Kannada_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_InterIndic.txt @@ -1,92 +1,92 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Kannada-InterIndic -\u0CC6\u0CD5>\uE047; # VOWEL SIGN EE -\u0CC6\u0CCD\u0CD6>\uE048\ue04d; # VOWEL SIGN AI -\u0CC6\u0CD6>\uE048; # VOWEL SIGN AI -\u0CC6\u0CC2\u0CD5>\uE04B; # VOWEL SIGN OO -\u0CC6\u0CC2>\uE04A; # VOWEL SIGN O -\u0CBF\u0CD5>\uE040; # VOWEL SIGN II - -\u0C82>\uE002; # SIGN ANUSVARA -\u0C83>\uE003; # SIGN VISARGA -\u0C85>\uE005; # LETTER A -\u0C86>\uE006; # LETTER AA -\u0C87>\uE007; # LETTER I -\u0C88>\uE008; # LETTER II -\u0C89>\uE009; # LETTER U -\u0C8A>\uE00A; # LETTER UU -\u0C8B>\uE00B; # LETTER VOCALIC R -\u0C8C>\uE00C; # LETTER VOCALIC L -\u0C8E>\uE00E; # LETTER E -\u0C8F>\uE00F; # LETTER EE -\u0C90>\uE010; # LETTER AI -\u0C92>\uE012; # LETTER O -\u0C93>\uE013; # LETTER OO -\u0C94>\uE014; # LETTER AU -\u0C95>\uE015; # LETTER KA -\u0C96>\uE016; # LETTER KHA -\u0C97>\uE017; # LETTER GA -\u0C98>\uE018; # LETTER GHA -\u0C99>\uE019; # LETTER NGA -\u0C9A>\uE01A; # LETTER CA -\u0C9B>\uE01B; # LETTER CHA -\u0C9C>\uE01C; # LETTER JA -\u0C9D>\uE01D; # LETTER JHA -\u0C9E>\uE01E; # LETTER NYA -\u0C9F>\uE01F; # LETTER TTA -\u0CA0>\uE020; # LETTER TTHA -\u0CA1>\uE021; # LETTER DDA -\u0CA2>\uE022; # LETTER DDHA -\u0CA3>\uE023; # LETTER NNA -\u0CA4>\uE024; # LETTER TA -\u0CA5>\uE025; # LETTER THA -\u0CA6>\uE026; # LETTER DA -\u0CA7>\uE027; # LETTER DHA -\u0CA8>\uE028; # LETTER NA -\u0CAA>\uE02A; # LETTER PA -\u0CAB>\uE02B; # LETTER PHA -\u0CAC>\uE02C; # LETTER BA -\u0CAD>\uE02D; # LETTER BHA -\u0CAE>\uE02E; # LETTER MA -\u0CAF>\uE02F; # LETTER YA -\u0CB0>\uE030; # LETTER RA -\u0CB1>\uE031; # LETTER RRA -\u0CB2>\uE032; # LETTER LA -\u0CB3>\uE033; # LETTER LLA -\u0CB5>\uE035; # LETTER VA -\u0CB6>\uE036; # LETTER SHA -\u0CB7>\uE037; # LETTER SSA -\u0CB8>\uE038; # LETTER SA -\u0CB9>\uE039; # LETTER HA -\u0CBC>\uE03C; # SIGN NUKTA -\u0CBD>\uE03D; # AVAGRAHA -\u0CBE>\uE03E; # VOWEL SIGN AA +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +\u0CC6ೕ>\uE047; # VOWEL SIGN EE +\u0CC6\u0CCDೖ>\uE048\uE04D; # VOWEL SIGN AI +\u0CC6ೖ>\uE048; # VOWEL SIGN AI +\u0CC6ೂೕ>\uE04B; # VOWEL SIGN OO +\u0CC6ೂ>\uE04A; # VOWEL SIGN O +\u0CBFೕ>\uE040; # VOWEL SIGN II +ಂ>\uE002; # SIGN ANUSVARA +ಃ>\uE003; # SIGN VISARGA +ಅ>\uE005; # LETTER A +ಆ>\uE006; # LETTER AA +ಇ>\uE007; # LETTER I +ಈ>\uE008; # LETTER II +ಉ>\uE009; # LETTER U +ಊ>\uE00A; # LETTER UU +ಋ>\uE00B; # LETTER VOCALIC R +ಌ>\uE00C; # LETTER VOCALIC L +ಎ>\uE00E; # LETTER E +ಏ>\uE00F; # LETTER EE +ಐ>\uE010; # LETTER AI +ಒ>\uE012; # LETTER O +ಓ>\uE013; # LETTER OO +ಔ>\uE014; # LETTER AU +ಕ>\uE015; # LETTER KA +ಖ>\uE016; # LETTER KHA +ಗ>\uE017; # LETTER GA +ಘ>\uE018; # LETTER GHA +ಙ>\uE019; # LETTER NGA +ಚ>\uE01A; # LETTER CA +ಛ>\uE01B; # LETTER CHA +ಜ>\uE01C; # LETTER JA +ಝ>\uE01D; # LETTER JHA +ಞ>\uE01E; # LETTER NYA +ಟ>\uE01F; # LETTER TTA +ಠ>\uE020; # LETTER TTHA +ಡ>\uE021; # LETTER DDA +ಢ>\uE022; # LETTER DDHA +ಣ>\uE023; # LETTER NNA +ತ>\uE024; # LETTER TA +ಥ>\uE025; # LETTER THA +ದ>\uE026; # LETTER DA +ಧ>\uE027; # LETTER DHA +ನ>\uE028; # LETTER NA +ಪ>\uE02A; # LETTER PA +ಫ>\uE02B; # LETTER PHA +ಬ>\uE02C; # LETTER BA +ಭ>\uE02D; # LETTER BHA +ಮ>\uE02E; # LETTER MA +ಯ>\uE02F; # LETTER YA +ರ>\uE030; # LETTER RA +ಱ>\uE031; # LETTER RRA +ಲ>\uE032; # LETTER LA +ಳ>\uE033; # LETTER LLA +ವ>\uE035; # LETTER VA +ಶ>\uE036; # LETTER SHA +ಷ>\uE037; # LETTER SSA +ಸ>\uE038; # LETTER SA +ಹ>\uE039; # LETTER HA +\u0CBC>\uE03C; # SIGN NUKTA +ಽ>\uE03D; # AVAGRAHA +ಾ>\uE03E; # VOWEL SIGN AA \u0CBF>\uE03F; # VOWEL SIGN I -\u0CC1>\uE041; # VOWEL SIGN U -\u0CC2>\uE042; # VOWEL SIGN UU -\u0CC3>\uE043; # VOWEL SIGN VOCALIC R -\u0CC4>\uE044; # VOWEL SIGN VOCALIC RR +ು>\uE041; # VOWEL SIGN U +ೂ>\uE042; # VOWEL SIGN UU +ೃ>\uE043; # VOWEL SIGN VOCALIC R +ೄ>\uE044; # VOWEL SIGN VOCALIC RR \u0CC6>\uE046; # VOWEL SIGN E \u0CCC>\uE04C; # VOWEL SIGN AU \u0CCD>\uE04D; # SIGN VIRAMA -\u0CD5>\uE055; # LENGTH MARK -\u0CD6>\uE056; # AI LENGTH MARK -\u0CDE>\uE034; # LETTER LLLA -\u0CE0>\uE060; # LETTER VOCALIC RR -\u0CE1>\uE061; # LETTER VOCALIC LL -\u0CE6>\uE066; # DIGIT ZERO -\u0CE7>\uE067; # DIGIT ONE -\u0CE8>\uE068; # DIGIT TWO -\u0CE9>\uE069; # DIGIT THREE -\u0CEA>\uE06A; # DIGIT FOUR -\u0CEB>\uE06B; # DIGIT FIVE -\u0CEC>\uE06C; # DIGIT SIX -\u0CED>\uE06D; # DIGIT SEVEN -\u0CEE>\uE06E; # DIGIT EIGHT -\u0CEF>\uE06F; # DIGIT NINE - -# eof +ೕ>\uE055; # LENGTH MARK +ೖ>\uE056; # AI LENGTH MARK +ೞ>\uE034; # LETTER LLLA +ೠ>\uE060; # LETTER VOCALIC RR +ೡ>\uE061; # LETTER VOCALIC LL +೦>\uE066; # DIGIT ZERO +೧>\uE067; # DIGIT ONE +೨>\uE068; # DIGIT TWO +೩>\uE069; # DIGIT THREE +೪>\uE06A; # DIGIT FOUR +೫>\uE06B; # DIGIT FIVE +೬>\uE06C; # DIGIT SIX +೭>\uE06D; # DIGIT SEVEN +೮>\uE06E; # DIGIT EIGHT +೯>\uE06F; # DIGIT NINE diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Latin.txt new file mode 100644 index 00000000000..c1400dd276c --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBC-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Malayalam.txt new file mode 100644 index 00000000000..0d50b3b4a60 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Oriya.txt new file mode 100644 index 00000000000..ef997a83484 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:16 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Tamil.txt new file mode 100644 index 00000000000..4eb365ea918 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Kannada_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Kannada_Telugu.txt new file mode 100644 index 00000000000..8adc3030ff5 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Kannada_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Kannada_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::[ಂ-ಃಅ-ಌಎ-ಐಒ-ನಪ-ಳವ-ಹ\u0CBCಽಾ-ೄ\u0CC6-ೈೊ-\u0CCDೕ-ೖೞೠ-ೡ೦-೯]; +::NFD; +::Kannada-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Armenian.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Armenian.txt new file mode 100644 index 00000000000..2a48c580469 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Armenian.txt @@ -0,0 +1,91 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Armenian.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::NFD(NFC); +ev <> և ; +tʻ <> թ ; +čʻ <> չ ; +cʻ <> ց ; +pʻ <> փ ; +kʻ <> ք ; +u <> ու ; +a <> ա ; +b <> բ ; +g <> գ ; +d <> դ ; +e <> ե ; +z <> զ ; +ē <> է ; +ə <> ը ; +ž <> ժ ; +i <> ի ; +l <> լ ; +x <> խ ; +c <> ծ ; +k <> կ ; +h <> հ ; +j <> ձ ; +ġ <> ղ ; +č <> ճ ; +m <> մ ; +y <> յ ; +n <> ն ; +š <> շ ; +o <> ո ; +p <> պ ; +ǰ <> ջ ; +ṙ <> ռ ; +s <> ս ; +v <> վ ; +t <> տ ; +r <> ր ; +w <> ւ ; +ō <> օ ; +f <> ֆ ; +U <> ՈՒ ; +EV <> ԵՒ ; +J\u030C <> Ջ ; +Pʻ <> Փ ; +Kʻ <> Ք ; +Tʻ <> Թ ; +Čʻ <> Չ ; +Cʻ <> Ց ; +A <> Ա ; +B <> Բ ; +G <> Գ ; +D <> Դ ; +E <> Ե ; +Z <> Զ ; +Ē <> Է ; +Ə <> Ը ; +Ž <> Ժ ; +I <> Ի ; +L <> Լ ; +X <> Խ ; +C <> Ծ ; +K <> Կ ; +H <> Հ ; +J <> Ձ ; +Ġ <> Ղ ; +Č <> Ճ ; +M <> Մ ; +Y <> Յ ; +N <> Ն ; +Š <> Շ ; +O <> Ո ; +P <> Պ ; +Ṙ <> Ռ ; +S <> Ս ; +V <> Վ ; +T <> Տ ; +R <> Ր ; +W <> Ւ ; +Ō <> Օ ; +F <> Ֆ ; +::NFC(NFD); diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Bengali.txt new file mode 100644 index 00000000000..b18255b984e --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Bengali.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_ConjoiningJamo.txt b/Build/source/libs/icu-xetex/data/translit/Latin_ConjoiningJamo.txt new file mode 100644 index 00000000000..261cfbd9740 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_ConjoiningJamo.txt @@ -0,0 +1,251 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_ConjoiningJamo.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +$Gi = ᄀ; +$GGi = ᄁ; +$Ni = ᄂ; +$Di = ᄃ; +$DD = ᄄ; +$R = ᄅ; +$Mi = ᄆ; +$Bi = ᄇ; +$BB = ᄈ; +$Si = ᄉ; +$SSi = ᄊ; +$IEUNG = ᄋ; # null initial, inserted during Latin-Jamo +$Ji = ᄌ; +$JJ = ᄍ; +$Ci = ᄎ; +$Ki = ᄏ; +$Ti = ᄐ; +$Pi = ᄑ; +$Hi = ᄒ; +$A = ᅡ; +$AE = ᅢ; +$YA = ᅣ; +$YAE = ᅤ; +$EO = ᅥ; +$E = ᅦ; +$YEO = ᅧ; +$YE = ᅨ; +$O = ᅩ; +$WA = ᅪ; +$WAE = ᅫ; +$OE = ᅬ; +$YO = ᅭ; +$U = ᅮ; +$WEO = ᅯ; +$WE = ᅰ; +$WI = ᅱ; +$YU = ᅲ; +$EU = ᅳ; # null medial, inserted during Latin-Jamo +$YI = ᅴ; +$I = ᅵ; +$Gf = ᆨ; +$GGf = ᆩ; +$GS = ᆪ; +$Nf = ᆫ; +$NJ = ᆬ; +$NH = ᆭ; +$Df = ᆮ; +$L = ᆯ; +$LG = ᆰ; +$LM = ᆱ; +$LB = ᆲ; +$LS = ᆳ; +$LT = ᆴ; +$LP = ᆵ; +$LH = ᆶ; +$Mf = ᆷ; +$Bf = ᆸ; +$BS = ᆹ; +$Sf = ᆺ; +$SSf = ᆻ; +$NG = ᆼ; +$Jf = ᆽ; +$Cf = ᆾ; +$Kf = ᆿ; +$Tf = ᇀ; +$Pf = ᇁ; +$Hf = ᇂ; +$jamoInitial = [ᄀ-ᄒ]; +$jamoMedial = [ᅡ-ᅵ]; +$latinInitial = [bcdghjkmnprst]; +$latinMedial = [aeiouwy]; +$latinMedialEnd = [aeiou]; +$sep = \'; +$sep $sep <> $sep; +$sep < $latinMedialEnd g {} $GGi; +$sep < $latinMedialEnd s {} $SSi; +$sep < [^$latinMedial] [y w] e {} [$O $OE]; +$sep < [^$latinMedial] e {} [$O $OE $U]; +$sep < [^$latinMedial] [o a] {} [$E $EO $EU]; +$sep < [^$latinMedial] [w y] a {} [$E $EO $EU]; +$sep < [^$latinMedial] [y w] e {} $IEUNG [$O $OE]; +$sep < [^$latinMedial] e {} $IEUNG [$O $OE $U]; +$sep < [^$latinMedial] [o a] {} $IEUNG [$E $EO $EU]; +$sep < [^$latinMedial] [w y] a {} $IEUNG [$E $EO $EU]; +$sep < $latinMedialEnd b {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd c {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd d {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd g {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd h {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd j {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd k {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd m {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd n {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd p {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd s {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd t {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd b s {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd g g {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd g s {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l b {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l g {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l h {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l m {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l p {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l s {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd l t {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd n g {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd n h {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd n j {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd s s {} $IEUNG $jamoMedial; +$sep < $latinMedialEnd b {} $Bi $jamoMedial; +$sep < $latinMedialEnd d {} $Di $jamoMedial; +$sep < $latinMedialEnd j {} $Ji $jamoMedial; +$sep < $latinMedialEnd g {} $Gi $jamoMedial; +$sep < $latinMedialEnd s {} $Si $jamoMedial; +$sep < $latinMedialEnd b s {} [$Si $SSi]; +$sep < $latinMedialEnd g s {} [$Si $SSi]; +$sep < $latinMedialEnd l b {} [$Bi $BB]; +$sep < $latinMedialEnd l g {} [$Gi $GGi]; +$sep < $latinMedialEnd l s {} [$Si $SSi]; +$sep < $latinMedialEnd n g {} [$Gi $GGi]; +$sep < $latinMedialEnd n j {} [$Ji $JJ]; +$jamoMedial {b s} $latinMedial > $Bf $Si; +$jamoMedial {g s} $latinMedial > $Gf $Si; +$jamoMedial {l b} $latinMedial > $L $Bi; +$jamoMedial {l g} $latinMedial > $L $Gi; +$jamoMedial {l h} $latinMedial > $L $Hi; +$jamoMedial {l m} $latinMedial > $L $Mi; +$jamoMedial {l p} $latinMedial > $L $Pi; +$jamoMedial {l s} $latinMedial > $L $Si; +$jamoMedial {l t} $latinMedial > $L $Ti; +$jamoMedial {n g} $latinMedial > $Nf $Gi; +$jamoMedial {n h} $latinMedial > $Nf $Hi; +$jamoMedial {n j} $latinMedial > $Nf $Ji; +$jamoMedial {b} $latinMedial > $Bi; +$jamoMedial {c} $latinMedial > $Ci; +$jamoMedial {d} $latinMedial > $Di; +$jamoMedial {g} $latinMedial > $Gi; +$jamoMedial {h} $latinMedial > $Hi; +$jamoMedial {j} $latinMedial > $Ji; +$jamoMedial {k} $latinMedial > $Ki; +$jamoMedial {m} $latinMedial > $Mi; +$jamoMedial {n} $latinMedial > $Ni; +$jamoMedial {p} $latinMedial > $Pi; +$jamoMedial {s} $latinMedial > $Si; +$jamoMedial {t} $latinMedial > $Ti; +$jamoMedial {b b} $latinMedial > $BB; +$jamoMedial {d d} $latinMedial > $DD; +$jamoMedial {j j} $latinMedial > $JJ; +$jamoMedial {g g} $latinMedial > $GGi; +$jamoMedial {s s} $latinMedial > $SSi; +$jamoMedial {b} s s > $Bf; +$jamoMedial {g} s s > $Gf; +$jamoMedial {l} b b > $L; +$jamoMedial {l} g g > $L; +$jamoMedial {l} s s > $L; +$jamoMedial {n} g g > $Nf; +$jamoMedial {n} j j > $Nf; +$jamoMedial {bs} <> $BS; +$jamoMedial {b} <> $Bf; +$jamoMedial {c} <> $Cf; +$jamoMedial {d} <> $Df; +$jamoMedial {gg} <> $GGf; +$jamoMedial {gs} <> $GS; +$jamoMedial {g} <> $Gf; +$jamoMedial {h} <> $Hf; +$jamoMedial {j} <> $Jf; +$jamoMedial {k} <> $Kf; +$jamoMedial {lb} <> $LB; $jamoMedial {lg} <> $LG; +$jamoMedial {lh} <> $LH; +$jamoMedial {lm} <> $LM; +$jamoMedial {lp} <> $LP; +$jamoMedial {ls} <> $LS; +$jamoMedial {lt} <> $LT; +$jamoMedial {l} <> $L; +$jamoMedial {m} <> $Mf; +$jamoMedial {ng} <> $NG; +$jamoMedial {nh} <> $NH; +$jamoMedial {nj} <> $NJ; +$jamoMedial {n} <> $Nf; +$jamoMedial {p} <> $Pf; +$jamoMedial {ss} <> $SSf; +$jamoMedial {s} <> $Sf; +$jamoMedial {t} <> $Tf; +{gg} $latinMedial <> $GGi; +{g} $latinMedial <> $Gi; +{n} $latinMedial <> $Ni; +{dd} $latinMedial <> $DD; +{d} $latinMedial <> $Di; +{r} $latinMedial <> $R; +{m} $latinMedial <> $Mi; +{bb} $latinMedial <> $BB; +{b} $latinMedial <> $Bi; +{ss} $latinMedial <> $SSi; +{s} $latinMedial <> $Si; +{jj} $latinMedial <> $JJ; +{j} $latinMedial <> $Ji; +{c} $latinMedial <> $Ci; +{k} $latinMedial <> $Ki; +{t} $latinMedial <> $Ti; +{p} $latinMedial <> $Pi; +{h} $latinMedial <> $Hi; +$jamoMedial {r} $latinInitial > | l; +$jamoInitial {} [bcdghjklmnpst] > $EU; +gg > $GGi $EU; +dd > $DD $EU; +bb > $BB $EU; +ss > $SSi $EU; +jj > $JJ $EU; +([bcdghjkmnprst]) > | $1 eu; +l > | r; +$jamoInitial {ae} <> $AE; +$jamoInitial {a} <> $A; +$jamoInitial {eo} <> $EO; +$jamoInitial {eu} <> $EU; +$jamoInitial {e} <> $E; +$jamoInitial {i} <> $I; +$jamoInitial {oe} <> $OE; +$jamoInitial {o} <> $O; +$jamoInitial {u} <> $U; +$jamoInitial {wae} <> $WAE; +$jamoInitial {wa} <> $WA; +$jamoInitial {weo} <> $WEO; +$jamoInitial {we} <> $WE; +$jamoInitial {wi} <> $WI; +$jamoInitial {yae} <> $YAE; +$jamoInitial {ya} <> $YA; +$jamoInitial {yeo} <> $YEO; +$jamoInitial {ye} <> $YE; +$jamoInitial {yi} <> $YI; +$jamoInitial {yo} <> $YO; +$jamoInitial {yu} <> $YU; +$jamoInitial {w} > | wi; +$jamoInitial {y} > | yu; +($latinMedial) > $IEUNG | $1; +f > | p; +q > | k; +v > | b; +x > | ks; +z > | s; +$sep > ; +< $IEUNG; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Devanagari.txt new file mode 100644 index 00000000000..2dce28f86ef --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Devanagari.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Ethiopic.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Ethiopic.txt new file mode 100644 index 00000000000..5a7cf4a6a4d --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Ethiopic.txt @@ -0,0 +1,353 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Ethiopic.txt +# Generated from CLDR: Thu Jul 20 14:57:48 PDT 2006 +# +ha<>ሀ; +ha < ሃ; +he<>ሄ; +hi<>ሂ; +hī<>ህ; +hu<>?; +ho<>ሆ; +hha<>?; +hha < ሓ; +hhe<>ሔ; +hhi<>ሒ; +hhī<>ሕ; +hhu<>ሑ; +hho<>ሖ; +hhwa<>ሗ; +ʿa<>ኣ; +ʿē<>አ; +ʿe<>ኤ; +ʿi<>ኢ; +ʿī<>እ; +ʿu<>ኡ; +ʿo<>ኦ; +ʿwa<>ኧ; +ʾa<>ዓ; +ʾē<>?; +ʾe<>ዔ; +ʾi<>ዒ; +ʾī<>ዕ; +ʾu<>ዑ; +ʾo<>ዖ; +qha<>ቓ; +qhē<>?; +qhe<>ቔ; +qhi<>ቒ; +qhī<>ቕ; +qhu<>ቑ; +qho<>ቖ; +qhwa<>ቛ; +qhwē<>ቘ; +qhwe<>ቜ; +qhwi<>ቚ; +qhwī<>?; +q a<>ቃ; +qē<>ቀ; +qe<>ቄ; +qi<>ቂ; +qī<>ቅ; +qu<>?; +qo<>ቆ; +qwa<>ቋ; +qwē<>ቈ; +qwe<>ቌ; +qwi<>ቊ; +qwī<>?; +ka<>ካ; +kē<>ከ; +ke<>ኬ; +ki<>ኪ; +kī<>ክ; +ku<>ኩ; +kwa<>ኳ; +kwē<>ኮ; +kwe<>ኴ; +kwi<>ኰ; +kwī<>ኵ; +kxa<>ኻ; +kxē<>ኸ; +kxe<>ኼ; +kxi<>ኺ; +kxī<>ኽ; +kxu<>ኹ; +kxo<>ኾ; +kxwa<>ዃ; +kxwē<>ዀ; +kxwe<>ዄ; +kxwi<>ዂ; +kxwī<>ዅ; +xa<>ኃ; +xē<>ኀ; +xe<>ኄ; +xi<>ኂ; +xī<>ኅ; +xu<>?; +xo<>ኆ; +xwa<>ኋ; +xwē<>ኈ; +xwe<>ኌ; +xwi<>ኊ; +xwī<>?; +gga<>ጛ; +ggē<>ጘ; +gge<>ጜ; +ggi<>ጚ; +ggī<>?; +ggu<>ጙ; +ggo<>ጞ; +ga<>ጋ; +gē<>ገ; +ge<>ጌ; +gi<>ጊ; +gī<>?; +gu<>ጉ; +go<>ጎ; +gwa<>ጓ; +gwē<>?; +gwe<>ጔ; +gwi<>ጒ; +gwī<>ጕ; +ca<>ቻ; +cē<>ቸ; +ce<>ቼ; +ci<>ቺ; +cī<>ች; +cu<>ቹ; +co<>ቾ; +cwa<>ቿ; +cha<>ጫ; +chē<>ጨ; +che<>ጬ; +chi<>ጪ; +chī<>ጭ; +chu<>ጩ; +cho<>ጮ; +chwa<>ጯ; +ja<>ጃ; +jē<>ጀ; +je<>ጄ; +ji<>ጂ; +jī<>ጅ; +ju<>?; +jo<>ጆ; +jwa<>ጇ; +za<>ዛ; +zē<>ዘ; +ze<>ዜ; +zi<>ዚ; +zī<>?; +zu<>ዙ; +zo<>ዞ; +zwa<>ዟ; +zha<>ዣ; +zhē<>ዠ; +zhe<>ዤ; +zhi<>ዢ; +zhī<>ዥ; +zhu<>ዡ; +zho<>ዦ; +zhwa<>ዧ; +sa<>ሳ; +sē<>ሰ; +se<>ሴ; +si<>ሲ; +sī<>ስ; +su<>ሱ; +so<>ሶ; +swa<>ሷ; +sha<>ሻ; +shē<>ሸ; +she<>ሼ; +shi<>ሺ; +shī<>ሽ; +shu<>ሹ; +sho<>ሾ; +shwa<>ሿ; +sza<>ሣ; +szē<>ሠ; +sze<>ሤ; +szi<>ሢ; +szī<>ሥ; +szu<>ሡ; +szo<>ሦ; +szwa<>ሧ; +tsa<>ጻ; +tsē<>ጸ; +tse<>ጼ; +tsi<>ጺ; +tsī<>ጽ; +tsu<>ጹ; +tso<>ጾ; +tswa<>ጿ; +tza<>?; +tzē<>?; +tze<>?; +tzi<>?; +tzī<>?; +tzu<>??; +tzo<>?; +tha<>ጣ; +thē<>ጠ; +the<>ጤ; +thi<>ጢ; +thī<>ጥ; +thu<>ጡ; +tho<>ጦ; +thwa<>ጧ; +ta<>ታ; +tē<>ተ; +te<>ቴ; +ti<>ቲ; +tī<>ት; +tu<>ቱ; +to<>ቶ; +twa<>ቷ; +dda<>ዻ; +ddē<>ዸ; +dde<>ዼ; +ddi<>ዺ; +ddī<>ዽ; +ddu<>ዹ; +ddo<>ዾ; +ddwa<>ዿ; +da<>ዳ; +dē<>ደ; +de<>ዴ; +di<>ዲ; +dī<>ድ; +du<>ዱ; +do<>ዶ; +dwa<>ዷ; +na<>ና; +nē<>?; +ne<>ኔ; +ni<>ኒ; +nī<>ን; +nu<>ኑ; +no<>ኖ; +nwa<>ኗ; +nya<>ኛ; +nyē<>ኘ; +nye<>ኜ; +nyi<>ኚ; +nyī<>?; +nyu<>ኙ; +nyo<>ኞ; +nywa<>ኟ; +ya<>ያ; +yē<>የ; +ye<>ዬ; +yi<>ዪ; +yī<>ይ; +yu<>ዩ; +yo<>ዮ; +ra<>ራ; +rē<>ረ; +re<>ሬ; +ri<>ሪ; +rī<>ር; +ru<>ሩ; +ro<>ሮ; +rwa<>ሯ; +rya<>?; +la<>ላ; +lē<>ለ; +le<>ሌ; +li<>ሊ; +lī<>?; +lu<>ሉ; +lo<>ሎ; +lwa<>?; +ma<>ማ; +mē<>መ; +me<>ሜ; +mi<>ሚ; +mī<>?; +mu<>ሙ; +mo<>ሞ; +mwa<>ሟ; +mya<>?; +ba<>ባ; +bē<>በ; +be<>ቤ; +bi<>ቢ; +bī<>ብ; +bu<>ቡ; +bo<>ቦ; +bwa<>ቧ; +pa<>?; +pē<>??; +pe<>?; +pi<>?; +pī<>?; +pu<>?; +po<>?; +pwa<>?; +pha<>ጳ; +phē<>ጰ; +phe<>ጴ; +phi<>ጲ; +phī<>ጵ; +phu<>ጱ; +pho<>ጶ; +phwa<>ጷ; +fa<>?; +fē<>?; +fe<>?; +fi<>?; +fī<>??; +fu<>?; +fo<>?; +fwa<>??; +fya<>?; +va<>ቫ; +vē<>ቨ; +ve<>ቬ; +vi<>ቪ; +vī<>ቭ; +vu<>ቩ; +vo<>ቮ; +vwa<>ቯ; +wa<>ዋ; +wē<>ወ; +we<>ዌ; +wi<>ዊ; +wī<>?; +wu<>ዉ; +wo<>ዎ; +'.'<>?; +','<>?; +';'<>?; +':'<>?; +':-' < ?; +'?'<>?; +'¶'<>?; +1<>?; +2<>?; +3<>?; +4<>?; +5<>?; +6<>?; +7<>?; +8<>?; +9<>?; +⑩<>?; +⑳<>?; +(30)<>?; +(40)<>?; +(50)<>?; +(60)<>?; +(70)<>?; +(80)<>?; +(90)<>?; +(100)<>?; +(10000)<>?; +' ' <> ? ; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Gujarati.txt new file mode 100644 index 00000000000..9cede039e21 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Gujarati.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Gurmukhi.txt new file mode 100644 index 00000000000..472b477d045 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Gurmukhi.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Hangul.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Hangul.txt new file mode 100644 index 00000000000..2f0c81a1069 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Hangul.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Hangul.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::['A-Za-zÀ-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǡǦ-ǭǰǴ-ǵǸ-ǻȀ-țȞ-ȟȦ-ȳḀ-ẙẠ-ỹK-Å]; +::NFD; +::Lower; +::Latin-ConjoiningJamo; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Latin_InterIndic.txt index 0c303bac507..340cafe9b25 100644 --- a/Build/source/libs/icu-xetex/data/translit/Latin_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Latin_InterIndic.txt @@ -1,395 +1,342 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Latin-InterIndic - #:: NFD; - #\u0e00 reserved - #consonants - $chandrabindu=\ue001; - $anusvara=\ue002; - $visarga=\ue003; - #\u0e004 reserved - # w<vowel> represents the stand-alone form - $wa=\ue005; - $waa=\ue006; - $wi=\ue007; - $wii=\ue008; - $wu=\ue009; - $wuu=\ue00a; - $wr=\ue00b; - $wl=\ue00c; - $wce=\ue00d; # LETTER CANDRA E - $wse=\ue00e; # LETTER SHORT E - $we=\ue00f; # \u090f LETTER E - $wai=\ue010; - $wco=\ue011; # LETTER CANDRA O - $wso=\ue012; # LETTER SHORT O - $wo=\ue013; # \u0913 LETTER O - $wau=\ue014; - $ka=\ue015; - $kha=\ue016; - $ga=\ue017; - $gha=\ue018; - $nga=\ue019; - $ca=\ue01a; - $cha=\ue01b; - $ja=\ue01c; - $jha=\ue01d; - $nya=\ue01e; - $tta=\ue01f; - $ttha=\ue020; - $dda=\ue021; - $ddha=\ue022; - $nna=\ue023; - $ta=\ue024; - $tha=\ue025; - $da=\ue026; - $dha=\ue027; - $na=\ue028; - $ena=\ue029; #compatibility - $pa=\ue02a; - $pha=\ue02b; - $ba=\ue02c; - $bha=\ue02d; - $ma=\ue02e; - $ya=\ue02f; - $ra=\ue030; - $rra=\ue031; - $la=\ue032; - $lla=\ue033; - $ela=\ue034; #compatibility - $va=\ue035; - $vva=\ue081; - $sha=\ue036; - $ssa=\ue037; - $sa=\ue038; - $ha=\ue039; -#\u093a Reserved -#\u093b Reserved - $nukta=\ue03c; - $avagraha=\ue03d; # SIGN AVAGRAHA - # <vowel> represents the dependent form - $aa=\ue03e; - $i=\ue03f; - $ii=\ue040; - $u=\ue041; - $uu=\ue042; - $rh=\ue043; - $lh=\ue044; - $ce=\ue045; #VOWEL SIGN CANDRA E - $se=\ue046; #VOWEL SIGN SHORT E - $e=\ue047; - $ai=\ue048; - $co=\ue049; # VOWEL SIGN CANDRA O - $so=\ue04a; # VOWEL SIGN SHORT O - $o=\ue04b; # \u094b - $au=\ue04c; - $virama=\ue04d; -# \u094e Reserved -# \u094f Reserved - $om = \ue050; # OM -# \u0951>; # UNMAPPED STRESS SIGN UDATTA -# \u0952>; # UNMAPPED STRESS SIGN ANUDATTA -# \u0953>; # UNMAPPED GRAVE ACCENT -# \u0954>; # UNMAPPED ACUTE ACCENT - $lm = \ue055;# Telugu Length Mark - $ailm=\ue056;# AI Length Mark - $aulm=\ue057;# AU Length Mark - #urdu compatibity forms - $uka=\ue058; - $ukha=\ue059; - $ugha=\ue05a; - $ujha=\ue05b; - $uddha=\ue05c; - $udha=\ue05d; - $ufa=\ue05e; - $uya=\ue05f; - $wrr=\ue060; - $wll=\ue061; - $rrh=\ue062; - $llh=\ue063; - $danda=\ue064; - $doubleDanda=\ue065; - $zero=\ue066; # DIGIT ZERO - $one=\ue067; # DIGIT ONE - $two=\ue068; # DIGIT TWO - $three=\ue069; # DIGIT THREE - $four=\ue06a; # DIGIT FOUR - $five=\ue06b; # DIGIT FIVE - $six=\ue06c; # DIGIT SIX - $seven=\ue06d; # DIGIT SEVEN - $eight=\ue06e; # DIGIT EIGHT - $nine=\ue06f; # DIGIT NINE - - $dgs=\ue082; - - # For all other scripts - $ecp0=\ue070; - $ecp1=\ue071; - $ecp2=\ue072; - $ecp3=\ue073; - $ecp4=\ue074; - $ecp5=\ue075; - $ecp6=\ue076; - $ecp7=\ue077; - $ecp8=\ue078; - $ecp9=\ue079; - $ecpA=\ue07a; - $ecpB=\ue07b; - $ecpC=\ue07c; - $ecpD=\ue07d; - $ecpE=\ue07e; - $ecpF=\ue07f; - - # Khanda-ta - $kta=\ue083; - -# \u0970>; # UNMAPPED ABBREVIATION SIGN - $depVowelAbove=[\ue03e-\ue040\ue045-\ue04c]; - $depVowelBelow=[\ue041-\ue044]; - $endThing=[$danda$doubleDanda]; - # $x was originally called '&'; $z was '%' - $x=[$virama$aa$ai$au$ii$i$uu$u$rrh$rh$lh$e$o$se$ce$so$co]; - $z=[bcdfghjklmnpqrstvwxyz]; - $consonants=[[$ka-$ha]$z[\u0915-\u0939][\u0995-\u09b9][\u0a15-\u0a39][\u0a95-\u0ab9][\u0b15-\u0b39][\u0b95-\u0bb9][\u0c15-\u0c39][\u0c95-\u0cb9][\u0d15-\u0d39]]; - \u0315 > $avagraha; - \u0303>$chandrabindu$anusvara; - m\u0310>$chandrabindu; - h\u0323>$visarga; - x>$ka$virama$sa; -# convert to independent forms at start of word or syllable: -# dependent forms for roundtrip - \u0314a\u0304>$aa; - \u0314ai>$ai; - \u0314au>$au; - \u0314ii>$ii; - \u0314i\u0304>$ii; - \u0314i>$i; - \u0314u\u0304>$uu; - \u0314u>$u; - \u0314r\u0325\u0304>$rrh; - \u0314r\u0325>$rh; - \u0314l\u0325\u0304>$llh; - \u0314lh>$lh; - \u0314l\u0325>$lh; - \u0314e\u0304>$e; - \u0314o\u0304>$o; - \u0314a>; - \u0314e\u0306>$ce; - \u0314o\u0306>$co; - \u0314e>$se; - \u0314o>$so; - -# preceeded by consonants - $consonants{ a\u0304>$aa; - $consonants{ ai>$ai; - $consonants{ au>$au; - $consonants{ ii>$ii; - $consonants{ i\u0304>$ii; - $consonants{ i>$i; - $consonants{ u\u0304>$uu; - $consonants{ u>$u; - $consonants{ r\u0325\u0304>$rrh; - $consonants{ r\u0325a>$rh; - $consonants{ r\u0325>$rh; - $consonants{ l\u0325\u0304>$llh; - $consonants{ lh>$lh; - $consonants{ l\u0325>$lh; - $consonants{ e\u0304>$e; - $consonants{ o\u0304>$o; - $consonants{ e\u0306>$ce; - $consonants{ o\u0306>$co; - $consonants{ e>$se; - $consonants{ o>$so; - -# e.g. keai -> {ka}{e}{wai}; k'ai -> {ka}{wai}; (ai) -> ({wai}) - a\u0304>$waa; - ai>$wai; - au>$wau; - i\u0304>$wii; - i>$wi; - u\u0304>$wuu; - u>$wu; - r\u0325\u0304>$wrr; - r\u0325>$wr; - l\u0325\u0304>$wll; - lh>$wl; - l\u0325>$wl; - e\u0304>$we; - o\u0304>$wo; - a>$wa; - e\u0306>$wce; - o\u0306>$wco; - e>$wse; - ''om>$om; - o>$wso; - - # rules for anusvara - n}r\u0325 > $na|$virama; - n}l\u0325 > $na|$virama; - n}na > $na|$virama; - n\u0307}[kg] > $anusvara; - n\u0307}n\u0307 > $anusvara; - n\u0304}[cj] > $anusvara; - n\u0304}n\u0303 > $anusvara; - n\u0323}[tdn]\u0323 > $anusvara; - n}[tdn] > $anusvara; - m}[pbm] > $anusvara; - n}[ylvshr] > $anusvara; - m\u0307 > $anusvara; - - #urdu compatibility - q>$uka|$virama; - k\u0331h\u0331>$ukha |$virama; - g\u0307> $ugha | $virama; - z > $ujha |$virama; - f > $ufa|$virama; - - t\u0331>$kta; - - # dev - y\u0307>$uya|$virama; - l\u0331>$ela|$virama; - n\u0331>$ena|$virama; - n\u0307>$nga|$virama; - n\u0303>$nya|$virama; - n\u0323>$nna|$virama; - t\u0323h>$ttha|$virama; - t\u0323>$tta|$virama; - r\u0323h>$udha|$virama; - r\u0323>$uddha|$virama; - d\u0323h>$ddha|$virama; - d\u0323>$dda|$virama; - kh>$kha|$virama; - k>$ka|$virama; - gh>$gha|$virama; - g>$ga|$virama; - ch>$cha|$virama; - c>$ca|$virama; - jh>$jha|$virama; - j>$ja|$virama; - ny>$nya|$virama; - tth>$ttha|$virama; - ddh>$ddha|$virama; - th>$tha|$virama; - t>$ta|$virama; - dh>$dha|$virama; - d>$da|$virama; - n>$na|$virama; - ph>$pha|$virama; - p>$pa|$virama; - bh>$bha|$virama; - b>$ba|$virama; - m>$ma|$virama; - y>$ya|$virama; - r\u0331>$rra|$virama; - r>$ra|$virama; - l\u0323>$lla|$virama; - l>$la|$virama; - v>$va|$virama; - w\u0307>$vva|$virama; - w>$va|$virama; - sh>$sha|$virama; - ss>$ssa|$virama; - s\u0323>$ssa|$virama; - s\u0301>$sha|$virama; - s>$sa|$virama; - h>$ha|$virama; - '.'>$danda; - $danda'.'>$doubleDanda; - $depVowelAbove{'~'>$anusvara; - $depVowelBelow{'~'>$chandrabindu; -# convert to dependent forms after consonant with no vowel: -# e.g. kai -> {ka}{virama}ai -> {ka}{ai} - #$virama aa>$aa; - $virama a\u0304>$aa; - $virama ai>$ai; - $virama au>$au; - $virama ii>$ii; - $virama i\u0304>$ii; - $virama i>$i; - #$virama uu>$uu; - $virama u\u0304>$uu; - $virama u>$u; - #$virama rrh>$rrh; - $virama r\u0325\u0304>$rrh; - #$virama rh>$rh; - $virama r\u0325a>$rh; - $virama r\u0325>$rh; - $virama l\u0325\u0304>$llh; - $virama lh>$lh; - $virama l\u0325>$lh; - $virama e\u0304>$e; - $virama o\u0304>$o; - $virama a>; - $virama e\u0306>$ce; - $virama o\u0306>$co; - $virama e>$se; - $virama o>$so; - - -# otherwise convert independent forms when separated by ': k'ai -> {ka}{virama}{wai} - #$virama''aa>$waa; - $virama''a\u0304>$waa; - $virama''ai>$wai; - $virama''au>$wau; - #$virama''ii>$wii; - $virama''i\u0304>$wii; - $virama''i>$wi; - #$virama''uu>$wuu; - $virama''u\u0304>$wuu; - $virama''u>$wu; - #$virama''rrh>$wrr; - $virama''r\u0325\u0304>$wrr; - #$virama''rh>$wr; - $virama''r\u0325>$wr; - $virama''l\u0325\u0304>$wll; - #$virama''lh>$wl; - $virama''l\u0325>$wl; - $virama''e\u0304>$we; - $virama''o\u0304>$wo; - $virama''a>$wa; - $virama''e\u0306>$wce; - $virama''o\u0306>$wco; - $virama''e>$wse; - $virama''o>$wso; -# no virama - ''a\u0304>$waa; - ''ai>$wai; - ''au>$wau; - ''i\u0304>$wii; - ''i>$wi; - ''u\u0304>$wuu; - ''u>$wu; - ''r\u0325\u0304>$wrr; - ''r\u0325>$wr; - ''l\u0325\u0304>$wll; - ''l\u0325>$wl; - ''e\u0304>$we; - ''o\u0304>$wo; - ''a>$wa; - ''e\u0306>$wce; - ''o\u0306>$wco; - ''e>$wse; - ''o>$wso; - - $virama } [$z] > $virama; - $virama } ' ' > $virama ; - $virama}$endThing>; - - \u0294>$dgs; # Glottal Stop - - 0>$zero; - 1>$one; - 2>$two; - 3>$three; - 4>$four; - 5>$five; - 6>$six; - 7>$seven; - 8>$eight; - 9>$nine; - ''>; - #:: NFC (NFD) ; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +$chandrabindu=\uE001; +$anusvara=\uE002; +$visarga=\uE003; +$wa=\uE005; +$waa=\uE006; +$wi=\uE007; +$wii=\uE008; +$wu=\uE009; +$wuu=\uE00A; +$wr=\uE00B; +$wl=\uE00C; +$wce=\uE00D; # LETTER CANDRA E +$wse=\uE00E; # LETTER SHORT E +$we=\uE00F; # ए LETTER E +$wai=\uE010; +$wco=\uE011; # LETTER CANDRA O +$wso=\uE012; # LETTER SHORT O +$wo=\uE013; # ओ LETTER O +$wau=\uE014; +$ka=\uE015; +$kha=\uE016; +$ga=\uE017; +$gha=\uE018; +$nga=\uE019; +$ca=\uE01A; +$cha=\uE01B; +$ja=\uE01C; +$jha=\uE01D; +$nya=\uE01E; +$tta=\uE01F; +$ttha=\uE020; +$dda=\uE021; +$ddha=\uE022; +$nna=\uE023; +$ta=\uE024; +$tha=\uE025; +$da=\uE026; +$dha=\uE027; +$na=\uE028; +$ena=\uE029; #compatibility +$pa=\uE02A; +$pha=\uE02B; +$ba=\uE02C; +$bha=\uE02D; +$ma=\uE02E; +$ya=\uE02F; +$ra=\uE030; +$rra=\uE031; +$la=\uE032; +$lla=\uE033; +$ela=\uE034; #compatibility +$va=\uE035; +$vva=\uE081; +$sha=\uE036; +$ssa=\uE037; +$sa=\uE038; +$ha=\uE039; +$nukta=\uE03C; +$avagraha=\uE03D; # SIGN AVAGRAHA +$aa=\uE03E; +$i=\uE03F; +$ii=\uE040; +$u=\uE041; +$uu=\uE042; +$rh=\uE043; +$lh=\uE044; +$ce=\uE045; #VOWEL SIGN CANDRA E +$se=\uE046; #VOWEL SIGN SHORT E +$e=\uE047; +$ai=\uE048; +$co=\uE049; # VOWEL SIGN CANDRA O +$so=\uE04A; # VOWEL SIGN SHORT O +$o=\uE04B; # ो +$au=\uE04C; +$virama=\uE04D; +$om = \uE050; # OM +$lm = \uE055;# Telugu Length Mark +$ailm=\uE056;# AI Length Mark +$aulm=\uE057;# AU Length Mark +$uka=\uE058; +$ukha=\uE059; +$ugha=\uE05A; +$ujha=\uE05B; +$uddha=\uE05C; +$udha=\uE05D; +$ufa=\uE05E; +$uya=\uE05F; +$wrr=\uE060; +$wll=\uE061; +$rrh=\uE062; +$llh=\uE063; +$danda=\uE064; +$doubleDanda=\uE065; +$zero=\uE066; # DIGIT ZERO +$one=\uE067; # DIGIT ONE +$two=\uE068; # DIGIT TWO +$three=\uE069; # DIGIT THREE +$four=\uE06A; # DIGIT FOUR +$five=\uE06B; # DIGIT FIVE +$six=\uE06C; # DIGIT SIX +$seven=\uE06D; # DIGIT SEVEN +$eight=\uE06E; # DIGIT EIGHT +$nine=\uE06F; # DIGIT NINE +$dgs=\uE082; +$ecp0=\uE070; +$ecp1=\uE071; +$ecp2=\uE072; +$ecp3=\uE073; +$ecp4=\uE074; +$ecp5=\uE075; +$ecp6=\uE076; +$ecp7=\uE077; +$ecp8=\uE078; +$ecp9=\uE079; +$ecpA=\uE07A; +$ecpB=\uE07B; +$ecpC=\uE07C; +$ecpD=\uE07D; +$ecpE=\uE07E; +$ecpF=\uE07F; +$kta=\uE083; +$depVowelAbove=[\uE03E-\uE040\uE045-\uE04C]; +$depVowelBelow=[\uE041-\uE044]; +$endThing=[$danda$doubleDanda]; +$x=[$virama$aa$ai$au$ii$i$uu$u$rrh$rh$lh$e$o$se$ce$so$co]; +$z=[bcdfghjklmnpqrstvwxyz]; +$consonants=[[$ka-$ha]$z[क-ह][ক-হ][ਕ-ਹ][ક-હ][କ-ହ][க-ஹ][క-హ][ಕ-ಹ][ക-ഹ]]; +\u0315 > $avagraha; +\u0303>$chandrabindu$anusvara; +m\u0310>$chandrabindu; +h\u0323>$visarga; +x>$ka$virama$sa; +\u0314a\u0304>$aa; +\u0314ai>$ai; +\u0314au>$au; +\u0314ii>$ii; +\u0314i\u0304>$ii; +\u0314i>$i; +\u0314u\u0304>$uu; +\u0314u>$u; +\u0314r\u0325\u0304>$rrh; +\u0314r\u0325>$rh; +\u0314l\u0325\u0304>$llh; +\u0314lh>$lh; +\u0314l\u0325>$lh; +\u0314e\u0304>$e; +\u0314o\u0304>$o; +\u0314a>; +\u0314e\u0306>$ce; +\u0314o\u0306>$co; +\u0314e>$se; +\u0314o>$so; +$consonants{ a\u0304>$aa; +$consonants{ ai>$ai; +$consonants{ au>$au; +$consonants{ ii>$ii; +$consonants{ i\u0304>$ii; +$consonants{ i>$i; +$consonants{ u\u0304>$uu; +$consonants{ u>$u; +$consonants{ r\u0325\u0304>$rrh; +$consonants{ r\u0325a>$rh; +$consonants{ r\u0325>$rh; +$consonants{ l\u0325\u0304>$llh; +$consonants{ lh>$lh; +$consonants{ l\u0325>$lh; +$consonants{ e\u0304>$e; +$consonants{ o\u0304>$o; +$consonants{ e\u0306>$ce; +$consonants{ o\u0306>$co; +$consonants{ e>$se; +$consonants{ o>$so; +a\u0304>$waa; +ai>$wai; +au>$wau; +i\u0304>$wii; +i>$wi; +u\u0304>$wuu; +u>$wu; +r\u0325\u0304>$wrr; +r\u0325>$wr; +l\u0325\u0304>$wll; +lh>$wl; +l\u0325>$wl; +e\u0304>$we; +o\u0304>$wo; +a>$wa; +e\u0306>$wce; +o\u0306>$wco; +e>$wse; +''om>$om; +o>$wso; +n}r\u0325 > $na|$virama; +n}l\u0325 > $na|$virama; +n}na > $na|$virama; +n\u0307}[kg] > $anusvara; +n\u0307}n\u0307 > $anusvara; +n\u0304}[cj] > $anusvara; +n\u0304}n\u0303 > $anusvara; +n\u0323}[tdn]\u0323 > $anusvara; +n}[tdn] > $anusvara; +m}[pbm] > $anusvara; +n}[ylvshr] > $anusvara; +m\u0307 > $anusvara; +q>$uka|$virama; +k\u0331h\u0331>$ukha |$virama; +g\u0307> $ugha | $virama; +z > $ujha |$virama; +f > $ufa|$virama; +t\u0331>$kta; +y\u0307>$uya|$virama; +l\u0331>$ela|$virama; +n\u0331>$ena|$virama; +n\u0307>$nga|$virama; +n\u0303>$nya|$virama; +n\u0323>$nna|$virama; +t\u0323h>$ttha|$virama; +t\u0323>$tta|$virama; +r\u0323h>$udha|$virama; +r\u0323>$uddha|$virama; +d\u0323h>$ddha|$virama; +d\u0323>$dda|$virama; +kh>$kha|$virama; +k>$ka|$virama; +gh>$gha|$virama; +g>$ga|$virama; +ch>$cha|$virama; +c>$ca|$virama; +jh>$jha|$virama; +j>$ja|$virama; +ny>$nya|$virama; +tth>$ttha|$virama; +ddh>$ddha|$virama; +th>$tha|$virama; +t>$ta|$virama; +dh>$dha|$virama; +d>$da|$virama; +n>$na|$virama; +ph>$pha|$virama; +p>$pa|$virama; +bh>$bha|$virama; +b>$ba|$virama; +m>$ma|$virama; +y>$ya|$virama; +r\u0331>$rra|$virama; +r>$ra|$virama; +l\u0323>$lla|$virama; +l>$la|$virama; +v>$va|$virama; +w\u0307>$vva|$virama; +w>$va|$virama; +sh>$sha|$virama; +ss>$ssa|$virama; +s\u0323>$ssa|$virama; +s\u0301>$sha|$virama; +s>$sa|$virama; +h>$ha|$virama; +'.'>$danda; +$danda'.'>$doubleDanda; +$depVowelAbove{'~'>$anusvara; +$depVowelBelow{'~'>$chandrabindu; +$virama a\u0304>$aa; +$virama ai>$ai; +$virama au>$au; +$virama ii>$ii; +$virama i\u0304>$ii; +$virama i>$i; +$virama u\u0304>$uu; +$virama u>$u; +$virama r\u0325\u0304>$rrh; +$virama r\u0325a>$rh; +$virama r\u0325>$rh; +$virama l\u0325\u0304>$llh; +$virama lh>$lh; +$virama l\u0325>$lh; +$virama e\u0304>$e; +$virama o\u0304>$o; +$virama a>; +$virama e\u0306>$ce; +$virama o\u0306>$co; +$virama e>$se; +$virama o>$so; +$virama''a\u0304>$waa; +$virama''ai>$wai; +$virama''au>$wau; +$virama''i\u0304>$wii; +$virama''i>$wi; +$virama''u\u0304>$wuu; +$virama''u>$wu; +$virama''r\u0325\u0304>$wrr; +$virama''r\u0325>$wr; +$virama''l\u0325\u0304>$wll; +$virama''l\u0325>$wl; +$virama''e\u0304>$we; +$virama''o\u0304>$wo; +$virama''a>$wa; +$virama''e\u0306>$wce; +$virama''o\u0306>$wco; +$virama''e>$wse; +$virama''o>$wso; +''a\u0304>$waa; +''ai>$wai; +''au>$wau; +''i\u0304>$wii; +''i>$wi; +''u\u0304>$wuu; +''u>$wu; +''r\u0325\u0304>$wrr; +''r\u0325>$wr; +''l\u0325\u0304>$wll; +''l\u0325>$wl; +''e\u0304>$we; +''o\u0304>$wo; +''a>$wa; +''e\u0306>$wce; +''o\u0306>$wco; +''e>$wse; +''o>$wso; +$virama } [$z] > $virama; +$virama } ' ' > $virama ; +$virama}$endThing>; +ʔ>$dgs; # Glottal Stop +0>$zero; +1>$one; +2>$two; +3>$three; +4>$four; +5>$five; +6>$six; +7>$seven; +8>$eight; +9>$nine; +''>; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Jamo.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Jamo.txt index 9d6591d7a6f..5063003bc0f 100644 --- a/Build/source/libs/icu-xetex/data/translit/Latin_Jamo.txt +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Jamo.txt @@ -1,522 +1,14 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -#- N.B. DO NOT put any filters, NFD, etc. here -- those are aliased in -#- the INDEX file. This transliterator is, by itself, not -#- instantiated. It is used as a part of Latin-Jamo, Latin-Hangul, or -#- inverses thereof. - -# Transliteration from Latin characters to Korean script is done in -# two steps: Latin to Jamo, then Jamo to Hangul. The Jamo-Hangul -# transliteration is done algorithmically following Unicode 3.0 -# section 3.11. This file implements the Latin to Jamo -# transliteration using rules. - -# Jamo occupy the block 1100-11FF. Within this block there are three -# groups of characters: initial consonants or choseong (I), medial -# vowels or jungseong (M), and trailing consonants or jongseong (F). -# Standard Korean syllables are of the form I+M+F*. - -# Section 3.11 describes the use of 'filler' jamo to convert -# nonstandard syllables to standard form: the choseong filler 115F and -# the junseong filler 1160. In this transliterator, we will not use -# 115F or 1160. - -# We will, however, insert two 'null' jamo to make foreign words -# conform to Korean syllable structure. These are the null initial -# consonant 110B (IEUNG) and the null vowel 1173 (EU). In Latin text, -# we will use the separator in order to disambiguate strings, -# e.g. "kan-ggan" (initial GG) vs. "kanggan" (final NG + initial G). - -# We will not use all of the characters in the jamo block. We will -# only use the 19 initials, 21 medials, and 27 finals possessing a -# jamo short name as defined in section 4.4 of the Unicode book. - -# Rules of thumb. These guidelines provide the basic framework -# for the rules. They are phrased in terms of Latin-Jamo transliteration. -# The Jamo-Latin rules derive from these, since the Jamo-Latin rules are -# just context-free transliteration of jamo to corresponding short names, -# with the addition of separators to maintain round-trip integrity -# in the context of the Latin-Jamo rules. - -# A sequence of vowels: -# - Take the longest sequence you can. If there are too many, or you don't -# have a starting consonant, introduce a 110B necessary. - -# A sequence of consonants. -# - First join the double consonants: G + G -> GG -# - In the remaining list, -# -- If there is no preceding vowel, take the first consonant, and insert EU -# after it. Continue with the rest of the consonants. -# -- If there is one consonant, attach to the following vowel -# -- If there are two consonants and a following vowel, attach one to the -# preceeding vowel, and one to the following vowel. -# -- If there are more than two consonants, join the first two together if you -# can: L + G => LG -# -- If you still end up with more than 2 consonants, insert EU after the -# first one, and continue with the rest of the consonants. - -#---------------------------------------------------------------------- -# Variables - -# Some latin consonants or consonant pairs only occur as initials, and -# some only as finals, but some occur as both. This makes some jamo -# consonants ambiguous when transliterated into latin. -# Initial only: IEUNG BB DD JJ R -# Final only: BS GS L LB LG LH LM LP LS LT NG NH NJ -# Initial and Final: B C D G GG H J K M N P S SS T - - $Gi = \u1100; - $GGi = \u1101; - $Ni = \u1102; - $Di = \u1103; - $DD = \u1104; - $R = \u1105; - $Mi = \u1106; - $Bi = \u1107; - $BB = \u1108; - $Si = \u1109; - $SSi = \u110A; - $IEUNG = \u110B; # null initial, inserted during Latin-Jamo - $Ji = \u110C; - $JJ = \u110D; - $Ci = \u110E; - $Ki = \u110F; - $Ti = \u1110; - $Pi = \u1111; - $Hi = \u1112; - - $A = \u1161; - $AE = \u1162; - $YA = \u1163; - $YAE = \u1164; - $EO = \u1165; - $E = \u1166; - $YEO = \u1167; - $YE = \u1168; - $O = \u1169; - $WA = \u116A; - $WAE = \u116B; - $OE = \u116C; - $YO = \u116D; - $U = \u116E; - $WEO = \u116F; - $WE = \u1170; - $WI = \u1171; - $YU = \u1172; - $EU = \u1173; # null medial, inserted during Latin-Jamo - $YI = \u1174; - $I = \u1175; - - $Gf = \u11A8; - $GGf = \u11A9; - $GS = \u11AA; - $Nf = \u11AB; - $NJ = \u11AC; - $NH = \u11AD; - $Df = \u11AE; - $L = \u11AF; - $LG = \u11B0; - $LM = \u11B1; - $LB = \u11B2; - $LS = \u11B3; - $LT = \u11B4; - $LP = \u11B5; - $LH = \u11B6; - $Mf = \u11B7; - $Bf = \u11B8; - $BS = \u11B9; - $Sf = \u11BA; - $SSf = \u11BB; - $NG = \u11BC; - $Jf = \u11BD; - $Cf = \u11BE; - $Kf = \u11BF; - $Tf = \u11C0; - $Pf = \u11C1; - $Hf = \u11C2; - - $jamoInitial = [\u1100-\u1112]; - - $jamoMedial = [\u1161-\u1175]; - - $latinInitial = [bcdghjkmnprst]; - - # Any character in the latin transliteration of a medial - $latinMedial = [aeiouwy]; - - # The last character of the latin transliteration of a medial - $latinMedialEnd = [aeiou]; - - # Disambiguation separator - $sep = \'; - -#---------------------------------------------------------------------- -# Jamo-Latin - -# Jamo to latin is relatively simple, since it is the latin that is -# ambiguous. Most rules are straightforward, and we encode them below -# as simple add-on back rule, e.g.: - -# $jamoMedial {bs} > $BS; - -# becomes - -# $jamoMedial {bs} <> $BS; - -# Furthermore, we don't care about the ordering for Jamo-Latin because -# we are going from single characters, so we can very easily piggyback -# on the Latin-Jamo. - -# The main issue with Jamo-Latin is when to insert separators. -# Separators are inserted to obtain correct round trip behavior. For -# example, the sequence Ki A Gf Gi E, if transliterated to "kagge", -# would then round trip to Ki A GGi E. To prevent this, we insert a -# separator: "kag-ge". IMPORTANT: The need for separators depends -# very specifically on the behavior of the Latin-Jamo rules. A change -# in the Latin-Jamo behavior can completely change the way the -# separator insertion must be done. - -# First try to preserve actual separators in the jamo text by doubling -# them. This fixes problems like: -# (Di)(A)(Ji)(U)(NG)-(IEUNG)(YEO)(Nf)(Gi)(YEO)(L) => dajung-yeongyeol -# => (Di)(A)(Ji)(U)(NG)(IEUNG)(YEO)(Nf)(Gi)(YEO)(L). This is optional -# -- if we don't care about losing separators in the jamo, we can delete -# this rule. - - $sep $sep <> $sep; - -# Triple consonants. For three consonants "axxx" we insert a -# separator between the first and second "x" if XXf, Xf, and Xi all -# exist, and we have A Xf XXi. This prevents the reverse -# transliteration to A XXf Xi. - - $sep < $latinMedialEnd g {} $GGi; - $sep < $latinMedialEnd s {} $SSi; - -# For vowels the rule is similar. If there is a vowel "ae" such that -# "a" by itself and "e" by itself are vowels, then we want to map A E -# to "a-e" so as not to round trip to AE. However, in the text Ki EO -# IEUNG E we don't need to map to "keo-e". "keoe" suffices. For -# vowels of the form "aei", both "ae" + "i" and "a" + "ei" must be -# tested. NOTE: These rules used to have a left context of -# $latinInitial instead of [^$latinMedial]. The problem with this is -# sequences where an initial IEUNG is transliterated away: -# (IEUNG)(A)(IEUNG)(EO) => aeo => (IEUNG)(AE)(IEUNG)(O) - - $sep < [^$latinMedial] [y w] e {} [$O $OE]; - $sep < [^$latinMedial] e {} [$O $OE $U]; - $sep < [^$latinMedial] [o a] {} [$E $EO $EU]; - $sep < [^$latinMedial] [w y] a {} [$E $EO $EU]; - -# Similar to the above, but with an intervening $IEUNG. - - $sep < [^$latinMedial] [y w] e {} $IEUNG [$O $OE]; - $sep < [^$latinMedial] e {} $IEUNG [$O $OE $U]; - $sep < [^$latinMedial] [o a] {} $IEUNG [$E $EO $EU]; - $sep < [^$latinMedial] [w y] a {} $IEUNG [$E $EO $EU]; - -# Single finals followed by IEUNG. The jamo sequence A Xf IEUNG E, -# where Xi also exists, must be transliterated as "ax-e" to prevent -# the round trip conversion to A Xi E. - - $sep < $latinMedialEnd b {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd c {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd d {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd g {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd h {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd j {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd k {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd m {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd n {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd p {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd s {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd t {} $IEUNG $jamoMedial; - -# Double finals followed by IEUNG. Similar to the single finals -# followed by IEUNG. Any latin consonant pair X Y, between medials, -# that we would split by Latin-Jamo, we must handle when it occurs as -# part of A XYf IEUNG E, to prevent round trip conversion to A Xf Yi -# E. - - $sep < $latinMedialEnd b s {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd g g {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd g s {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l b {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l g {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l h {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l m {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l p {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l s {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd l t {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd n g {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd n h {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd n j {} $IEUNG $jamoMedial; - $sep < $latinMedialEnd s s {} $IEUNG $jamoMedial; - -# Split doubles. Text of the form A Xi Xf E, where XXi also occurs, -# we transliterate as "ax-xe" to prevent round trip transliteration as -# A XXi E. - - $sep < $latinMedialEnd b {} $Bi $jamoMedial; - $sep < $latinMedialEnd d {} $Di $jamoMedial; - $sep < $latinMedialEnd j {} $Ji $jamoMedial; - $sep < $latinMedialEnd g {} $Gi $jamoMedial; - $sep < $latinMedialEnd s {} $Si $jamoMedial; - -# XYY. This corresponds to the XYY rule in Latin-Jamo. By default -# Latin-Jamo maps "xyy" to Xf YYi, to keep YY together. As a result, -# "xyy" forms that correspond to XYf Yi must be transliterated as -# "xy-y". - - $sep < $latinMedialEnd b s {} [$Si $SSi]; - $sep < $latinMedialEnd g s {} [$Si $SSi]; - $sep < $latinMedialEnd l b {} [$Bi $BB]; - $sep < $latinMedialEnd l g {} [$Gi $GGi]; - $sep < $latinMedialEnd l s {} [$Si $SSi]; - $sep < $latinMedialEnd n g {} [$Gi $GGi]; - $sep < $latinMedialEnd n j {} [$Ji $JJ]; - -# Deletion of IEUNG is handled below. - -#---------------------------------------------------------------------- -# Latin-Jamo - -# [Basic, context-free Jamo-Latin rules are embedded here too. See -# above.] - -# Split digraphs: Text of the form 'axye', where 'xy' is a final -# digraph, 'x' is a final (by itself), 'y' is an initial, and 'a' and -# 'e' are medials, we want to transliterate this as A Xf Yi E rather -# than A XYf IEUNG E. We do NOT include text of the form "axxe", -# since that is handled differently below. These rules are generated -# programmatically from the jamo data. - - $jamoMedial {b s} $latinMedial > $Bf $Si; - $jamoMedial {g s} $latinMedial > $Gf $Si; - $jamoMedial {l b} $latinMedial > $L $Bi; - $jamoMedial {l g} $latinMedial > $L $Gi; - $jamoMedial {l h} $latinMedial > $L $Hi; - $jamoMedial {l m} $latinMedial > $L $Mi; - $jamoMedial {l p} $latinMedial > $L $Pi; - $jamoMedial {l s} $latinMedial > $L $Si; - $jamoMedial {l t} $latinMedial > $L $Ti; - $jamoMedial {n g} $latinMedial > $Nf $Gi; - $jamoMedial {n h} $latinMedial > $Nf $Hi; - $jamoMedial {n j} $latinMedial > $Nf $Ji; - -# Single consonants are initials: Text of the form 'axe', where 'x' -# can be an initial or a final, and 'a' and 'e' are medials, we want -# to transliterate as A Xi E rather than A Xf IEUNG E. - - $jamoMedial {b} $latinMedial > $Bi; - $jamoMedial {c} $latinMedial > $Ci; - $jamoMedial {d} $latinMedial > $Di; - $jamoMedial {g} $latinMedial > $Gi; - $jamoMedial {h} $latinMedial > $Hi; - $jamoMedial {j} $latinMedial > $Ji; - $jamoMedial {k} $latinMedial > $Ki; - $jamoMedial {m} $latinMedial > $Mi; - $jamoMedial {n} $latinMedial > $Ni; - $jamoMedial {p} $latinMedial > $Pi; - $jamoMedial {s} $latinMedial > $Si; - $jamoMedial {t} $latinMedial > $Ti; - -# Doubled initials. The sequence "axxe", where XX exists as an initial -# (XXi), and also Xi and Xf exist (true of all digraphs XX), we want -# to transliterate as A XXi E, rather than split to A Xf Xi E. - - $jamoMedial {b b} $latinMedial > $BB; - $jamoMedial {d d} $latinMedial > $DD; - $jamoMedial {j j} $latinMedial > $JJ; - $jamoMedial {g g} $latinMedial > $GGi; - $jamoMedial {s s} $latinMedial > $SSi; - -# XYY. Because doubled consonants bind more strongly than XY -# consonants, we must handle the sequence "axyy" specially. Here XYf -# and YYi must exist. In these cases, we map to Xf YYi rather than -# XYf. - - $jamoMedial {b} s s > $Bf; - $jamoMedial {g} s s > $Gf; - $jamoMedial {l} b b > $L; - $jamoMedial {l} g g > $L; - $jamoMedial {l} s s > $L; - $jamoMedial {n} g g > $Nf; - $jamoMedial {n} j j > $Nf; - -# Finals: Attach consonant with preceding medial to preceding medial. -# Do this BEFORE mapping consonants to initials. Longer keys must -# precede shorter keys that they start with, e.g., the rule for 'bs' -# must precede 'b'. - -# [BASIC Jamo-Latin FINALS handled here. Order irrelevant within this -# block for Jamo-Latin.] - - $jamoMedial {bs} <> $BS; - $jamoMedial {b} <> $Bf; - $jamoMedial {c} <> $Cf; - $jamoMedial {d} <> $Df; - $jamoMedial {gg} <> $GGf; - $jamoMedial {gs} <> $GS; - $jamoMedial {g} <> $Gf; - $jamoMedial {h} <> $Hf; - $jamoMedial {j} <> $Jf; - $jamoMedial {k} <> $Kf; - $jamoMedial {lb} <> $LB; $jamoMedial {lg} <> $LG; - $jamoMedial {lh} <> $LH; - $jamoMedial {lm} <> $LM; - $jamoMedial {lp} <> $LP; - $jamoMedial {ls} <> $LS; - $jamoMedial {lt} <> $LT; - $jamoMedial {l} <> $L; - $jamoMedial {m} <> $Mf; - $jamoMedial {ng} <> $NG; - $jamoMedial {nh} <> $NH; - $jamoMedial {nj} <> $NJ; - $jamoMedial {n} <> $Nf; - $jamoMedial {p} <> $Pf; - $jamoMedial {ss} <> $SSf; - $jamoMedial {s} <> $Sf; - $jamoMedial {t} <> $Tf; - -# Initials: Attach single consonant to following medial. Do this -# AFTER mapping finals. Longer keys must precede shorter keys that -# they start with, e.g., the rule for 'gg' must precede 'g'. - -# [BASIC Jamo-Latin INITIALS handled here. Order irrelevant within -# this block for Jamo-Latin.] - - {gg} $latinMedial <> $GGi; - {g} $latinMedial <> $Gi; - {n} $latinMedial <> $Ni; - {dd} $latinMedial <> $DD; - {d} $latinMedial <> $Di; - {r} $latinMedial <> $R; - {m} $latinMedial <> $Mi; - {bb} $latinMedial <> $BB; - {b} $latinMedial <> $Bi; - {ss} $latinMedial <> $SSi; - {s} $latinMedial <> $Si; - {jj} $latinMedial <> $JJ; - {j} $latinMedial <> $Ji; - {c} $latinMedial <> $Ci; - {k} $latinMedial <> $Ki; - {t} $latinMedial <> $Ti; - {p} $latinMedial <> $Pi; - {h} $latinMedial <> $Hi; - -# 'r' in final position. Because of the equivalency of the 'l' and -# 'r' jamo (the glyphs are the same), we try to provide the same -# equivalency in Latin-Jamo. The 'l' to 'r' conversion is handled -# below. If we see an 'r' in an apparent final position, treat it -# like 'l'. For example, "karka" => Ki A R EU Ki A without this rule. -# Instead, we want Ki A L Ki A. - - $jamoMedial {r} $latinInitial > | l; - -# Initial + Final: If we match the next rule, we have initial then -# final consonant with no intervening medial. We insert the null -# vowel BEFORE it to create a well-formed syllable. (In the next rule -# we insert a null vowel AFTER an anomalous initial.) - - $jamoInitial {} [bcdghjklmnpst] > $EU; - -# Initial + X: This block matches an initial consonant not followed by -# a medial. We insert the null vowel after it. We handle double -# initials explicitly here; for single initial consonants we insert EU -# (as Latin) after them and let standard rules do the rest. - -# BREAKS ROUND TRIP INTEGRITY - - gg > $GGi $EU; - dd > $DD $EU; - bb > $BB $EU; - ss > $SSi $EU; - jj > $JJ $EU; - - ([bcdghjkmnprst]) > | $1 eu; - -# X + Final: Finally we have to deal with a consonant that can only be -# interpreted as a final (not an initial) and which is preceded -# neither by an initial nor a medial. It is the start of the -# syllable, but cannot be. Most of these will already be handled by -# the above rules. 'bs' splits into Bi EU Sf. Similar for 'gs' 'ng' -# 'nh' 'nj'. The only problem is 'l' and digraphs starting with 'l'. -# For this isolated case, we could add a null initial and medial, -# which would give "la" => IEUNG EU L IEUNG A, for example. A more -# economical solution is to transliterate isolated "l" (that is, -# initial "l") to "r". (Other similar conversions of consonants that -# occur neither as initials nor as finals are handled below.) - - l > | r; - -# Medials. If a medial is preceded by an initial, then we proceed -# normally. As usual, longer keys must precede shorter ones. - -# [BASIC Jamo-Latin MEDIALS handled here. Order irrelevant within -# this block for Jamo-Latin.] - - $jamoInitial {ae} <> $AE; - $jamoInitial {a} <> $A; - $jamoInitial {eo} <> $EO; - $jamoInitial {eu} <> $EU; - $jamoInitial {e} <> $E; - $jamoInitial {i} <> $I; - $jamoInitial {oe} <> $OE; - $jamoInitial {o} <> $O; - $jamoInitial {u} <> $U; - $jamoInitial {wae} <> $WAE; - $jamoInitial {wa} <> $WA; - $jamoInitial {weo} <> $WEO; - $jamoInitial {we} <> $WE; - $jamoInitial {wi} <> $WI; - $jamoInitial {yae} <> $YAE; - $jamoInitial {ya} <> $YA; - $jamoInitial {yeo} <> $YEO; - $jamoInitial {ye} <> $YE; - $jamoInitial {yi} <> $YI; - $jamoInitial {yo} <> $YO; - $jamoInitial {yu} <> $YU; - -# We may see an anomalous isolated 'w' or 'y'. In that case, we -# interpret it as 'wi' and 'yu', respectively. - -# BREAKS ROUND TRIP INTEGRITY - - $jamoInitial {w} > | wi; - $jamoInitial {y} > | yu; - -# Otherwise, insert a null consonant IEUNG before the medial (which is -# still an untransliterated latin vowel). - - ($latinMedial) > $IEUNG | $1; - -# Convert non-jamo latin consonants to equivalents. These occur as -# neither initials nor finals in jamo. 'l' occurs as a final, but not -# an initial; it is handled above. The following letters (left hand -# side) will never be output by Jamo-Latin. - - f > | p; - q > | k; - v > | b; - x > | ks; - z > | s; - -# Delete separators (Latin-Jamo). - - $sep > ; - -# Delete null consonants (Jamo-Latin). Do NOT delete null EU vowels, -# since these may also occur in text. - - < $IEUNG; - -#- N.B. DO NOT put any filters, NFD, etc. here -- those are aliased in -#- the INDEX file. This transliterator is, by itself, not -#- instantiated. It is used as a part of Latin-Jamo, Latin-Hangul, or -#- inverses thereof. - -# eof +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Jamo.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::[[:script=Latin:][:M:]']; +::NFD; +::Lower; +::Latin-ConjoiningJamo; +::[[:script=Latin:][:M:]] NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Kannada.txt new file mode 100644 index 00000000000..0565d8a7e63 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Kannada.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Katakana.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Katakana.txt index 5b7fc17605c..0bc2d0b7a21 100644 --- a/Build/source/libs/icu-xetex/data/translit/Latin_Katakana.txt +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Katakana.txt @@ -1,179 +1,73 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# note: a global filter is more efficient, but MUST include all source chars -#:: [\u0000-\u007E \u3001\u3002 \u3099-\u309C \u30A1-\u30FC \uFF61-\uFF9F [:Latin:][:Katakana:] [:nonspacing mark:]] ; -# MINIMAL FILTER GENERATED FOR: Latin-Katakana -### WARNING -- must add width filter, both here and below!!! ### -:: [[\u1100-\u1112\u111A\u1121\u1160-\u1175\u11AA\u11AC-\u11AD\u11B0-\u11B5\u2190-\u2193\u2502\u25A0\u25CB\u3000-\u3002\u300C-\u300D\u3099-\u309A\u30A1-\u30ED\u30EF\u30F2-\u30F4\u30F7\u30FA-\u30FC\uFF01-\uFF5E\uFFE0-\uFFE6][',.A-Za-z~\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0304\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1FB1\u1FB9\u1FD1\u1FD9\u1FE1\u1FE9\u212A-\u212B]] ; - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Katakana.txt +# Generated from CLDR: Thu Jul 20 16:27:17 PDT 2006 +# +:: [[ᄀ-ᄒᄚᄡ\u1160-ᅵᆪᆬ-ᆭᆰ-ᆵ<-↓│■○\u3000-。「-」\u3099-\u309Aァ-ロワヲ-ヴヷヺ-ー!-~¢-₩][',.A-Za-z~À-ÖØ-öø-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳ\u0304Ӣ-ӣӮ-ӯḀ-ẙẠ-ỹᾱᾹῑῙῡῩK-Å]] ; :: [:Latin:] fullwidth-halfwidth (); :: NFD (NFC); :: Lower (); # whenever transliterating from cased to uncased script, include this -# :: NFD () ; # this would catch the odd cases where a lowercase is not in NFD, but none are important for Japanese - -# Uses modified Hepburn. Small changes to make unambiguous. - -# | Kunrei-shiki: Hepburn/MHepburn -# | ------------------------------ -# | si: shi -# | si ~ya: sha -# | si ~yu: shu -# | si ~yo: sho -# | zi: ji -# | zi ~ya: ja -# | zi ~yu: ju -# | zi ~yo: jo -# | ti: chi -# | ti ~ya: cha -# | ti ~yu: chu -# | ti ~yu: cho -# | tu: tsu -# | di: ji/dji -# | du: zu/dzu -# | hu: fu - -# | For foreign words: -# | ----------------- -# | se ~i si -# | si ~e she -# | -# | ze ~i zi -# | zi ~e je -# | -# | te ~i ti -# | ti ~e che -# | te ~u tu -# | -# | de ~i di -# | de ~u du -# | de ~i di -# | -# | he ~u: hu -# | hu ~a fa -# | hu ~i fi -# | hu ~e he -# | hu ~o ho - -# Most small forms are generated, but if necessary -# explicit small forms are given with ~a, ~ya, etc. - -#------------------------------------------------------ -# Variables - $vowel = [aeiou] ; $consonant = [bcdfghjklmnpqrstvwxyz] ; $macron = \u0304 ; - -# Variables used for doubled-consonants with tsu - -$kana = [\u3041-\u3094] ; - -$voice = [\u3099\u309B]; -$semivoice = [\u309A\u309C]; - +$kana = [ぁ-ゔ] ; +$voice = [\u3099゛]; +$semivoice = [\u309A゜]; $k_start = [カキクケコかきくけこ] ; - $s_start = [サシスセソさしすせそ] ; - $j_start = [シし] $voice ; - $t_start = [タチツテトたちつてと] ; - $n_start = [ナニヌネノンなにぬねの] ; - $h_start = [ハヒヘホはひへほ] ; $f_start = [フふ] ; - $m_start = [マミムメモまみむめも] ; - $y_start = [ヤユヨやゆよ] ; - $r_start = [ラリルレロらりるれろ] ; - $w_start = [ワヰヱヲわゐゑを] ; - -$v_start = [ワヰヱヲ]゙ ; - -# if ン is followed by $n_quoter, then it needs an -# apostrophe after its romaji form to disambiguate it. -# e.g., ン ア ! = ナ, so represent as "n'a", not "na". - +$v_start = [ワヰヱヲ]\u3099 ; $n_quoter = [ア イ ウ エ オ ナ ニ ヌ ネ ノ ヤ ユ ヨ ン] ; - $small_y = [ャィュェョ] ; - -$iteration = \u309D ; - -#------------------------------------------------------ -# katakana rules - -# Punctuation - +$iteration = ゝ ; '.' <> 。; ',' <> 、; -# ' ' } [a-z] > ; # delete spaces before latin -# ' ' < [^' '\u30A0-\u30ff] {} ['\u30A0-\u30ff] ; #insert spaces before hiragana - -# Iteration Mark -# Copy previous letter & marks - -# TODO -# | $1 $1 < ($kana [[:M:]$voice$semivoice]?) $iteration - -# Specials for katakana -- not shared with hiragana - -va <> ヷ ; -vi <> ヸ ; -ve <> ヹ ; -vo <> ヺ ; +va <> ワ\u3099 ; +vi <> ヰ\u3099 ; +ve <> ヱ\u3099 ; +vo <> ヲ\u3099 ; '~ka' <> ヵ ; '~ke' <> ヶ ; - -# ~~~ begin shared rules ~~~ - -#special - ya < '~'ャ; yi < '~'ィ ; yu < '~'ュ; ye < '~'ェ; yo < '~'ョ; - -#normal - a <> ア ; - -b | '~' < ヒ ゙} $small_y ; -by } $vowel > ビ | '~y' ; - -ba <> バ ; -bi <> ビ ; -bu <> ブ ; -be <> ベ ; -bo <> ボ ; - +b | '~' < ヒ \u3099} $small_y ; +by } $vowel > ヒ\u3099 | '~y' ; +ba <> ハ\u3099 ; +bi <> ヒ\u3099 ; +bu <> フ\u3099 ; +be <> ヘ\u3099 ; +bo <> ホ\u3099 ; c } i > | s ; c } e > | s ; - -da <> ダ ; -di <> ディ ; -du <> デゥ ; -de <> デ ; -do <> ド ; -dzu <> ヅ ; -dja < ヂャ ; -dji'~i' < ヂィ ; # liu -dju < ヂュ ; -dje < ヂェ ; -djo < ヂョ ; -dji <> ヂ ; -dj } $vowel > ヂ | '~y' ; - -# TODO: QUESTION: use ĵĴżŻ instead of dj, dz - +da <> タ\u3099 ; +di <> テ\u3099ィ ; +du <> テ\u3099ゥ ; +de <> テ\u3099 ; +do <> ト\u3099 ; +dzu <> ツ\u3099 ; +dja < チ\u3099ャ ; +dji'~i' < チ\u3099ィ ; # liu +dju < チ\u3099ュ ; +dje < チ\u3099ェ ; +djo < チ\u3099ョ ; +dji <> チ\u3099 ; +dj } $vowel > チ\u3099 | '~y' ; cha < チャ ; chi'~i' < チィ ; # liu chu < チュ ; @@ -181,108 +75,80 @@ che < チェ ; cho < チョ ; chi <> チ ; ch } $vowel > チ | '~y' ; - e <> エ ; - -g | '~' < ギ} $small_y ; -gy } $vowel > ギ | '~y' ; - -ga <> ガ ; -gi <> ギ ; -gu <> グ ; -ge <> ゲ ; -go <> ゴ ; - +g | '~' < キ\u3099} $small_y ; +gy } $vowel > キ\u3099 | '~y' ; +ga <> カ\u3099 ; +gi <> キ\u3099 ; +gu <> ク\u3099 ; +ge <> ケ\u3099 ; +go <> コ\u3099 ; i <> イ ; - -# j } $vowel > ジ | '~y' ; - -ja <> ジャ ; -ji'~i' < ジィ ; # liu -ju <> ジュ ; -je <> ジェ ; -jo <> ジョ ; -ji <> ジ ; - +ja <> シ\u3099ャ ; +ji'~i' < シ\u3099ィ ; # liu +ju <> シ\u3099ュ ; +je <> シ\u3099ェ ; +jo <> シ\u3099ョ ; +ji <> シ\u3099 ; k | '~' < キ} $small_y ; ky } $vowel > キ | '~y' ; - ka <> カ ; ki <> キ ; ku <> ク ; ke <> ケ ; ko <> コ ; - m | '~' < ミ} $small_y ; my } $vowel > ミ | '~y' ; - ma <> マ ; mi <> ミ ; mu <> ム ; me <> メ ; mo <> モ ; - m } [pbfv] > ン ; - n | '~' < ニ } $small_y ; ny } $vowel > ニ | '~y' ; - na <> ナ ; ni <> ニ ; nu <> ヌ ; ne <> ネ ; no <> ノ ; - o <> オ ; - -p | '~' < ピ } $small_y ; -py } $vowel > ピ | '~y' ; - -pa <> パ ; -pi <> ピ ; -pu <> プ ; -pe <> ペ ; -po <> ポ ; - +p | '~' < ヒ\u309A } $small_y ; +py } $vowel > ヒ\u309A | '~y' ; +pa <> ハ\u309A ; +pi <> ヒ\u309A ; +pu <> フ\u309A ; +pe <> ヘ\u309A ; +po <> ホ\u309A ; h | '~' < ヒ } $small_y ; hy } $vowel > ヒ | '~y' ; - ha <> ハ ; hi <> ヒ ; hu <> ヘゥ ; he <> ヘ ; ho <> ホ ; - -# f | '~' < フ } $small_y ; -# f } $vowel > フ | '~' ; - fa <> ファ ; fi <> フィ ; fe <> フェ ; fo <> フォ ; fu <> フ ; - r | '~' < リ } $small_y ; ry } $vowel > リ | '~y' ; - ra <> ラ ; ri <> リ ; ru <> ル ; re <> レ ; ro <> ロ ; - -za <> ザ ; -zi <> ゼィ ; -zu <> ズ ; -ze <> ゼ ; -zo <> ゾ ; - +za <> サ\u3099 ; +zi <> セ\u3099ィ ; +zu <> ス\u3099 ; +ze <> セ\u3099 ; +zo <> ソ\u3099 ; sa <> サ ; si <> セィ ; su <> ス ; se <> セ ; so <> ソ ; - sha < シャ ; shi'~i' < シィ ; # liu shu < シュ ; @@ -290,58 +156,33 @@ she < シェ ; sho < ショ ; shi <> シ ; sh } $vowel > シ | '~y' ; - ta <> タ ; ti <> ティ ; tu <> テゥ ; te <> テ ; to <> ト ; - tsu <> ツ ; - -# v } $vowel > ヴ | '~' ; - -#'v~a' < ヴァ ; # liu -#'v~i' < ヴィ ; # liu -#'v~e' < ヴェ ; # liu -#'v~o' < ヴォ ; # liu -vu <> ヴ ; - +vu <> ウ\u3099 ; u <> ウ ; - -# w } $vowel > ウ | '~' ; - wa <> ワ ; wi <> ヰ ; wu > ウ ; we <> ヱ ; wo <> ヲ ; - ya <> ヤ ; yi > イ ; yu <> ユ ; ye > エ ; yo <> ヨ ; - -# double consonants - -#specials s } sh > ッ ; t } ch > ッ ; - -#voiced - j } j <> ッ } $j_start ; b } b <> ッ } [$h_start$f_start] $voice; d } d <> ッ } $t_start $voice; g } g <> ッ } $k_start $voice; p } p <> ッ } [$h_start$f_start] $semivoice; -# v } v <> ッ } [ワヰウヱヲう] $voice ; z } z <> ッ } $s_start $voice; v } v <> ッ } $v_start; - -# normal - k } k <> ッ } $k_start ; m } m <> ッ } $m_start ; n } n <> ッ } $n_start ; @@ -350,33 +191,15 @@ f } f <> ッ } $f_start ; r } r <> ッ } $r_start ; t } t <> ッ } $t_start ; s } s <> ッ } $s_start ; - w } w <> ッ } $w_start; y } y <> ッ } $y_start; - -# completeness x } x > ッ ; c } k > ッ ; c } c > ッ ; c } q > ッ ; l } l > ッ ; q } q > ッ ; -# y } y > ッ ; -# w } w > ッ ; - -# prolonged vowel mark. this indicates a doubling of -# the preceding vowel sound - -#a < a { ー ; # liu -#e < e { ー ; # liu -#i < i { ー ; # liu -#o < o { ー ; # liu -#u < u { ー ; # liu - $macron <> ー ; - -# small forms - '~a' <> ァ ; '~i' <> ィ ; '~u' <> ゥ ; @@ -389,107 +212,63 @@ $macron <> ー ; '~yu' <> ュ ; '~ye' > ェ ; '~yo' <> ョ ; - -# iteration marks -# TODO: make more accurate - j $1 < sh (y* $vowel) {ヽ$voice ; dj $1 < ch (y* $vowel) {ヽ$voice ; dz $1 < ts (y* $vowel) {ヽ$voice ; - g $1 < k (y* $vowel) {ヽ$voice ; z $1 < s (y* $vowel) {ヽ$voice ; d $1 < t (y* $vowel) {ヽ$voice ; h $1 < b (y* $vowel) {ヽ$voice ; v $1 < w (y* $vowel) {ヽ$voice ; - sh $1 < sh (y* $vowel) {ヽ$voice ; j $1 < j (y* $vowel) {ヽ$voice ; ch $1 < ch (y* $vowel) {ヽ$voice ; dj $1 < dj(y* $vowel) {ヽ$voice ; ts $1 < ts (y* $vowel) {ヽ$voice ; dz $1 < dz (y* $vowel) {ヽ$voice ; - $1 < ($consonant y* $vowel) {ヽ$voice? ; $1 < (.) {ヽ $voice? ; # otherwise repeat last character - < ヽ $voice? ; # delete if no characters found - -# h- rule: lengthens vowel if not followed by a vowel - +< ヽ $voice? ; # delete if no characters found [aeiou] } h > ー ; - -# one-way latin- > kana rules. these do not occur in -# well-formed romaji representing actual japanese text. -# their purpose is to make all romaji map to kana of -# some sort. - -# the following are not really necessary, but produce -# slightly more natural results. - cy > セィ ; -dy > ディ ; +dy > テ\u3099ィ ; hy > ヒ ; sy > セィ ; ty > ティ ; -zy > ゼィ ; - +zy > セ\u3099ィ ; h > ヘ ; - -# isolated consonants listed here so as not to mask -# longer rules above. - ch > チ; sh > シ ; -dz > ヅ ; -dj > ヂ; - -b > ブ ; -d > デ ; -g > グ ; +dz > ツ\u3099 ; +dj > チ\u3099; +b > フ\u3099 ; +d > テ\u3099 ; +g > ク\u3099 ; k > ク ; m > ム ; n'' < ン } $n_quoter ; n <> ン ; -p > プ ; +p > フ\u309A ; r > ル ; s > ス ; t > テ ; y > イ ; -z > ズ ; -v > ヴ ; - +z > ス\u3099 ; +v > ウ\u3099 ; f > フ; -j > ジ; +j > シ\u3099; w > ウ; - ß > | ss ; æ > | e ; ð > | d ; ø > | u ; þ > | th ; - -# simple substitutions using backup - c > | k ; l > | r ; q > | k ; x > | ks ; - -# ~~~ END shared rules ~~~ - -#------------------------------------------------------ -# Final cleanup - '~' > ; # delete stray tildes between letters [:Katakana:] { '' } [:Latin:] > ; # delete stray quotes between letters -# [\u02BE[:Nonspacing Mark:]-[\u3099-\u309C]] > ; # delete any non-spacing marks that we didn't use - -:: NFC (NFD) ; +:: NFC (NFD) ; :: ([:Katakana:] halfwidth-fullwidth); - -# note: a global filter is more efficient, but MUST include all source chars!! -#:: ([\u0000-\u007E \u3001\u3002 \u3099-\u309C \u30A1-\u30FC \uFF61-\uFF9F [:Latin:][:Katakana:] [:nonspacing mark:]]); -# MINIMAL FILTER GENERATED FOR: Latin-Katakana BACKWARD -:: ( [[\ -~\u00A2-\u00A3\u00A5-\u00A6\u00AC\u0304\u20A9\uFF61-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC\uFFE8-\uFFEE][~\u3001-\u3002\u304C\u304E\u3050\u3052\u3054\u3056\u3058\u305A\u305C\u305E\u3060\u3062\u3065\u3067\u3069\u3070-\u3071\u3073-\u3074\u3076-\u3077\u3079-\u307A\u307C-\u307D\u3094\u3099-\u309B\u309E\u30A1-\u30FA\u30FC-\u30FE]] ) ; - -# eof +:: ( [[\ -~¢-£¥-¦¬\u0304₩。-하-ᅦᅧ-ᅬᅭ-ᅲᅳ-ᅵ│-○][~、-。がぎぐげござじずぜぞだぢづでどば-ぱび-ぴぶ-ぷべ-ぺぼ-ぽゔ\u3099-゛ゞァ-ヺー-ヾ]] ) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Malayalam.txt new file mode 100644 index 00000000000..376c99096dc --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Malayalam.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_NumericPinyin.txt b/Build/source/libs/icu-xetex/data/translit/Latin_NumericPinyin.txt index 0296ebd8b8d..867f52d1fa0 100644 --- a/Build/source/libs/icu-xetex/data/translit/Latin_NumericPinyin.txt +++ b/Build/source/libs/icu-xetex/data/translit/Latin_NumericPinyin.txt @@ -1,32 +1,17 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# According to the pinyin definitions I've been able to find: -# 'a', 'e' are the preferred bases -# otherwise 'o' -# otherwise last vowel - -# The trailing form of syllables are the following: -# "a", "ai", "ao", "an", "ang", -# "o", "ou", "ong", -# "e", "ei", "er", "en", "eng", -# "i", "ia", "iao", "ie", "iu", "ian", "in", "iang", "ing", "iong", -# "u", "ua", "uo", "uai", "ui", "uan", "un", "uang", "ueng", -# "ü", "üe", "üan", "ün" -# so the letters the tone will 'hop' are: - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_NumericPinyin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# ::NFD (NFC); $tone = [\u0304\u0301\u030C\u0300\u0306] ; - -# Move the tone to the end of a syllable, and convert to number e {($tone) r} > r &tone-digit($1); ($tone) ( [i o n u {o n} {n g}]) > $2 &tone-digit($1); ($tone) > &tone-digit($1); - -# The following backs up until it finds the right vowel, then deposits the tone - $vowel = [aAeEiIoOuUüÜ {u\u0308} {U\u0308} ]; $consonant = [[a-z A-Z] - [$vowel]]; $digit = [1-5]; @@ -34,8 +19,4 @@ $1 &digit-tone($3) $2 < ([aAeE]) ($vowel* $consonant*) ($digit); $1 &digit-tone($3) $2 < ([oO]) ([$vowel-[aeAE]]* $consonant*) ($digit); $1 &digit-tone($3) $2 < ($vowel) ($consonant*) ($digit); &digit-tone($1) < [:letter:] {($digit)}; - ::NFC (NFD); - - - diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Oriya.txt new file mode 100644 index 00000000000..3b5c625f882 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Oriya.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Tamil.txt new file mode 100644 index 00000000000..31b2e2afc47 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Tamil.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Telugu.txt new file mode 100644 index 00000000000..eade0ed9ac7 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Telugu.txt @@ -0,0 +1,15 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::['.0-9A-Za-z~À-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳʔ\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЃЌЎЙйѓќўӁ-ӂӐ-ӑӖ-ӗӢ-ӣӮ-ӯḀ-ẙẠ-ỹἁἃ-ἅἇἉἋ-ἍἏἑἓ-ἕἙἛ-Ἕἡἣ-ἥἧἩἫ-ἭἯἱἳ-ἵἷἹἻ-ἽἿὁὃ-ὅὉὋ-Ὅὑὓ-ὕὗὙὛὝὟὡὣ-ὥὧὩὫ-ὭὯάέήίόύώᾁᾃ-ᾅᾇᾉᾋ-ᾍᾏᾑᾓ-ᾕᾗᾙᾛ-ᾝᾟᾡᾣ-ᾥᾧᾩᾫ-ᾭᾯ-ᾱᾴᾸ-ᾹΆῄΈΉ῎ῐ-ῑΐῘ-ῙΊ῞ῠ-ῡΰῥῨ-ῩΎ-Ῥ΅ῴΌΏK-Å\uE04D\uE064]; +::NFD; +::Lower; +::Latin-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Latin_Thai.txt b/Build/source/libs/icu-xetex/data/translit/Latin_Thai.txt new file mode 100644 index 00000000000..950ae20b465 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Latin_Thai.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Latin_Thai.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[[:Latin:][:Mn:][:Me:] \u0020\u0026 ;0-9|~«»ʹʹ‡ˌ]; +::NFD; +::Latin-ThaiLogical; +::ThaiLogical-Thai; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Bengali.txt new file mode 100644 index 00000000000..4f9a4ad54e5 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Devanagari.txt new file mode 100644 index 00000000000..a0407183abe --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Gujarati.txt new file mode 100644 index 00000000000..444ff4d8e01 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Gurmukhi.txt new file mode 100644 index 00000000000..87f5254fb67 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_InterIndic.txt index 3fd42e086c7..b253e6c3e51 100644 --- a/Build/source/libs/icu-xetex/data/translit/Malayalam_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_InterIndic.txt @@ -1,85 +1,84 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Malayalam-InterIndic -#:: NFD (NFC) ; - -\u0D02>\uE002; # SIGN ANUSVARA -\u0D03>\uE003; # SIGN VISARGA -\u0D05>\uE005; # LETTER A -\u0D06>\uE006; # LETTER AA -\u0D07>\uE007; # LETTER I -\u0D08>\uE008; # LETTER II -\u0D09>\uE009; # LETTER U -\u0D0A>\uE00A; # LETTER UU -\u0D0B>\uE00B; # LETTER VOCALIC R -\u0D0C>\uE00C; # LETTER VOCALIC L -\u0D0E>\uE00E; # LETTER E -\u0D0F>\uE00F; # LETTER EE -\u0D10>\uE010; # LETTER AI -\u0D12>\uE012; # LETTER O -\u0D13>\uE013; # LETTER OO -\u0D14>\uE014; # LETTER AU -\u0D15>\uE015; # LETTER KA -\u0D16>\uE016; # LETTER KHA -\u0D17>\uE017; # LETTER GA -\u0D18>\uE018; # LETTER GHA -\u0D19>\uE019; # LETTER NGA -\u0D1A>\uE01A; # LETTER CA -\u0D1B>\uE01B; # LETTER CHA -\u0D1C>\uE01C; # LETTER JA -\u0D1D>\uE01D; # LETTER JHA -\u0D1E>\uE01E; # LETTER NYA -\u0D1F>\uE01F; # LETTER TTA -\u0D20>\uE020; # LETTER TTHA -\u0D21>\uE021; # LETTER DDA -\u0D22>\uE022; # LETTER DDHA -\u0D23>\uE023; # LETTER NNA -\u0D24>\uE024; # LETTER TA -\u0D25>\uE025; # LETTER THA -\u0D26>\uE026; # LETTER DA -\u0D27>\uE027; # LETTER DHA -\u0D28>\uE028; # LETTER NA -\u0D2A>\uE02A; # LETTER PA -\u0D2B>\uE02B; # LETTER PHA -\u0D2C>\uE02C; # LETTER BA -\u0D2D>\uE02D; # LETTER BHA -\u0D2E>\uE02E; # LETTER MA -\u0D2F>\uE02F; # LETTER YA -\u0D30>\uE030; # LETTER RA -\u0D31>\uE031; # LETTER RRA -\u0D32>\uE032; # LETTER LA -\u0D33>\uE033; # LETTER LLA -\u0D34>\uE034; # LETTER LLLA -\u0D35>\uE035; # LETTER VA -\u0D36>\uE036; # LETTER SHA -\u0D37>\uE037; # LETTER SSA -\u0D38>\uE038; # LETTER SA -\u0D39>\uE039; # LETTER HA -\u0D3E>\uE03E; # VOWEL SIGN AA -\u0D3F>\uE03F; # VOWEL SIGN I -\u0D40>\uE040; # VOWEL SIGN II +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +ം>\uE002; # SIGN ANUSVARA +ഃ>\uE003; # SIGN VISARGA +അ>\uE005; # LETTER A +ആ>\uE006; # LETTER AA +ഇ>\uE007; # LETTER I +ഈ>\uE008; # LETTER II +ഉ>\uE009; # LETTER U +ഊ>\uE00A; # LETTER UU +ഋ>\uE00B; # LETTER VOCALIC R +ഌ>\uE00C; # LETTER VOCALIC L +എ>\uE00E; # LETTER E +ഏ>\uE00F; # LETTER EE +ഐ>\uE010; # LETTER AI +ഒ>\uE012; # LETTER O +ഓ>\uE013; # LETTER OO +ഔ>\uE014; # LETTER AU +ക>\uE015; # LETTER KA +ഖ>\uE016; # LETTER KHA +ഗ>\uE017; # LETTER GA +ഘ>\uE018; # LETTER GHA +ങ>\uE019; # LETTER NGA +ച>\uE01A; # LETTER CA +ഛ>\uE01B; # LETTER CHA +ജ>\uE01C; # LETTER JA +ഝ>\uE01D; # LETTER JHA +ഞ>\uE01E; # LETTER NYA +ട>\uE01F; # LETTER TTA +ഠ>\uE020; # LETTER TTHA +ഡ>\uE021; # LETTER DDA +ഢ>\uE022; # LETTER DDHA +ണ>\uE023; # LETTER NNA +ത>\uE024; # LETTER TA +ഥ>\uE025; # LETTER THA +ദ>\uE026; # LETTER DA +ധ>\uE027; # LETTER DHA +ന>\uE028; # LETTER NA +പ>\uE02A; # LETTER PA +ഫ>\uE02B; # LETTER PHA +ബ>\uE02C; # LETTER BA +ഭ>\uE02D; # LETTER BHA +മ>\uE02E; # LETTER MA +യ>\uE02F; # LETTER YA +ര>\uE030; # LETTER RA +റ>\uE031; # LETTER RRA +ല>\uE032; # LETTER LA +ള>\uE033; # LETTER LLA +ഴ>\uE034; # LETTER LLLA +വ>\uE035; # LETTER VA +ശ>\uE036; # LETTER SHA +ഷ>\uE037; # LETTER SSA +സ>\uE038; # LETTER SA +ഹ>\uE039; # LETTER HA +ാ>\uE03E; # VOWEL SIGN AA +ി>\uE03F; # VOWEL SIGN I +ീ>\uE040; # VOWEL SIGN II \u0D41>\uE041; # VOWEL SIGN U \u0D42>\uE042; # VOWEL SIGN UU \u0D43>\uE043; # VOWEL SIGN VOCALIC R -\u0D46>\uE046; # VOWEL SIGN E -\u0D47>\uE047; # VOWEL SIGN EE -\u0D48>\uE048; # VOWEL SIGN AI +െ>\uE046; # VOWEL SIGN E +േ>\uE047; # VOWEL SIGN EE +ൈ>\uE048; # VOWEL SIGN AI \u0D4D>\uE04D; # SIGN VIRAMA -\u0D57>\uE057; # AU LENGTH MARK -\u0D60>\uE060; # LETTER VOCALIC RR -\u0D61>\uE061; # LETTER VOCALIC LL -\u0D66>\uE066; # DIGIT ZERO -\u0D67>\uE067; # DIGIT ONE -\u0D68>\uE068; # DIGIT TWO -\u0D69>\uE069; # DIGIT THREE -\u0D6A>\uE06A; # DIGIT FOUR -\u0D6B>\uE06B; # DIGIT FIVE -\u0D6C>\uE06C; # DIGIT SIX -\u0D6D>\uE06D; # DIGIT SEVEN -\u0D6E>\uE06E; # DIGIT EIGHT -\u0D6F>\uE06F; # DIGIT NINE -# :: NFC (NFD) ; -# eof +ൗ>\uE057; # AU LENGTH MARK +ൠ>\uE060; # LETTER VOCALIC RR +ൡ>\uE061; # LETTER VOCALIC LL +൦>\uE066; # DIGIT ZERO +൧>\uE067; # DIGIT ONE +൨>\uE068; # DIGIT TWO +൩>\uE069; # DIGIT THREE +൪>\uE06A; # DIGIT FOUR +൫>\uE06B; # DIGIT FIVE +൬>\uE06C; # DIGIT SIX +൭>\uE06D; # DIGIT SEVEN +൮>\uE06E; # DIGIT EIGHT +൯>\uE06F; # DIGIT NINE diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Kannada.txt new file mode 100644 index 00000000000..4f715c58a67 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Latin.txt new file mode 100644 index 00000000000..d335bbba340 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Oriya.txt new file mode 100644 index 00000000000..127507d7027 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Tamil.txt new file mode 100644 index 00000000000..7cfd2e3e044 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Malayalam_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Malayalam_Telugu.txt new file mode 100644 index 00000000000..283daf98eba --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Malayalam_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Malayalam_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ം-ഃഅ-ഌഎ-ഐഒ-നപ-ഹാ-\u0D43െ-ൈൊ-\u0D4Dൗൠ-ൡ൦-൯]; +::NFD; +::Malayalam-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Bengali.txt new file mode 100644 index 00000000000..96fdd548b0a --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Devanagari.txt new file mode 100644 index 00000000000..a9a67f18499 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Gujarati.txt new file mode 100644 index 00000000000..5d5e956db5b --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Gurmukhi.txt new file mode 100644 index 00000000000..90e418c6f8a --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_InterIndic.txt index 937d919cdf7..cb2dec53e70 100644 --- a/Build/source/libs/icu-xetex/data/translit/Oriya_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_InterIndic.txt @@ -1,95 +1,90 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Oriya-InterIndic -#:: NFD (NFC) ; -#\u0B21\u0B3C>\uE05C;# LETTER RRA -#\u0B22\u0B3C>\uE05D;# LETTER RHA -\u0B47\u0B56>\uE048;# VOWEL SIGN AI -\u0B47\u0B3E>\uE04B;# VOWEL SIGN O -\u0B47\u0B57>\uE04C;# VOWEL SIGN AU - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +େ\u0B56>\uE048;# VOWEL SIGN AI +ୋ>\uE04B;# VOWEL SIGN O +ୌ>\uE04C;# VOWEL SIGN AU \u0B01>\uE001; # SIGN CANDRABINDU -\u0B02>\uE002; # SIGN ANUSVARA -\u0B03>\uE003; # SIGN VISARGA -\u0B05>\uE005; # LETTER A -\u0B06>\uE006; # LETTER AA -\u0B07>\uE007; # LETTER I -\u0B08>\uE008; # LETTER II -\u0B09>\uE009; # LETTER U -\u0B0A>\uE00A; # LETTER UU -\u0B0B>\uE00B; # LETTER VOCALIC R -\u0B0C>\uE00C; # LETTER VOCALIC L -\u0B0F>\uE00F; # LETTER E -\u0B10>\uE010; # LETTER AI -\u0B13>\uE013; # LETTER O -\u0B14>\uE014; # LETTER AU -\u0B15>\uE015; # LETTER KA -\u0B16>\uE016; # LETTER KHA -\u0B17>\uE017; # LETTER GA -\u0B18>\uE018; # LETTER GHA -\u0B19>\uE019; # LETTER NGA -\u0B1A>\uE01A; # LETTER CA -\u0B1B>\uE01B; # LETTER CHA -\u0B1C>\uE01C; # LETTER JA -\u0B1D>\uE01D; # LETTER JHA -\u0B1E>\uE01E; # LETTER NYA -\u0B1F>\uE01F; # LETTER TTA -\u0B20>\uE020; # LETTER TTHA -\u0B21>\uE021; # LETTER DDA -\u0B22>\uE022; # LETTER DDHA -\u0B23>\uE023; # LETTER NNA -\u0B24>\uE024; # LETTER TA -\u0B25>\uE025; # LETTER THA -\u0B26>\uE026; # LETTER DA -\u0B27>\uE027; # LETTER DHA -\u0B28>\uE028; # LETTER NA -\u0B2A>\uE02A; # LETTER PA -\u0B2B>\uE02B; # LETTER PHA -\u0B2C>\uE02C; # LETTER BA -\u0B2D>\uE02D; # LETTER BHA -\u0B2E>\uE02E; # LETTER MA -\u0B2F>\uE02F; # LETTER YA -\u0B30>\uE030; # LETTER RA -\u0B32>\uE032; # LETTER LA -\u0B33>\uE033; # LETTER LLA -\u0B35>\uE035; # LETTER VA -\u0B36>\uE036; # LETTER SHA -\u0B37>\uE037; # LETTER SSA -\u0B38>\uE038; # LETTER SA -\u0B39>\uE039; # LETTER HA +ଂ>\uE002; # SIGN ANUSVARA +ଃ>\uE003; # SIGN VISARGA +ଅ>\uE005; # LETTER A +ଆ>\uE006; # LETTER AA +ଇ>\uE007; # LETTER I +ଈ>\uE008; # LETTER II +ଉ>\uE009; # LETTER U +ଊ>\uE00A; # LETTER UU +ଋ>\uE00B; # LETTER VOCALIC R +ଌ>\uE00C; # LETTER VOCALIC L +ଏ>\uE00F; # LETTER E +ଐ>\uE010; # LETTER AI +ଓ>\uE013; # LETTER O +ଔ>\uE014; # LETTER AU +କ>\uE015; # LETTER KA +ଖ>\uE016; # LETTER KHA +ଗ>\uE017; # LETTER GA +ଘ>\uE018; # LETTER GHA +ଙ>\uE019; # LETTER NGA +ଚ>\uE01A; # LETTER CA +ଛ>\uE01B; # LETTER CHA +ଜ>\uE01C; # LETTER JA +ଝ>\uE01D; # LETTER JHA +ଞ>\uE01E; # LETTER NYA +ଟ>\uE01F; # LETTER TTA +ଠ>\uE020; # LETTER TTHA +ଡ>\uE021; # LETTER DDA +ଢ>\uE022; # LETTER DDHA +ଣ>\uE023; # LETTER NNA +ତ>\uE024; # LETTER TA +ଥ>\uE025; # LETTER THA +ଦ>\uE026; # LETTER DA +ଧ>\uE027; # LETTER DHA +ନ>\uE028; # LETTER NA +ପ>\uE02A; # LETTER PA +ଫ>\uE02B; # LETTER PHA +ବ>\uE02C; # LETTER BA +ଭ>\uE02D; # LETTER BHA +ମ>\uE02E; # LETTER MA +ଯ>\uE02F; # LETTER YA +ର>\uE030; # LETTER RA +ଲ>\uE032; # LETTER LA +ଳ>\uE033; # LETTER LLA +ଵ>\uE035; # LETTER VA +ଶ>\uE036; # LETTER SHA +ଷ>\uE037; # LETTER SSA +ସ>\uE038; # LETTER SA +ହ>\uE039; # LETTER HA \u0B3C>\uE03C; # SIGN NUKTA -\u0B3D>\uE03D; # SIGN AVAGRAHA -\u0B3E>\uE03E; # VOWEL SIGN AA +ଽ>\uE03D; # SIGN AVAGRAHA +ା>\uE03E; # VOWEL SIGN AA \u0B3F>\uE03F; # VOWEL SIGN I -\u0B40>\uE040; # VOWEL SIGN II +ୀ>\uE040; # VOWEL SIGN II \u0B41>\uE041; # VOWEL SIGN U \u0B42>\uE042; # VOWEL SIGN UU \u0B43>\uE043; # VOWEL SIGN VOCALIC R -\u0B47>\uE047; # VOWEL SIGN E -# +େ>\uE047; # VOWEL SIGN E \u0B4D>\uE04D; # SIGN VIRAMA \u0B56>\uE056; # AI LENGTH MARK -\u0B57>\uE057; # AU LENGTH MARK -\u0964>\ue064; # DANDA -\u0965>\ue065; # DOUBLE DANDA -# -\u0B5F>\uE05F; # LETTER YYA -\u0B60>\uE060; # LETTER VOCALIC RR -\u0B61>\uE061; # LETTER VOCALIC LL -\u0B66>\uE066; # DIGIT ZERO -\u0B67>\uE067; # DIGIT ONE -\u0B68>\uE068; # DIGIT TWO -\u0B69>\uE069; # DIGIT THREE -\u0B6A>\uE06A; # DIGIT FOUR -\u0B6B>\uE06B; # DIGIT FIVE -\u0B6C>\uE06C; # DIGIT SIX -\u0B6D>\uE06D; # DIGIT SEVEN -\u0B6E>\uE06E; # DIGIT EIGHT -\u0B6F>\uE06F; # DIGIT NINE -\u0B70>\ue07B; # ISSHAR -\u0B71>\ue081; # LETTER WA -# :: NFC (NFD) ; -# eof +ୗ>\uE057; # AU LENGTH MARK +।>\uE064; # DANDA +॥>\uE065; # DOUBLE DANDA +ୟ>\uE05F; # LETTER YYA +ୠ>\uE060; # LETTER VOCALIC RR +ୡ>\uE061; # LETTER VOCALIC LL +୦>\uE066; # DIGIT ZERO +୧>\uE067; # DIGIT ONE +୨>\uE068; # DIGIT TWO +୩>\uE069; # DIGIT THREE +୪>\uE06A; # DIGIT FOUR +୫>\uE06B; # DIGIT FIVE +୬>\uE06C; # DIGIT SIX +୭>\uE06D; # DIGIT SEVEN +୮>\uE06E; # DIGIT EIGHT +୯>\uE06F; # DIGIT NINE +୰>\uE07B; # ISSHAR +ୱ>\uE081; # LETTER WA diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Kannada.txt new file mode 100644 index 00000000000..797e7010af3 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Latin.txt new file mode 100644 index 00000000000..54ac76fad59 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[।-॥\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵଶ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-୰ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Malayalam.txt new file mode 100644 index 00000000000..c59d1e8afae --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Tamil.txt new file mode 100644 index 00000000000..529584da38b --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Oriya_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Oriya_Telugu.txt new file mode 100644 index 00000000000..29469ee634c --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Oriya_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Oriya_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[\u0B01-ଃଅ-ଌଏ-ଐଓ-ନପ-ରଲ-ଳଵ-ହ\u0B3C-\u0B43େ-ୈୋ-\u0B4D\u0B56-ୗଡ଼-ଢ଼ୟ-ୡ୦-ୱ]; +::NFD; +::Oriya-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Pinyin_NumericPinyin.txt b/Build/source/libs/icu-xetex/data/translit/Pinyin_NumericPinyin.txt new file mode 100644 index 00000000000..6062cb0ffc6 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Pinyin_NumericPinyin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Pinyin_NumericPinyin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +\u0304 <> 1; +\u0301 <> 2; +\u030C <> 3; +\u0300 <> 4; +< 5; diff --git a/Build/source/libs/icu-xetex/data/translit/Spacedhan_Han.txt b/Build/source/libs/icu-xetex/data/translit/Spacedhan_Han.txt new file mode 100644 index 00000000000..8f2f39edb4a --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Spacedhan_Han.txt @@ -0,0 +1,10 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Spacedhan_Han.txt +# Generated from CLDR: Thu Jul 20 14:55:41 PDT 2006 +# +::null; diff --git a/Build/source/libs/icu-xetex/data/translit/Syriac_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Syriac_Latin.txt new file mode 100644 index 00000000000..ed746144933 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Syriac_Latin.txt @@ -0,0 +1,56 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Syriac_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +ܫ <> sh; +ܞ > yh; +ܖ <> dr; +ܐ <> ʾ; +\u0711 > ʾ; +ܒ <> b; +ܓ <> g; +ܔ > g; +ܕ <> d; +ܗ <> h; +ܘ <> w; +ܙ <> z; +ܚ <> ḥ; +ܛ <> t\u0323; +ܜ > t\u0323; +ܝ <> y; +ܟ <> k; +ܠ <> l; +ܡ <> m; +ܢ <> n; +ܣ <> s; +ܤ > s; +ܥ > ʿ; +ܦ <> p; +ܧ > p; +ܨ <> ṣ; +ܩ <> q; +ܪ <> r; +ܬ <> t; +\u0730 > a; +\u0731 > a; +\u0732 <> a; +\u0733 > o; +\u0734 > o; +\u0735 > a; +\u0736 > e; +\u0737 > e; +\u0738 <> e; +\u0739 <> ē; +\u073A > i; +\u073B > i; +\u0742 <> i; +\u073D > u; +\u073E > u; +\u073C <> u; +\u073F <> o; +܍ > \*; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Bengali.txt new file mode 100644 index 00000000000..f3d7590cd47 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Devanagari.txt new file mode 100644 index 00000000000..b86606f961e --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Gujarati.txt new file mode 100644 index 00000000000..697f5290d84 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Gurmukhi.txt new file mode 100644 index 00000000000..ad77928b669 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_InterIndic.txt index c7808b539ca..f6a11883449 100644 --- a/Build/source/libs/icu-xetex/data/translit/Tamil_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_InterIndic.txt @@ -1,77 +1,73 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2005, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Tamil-InterIndic -#:: NFD (NFC) ; - -\u0BC6\u0BBE>\uE04A;# VOWEL SIGN O -\u0BC7\u0BBE>\uE04B;# VOWEL SIGN OO -\u0BC6\u0BD7>\uE04C;# VOWEL SIGN AU -\u0B92\u0BD7>\uE014;# LETTER AU - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +ொ>\uE04A;# VOWEL SIGN O +ோ>\uE04B;# VOWEL SIGN OO +ௌ>\uE04C;# VOWEL SIGN AU +ஔ>\uE014;# LETTER AU \u0B82>\uE002; # SIGN ANUSVARA -\u0B83>\uE003; # SIGN VISARGA -\u0B85>\uE005; # LETTER A -\u0B86>\uE006; # LETTER AA -\u0B87>\uE007; # LETTER I -\u0B88>\uE008; # LETTER II -\u0B89>\uE009; # LETTER U -\u0B8A>\uE00A; # LETTER UU -\u0B8E>\uE00E; # LETTER E -\u0B8F>\uE00F; # LETTER EE -\u0B90>\uE010; # LETTER AI -\u0B92>\uE012; # LETTER O -\u0B93>\uE013; # LETTER OO -\u0B94>\uE014; # LETTER AU -\u0B95>\uE015; # LETTER KA -\u0B99>\uE019; # LETTER NGA -\u0B9A>\uE01A; # LETTER CA -\u0B9C>\uE01C; # LETTER JA -\u0B9E>\uE01E; # LETTER NYA -\u0B9F>\uE01F; # LETTER TTA -\u0BA3>\uE023; # LETTER NNA -\u0BA4>\uE024; # LETTER TA -\u0BA8>\uE028; # LETTER NA -\u0BA9>\uE029; # LETTER NNNA -\u0BAA>\uE02A; # LETTER PA -\u0BAE>\uE02E; # LETTER MA -\u0BAF>\uE02F; # LETTER YA -\u0BB0>\uE030; # LETTER RA -\u0BB1>\uE031; # LETTER RRA -\u0BB2>\uE032; # LETTER LA -\u0BB3>\uE033; # LETTER LLA -\u0BB4>\uE034; # LETTER LLLA -\u0BB5>\uE035; # LETTER VA -\u0BB6>\uE036; # LETTER SHA -\u0BB7>\uE037; # LETTER SSA -\u0BB8>\uE038; # LETTER SA -\u0BB9>\uE039; # LETTER HA -\u0BBE>\uE03E; # VOWEL SIGN AA -\u0BBF>\uE03F; # VOWEL SIGN I +ஃ>\uE003; # SIGN VISARGA +அ>\uE005; # LETTER A +ஆ>\uE006; # LETTER AA +இ>\uE007; # LETTER I +ஈ>\uE008; # LETTER II +உ>\uE009; # LETTER U +ஊ>\uE00A; # LETTER UU +எ>\uE00E; # LETTER E +ஏ>\uE00F; # LETTER EE +ஐ>\uE010; # LETTER AI +ஒ>\uE012; # LETTER O +ஓ>\uE013; # LETTER OO +ஔ>\uE014; # LETTER AU +க>\uE015; # LETTER KA +ங>\uE019; # LETTER NGA +ச>\uE01A; # LETTER CA +ஜ>\uE01C; # LETTER JA +ஞ>\uE01E; # LETTER NYA +ட>\uE01F; # LETTER TTA +ண>\uE023; # LETTER NNA +த>\uE024; # LETTER TA +ந>\uE028; # LETTER NA +ன>\uE029; # LETTER NNNA +ப>\uE02A; # LETTER PA +ம>\uE02E; # LETTER MA +ய>\uE02F; # LETTER YA +ர>\uE030; # LETTER RA +ற>\uE031; # LETTER RRA +ல>\uE032; # LETTER LA +ள>\uE033; # LETTER LLA +ழ>\uE034; # LETTER LLLA +வ>\uE035; # LETTER VA +ஶ>\uE036; # LETTER SHA +ஷ>\uE037; # LETTER SSA +ஸ>\uE038; # LETTER SA +ஹ>\uE039; # LETTER HA +ா>\uE03E; # VOWEL SIGN AA +ி>\uE03F; # VOWEL SIGN I \u0BC0>\uE040; # VOWEL SIGN II -\u0BC1>\uE041; # VOWEL SIGN U -\u0BC2>\uE042; # VOWEL SIGN UU -\u0BC6>\uE046; # VOWEL SIGN E -\u0BC7>\uE047; # VOWEL SIGN EE -\u0BC8>\uE048; # VOWEL SIGN AI - +ு>\uE041; # VOWEL SIGN U +ூ>\uE042; # VOWEL SIGN UU +ெ>\uE046; # VOWEL SIGN E +ே>\uE047; # VOWEL SIGN EE +ை>\uE048; # VOWEL SIGN AI \u0BCD>\uE04D; # SIGN VIRAMA -\u0BD7>\uE057; # AU LENGTH MARK -\u0BE7>\uE067; # DIGIT ONE -\u0BE8>\uE068; # DIGIT TWO -\u0BE9>\uE069; # DIGIT THREE -\u0BEA>\uE06A; # DIGIT FOUR -\u0BEB>\uE06B; # DIGIT FIVE -\u0BEC>\uE06C; # DIGIT SIX -\u0BED>\uE06D; # DIGIT SEVEN -\u0BEE>\uE06E; # DIGIT EIGHT -\u0BEF>\uE06F; # DIGIT NINE -\u0BF0>\uE067\uE066; # UNMAPPED Tamil-InterIndic: NUMBER TEN -\u0BF1>\uE067\uE066\uE066; # UNMAPPED Tamil-InterIndic: NUMBER ONE HUNDRED -\u0BF2>\uE067\uE066\uE066\uE066;# UNMAPPED Tamil-InterIndic: NUMBER ONE THOUSAND -0>\ue066; - -# :: NFC (NFD) ; -# eof +ௗ>\uE057; # AU LENGTH MARK +௧>\uE067; # DIGIT ONE +௨>\uE068; # DIGIT TWO +௩>\uE069; # DIGIT THREE +௪>\uE06A; # DIGIT FOUR +௫>\uE06B; # DIGIT FIVE +௬>\uE06C; # DIGIT SIX +௭>\uE06D; # DIGIT SEVEN +௮>\uE06E; # DIGIT EIGHT +௯>\uE06F; # DIGIT NINE +௰>\uE067\uE066; # UNMAPPED Tamil-InterIndic: NUMBER TEN +௱>\uE067\uE066\uE066; # UNMAPPED Tamil-InterIndic: NUMBER ONE HUNDRED +௲>\uE067\uE066\uE066\uE066;# UNMAPPED Tamil-InterIndic: NUMBER ONE THOUSAND +0>\uE066; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Kannada.txt new file mode 100644 index 00000000000..2e0063b74d9 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Latin.txt new file mode 100644 index 00000000000..4d809bb2ba1 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Malayalam.txt new file mode 100644 index 00000000000..335bdf362a4 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Oriya.txt new file mode 100644 index 00000000000..08fcacc5397 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Tamil_Telugu.txt b/Build/source/libs/icu-xetex/data/translit/Tamil_Telugu.txt new file mode 100644 index 00000000000..69e95887325 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Tamil_Telugu.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Tamil_Telugu.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[0\u0B82-ஃஅ-ஊஎ-ஐஒ-கங-சஜஞ-டண-தந-பம-வஷ-ஹா-ூெ-ைொ-\u0BCDௗ௧-௲ஶ]; +::NFD; +::Tamil-InterIndic; +::InterIndic-Telugu; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Bengali.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Bengali.txt new file mode 100644 index 00000000000..a8a9b2292fe --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Bengali.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Bengali.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Bengali; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Devanagari.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Devanagari.txt new file mode 100644 index 00000000000..744f13860bc --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Devanagari.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Devanagari; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Gujarati.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Gujarati.txt new file mode 100644 index 00000000000..5a8878bf31b --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Gujarati.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Gujarati.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Gujarati; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Gurmukhi.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Gurmukhi.txt new file mode 100644 index 00000000000..acde8f546ff --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Gurmukhi.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Gurmukhi.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Gurmukhi; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_InterIndic.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_InterIndic.txt index b8ce53064d5..d08cfef7b7e 100644 --- a/Build/source/libs/icu-xetex/data/translit/Telugu_InterIndic.txt +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_InterIndic.txt @@ -1,71 +1,73 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Telugu-InterIndic -#:: NFD (NFC) ; -\u0c46\u0c4d\u0c56>\ue048\ue04d; +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_InterIndic.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +\u0C46\u0C4D\u0C56>\uE048\uE04D; \u0C46\u0C56>\uE048;# VOWEL SIGN AI -\u0C01>\uE001; # SIGN CANDRABINDU -\u0C02>\uE002; # SIGN ANUSVARA -\u0C03>\uE003; # SIGN VISARGA -\u0C05>\uE005; # LETTER A -\u0C06>\uE006; # LETTER AA -\u0C07>\uE007; # LETTER I -\u0C08>\uE008; # LETTER II -\u0C09>\uE009; # LETTER U -\u0C0A>\uE00A; # LETTER UU -\u0C0B>\uE00B; # LETTER VOCALIC R -\u0C0C>\uE00C; # LETTER VOCALIC L -\u0C0E>\uE00E; # LETTER E -\u0C0F>\uE00F; # LETTER EE -\u0C10>\uE010; # LETTER AI -\u0C12>\uE012; # LETTER O -\u0C13>\uE013; # LETTER OO -\u0C14>\uE014; # LETTER AU -\u0C15>\uE015; # LETTER KA -\u0C16>\uE016; # LETTER KHA -\u0C17>\uE017; # LETTER GA -\u0C18>\uE018; # LETTER GHA -\u0C19>\uE019; # LETTER NGA -\u0C1A>\uE01A; # LETTER CA -\u0C1B>\uE01B; # LETTER CHA -\u0C1C>\uE01C; # LETTER JA -\u0C1D>\uE01D; # LETTER JHA -\u0C1E>\uE01E; # LETTER NYA -\u0C1F>\uE01F; # LETTER TTA -\u0C20>\uE020; # LETTER TTHA -\u0C21>\uE021; # LETTER DDA -\u0C22>\uE022; # LETTER DDHA -\u0C23>\uE023; # LETTER NNA -\u0C24>\uE024; # LETTER TA -\u0C25>\uE025; # LETTER THA -\u0C26>\uE026; # LETTER DA -\u0C27>\uE027; # LETTER DHA -\u0C28>\uE028; # LETTER NA -\u0C2A>\uE02A; # LETTER PA -\u0C2B>\uE02B; # LETTER PHA -\u0C2C>\uE02C; # LETTER BA -\u0C2D>\uE02D; # LETTER BHA -\u0C2E>\uE02E; # LETTER MA -\u0C2F>\uE02F; # LETTER YA -\u0C30>\uE030; # LETTER RA -\u0C31>\uE031; # LETTER RRA -\u0C32>\uE032; # LETTER LA -\u0C33>\uE033; # LETTER LLA -\u0C35>\uE035; # LETTER VA -\u0C36>\uE036; # LETTER SHA -\u0C37>\uE037; # LETTER SSA -\u0C38>\uE038; # LETTER SA -\u0C39>\uE039; # LETTER HA +ఁ>\uE001; # SIGN CANDRABINDU +ం>\uE002; # SIGN ANUSVARA +ః>\uE003; # SIGN VISARGA +అ>\uE005; # LETTER A +ఆ>\uE006; # LETTER AA +ఇ>\uE007; # LETTER I +ఈ>\uE008; # LETTER II +ఉ>\uE009; # LETTER U +ఊ>\uE00A; # LETTER UU +ఋ>\uE00B; # LETTER VOCALIC R +ఌ>\uE00C; # LETTER VOCALIC L +ఎ>\uE00E; # LETTER E +ఏ>\uE00F; # LETTER EE +ఐ>\uE010; # LETTER AI +ఒ>\uE012; # LETTER O +ఓ>\uE013; # LETTER OO +ఔ>\uE014; # LETTER AU +క>\uE015; # LETTER KA +ఖ>\uE016; # LETTER KHA +గ>\uE017; # LETTER GA +ఘ>\uE018; # LETTER GHA +ఙ>\uE019; # LETTER NGA +చ>\uE01A; # LETTER CA +ఛ>\uE01B; # LETTER CHA +జ>\uE01C; # LETTER JA +ఝ>\uE01D; # LETTER JHA +ఞ>\uE01E; # LETTER NYA +ట>\uE01F; # LETTER TTA +ఠ>\uE020; # LETTER TTHA +డ>\uE021; # LETTER DDA +ఢ>\uE022; # LETTER DDHA +ణ>\uE023; # LETTER NNA +త>\uE024; # LETTER TA +థ>\uE025; # LETTER THA +ద>\uE026; # LETTER DA +ధ>\uE027; # LETTER DHA +న>\uE028; # LETTER NA +ప>\uE02A; # LETTER PA +ఫ>\uE02B; # LETTER PHA +బ>\uE02C; # LETTER BA +భ>\uE02D; # LETTER BHA +మ>\uE02E; # LETTER MA +య>\uE02F; # LETTER YA +ర>\uE030; # LETTER RA +ఱ>\uE031; # LETTER RRA +ల>\uE032; # LETTER LA +ళ>\uE033; # LETTER LLA +వ>\uE035; # LETTER VA +శ>\uE036; # LETTER SHA +ష>\uE037; # LETTER SSA +స>\uE038; # LETTER SA +హ>\uE039; # LETTER HA \u0C3E>\uE03E; # VOWEL SIGN AA \u0C3F>\uE03F; # VOWEL SIGN I \u0C40>\uE040; # VOWEL SIGN II -\u0C41>\uE041; # VOWEL SIGN U -\u0C42>\uE042; # VOWEL SIGN UU -\u0C43>\uE043; # VOWEL SIGN VOCALIC R -\u0C44>\uE044; # VOWEL SIGN VOCALIC RR +ు>\uE041; # VOWEL SIGN U +ూ>\uE042; # VOWEL SIGN UU +ృ>\uE043; # VOWEL SIGN VOCALIC R +ౄ>\uE044; # VOWEL SIGN VOCALIC RR \u0C46>\uE046; # VOWEL SIGN E \u0C47>\uE047; # VOWEL SIGN EE \u0C4A>\uE04A; # VOWEL SIGN O @@ -74,17 +76,15 @@ \u0C4D>\uE04D; # SIGN VIRAMA \u0C55>\uE055; # LENGTH MARK \u0C56>\uE056; # AI LENGTH MARK -\u0C60>\uE060; # LETTER VOCALIC RR -\u0C61>\uE061; # LETTER VOCALIC LL -\u0C66>\uE066; # DIGIT ZERO -\u0C67>\uE067; # DIGIT ONE -\u0C68>\uE068; # DIGIT TWO -\u0C69>\uE069; # DIGIT THREE -\u0C6A>\uE06A; # DIGIT FOUR -\u0C6B>\uE06B; # DIGIT FIVE -\u0C6C>\uE06C; # DIGIT SIX -\u0C6D>\uE06D; # DIGIT SEVEN -\u0C6E>\uE06E; # DIGIT EIGHT -\u0C6F>\uE06F; # DIGIT NINE -# :: NFC (NFD) ; -# eof +ౠ>\uE060; # LETTER VOCALIC RR +ౡ>\uE061; # LETTER VOCALIC LL +౦>\uE066; # DIGIT ZERO +౧>\uE067; # DIGIT ONE +౨>\uE068; # DIGIT TWO +౩>\uE069; # DIGIT THREE +౪>\uE06A; # DIGIT FOUR +౫>\uE06B; # DIGIT FIVE +౬>\uE06C; # DIGIT SIX +౭>\uE06D; # DIGIT SEVEN +౮>\uE06E; # DIGIT EIGHT +౯>\uE06F; # DIGIT NINE diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Kannada.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Kannada.txt new file mode 100644 index 00000000000..5ef8d344374 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Kannada.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Kannada.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Kannada; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Latin.txt new file mode 100644 index 00000000000..2ec4f785dbb --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Latin.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Malayalam.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Malayalam.txt new file mode 100644 index 00000000000..76968131b44 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Malayalam.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Malayalam.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Malayalam; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Oriya.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Oriya.txt new file mode 100644 index 00000000000..bc700a23b26 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Oriya.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Oriya.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Oriya; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Telugu_Tamil.txt b/Build/source/libs/icu-xetex/data/translit/Telugu_Tamil.txt new file mode 100644 index 00000000000..5a3a9817e6d --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Telugu_Tamil.txt @@ -0,0 +1,14 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Telugu_Tamil.txt +# Generated from CLDR: Thu Jul 20 16:27:18 PDT 2006 +# +::[ఁ-ఃఅ-ఌఎ-ఐఒ-నప-ళవ-హ\u0C3E-ౄ\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56ౠ-ౡ౦-౯]; +::NFD; +::Telugu-InterIndic; +::InterIndic-Tamil; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Thaana_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Thaana_Latin.txt new file mode 100644 index 00000000000..c514eb8e075 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Thaana_Latin.txt @@ -0,0 +1,440 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Thaana_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:19 PDT 2006 +# +tta <> ޘ\u07A6 ; +ḥa <> ޙ\u07A6 ; +kha <> ޚ\u07A6 ; +dha <> ޛ\u07A6 ; +ša < ޝ\u07A6 ; +ṣa <> ޞ\u07A6 ; +ḏa <> ޟ\u07A6 ; +t\u0324a <> ޠ\u07A6 ; +ʿa <> ޢ\u07A6 ; +ǧa <> ޣ\u07A6 ; +qa <> ޤ\u07A6 ; +ha <> ހ\u07A6 ; +ša <> ށ\u07A6 ; +na <> ނ\u07A6 ; +ra <> ރ\u07A6 ; +ba <> ބ\u07A6 ; +ḷa <> ޅ\u07A6 ; +ka <> ކ\u07A6 ; +‘a <> އ\u07A6 ; +va <> ވ\u07A6 ; +ma <> މ\u07A6 ; +fa <> ފ\u07A6 ; +da <> ދ\u07A6 ; +ta <> ތ\u07A6 ; +la <> ލ\u07A6 ; +ga <> ގ\u07A6 ; +ña <> ޏ\u07A6 ; +sa <> ސ\u07A6 ; +ḍa <> ޑ\u07A6 ; +ja <> ޖ\u07A6 ; +ča <> ޗ\u07A6 ; +za <> ޒ\u07A6 ; +ṭa <> ޓ\u07A6 ; +pa <> ޕ\u07A6 ; +ya <> ޔ\u07A6 ; +ttā <> ޘ\u07A7 ; +ḥā <> ޙ\u07A7 ; +khā <> ޚ\u07A7 ; +dhā <> ޛ\u07A7 ; +šā < ޝ\u07A7 ; +ṣā <> ޞ\u07A7 ; +ḏā <> ޟ\u07A7 ; +t\u0324ā <> ޠ\u07A7 ; +ʿā <> ޢ\u07A7 ; +ǧā <> ޣ\u07A7 ; +qā <> ޤ\u07A7 ; +hā <> ހ\u07A7 ; +šā <> ށ\u07A7 ; +nā <> ނ\u07A7 ; +rā <> ރ\u07A7 ; +bā <> ބ\u07A7 ; +ḷā <> ޅ\u07A7 ; +kā <> ކ\u07A7 ; +‘ā <> އ\u07A7 ; +vā <> ވ\u07A7 ; +mā <> މ\u07A7 ; +fā <> ފ\u07A7 ; +dā <> ދ\u07A7 ; +tā <> ތ\u07A7 ; +lā <> ލ\u07A7 ; +gā <> ގ\u07A7 ; +ñā <> ޏ\u07A7 ; +sā <> ސ\u07A7 ; +ḍā <> ޑ\u07A7 ; +jā <> ޖ\u07A7 ; +čā <> ޗ\u07A7 ; +zā <> ޒ\u07A7 ; +ṭā <> ޓ\u07A7 ; +pā <> ޕ\u07A7 ; +yā <> ޔ\u07A7 ; +tti <> ޘ\u07A8 ; +ḥi <> ޙ\u07A8 ; +khi <> ޚ\u07A8 ; +dhi <> ޛ\u07A8 ; +ši < ޝ\u07A8 ; +ṣi <> ޞ\u07A8 ; +ḏi <> ޟ\u07A8 ; +t\u0324i <> ޠ\u07A8 ; +ʿi <> ޢ\u07A8 ; +ǧi <> ޣ\u07A8 ; +qi <> ޤ\u07A8 ; +hi <> ހ\u07A8 ; +ši <> ށ\u07A8 ; +ni <> ނ\u07A8 ; +ri <> ރ\u07A8 ; +bi <> ބ\u07A8 ; +ḷi <> ޅ\u07A8 ; +ki <> ކ\u07A8 ; +‘i <> އ\u07A8 ; +vi <> ވ\u07A8 ; +mi <> މ\u07A8 ; +fi <> ފ\u07A8 ; +di <> ދ\u07A8 ; +ti <> ތ\u07A8 ; +li <> ލ\u07A8 ; +gi <> ގ\u07A8 ; +ñi <> ޏ\u07A8 ; +si <> ސ\u07A8 ; +ḍi <> ޑ\u07A8 ; +ji <> ޖ\u07A8 ; +či <> ޗ\u07A8 ; +zi <> ޒ\u07A8 ; +ṭi <> ޓ\u07A8 ; +pi <> ޕ\u07A8 ; +yi <> ޔ\u07A8 ; +ttī <> ޘ\u07A9 ; +ḥī <> ޙ\u07A9 ; +khī <> ޚ\u07A9 ; +dhī <> ޛ\u07A9 ; +šī < ޝ\u07A9 ; +ṣī <> ޞ\u07A9 ; +ḏī <> ޟ\u07A9 ; +t\u0324ī <> ޠ\u07A9 ; +ʿī <> ޢ\u07A9 ; +ǧī <> ޣ\u07A9 ; +qī <> ޤ\u07A9 ; +hī <> ހ\u07A9 ; +šī <> ށ\u07A9 ; +nī <> ނ\u07A9 ; +rī <> ރ\u07A9 ; +bī <> ބ\u07A9 ; +ḷī <> ޅ\u07A9 ; +kī <> ކ\u07A9 ; +‘ī <> އ\u07A9 ; +vī <> ވ\u07A9 ; +mī <> މ\u07A9 ; +fī <> ފ\u07A9 ; +dī <> ދ\u07A9 ; +tī <> ތ\u07A9 ; +lī <> ލ\u07A9 ; +gī <> ގ\u07A9 ; +ñī <> ޏ\u07A9 ; +sī <> ސ\u07A9 ; +ḍī <> ޑ\u07A9 ; +jī <> ޖ\u07A9 ; +čī <> ޗ\u07A9 ; +zī <> ޒ\u07A9 ; +ṭī <> ޓ\u07A9 ; +pī <> ޕ\u07A9 ; +yī <> ޔ\u07A9 ; +ttu <> ޘ\u07AA ; +ḥu <> ޙ\u07AA ; +khu <> ޚ\u07AA ; +dhu <> ޛ\u07AA ; +šu < ޝ\u07AA ; +ṣu <> ޞ\u07AA ; +ḏu <> ޟ\u07AA ; +t\u0324u <> ޠ\u07AA ; +ʿu <> ޢ\u07AA ; +ǧu <> ޣ\u07AA ; +qu <> ޤ\u07AA ; +hu <> ހ\u07AA ; +šu <> ށ\u07AA ; +nu <> ނ\u07AA ; +ru <> ރ\u07AA ; +bu <> ބ\u07AA ; +ḷu <> ޅ\u07AA ; +ku <> ކ\u07AA ; +‘u <> އ\u07AA ; +vu <> ވ\u07AA ; +mu <> މ\u07AA ; +fu <> ފ\u07AA ; +du <> ދ\u07AA ; +tu <> ތ\u07AA ; +lu <> ލ\u07AA ; +gu <> ގ\u07AA ; +ñu <> ޏ\u07AA ; +su <> ސ\u07AA ; +ḍu <> ޑ\u07AA ; +ju <> ޖ\u07AA ; +ču <> ޗ\u07AA ; +zu <> ޒ\u07AA ; +ṭu <> ޓ\u07AA ; +pu <> ޕ\u07AA ; +yu <> ޔ\u07AA ; +ttū <> ޘ\u07AB ; +ḥū <> ޙ\u07AB ; +khū <> ޚ\u07AB ; +dhū <> ޛ\u07AB ; +šū < ޝ\u07AB ; +ṣū <> ޞ\u07AB ; +ḏū <> ޟ\u07AB ; +t\u0324ū <> ޠ\u07AB ; +ʿū <> ޢ\u07AB ; +ǧū <> ޣ\u07AB ; +qū <> ޤ\u07AB ; +hū <> ހ\u07AB ; +šū <> ށ\u07AB ; +nū <> ނ\u07AB ; +rū <> ރ\u07AB ; +bū <> ބ\u07AB ; +ḷū <> ޅ\u07AB ; +kū <> ކ\u07AB ; +‘ū <> އ\u07AB ; +vū <> ވ\u07AB ; +mū <> މ\u07AB ; +fū <> ފ\u07AB ; +dū <> ދ\u07AB ; +tū <> ތ\u07AB ; +lū <> ލ\u07AB ; +gū <> ގ\u07AB ; +ñū <> ޏ\u07AB ; +sū <> ސ\u07AB ; +ḍū <> ޑ\u07AB ; +jū <> ޖ\u07AB ; +čū <> ޗ\u07AB ; +zū <> ޒ\u07AB ; +ṭū <> ޓ\u07AB ; +pū <> ޕ\u07AB ; +yū <> ޔ\u07AB ; +tte <> ޘ\u07AC ; +ḥe <> ޙ\u07AC ; +khe <> ޚ\u07AC ; +dhe <> ޛ\u07AC ; +še < ޝ\u07AC ; +ṣe <> ޞ\u07AC ; +ḏe <> ޟ\u07AC ; +t\u0324e <> ޠ\u07AC ; +ʿe <> ޢ\u07AC ; +ǧe <> ޣ\u07AC ; +qe <> ޤ\u07AC ; +he <> ހ\u07AC ; +še <> ށ\u07AC ; +ne <> ނ\u07AC ; +re <> ރ\u07AC ; +be <> ބ\u07AC ; +ḷe <> ޅ\u07AC ; +ke <> ކ\u07AC ; +‘e <> އ\u07AC ; +ve <> ވ\u07AC ; +me <> މ\u07AC ; +fe <> ފ\u07AC ; +de <> ދ\u07AC ; +te <> ތ\u07AC ; +le <> ލ\u07AC ; +ge <> ގ\u07AC ; +ñe <> ޏ\u07AC ; +se <> ސ\u07AC ; +ḍe <> ޑ\u07AC ; +je <> ޖ\u07AC ; +če <> ޗ\u07AC ; +ze <> ޒ\u07AC ; +ṭe <> ޓ\u07AC ; +pe <> ޕ\u07AC ; +ye <> ޔ\u07AC ; +ttē <> ޘ\u07AD ; +ḥē <> ޙ\u07AD ; +khē <> ޚ\u07AD ; +dhē <> ޛ\u07AD ; +šē < ޝ\u07AD ; +ṣē <> ޞ\u07AD ; +ḏē <> ޟ\u07AD ; +t\u0324ē <> ޠ\u07AD ; +ʿē <> ޢ\u07AD ; +ǧē <> ޣ\u07AD ; +qē <> ޤ\u07AD ; +hē <> ހ\u07AD ; +šē <> ށ\u07AD ; +nē <> ނ\u07AD ; +rē <> ރ\u07AD ; +bē <> ބ\u07AD ; +ḷē <> ޅ\u07AD ; +kē <> ކ\u07AD ; +‘ē <> އ\u07AD ; +vē <> ވ\u07AD ; +mē <> މ\u07AD ; +fē <> ފ\u07AD ; +dē <> ދ\u07AD ; +tē <> ތ\u07AD ; +lē <> ލ\u07AD ; +gē <> ގ\u07AD ; +ñē <> ޏ\u07AD ; +sē <> ސ\u07AD ; +ḍē <> ޑ\u07AD ; +jē <> ޖ\u07AD ; +čē <> ޗ\u07AD ; +zē <> ޒ\u07AD ; +ṭē <> ޓ\u07AD ; +pē <> ޕ\u07AD ; +yē <> ޔ\u07AD ; +tto <> ޘ\u07AE ; +ḥo <> ޙ\u07AE ; +kho <> ޚ\u07AE ; +dho <> ޛ\u07AE ; +šo < ޝ\u07AE ; +ṣo <> ޞ\u07AE ; +ḏo <> ޟ\u07AE ; +t\u0324o <> ޠ\u07AE ; +ʿo <> ޢ\u07AE ; +ǧo <> ޣ\u07AE ; +qo <> ޤ\u07AE ; +ho <> ހ\u07AE ; +šo <> ށ\u07AE ; +no <> ނ\u07AE ; +ro <> ރ\u07AE ; +bo <> ބ\u07AE ; +ḷo <> ޅ\u07AE ; +ko <> ކ\u07AE ; +‘o <> އ\u07AE ; +vo <> ވ\u07AE ; +mo <> މ\u07AE ; +fo <> ފ\u07AE ; +do <> ދ\u07AE ; +to <> ތ\u07AE ; +lo <> ލ\u07AE ; +go <> ގ\u07AE ; +ño <> ޏ\u07AE ; +so <> ސ\u07AE ; +ḍo <> ޑ\u07AE ; +jo <> ޖ\u07AE ; +čo <> ޗ\u07AE ; +zo <> ޒ\u07AE ; +ṭo <> ޓ\u07AE ; +po <> ޕ\u07AE ; +yo <> ޔ\u07AE ; +ttō <> ޘ\u07AF ; +ḥō <> ޙ\u07AF ; +khō <> ޚ\u07AF ; +dhō <> ޛ\u07AF ; +šō < ޝ\u07AF ; +ṣō <> ޞ\u07AF ; +ḏō <> ޟ\u07AF ; +t\u0324ō <> ޠ\u07AF ; +ʿō <> ޢ\u07AF ; +ǧō <> ޣ\u07AF ; +qō <> ޤ\u07AF ; +hō <> ހ\u07AF ; +šō <> ށ\u07AF ; +nō <> ނ\u07AF ; +rō <> ރ\u07AF ; +bō <> ބ\u07AF ; +ḷō <> ޅ\u07AF ; +kō <> ކ\u07AF ; +‘ō <> އ\u07AF ; +vō <> ވ\u07AF ; +mō <> މ\u07AF ; +fō <> ފ\u07AF ; +dō <> ދ\u07AF ; +tō <> ތ\u07AF ; +lō <> ލ\u07AF ; +gō <> ގ\u07AF ; +ñō <> ޏ\u07AF ; +sō <> ސ\u07AF ; +ḍō <> ޑ\u07AF ; +jō <> ޖ\u07AF ; +čō <> ޗ\u07AF ; +zō <> ޒ\u07AF ; +ṭō <> ޓ\u07AF ; +pō <> ޕ\u07AF ; +yō <> ޔ\u07AF ; +tt <> ޘ\u07B0 ; +ḥ <> ޙ\u07B0 ; +kh <> ޚ\u07B0 ; +dh <> ޛ\u07B0 ; +š < ޝ\u07B0 ; +ṣ <> ޞ\u07B0 ; +ḏ <> ޟ\u07B0 ; +t\u0324 <> ޠ\u07B0 ; +ʿ <> ޢ\u07B0 ; +ǧ <> ޣ\u07B0 ; +q <> ޤ\u07B0 ; +h <> ހ\u07B0 ; +š <> ށ\u07B0 ; +n <> ނ\u07B0 ; +r <> ރ\u07B0 ; +b <> ބ\u07B0 ; +ḷ <> ޅ\u07B0 ; +k <> ކ\u07B0 ; +‘ <> އ\u07B0 ; +v <> ވ\u07B0 ; +m <> މ\u07B0 ; +f <> ފ\u07B0 ; +d <> ދ\u07B0 ; +t <> ތ\u07B0 ; +l <> ލ\u07B0 ; +g <> ގ\u07B0 ; +ñ <> ޏ\u07B0 ; +s <> ސ\u07B0 ; +ḍ <> ޑ\u07B0 ; +j <> ޖ\u07B0 ; +č <> ޗ\u07B0 ; +z <> ޒ\u07B0 ; +ṭ <> ޓ\u07B0 ; +p <> ޕ\u07B0 ; +y <> ޔ\u07B0 ; +h < ހ ; +š < ށ ; +n < ނ ; +r < ރ ; +b < ބ ; +ḷ < ޅ ; +k < ކ ; +‘ < އ ; +v < ވ ; +m < މ ; +f < ފ ; +d < ދ ; +t < ތ ; +l < ލ ; +g < ގ ; +ñ < ޏ ; +s < ސ ; +ḍ < ޑ ; +j < ޖ ; +č < ޗ ; +z < ޒ ; +ṭ < ޓ ; +p < ޕ ; +y < ޔ ; +tt < ޘ ; +ḥ < ޙ ; +kh < ޚ ; +dh < ޛ ; +š < ޝ ; +ṣ < ޞ ; +ḏ < ޟ ; +t\u0324 < ޠ ; +ʿ < ޢ ; +ǧ < ޣ ; +q < ޤ ; +a <> \u07A6 ; +ā <> \u07A7 ; +i <> \u07A8 ; +ī <> \u07A9 ; +u <> \u07AA ; +ū <> \u07AB ; +e <> \u07AC ; +ē <> \u07AD ; +o <> \u07AE ; +ō <> \u07AF ; +< \u07B0 ; diff --git a/Build/source/libs/icu-xetex/data/translit/ThaiLogical_Latin.txt b/Build/source/libs/icu-xetex/data/translit/ThaiLogical_Latin.txt index 558fd84a173..16a4ab61651 100644 --- a/Build/source/libs/icu-xetex/data/translit/ThaiLogical_Latin.txt +++ b/Build/source/libs/icu-xetex/data/translit/ThaiLogical_Latin.txt @@ -1,160 +1,102 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Thai-Latin -# This set of rules follows ISO 11940 -# see http://homepage.mac.com/sirbinks/pdf/Thai.r2.pdf -# except that that does not mention an implicit vowel, so we use ọ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: ThaiLogical_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:19 PDT 2006 # -# The transcription is fairly ugly, so we ought to also do the UNGEGN version -# see: http://www.eki.ee/wgrs/rom1_th.pdf -# and probably make that the main variant. - -# Note: this is an internal file. The NFD/NFC is handled externally, in the index -# The insertion of spaces between words, the reversal of the vowels -# and the conversion of space to semicolon are done *outside* of these rules. -# So as far as these rules are concerned, the vowels are in logical order! - -# insert implicit vowel (and remove it going the other way) -# COMMENTED out: the implicit vowel positions cannot be predicted algorithmically -#$consonant = [ก-ฮ]; -#$vowel = [ะ-ฺเ-ไ็]; - -#{ ( $consonant ) } [^$vowel ] > | $1 ; -# > ọ ; -# < ọ ; - $notAbove = [^\p{ccc=0}\p{ccc=above}] ; $notBelow = [^\p{ccc=0}\p{ccc=below}] ; - -# Consonants -# Warning: the 'h's need to be handled carefully! -# What we really want to say is the following, but we can't -# $notHAccent = !($notAbove* ̄ | $notBelow* ̣) ; - -# Since the only accents we care about that could cause problems are free-standing accents below, we use instead: $freeStandingBelow = [\u0325 ]; -$hAccent = [ ̄ ̣]; +$hAccent = [ \u0304 \u0323]; $notHAccent0 = [^$freeStandingBelow$hAccent]; $notHAccent1 = $freeStandingBelow [^$hAccent]; - -ห > h̄ ; # THAI CHARACTER HO HIP - ห | $1 < h ($notAbove*) ̄; # backward case, account for reordering -ฮ <> ḥ ; # THAI CHARACTER HO NOKHUK - -ข <> k̄h ; # THAI CHARACTER KHO KHAI -ฃ <> ḳ̄h ; # THAI CHARACTER KHO KHUAT -ฅ <> kʹh ; # THAI CHARACTER KHO KHON -ฆ <> ḳh ; # THAI CHARACTER KHO RAKHANG -ค < kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI -ค <> kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI +ห > h\u0304 ; # THAI CHARACTER HO HIP +ห | $1 < h ($notAbove*) \u0304; # backward case, account for reordering +ฮ <> h\u0323 ; # THAI CHARACTER HO NOKHUK +ข <> k\u0304h ; # THAI CHARACTER KHO KHAI +ฃ <> k\u0323\u0304h ; # THAI CHARACTER KHO KHUAT +ฅ <> kʹh ; # THAI CHARACTER KHO KHON +ฆ <> k\u0323h ; # THAI CHARACTER KHO RAKHANG +ค < kh } $notHAccent1 ; # THAI CHARACTER KHO KHWAI +ค <> kh } $notHAccent0 ; # THAI CHARACTER KHO KHWAI ก <> k ; # THAI CHARACTER KO KAI - -ภ <> p̣h ; # THAI CHARACTER PHO SAMPHAO -ผ <> p̄h ; # THAI CHARACTER PHO PHUNG +ภ <> p\u0323h ; # THAI CHARACTER PHO SAMPHAO +ผ <> p\u0304h ; # THAI CHARACTER PHO PHUNG พ < ph } $notHAccent1 ; # THAI CHARACTER PHO PHAN พ <> ph } $notHAccent0 ; # THAI CHARACTER PHO PHAN ป <> p ; # THAI CHARACTER PO PLA - -ฉ <> c̄h ; # THAI CHARACTER CHO CHING -ฌ <> c̣h ; # THAI CHARACTER CHO CHOE +ฉ <> c\u0304h ; # THAI CHARACTER CHO CHING +ฌ <> c\u0323h ; # THAI CHARACTER CHO CHOE ช < ch } $notHAccent1 ; # THAI CHARACTER CHO CHANG ช <> ch } $notHAccent0 ; # THAI CHARACTER CHO CHANG จ <> c ; # THAI CHARACTER CHO CHAN - -ฐ <> ṭ̄h ; # THAI CHARACTER THO THAN -ฑ <> ṯh ; # THAI CHARACTER THO NANGMONTHO +ฐ <> t\u0323\u0304h ; # THAI CHARACTER THO THAN +ฑ <> t\u0331h ; # THAI CHARACTER THO NANGMONTHO ฒ <> tʹh ; # THAI CHARACTER THO PHUTHAO -ถ <> t̄h ; # THAI CHARACTER THO THUNG -ธ <> ṭh ; # THAI CHARACTER THO THONG +ถ <> t\u0304h ; # THAI CHARACTER THO THUNG +ธ <> t\u0323h ; # THAI CHARACTER THO THONG ท < th } $notHAccent1 ; # THAI CHARACTER THO THAHAN ท <> th } $notHAccent0 ; # THAI CHARACTER THO THAHAN -#Note: TO PATAK deviates from ISO since t-dotunder + h would be ambigous. So it uses vertical tick. -ฏ <> t̩ ; # THAI CHARACTER TO PATAK +ฏ <> t\u0329 ; # THAI CHARACTER TO PATAK ต <> t ; # THAI CHARACTER TO TAO - -# since there is no singleton g (generated), don't worry about that. ง <> ng ; # THAI CHARACTER NGO NGU -ณ <> ṇ ; # THAI CHARACTER NO NEN +ณ <> n\u0323 ; # THAI CHARACTER NO NEN น <> n ; # THAI CHARACTER NO NU - -ญ <> ỵ ; # THAI CHARACTER YO YING -ฎ <> ḍ ; # THAI CHARACTER DO CHADA +ญ <> y\u0323 ; # THAI CHARACTER YO YING +ฎ <> d\u0323 ; # THAI CHARACTER DO CHADA ด <> d ; # THAI CHARACTER DO DEK - บ <> b ; # THAI CHARACTER BO BAIMAI -ฝ <> f̄ ; # THAI CHARACTER FO FA - ฝ | $1 < f ($notAbove*) ̄; # backward case, account for reordering - +ฝ <> f\u0304 ; # THAI CHARACTER FO FA +ฝ | $1 < f ($notAbove*) \u0304; # backward case, account for reordering ม <> m ; # THAI CHARACTER MO MA ย <> y ; # THAI CHARACTER YO YAK ร <> r ; # THAI CHARACTER RO RUA ฤ <> v ; # THAI CHARACTER RU ฦ <> ł ; # THAI CHARACTER LU ว <> w ; # THAI CHARACTER WO WAEN - -ศ <> ṣ̄ ; # THAI CHARACTER SO SALA*** - ศ | $1 < s ̣ ($notAbove*) ̄; # backward case, account for reordering -ษ <> s̄ʹ ; # THAI CHARACTER SO RUSI -ส > s̄ ; # THAI CHARACTER SO SUA*** - ส | $1 < s ($notAbove*) ̄; # backward case, account for reordering - -ฬ <> ḷ ; # THAI CHARACTER LO CHULA +ศ <> s\u0323\u0304 ; # THAI CHARACTER SO SALA*** +ศ | $1 < s \u0323 ($notAbove*) \u0304; # backward case, account for reordering +ษ <> s\u0304ʹ ; # THAI CHARACTER SO RUSI +ส > s\u0304 ; # THAI CHARACTER SO SUA*** +ส | $1 < s ($notAbove*) \u0304; # backward case, account for reordering +ฬ <> l\u0323 ; # THAI CHARACTER LO CHULA ล <> l ; # THAI CHARACTER LO LING ฟ <> f ; # THAI CHARACTER FO FAN - อ <> x ; # THAI CHARACTER O ANG ซ <> s ; # THAI CHARACTER SO SO - -# vowels - - ั <> ạ ; # THAI CHARACTER MAI HAN-AKAT - -า > ā ; # THAI CHARACTER SARA AA - า | $1 < a ($notAbove*) ̄; # backward case, account for reordering - -# We deviate from ISO for SARA AM for disambiguation -ำ > a ̉; # THAI CHARACTER SARA AM - ำ | $1 < a ($notAbove*) ̉ ; # backward case, account for reordering - +\u0E31 <> a\u0323 ; # THAI CHARACTER MAI HAN-AKAT +า > a\u0304 ; # THAI CHARACTER SARA AA +า | $1 < a ($notAbove*) \u0304; # backward case, account for reordering +ำ > a \u0309; # THAI CHARACTER SARA AM +ำ | $1 < a ($notAbove*) \u0309 ; # backward case, account for reordering ะ <> a ; # THAI CHARACTER SARA A - ี <> ī ; # THAI CHARACTER SARA II - ี | $1 < i ($notAbove*) ̄ ; # backward case, account for reordering - - ื <> ụ̄ ; # THAI CHARACTER SARA UEE - ื | $1 < u ̣ ($notAbove*) ̄ ; # backward case, account for reordering - - ึ <> ụ ; # THAI CHARACTER SARA UE - ู <> ū ; # THAI CHARACTER SARA UU - ู | $1 < u ($notAbove*) ̄ ; # backward case, account for reordering - - ุ <> u ; # THAI CHARACTER SARA U - +\u0E35 <> i\u0304 ; # THAI CHARACTER SARA II +\u0E35 | $1 < i ($notAbove*) \u0304 ; # backward case, account for reordering +\u0E37 <> u\u0323\u0304 ; # THAI CHARACTER SARA UEE +\u0E37 | $1 < u \u0323 ($notAbove*) \u0304 ; # backward case, account for reordering +\u0E36 <> u\u0323 ; # THAI CHARACTER SARA UE +\u0E39 <> u\u0304 ; # THAI CHARACTER SARA UU +\u0E39 | $1 < u ($notAbove*) \u0304 ; # backward case, account for reordering +\u0E38 <> u ; # THAI CHARACTER SARA U ฯ <> ‡ ; # THAI CHARACTER PAIYANNOI - -# ฿ <> XXX ; # THAI CURRENCY SYMBOL BAHT - เ <> e ; # THAI CHARACTER SARA E แ <> æ ; # THAI CHARACTER SARA AE โ <> o ; # THAI CHARACTER SARA O ใ <> ı ; # THAI CHARACTER SARA AI MAIMUAN -ไ <> ị ; # THAI CHARACTER SARA AI MAIMALAI +ไ <> i\u0323 ; # THAI CHARACTER SARA AI MAIMALAI ๅ <> ɨ ; # THAI CHARACTER LAKKHANGYAO - ็ <> ̆ ; # THAI CHARACTER MAITAIKHU - ่ <> ̀ ; # THAI CHARACTER MAI EK - ้ <> ̂ ; # THAI CHARACTER MAI THO - ๊ <> ́ ; # THAI CHARACTER MAI TRI - ๋ <> ̌ ; # THAI CHARACTER MAI CHATTAWA - ์ <> ̒ ; # THAI CHARACTER THANTHAKHAT - ๎ <> '~' ; # THAI CHARACTER YAMAKKAN - -# We deviate from ISO for disambiguation - ํ <> ̊ ; # THAI CHARACTER NIKHAHIT - -๏ <> § ; # THAI CHARACTER FONGMAN - +\u0E47 <> \u0306 ; # THAI CHARACTER MAITAIKHU +\u0E48 <> \u0300 ; # THAI CHARACTER MAI EK +\u0E49 <> \u0302 ; # THAI CHARACTER MAI THO +\u0E4A <> \u0301 ; # THAI CHARACTER MAI TRI +\u0E4B <> \u030C ; # THAI CHARACTER MAI CHATTAWA +\u0E4C <> \u0312 ; # THAI CHARACTER THANTHAKHAT +\u0E4E <> '~' ; # THAI CHARACTER YAMAKKAN +\u0E4D <> \u030A ; # THAI CHARACTER NIKHAHIT +๏ <> '§' ; # THAI CHARACTER FONGMAN ๐ <> 0 ; # THAI DIGIT ZERO ๑ <> 1 ; # THAI DIGIT ONE ๒ <> 2 ; # THAI DIGIT TWO @@ -165,23 +107,14 @@ $notHAccent1 = $freeStandingBelow [^$hAccent]; ๗ <> 7 ; # THAI DIGIT SEVEN ๘ <> 8 ; # THAI DIGIT EIGHT ๙ <> 9 ; # THAI DIGIT NINE - ๚ <> '||' ; # THAI CHARACTER ANGKHANKHU - ๛ <> » ; # THAI CHARACTER KHOMUT ๆ <> « ; # THAI CHARACTER MAIYAMOK - -# moved down to make shorter first -#Note: PHINTHU deviates from ISO since underring causes canonical problems. So it uses spacing tick below. - ฺ <> ˌ ; # THAI CHARACTER PHINTHU - ิ <> i ; # THAI CHARACTER SARA I - -# fallbacks - +\u0E3A <> ˌ ; # THAI CHARACTER PHINTHU +\u0E34 <> i ; # THAI CHARACTER SARA I | k < g ; | k < h ; | c < j ; | k < q ; | s < z ; - :: (lower); diff --git a/Build/source/libs/icu-xetex/data/translit/Thai_Latin.txt b/Build/source/libs/icu-xetex/data/translit/Thai_Latin.txt new file mode 100644 index 00000000000..1ce874eb210 --- /dev/null +++ b/Build/source/libs/icu-xetex/data/translit/Thai_Latin.txt @@ -0,0 +1,16 @@ +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Thai_Latin.txt +# Generated from CLDR: Thu Jul 20 16:27:19 PDT 2006 +# +::[[:thai:] ก-\u0E3Aเ-๛]; +::NFD; +::Thai-ThaiSemi; +::Any-BreakInternal; +::Thai-ThaiLogical; +::ThaiLogical-Latin; +::NFC; diff --git a/Build/source/libs/icu-xetex/data/translit/Thai_ThaiLogical.txt b/Build/source/libs/icu-xetex/data/translit/Thai_ThaiLogical.txt index 52764c55598..f4bb6d4d37f 100644 --- a/Build/source/libs/icu-xetex/data/translit/Thai_ThaiLogical.txt +++ b/Build/source/libs/icu-xetex/data/translit/Thai_ThaiLogical.txt @@ -1,26 +1,16 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# This reverses the Thai LogicalOrderException vowels, and does (part of) spaces -# The rules that convert space into semicolon are in another file; -# since they have to come BEFORE the break iterator - -$thai = [[:thai:] \u0E01-\u0E3A\u0E40-\u0E5B] ; - -# First convert the semicolon back - +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Thai_ThaiLogical.txt +# Generated from CLDR: Thu Jul 20 16:27:19 PDT 2006 +# +$thai = [[:thai:] ก-\u0E3Aเ-๛] ; ' ' < $thai { '; ' } $thai; - -# Remove any other spaces between thai letters - < $thai { ' ' } $thai; - -# Now vowels $thai_reversing = [[:Logical_Order_Exception:] & $thai]; $thai_non_reversing = [$thai - $thai_reversing ]; - ( $thai_reversing ) ( $thai_non_reversing ) > $2 $1; -# other direction -$2 $1 < ( $thai_non_reversing ) ( $thai_reversing ) ;
\ No newline at end of file +$2 $1 < ( $thai_non_reversing ) ( $thai_reversing ) ; diff --git a/Build/source/libs/icu-xetex/data/translit/Thai_ThaiSemi.txt b/Build/source/libs/icu-xetex/data/translit/Thai_ThaiSemi.txt index ce1f3ff0ecb..64555f21f4f 100644 --- a/Build/source/libs/icu-xetex/data/translit/Thai_ThaiSemi.txt +++ b/Build/source/libs/icu-xetex/data/translit/Thai_ThaiSemi.txt @@ -1,11 +1,11 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# The rules that convert space into semicolon are in this file; -# since they have to come BEFORE the break iterator. - -$thai = [[:thai:] \u0E01-\u0E3A\u0E40-\u0E5B] ; - -$thai { ' ' } $thai > '; ' ;
\ No newline at end of file +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: Thai_ThaiSemi.txt +# Generated from CLDR: Thu Jul 20 16:27:19 PDT 2006 +# +$thai = [[:thai:] ก-\u0E3Aเ-๛] ; +$thai { ' ' } $thai > '; ' ; diff --git a/Build/source/libs/icu-xetex/data/translit/Tone_Digit.txt b/Build/source/libs/icu-xetex/data/translit/Tone_Digit.txt deleted file mode 100644 index 489d79f1948..00000000000 --- a/Build/source/libs/icu-xetex/data/translit/Tone_Digit.txt +++ /dev/null @@ -1,11 +0,0 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# Only intended for internal use -\u0304 <> 1; -\u0301 <> 2; -\u030C <> 3; -\u0300 <> 4; - < 5;
\ No newline at end of file diff --git a/Build/source/libs/icu-xetex/data/translit/el.txt b/Build/source/libs/icu-xetex/data/translit/el.txt index 23cc342eed5..24416b35aed 100644 --- a/Build/source/libs/icu-xetex/data/translit/el.txt +++ b/Build/source/libs/icu-xetex/data/translit/el.txt @@ -1,6 +1,6 @@ // *************************************************************************** // * -// * Copyright (C) 2004, International Business Machines +// * Copyright (C) 2004-2006, International Business Machines // * Corporation and others. All Rights Reserved. // * // *************************************************************************** diff --git a/Build/source/libs/icu-xetex/data/translit/en.txt b/Build/source/libs/icu-xetex/data/translit/en.txt index 6c6ccd63e19..0dc8feb512c 100644 --- a/Build/source/libs/icu-xetex/data/translit/en.txt +++ b/Build/source/libs/icu-xetex/data/translit/en.txt @@ -1,6 +1,6 @@ // *************************************************************************** // * -// * Copyright (C) 2004, International Business Machines +// * Copyright (C) 2004-2006, International Business Machines // * Corporation and others. All Rights Reserved. // * // *************************************************************************** diff --git a/Build/source/libs/icu-xetex/data/translit/root.txt b/Build/source/libs/icu-xetex/data/translit/root.txt index 8675ff15817..d41f9d4c2b7 100644 --- a/Build/source/libs/icu-xetex/data/translit/root.txt +++ b/Build/source/libs/icu-xetex/data/translit/root.txt @@ -1,778 +1,1144 @@ -// *************************************************************************** +// *************************************************************************** // * -// * Copyright (C) 2004-2005, International Business Machines -// * Corporation and others. All Rights Reserved. +// * Copyright (C) 2004-2006, International Business Machines +// * Corporation; Unicode, Inc.; and others. All Rights Reserved. // * // *************************************************************************** -// - -root{ - - RuleBasedTransliteratorIDs{ -//-------------------------------------------------------------------- -//-------------------------------------------------------------------- -// -// TRANSLITERATOR INDEX FILE. This file lists the non-algorithmic -// system transliterators. It allows arbitrary mappings between -// transliterator IDs and file names, and also allows the system to -// define aliases for transliterators, so that "Latin-Hangul", for -// example, can be implemented transparently as the compound -// "Latin-Jamo;Jamo-Hangul". Internal IDs may also be defined; these -// are invisible to the user, but can be composed together by the -// system to create visible transliterators. -// -// Blank lines and lines beginning with '#' are ignored. -// -// Lines in this file have one of the following forms (text not -// enclosed by <> is literal): -// -// <id>:file:<resource>:<encoding>:<direction> -// <id>:internal:<resource>:<encoding>:<direction> -// <id>:alias:<getInstanceArg> -// -// <id> is the ID of the system transliterator being defined. These -// are public IDs enumerated by Transliterator.getAvailableIDs(), -// unless the second field is "internal". -// -// <resource> is a ResourceReader resource name. Currently these refer -// to file names under com/ibm/text/resources. This string is passed -// directly to ResourceReader, together with <encoding>. -// -// <encoding> is the character encoding to use when reading <resource>; -// passed directly to ResourceReader. E.g., "UTF8". +// File: root.txt +// Generated from CLDR: Thu Jul 20 16:27:11 PDT 2006 // -// <direction> is either "FORWARD" or "REVERSE". -// -// <getInstanceArg> is a string to be passed directly to -// Transliterator.getInstance(). The returned Transliterator object -// then has its ID changed to <id> and is returned. - - -// Bidirectional rule files - - Fullwidth-Halfwidth { +root { + RuleBasedTransliteratorIDs { + Tone-Digit { + alias {"Pinyin-NumericPinyin"} + } + Digit-Tone { + alias {"NumericPinyin-Pinyin"} + } + Any-Accents { file { - resource:process(transliterator){"Fullwidth_Halfwidth.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Any_Accents.txt"} + direction {"FORWARD"} + } } - Halfwidth-Fullwidth { + Accents-Any { file { - resource:process(transliterator){"Fullwidth_Halfwidth.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Any_Accents.txt"} + direction {"REVERSE"} + } } - Latin-Cyrillic { + Any-Publishing { file { - resource:process(transliterator){"Cyrillic_Latin.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Any_Publishing.txt"} + direction {"FORWARD"} + } } - Cyrillic-Latin { + Publishing-Any { file { - resource:process(transliterator){"Cyrillic_Latin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Any_Publishing.txt"} + direction {"REVERSE"} + } } - Latin-Hebrew { + Arabic-Latin { file { - resource:process(transliterator){"Hebrew_Latin.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Arabic_Latin.txt"} + direction {"FORWARD"} + } } - Hebrew-Latin { + Latin-Arabic { file { - resource:process(transliterator){"Hebrew_Latin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Arabic_Latin.txt"} + direction {"REVERSE"} + } } - Latin-Arabic { + Bengali-Devanagari { file { - resource:process(transliterator){"Arabic_Latin.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Bengali_Devanagari.txt"} + direction {"FORWARD"} + } } - Arabic-Latin { + + Bengali-Gujarati { file { - resource:process(transliterator){"Arabic_Latin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Bengali_Gujarati.txt"} + direction {"FORWARD"} + } } - Tone-Digit { - internal { - resource:process(transliterator){"Tone_Digit.txt"} - direction{"FORWARD"} - } + Bengali-Gurmukhi { + file { + resource:process(transliterator) {"Bengali_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Digit-Tone { + + Bengali-InterIndic { internal { - resource:process(transliterator){"Tone_Digit.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Bengali_InterIndic.txt"} + direction {"FORWARD"} + } } - Latin-NumericPinyin { + Bengali-Kannada { file { - resource:process(transliterator){"Latin_NumericPinyin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Bengali_Kannada.txt"} + direction {"FORWARD"} + } } - NumericPinyin-Latin { + + Bengali-Latin { file { - resource:process(transliterator){"Latin_NumericPinyin.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Bengali_Latin.txt"} + direction {"FORWARD"} + } } - Han-Spacedhan { - internal { - resource:process(transliterator){"Han_Spacedhan.txt"} - direction{"FORWARD"} - } + Bengali-Malayalam { + file { + resource:process(transliterator) {"Bengali_Malayalam.txt"} + direction {"FORWARD"} + } } - Spacedhan-Han { - alias {"null"} + + Bengali-Oriya { + file { + resource:process(transliterator) {"Bengali_Oriya.txt"} + direction {"FORWARD"} + } } - Han-Latin { + Bengali-Tamil { file { - resource:process(transliterator){"Han_Latin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Bengali_Tamil.txt"} + direction {"FORWARD"} + } } -//Latin-Han:file:Transliterator_Han_Latin.txt:UTF8:REVERSE # no round trip! - Latin-Han { - alias {"null"} + + Bengali-Telugu { + file { + resource:process(transliterator) {"Bengali_Telugu.txt"} + direction {"FORWARD"} + } } -// Comment these out; they are only for testing -// Latin-Han/definition:file:Transliterator_Han_Latin_Definition.txt:UTF8:REVERSE -// Han-Latin/definition:file:Transliterator_Han_Latin_Definition.txt:UTF8:FORWARD + Cyrillic-Latin { + file { + resource:process(transliterator) {"Cyrillic_Latin.txt"} + direction {"FORWARD"} + } + } + Latin-Cyrillic { + file { + resource:process(transliterator) {"Cyrillic_Latin.txt"} + direction {"REVERSE"} + } + } -//Latin-Han/EDICT:file:Transliterator_Han_Latin_EDICT.txt:UTF8:REVERSE -//Han-Latin/EDICT:file:Transliterator_Han_Latin_EDICT.txt:UTF8:FORWARD + Devanagari-Bengali { + file { + resource:process(transliterator) {"Devanagari_Bengali.txt"} + direction {"FORWARD"} + } + } - Latin-Greek { + Devanagari-Gujarati { file { - resource:process(transliterator){"Greek_Latin.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Devanagari_Gujarati.txt"} + direction {"FORWARD"} + } } - Greek-Latin { + + Devanagari-Gurmukhi { file { - resource:process(transliterator){"Greek_Latin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Devanagari_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Latin-Greek/UNGEGN { + Devanagari-InterIndic { + internal { + resource:process(transliterator) {"Devanagari_InterIndic.txt"} + direction {"FORWARD"} + } + } + + Devanagari-Kannada { file { - resource:process(transliterator){"Greek_Latin_UNGEGN.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Devanagari_Kannada.txt"} + direction {"FORWARD"} + } } - Greek-Latin/UNGEGN { + + Devanagari-Latin { file { - resource:process(transliterator){"Greek_Latin_UNGEGN.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Devanagari_Latin.txt"} + direction {"FORWARD"} + } } - Latin-Katakana { + Devanagari-Malayalam { file { - resource:process(transliterator){"Latin_Katakana.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Devanagari_Malayalam.txt"} + direction {"FORWARD"} + } } - Katakana-Latin { + + Devanagari-Oriya { file { - resource:process(transliterator){"Latin_Katakana.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Devanagari_Oriya.txt"} + direction {"FORWARD"} + } } - Latin-Hiragana { + Devanagari-Tamil { file { - resource:process(transliterator){"Hiragana_Latin.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Devanagari_Tamil.txt"} + direction {"FORWARD"} + } } - Hiragana-Latin { + + Devanagari-Telugu { file { - resource:process(transliterator){"Hiragana_Latin.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Devanagari_Telugu.txt"} + direction {"FORWARD"} + } } -//Thai Stuff: will change if we get \b into Transliterator + Fullwidth-Halfwidth { + file { + resource:process(transliterator) {"Fullwidth_Halfwidth.txt"} + direction {"FORWARD"} + } + } + Halfwidth-Fullwidth { + file { + resource:process(transliterator) {"Fullwidth_Halfwidth.txt"} + direction {"REVERSE"} + } + } - Thai-ThaiSemi { - internal { - resource:process(transliterator){"Thai_ThaiSemi.txt"} - direction{"FORWARD"} - } + Georgian-Latin { + file { + resource:process(transliterator) {"Georgian_Latin.txt"} + direction {"FORWARD"} + } + } + Latin-Georgian { + file { + resource:process(transliterator) {"Georgian_Latin.txt"} + direction {"REVERSE"} + } } - Thai-ThaiLogical { - internal { - resource:process(transliterator){"Thai_ThaiLogical.txt"} - direction{"FORWARD"} - } + Greek-Latin { + file { + resource:process(transliterator) {"Greek_Latin.txt"} + direction {"FORWARD"} + } } - ThaiLogical-Thai { - internal { - resource:process(transliterator){"Thai_ThaiLogical.txt"} - direction{"REVERSE"} - } + Latin-Greek { + file { + resource:process(transliterator) {"Greek_Latin.txt"} + direction {"REVERSE"} + } } - ThaiLogical-Latin { - internal { - resource:process(transliterator){"ThaiLogical_Latin.txt"} - direction{"FORWARD"} - } + Greek-Latin/UNGEGN { + file { + resource:process(transliterator) {"Greek_Latin_UNGEGN.txt"} + direction {"FORWARD"} + } } - Latin-ThaiLogical { - internal { - resource:process(transliterator){"ThaiLogical_Latin.txt"} - direction{"REVERSE"} - } + Latin-Greek/UNGEGN { + file { + resource:process(transliterator) {"Greek_Latin_UNGEGN.txt"} + direction {"REVERSE"} + } } -// Must use the order below! -// We need two separate passes because of the Thai vowel reversal -// Thai-Logical also converts spaces to semicolons. That has to be done before we insert latin spaces + Gujarati-Bengali { + file { + resource:process(transliterator) {"Gujarati_Bengali.txt"} + direction {"FORWARD"} + } + } - Thai-Latin { - alias {"[[:thai:] \u0E01-\u0E3A\u0E40-\u0E5B];NFD;Thai-ThaiSemi;Any-BreakInternal;Thai-ThaiLogical;ThaiLogical-Latin;NFC"} + Gujarati-Devanagari { + file { + resource:process(transliterator) {"Gujarati_Devanagari.txt"} + direction {"FORWARD"} + } } - Latin-Thai { - alias {"[[:Latin:][:Mn:][:Me:] \\u0020 \;0-9|~\u00A7\u00AB\u00BB\u02B9\u0374\u2021\u02CC];NFD;Latin-ThaiLogical;ThaiLogical-Thai;NFC"} + + Gujarati-Gurmukhi { + file { + resource:process(transliterator) {"Gujarati_Gurmukhi.txt"} + direction {"FORWARD"} + } } -// end of Thai Stuff + Gujarati-InterIndic { + internal { + resource:process(transliterator) {"Gujarati_InterIndic.txt"} + direction {"FORWARD"} + } + } - Hiragana-Katakana { + Gujarati-Kannada { file { - resource:process(transliterator){"Hiragana_Katakana.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Gujarati_Kannada.txt"} + direction {"FORWARD"} + } } - Katakana-Hiragana { + + Gujarati-Latin { file { - resource:process(transliterator){"Hiragana_Katakana.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Gujarati_Latin.txt"} + direction {"FORWARD"} + } } - Any-Accents { + Gujarati-Malayalam { file { - resource:process(transliterator){"Any_Accents.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Gujarati_Malayalam.txt"} + direction {"FORWARD"} + } } - Accents-Any { + + Gujarati-Oriya { file { - resource:process(transliterator){"Any_Accents.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Gujarati_Oriya.txt"} + direction {"FORWARD"} + } } - Any-Publishing { + Gujarati-Tamil { file { - resource:process(transliterator){"Any_Publishing.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Gujarati_Tamil.txt"} + direction {"FORWARD"} + } } - Publishing-Any { + + Gujarati-Telugu { + file { + resource:process(transliterator) {"Gujarati_Telugu.txt"} + direction {"FORWARD"} + } + } + + Gurmukhi-Bengali { file { - resource:process(transliterator){"Any_Publishing.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Gurmukhi_Bengali.txt"} + direction {"FORWARD"} + } } -// Korean -// N.B. Don't end Latin-Jamo with NFC; that produces Hangul. For -// Hangul output use Latin-Hangul. + Gurmukhi-Devanagari { + file { + resource:process(transliterator) {"Gurmukhi_Devanagari.txt"} + direction {"FORWARD"} + } + } - LowerLatin-Jamo { - internal { - resource:process(transliterator){"Latin_Jamo.txt"} - direction{"FORWARD"} - } + Gurmukhi-Gujarati { + file { + resource:process(transliterator) {"Gurmukhi_Gujarati.txt"} + direction {"FORWARD"} + } } - Jamo-LowerLatin { + + Gurmukhi-InterIndic { internal { - resource:process(transliterator){"Latin_Jamo.txt"} - direction{"REVERSE"} - } + resource:process(transliterator) {"Gurmukhi_InterIndic.txt"} + direction {"FORWARD"} + } } - Latin-Jamo { - alias {"['A-Za-z\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E1\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u01FB\u0200-\u021B\u021E-\u021F\u0226-\u0233\u1E00-\u1E99\u1EA0-\u1EF9\u212A-\u212B];NFD;Lower;LowerLatin-Jamo"} + + Gurmukhi-Kannada { + file { + resource:process(transliterator) {"Gurmukhi_Kannada.txt"} + direction {"FORWARD"} + } } - Jamo-Latin { - alias {"['\u1100-\u1112\u1161-\u1175\u11A8-\u11C2\uAC00-\uD7A3];NFD;Jamo-LowerLatin;NFC"} + + Gurmukhi-Latin { + file { + resource:process(transliterator) {"Gurmukhi_Latin.txt"} + direction {"FORWARD"} + } } - Latin-Hangul { - alias {"['A-Za-z\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E1\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u01FB\u0200-\u021B\u021E-\u021F\u0226-\u0233\u1E00-\u1E99\u1EA0-\u1EF9\u212A-\u212B];NFD;Lower;LowerLatin-Jamo;NFC"} + + Gurmukhi-Malayalam { + file { + resource:process(transliterator) {"Gurmukhi_Malayalam.txt"} + direction {"FORWARD"} + } } - Hangul-Latin { - alias {"['\u1100-\u1112\u1161-\u1175\u11A8-\u11C2\u3131-\u313F\u3141-\u3143\u3145-\u3163\u3200-\u321C\u3260-\u327B\uAC00-\uD7A3\uFF07\uFFA1-\uFFAF\uFFB1-\uFFB3\uFFB5-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC];NFKD;Jamo-LowerLatin;NFC"} + + Gurmukhi-Oriya { + file { + resource:process(transliterator) {"Gurmukhi_Oriya.txt"} + direction {"FORWARD"} + } } -// Inter-Indic composed rules - Latin-InterIndic { - internal { - resource:process(transliterator){"Latin_InterIndic.txt"} - direction{"FORWARD"} - } + Gurmukhi-Tamil { + file { + resource:process(transliterator) {"Gurmukhi_Tamil.txt"} + direction {"FORWARD"} + } } - Devanagari-InterIndic { - internal { - resource:process(transliterator){"Devanagari_InterIndic.txt"} - direction{"FORWARD"} - } + + Gurmukhi-Telugu { + file { + resource:process(transliterator) {"Gurmukhi_Telugu.txt"} + direction {"FORWARD"} + } } - Bengali-InterIndic { - internal { - resource:process(transliterator){"Bengali_InterIndic.txt"} - direction{"FORWARD"} - } + + Han-Latin { + file { + resource:process(transliterator) {"Han_Latin.txt"} + direction {"FORWARD"} + } } - Gurmukhi-InterIndic { - internal { - resource:process(transliterator){"Gurmukhi_InterIndic.txt"} - direction{"FORWARD"} - } + Latin-Han { + file { + resource:process(transliterator) {"Han_Latin.txt"} + direction {"REVERSE"} + } } - Gujarati-InterIndic { + + Han-Spacedhan { internal { - resource:process(transliterator){"Gujarati_InterIndic.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Han_Spacedhan.txt"} + direction {"FORWARD"} + } } - Oriya-InterIndic { + Spacedhan-Han { internal { - resource:process(transliterator){"Oriya_InterIndic.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"Han_Spacedhan.txt"} + direction {"REVERSE"} + } } - Tamil-InterIndic { - internal { - resource:process(transliterator){"Tamil_InterIndic.txt"} - direction{"FORWARD"} - } + + Hangul-Latin { + file { + resource:process(transliterator) {"Hangul_Latin.txt"} + direction {"FORWARD"} + } } - Telugu-InterIndic { - internal { - resource:process(transliterator){"Telugu_InterIndic.txt"} - direction{"FORWARD"} - } + + Hebrew-Latin { + file { + resource:process(transliterator) {"Hebrew_Latin.txt"} + direction {"FORWARD"} + } } - Kannada-InterIndic { - internal { - resource:process(transliterator){"Kannada_InterIndic.txt"} - direction{"FORWARD"} - } + Latin-Hebrew { + file { + resource:process(transliterator) {"Hebrew_Latin.txt"} + direction {"REVERSE"} + } } - Malayalam-InterIndic { - internal { - resource:process(transliterator){"Malayalam_InterIndic.txt"} - direction{"FORWARD"} - } + + Hiragana-Katakana { + file { + resource:process(transliterator) {"Hiragana_Katakana.txt"} + direction {"FORWARD"} + } + } + Katakana-Hiragana { + file { + resource:process(transliterator) {"Hiragana_Katakana.txt"} + direction {"REVERSE"} + } } - InterIndic-Latin { - internal { - resource:process(transliterator){"InterIndic_Latin.txt"} - direction{"FORWARD"} - } + Hiragana-Latin { + file { + resource:process(transliterator) {"Hiragana_Latin.txt"} + direction {"FORWARD"} + } } - InterIndic-Devanagari { - internal { - resource:process(transliterator){"InterIndic_Devanagari.txt"} - direction{"FORWARD"} - } + Latin-Hiragana { + file { + resource:process(transliterator) {"Hiragana_Latin.txt"} + direction {"REVERSE"} + } } + InterIndic-Bengali { internal { - resource:process(transliterator){"InterIndic_Bengali.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Bengali.txt"} + direction {"FORWARD"} + } } - InterIndic-Gurmukhi { + + InterIndic-Devanagari { internal { - resource:process(transliterator){"InterIndic_Gurmukhi.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Devanagari.txt"} + direction {"FORWARD"} + } } + InterIndic-Gujarati { internal { - resource:process(transliterator){"InterIndic_Gujarati.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Gujarati.txt"} + direction {"FORWARD"} + } } - InterIndic-Oriya { - internal { - resource:process(transliterator){"InterIndic_Oriya.txt"} - direction{"FORWARD"} - } - } - InterIndic-Tamil { + + InterIndic-Gurmukhi { internal { - resource:process(transliterator){"InterIndic_Tamil.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Gurmukhi.txt"} + direction {"FORWARD"} + } } - InterIndic-Telugu { + + InterIndic-Kannada { internal { - resource:process(transliterator){"InterIndic_Telugu.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Kannada.txt"} + direction {"FORWARD"} + } } - InterIndic-Kannada { + + InterIndic-Latin { internal { - resource:process(transliterator){"InterIndic_Kannada.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Latin.txt"} + direction {"FORWARD"} + } } + InterIndic-Malayalam { internal { - resource:process(transliterator){"InterIndic_Malayalam.txt"} - direction{"FORWARD"} - } + resource:process(transliterator) {"InterIndic_Malayalam.txt"} + direction {"FORWARD"} + } } -//Latin-Indic transliterators - Latin-Devanagari { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Devanagari;NFC"} - } - Latin-Bengali { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Bengali;NFC"} + InterIndic-Oriya { + internal { + resource:process(transliterator) {"InterIndic_Oriya.txt"} + direction {"FORWARD"} + } } - Latin-Gurmukhi { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Gurmukhi;NFC"} + + InterIndic-Tamil { + internal { + resource:process(transliterator) {"InterIndic_Tamil.txt"} + direction {"FORWARD"} + } } - Latin-Gujarati { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Gujarati;NFC"} + + InterIndic-Telugu { + internal { + resource:process(transliterator) {"InterIndic_Telugu.txt"} + direction {"FORWARD"} + } } - Latin-Oriya { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Oriya;NFC"} + + Jamo-Latin { + file { + resource:process(transliterator) {"Jamo_Latin.txt"} + direction {"FORWARD"} + } } - Latin-Tamil { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Tamil;NFC"} + + Kannada-Bengali { + file { + resource:process(transliterator) {"Kannada_Bengali.txt"} + direction {"FORWARD"} + } } - Latin-Telugu { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Telugu;NFC"} + + Kannada-Devanagari { + file { + resource:process(transliterator) {"Kannada_Devanagari.txt"} + direction {"FORWARD"} + } } - Latin-Kannada { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Kannada;NFC"} + + Kannada-Gujarati { + file { + resource:process(transliterator) {"Kannada_Gujarati.txt"} + direction {"FORWARD"} + } } - Latin-Malayalam { - alias {"['.0-9A-Za-z~\u00C0-\u00C5\u00C7-\u00CF\u00D1-\u00D6\u00D9-\u00DD\u00E0-\u00E5\u00E7-\u00EF\u00F1-\u00F6\u00F9-\u00FD\u00FF-\u010F\u0112-\u0125\u0128-\u0130\u0134-\u0137\u0139-\u013E\u0143-\u0148\u014C-\u0151\u0154-\u0165\u0168-\u017E\u01A0-\u01A1\u01AF-\u01B0\u01CD-\u01DC\u01DE-\u01E3\u01E6-\u01ED\u01F0\u01F4-\u01F5\u01F8-\u021B\u021E-\u021F\u0226-\u0233\u0294\u0301\u0303-\u0304\u0306-\u0307\u0310\u0314-\u0315\u0323\u0325\u0331\u0341\u0344\u0385-\u0386\u0388-\u038A\u038C\u038E-\u0390\u03AC-\u03B0\u03CC-\u03CE\u03D3\u0403\u040C\u040E\u0419\u0439\u0453\u045C\u045E\u04C1-\u04C2\u04D0-\u04D1\u04D6-\u04D7\u04E2-\u04E3\u04EE-\u04EF\u1E00-\u1E99\u1EA0-\u1EF9\u1F01\u1F03-\u1F05\u1F07\u1F09\u1F0B-\u1F0D\u1F0F\u1F11\u1F13-\u1F15\u1F19\u1F1B-\u1F1D\u1F21\u1F23-\u1F25\u1F27\u1F29\u1F2B-\u1F2D\u1F2F\u1F31\u1F33-\u1F35\u1F37\u1F39\u1F3B-\u1F3D\u1F3F\u1F41\u1F43-\u1F45\u1F49\u1F4B-\u1F4D\u1F51\u1F53-\u1F55\u1F57\u1F59\u1F5B\u1F5D\u1F5F\u1F61\u1F63-\u1F65\u1F67\u1F69\u1F6B-\u1F6D\u1F6F\u1F71\u1F73\u1F75\u1F77\u1F79\u1F7B\u1F7D\u1F81\u1F83-\u1F85\u1F87\u1F89\u1F8B-\u1F8D\u1F8F\u1F91\u1F93-\u1F95\u1F97\u1F99\u1F9B-\u1F9D\u1F9F\u1FA1\u1FA3-\u1FA5\u1FA7\u1FA9\u1FAB-\u1FAD\u1FAF-\u1FB1\u1FB4\u1FB8-\u1FB9\u1FBB\u1FC4\u1FC9\u1FCB\u1FCE\u1FD0-\u1FD1\u1FD3\u1FD8-\u1FD9\u1FDB\u1FDE\u1FE0-\u1FE1\u1FE3\u1FE5\u1FE8-\u1FE9\u1FEB-\u1FEC\u1FEE\u1FF4\u1FF9\u1FFB\u212A-\u212B\uE04D\uE064];NFD;Lower;Latin-InterIndic;InterIndic-Malayalam;NFC"} + + Kannada-Gurmukhi { + file { + resource:process(transliterator) {"Kannada_Gurmukhi.txt"} + direction {"FORWARD"} + } } - -//Indic-Latin transliterators - Devanagari-Latin { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Latin;NFC"} + + Kannada-InterIndic { + internal { + resource:process(transliterator) {"Kannada_InterIndic.txt"} + direction {"FORWARD"} + } } - Bengali-Latin { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Latin;NFC"} + + Kannada-Latin { + file { + resource:process(transliterator) {"Kannada_Latin.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Latin { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Latin;NFC"} + + Kannada-Malayalam { + file { + resource:process(transliterator) {"Kannada_Malayalam.txt"} + direction {"FORWARD"} + } } - Gujarati-Latin { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Latin;NFC"} + + Kannada-Oriya { + file { + resource:process(transliterator) {"Kannada_Oriya.txt"} + direction {"FORWARD"} + } } - Oriya-Latin { - alias {"[\u0964-\u0965\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35\u0B36-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B70\u0B71];NFD;Oriya-InterIndic;InterIndic-Latin;NFC"} + + Kannada-Tamil { + file { + resource:process(transliterator) {"Kannada_Tamil.txt"} + direction {"FORWARD"} + } } - Tamil-Latin { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Latin;NFC"} + + Kannada-Telugu { + file { + resource:process(transliterator) {"Kannada_Telugu.txt"} + direction {"FORWARD"} + } } - Telugu-Latin { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Latin;NFC"} + + Latin-Armenian { + file { + resource:process(transliterator) {"Latin_Armenian.txt"} + direction {"FORWARD"} + } } - Kannada-Latin { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Latin;NFC"} + Armenian-Latin { + file { + resource:process(transliterator) {"Latin_Armenian.txt"} + direction {"REVERSE"} + } } - Malayalam-Latin { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Latin;NFC"} + + Latin-Bengali { + file { + resource:process(transliterator) {"Latin_Bengali.txt"} + direction {"FORWARD"} + } } - Devanagari-Bengali { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Bengali;NFC"} + Latin-ConjoiningJamo { + internal { + resource:process(transliterator) {"Latin_ConjoiningJamo.txt"} + direction {"FORWARD"} + } } - Devanagari-Gurmukhi { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Gurmukhi;NFC"} + ConjoiningJamo-Latin { + internal { + resource:process(transliterator) {"Latin_ConjoiningJamo.txt"} + direction {"REVERSE"} + } } - Devanagari-Gujarati { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Gujarati;NFC"} + + Latin-Devanagari { + file { + resource:process(transliterator) {"Latin_Devanagari.txt"} + direction {"FORWARD"} + } } - Devanagari-Oriya { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Oriya;NFC"} + + Latin-Gujarati { + file { + resource:process(transliterator) {"Latin_Gujarati.txt"} + direction {"FORWARD"} + } } - Devanagari-Tamil { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Tamil;NFC"} + + Latin-Gurmukhi { + file { + resource:process(transliterator) {"Latin_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Devanagari-Telugu { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Telugu;NFC"} + + Latin-Hangul { + file { + resource:process(transliterator) {"Latin_Hangul.txt"} + direction {"FORWARD"} + } } - Devanagari-Kannada { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Kannada;NFC"} + + Latin-InterIndic { + internal { + resource:process(transliterator) {"Latin_InterIndic.txt"} + direction {"FORWARD"} + } } - Devanagari-Malayalam { - alias {"[\u0901-\u0903\u0904\u0905-\u0939\u093C-\u094D\u0950-\u0954\u0958-\u096F\u097D];NFD;Devanagari-InterIndic;InterIndic-Malayalam;NFC"} + + Latin-Jamo { + file { + resource:process(transliterator) {"Latin_Jamo.txt"} + direction {"FORWARD"} + } } - Bengali-Devanagari { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Devanagari;NFC"} + Latin-Kannada { + file { + resource:process(transliterator) {"Latin_Kannada.txt"} + direction {"FORWARD"} + } } - Bengali-Gurmukhi { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Gurmukhi;NFC"} + + Latin-Katakana { + file { + resource:process(transliterator) {"Latin_Katakana.txt"} + direction {"FORWARD"} + } } - Bengali-Gujarati { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Gujarati;NFC"} + Katakana-Latin { + file { + resource:process(transliterator) {"Latin_Katakana.txt"} + direction {"REVERSE"} + } } - Bengali-Oriya { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Oriya;NFC"} + + Latin-Malayalam { + file { + resource:process(transliterator) {"Latin_Malayalam.txt"} + direction {"FORWARD"} + } } - Bengali-Tamil { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Tamil;NFC"} + + Latin-NumericPinyin { + file { + resource:process(transliterator) {"Latin_NumericPinyin.txt"} + direction {"FORWARD"} + } } - Bengali-Telugu { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Telugu;NFC"} + NumericPinyin-Latin { + file { + resource:process(transliterator) {"Latin_NumericPinyin.txt"} + direction {"REVERSE"} + } } - Bengali-Kannada { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Kannada;NFC"} + + Latin-Oriya { + file { + resource:process(transliterator) {"Latin_Oriya.txt"} + direction {"FORWARD"} + } } - Bengali-Malayalam { - alias {"[\u0964-\u0965\u0981-\u0983\u0985-\u098C\u098F-\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BC-\u09C4\u09C7-\u09C8\u09CB-\u09CD\u09D7\u09DC-\u09DD\u09DF-\u09E3\u09E6-\u09FA\u09ce];NFD;Bengali-InterIndic;InterIndic-Malayalam;NFC"} + + Latin-Tamil { + file { + resource:process(transliterator) {"Latin_Tamil.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Devanagari { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Devanagari;NFC"} + Latin-Telugu { + file { + resource:process(transliterator) {"Latin_Telugu.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Bengali { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Bengali;NFC"} + + Latin-Thai { + file { + resource:process(transliterator) {"Latin_Thai.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Gujarati { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Gujarati;NFC"} + + Malayalam-Bengali { + file { + resource:process(transliterator) {"Malayalam_Bengali.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Oriya { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Oriya;NFC"} + + Malayalam-Devanagari { + file { + resource:process(transliterator) {"Malayalam_Devanagari.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Tamil { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Tamil;NFC"} + + Malayalam-Gujarati { + file { + resource:process(transliterator) {"Malayalam_Gujarati.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Telugu { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Telugu;NFC"} + + Malayalam-Gurmukhi { + file { + resource:process(transliterator) {"Malayalam_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Kannada { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Kannada;NFC"} + + Malayalam-InterIndic { + internal { + resource:process(transliterator) {"Malayalam_InterIndic.txt"} + direction {"FORWARD"} + } } - Gurmukhi-Malayalam { - alias {"[\u0964-\u0965\u0A01\u0A02\u0A05-\u0A0A\u0A0F-\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32-\u0A33\u0A35-\u0A36\u0A38-\u0A39\u0A3C\u0A3E-\u0A42\u0A47-\u0A48\u0A4B-\u0A4D\u0A59-\u0A5C\u0A5E\u0A66-\u0A74];NFD;Gurmukhi-InterIndic;InterIndic-Malayalam;NFC"} + + Malayalam-Kannada { + file { + resource:process(transliterator) {"Malayalam_Kannada.txt"} + direction {"FORWARD"} + } } - Gujarati-Devanagari { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Devanagari;NFC"} + Malayalam-Latin { + file { + resource:process(transliterator) {"Malayalam_Latin.txt"} + direction {"FORWARD"} + } } - Gujarati-Bengali { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Bengali;NFC"} + + Malayalam-Oriya { + file { + resource:process(transliterator) {"Malayalam_Oriya.txt"} + direction {"FORWARD"} + } } - Gujarati-Gurmukhi { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Gurmukhi;NFC"} + + Malayalam-Tamil { + file { + resource:process(transliterator) {"Malayalam_Tamil.txt"} + direction {"FORWARD"} + } } - Gujarati-Oriya { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Oriya;NFC"} + + Malayalam-Telugu { + file { + resource:process(transliterator) {"Malayalam_Telugu.txt"} + direction {"FORWARD"} + } } - Gujarati-Tamil { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Tamil;NFC"} + + Oriya-Bengali { + file { + resource:process(transliterator) {"Oriya_Bengali.txt"} + direction {"FORWARD"} + } } - Gujarati-Telugu { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Telugu;NFC"} + + Oriya-Devanagari { + file { + resource:process(transliterator) {"Oriya_Devanagari.txt"} + direction {"FORWARD"} + } } - Gujarati-Kannada { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Kannada;NFC"} + + Oriya-Gujarati { + file { + resource:process(transliterator) {"Oriya_Gujarati.txt"} + direction {"FORWARD"} + } } - Gujarati-Malayalam { - alias {"[\u0964-\u0965\u0A81-\u0A83\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2-\u0AB3\u0AB5-\u0AB9\u0ABC-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AD0\u0AE0\u0AE1\u0AE6-\u0AEF];NFD;Gujarati-InterIndic;InterIndic-Malayalam;NFC"} + + Oriya-Gurmukhi { + file { + resource:process(transliterator) {"Oriya_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Oriya-Devanagari { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Devanagari;NFC"} + Oriya-InterIndic { + internal { + resource:process(transliterator) {"Oriya_InterIndic.txt"} + direction {"FORWARD"} + } } - Oriya-Bengali { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Bengali;NFC"} + + Oriya-Kannada { + file { + resource:process(transliterator) {"Oriya_Kannada.txt"} + direction {"FORWARD"} + } } - Oriya-Gurmukhi { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Gurmukhi;NFC"} + + Oriya-Latin { + file { + resource:process(transliterator) {"Oriya_Latin.txt"} + direction {"FORWARD"} + } } - Oriya-Gujarati { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Gujarati;NFC"} + + Oriya-Malayalam { + file { + resource:process(transliterator) {"Oriya_Malayalam.txt"} + direction {"FORWARD"} + } } + Oriya-Tamil { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Tamil;NFC"} + file { + resource:process(transliterator) {"Oriya_Tamil.txt"} + direction {"FORWARD"} + } } + Oriya-Telugu { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Telugu;NFC"} + file { + resource:process(transliterator) {"Oriya_Telugu.txt"} + direction {"FORWARD"} + } } - Oriya-Kannada { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Kannada;NFC"} + + Pinyin-NumericPinyin { + file { + resource:process(transliterator) {"Pinyin_NumericPinyin.txt"} + direction {"FORWARD"} + } } - Oriya-Malayalam { - alias {"[\u0B01-\u0B03\u0B05-\u0B0C\u0B0F-\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32-\u0B33\u0B35-\u0B39\u0B3C-\u0B43\u0B47-\u0B48\u0B4B-\u0B4D\u0B56-\u0B57\u0B5C-\u0B5D\u0B5F-\u0B61\u0B66-\u0B71];NFD;Oriya-InterIndic;InterIndic-Malayalam;NFC"} + NumericPinyin-Pinyin { + file { + resource:process(transliterator) {"Pinyin_NumericPinyin.txt"} + direction {"REVERSE"} + } } - Tamil-Devanagari { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Devanagari;NFC"} + Syriac-Latin { + file { + resource:process(transliterator) {"Syriac_Latin.txt"} + direction {"FORWARD"} + } + } + Latin-Syriac { + file { + resource:process(transliterator) {"Syriac_Latin.txt"} + direction {"REVERSE"} + } } + Tamil-Bengali { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Bengali;NFC"} + file { + resource:process(transliterator) {"Tamil_Bengali.txt"} + direction {"FORWARD"} + } } - Tamil-Gurmukhi { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Gurmukhi;NFC"} + + Tamil-Devanagari { + file { + resource:process(transliterator) {"Tamil_Devanagari.txt"} + direction {"FORWARD"} + } } + Tamil-Gujarati { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Gujarati;NFC"} + file { + resource:process(transliterator) {"Tamil_Gujarati.txt"} + direction {"FORWARD"} + } } - Tamil-Oriya { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Oriya;NFC"} + + Tamil-Gurmukhi { + file { + resource:process(transliterator) {"Tamil_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Tamil-Telugu { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Telugu;NFC"} + + Tamil-InterIndic { + internal { + resource:process(transliterator) {"Tamil_InterIndic.txt"} + direction {"FORWARD"} + } } + Tamil-Kannada { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Kannada;NFC"} + file { + resource:process(transliterator) {"Tamil_Kannada.txt"} + direction {"FORWARD"} + } } + + Tamil-Latin { + file { + resource:process(transliterator) {"Tamil_Latin.txt"} + direction {"FORWARD"} + } + } + Tamil-Malayalam { - alias {"[0\u0B82-\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99-\u0B9A\u0B9C\u0B9E-\u0B9F\u0BA3-\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB5\u0BB7-\u0BB9\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0BE7-\u0BF2\u0BB6];NFD;Tamil-InterIndic;InterIndic-Malayalam;NFC"} + file { + resource:process(transliterator) {"Tamil_Malayalam.txt"} + direction {"FORWARD"} + } } - Telugu-Devanagari { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Devanagari;NFC"} + Tamil-Oriya { + file { + resource:process(transliterator) {"Tamil_Oriya.txt"} + direction {"FORWARD"} + } + } + + Tamil-Telugu { + file { + resource:process(transliterator) {"Tamil_Telugu.txt"} + direction {"FORWARD"} + } } + Telugu-Bengali { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Bengali;NFC"} + file { + resource:process(transliterator) {"Telugu_Bengali.txt"} + direction {"FORWARD"} + } } - Telugu-Gurmukhi { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Gurmukhi;NFC"} + + Telugu-Devanagari { + file { + resource:process(transliterator) {"Telugu_Devanagari.txt"} + direction {"FORWARD"} + } } + Telugu-Gujarati { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Gujarati;NFC"} + file { + resource:process(transliterator) {"Telugu_Gujarati.txt"} + direction {"FORWARD"} + } } - Telugu-Oriya { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Oriya;NFC"} + + Telugu-Gurmukhi { + file { + resource:process(transliterator) {"Telugu_Gurmukhi.txt"} + direction {"FORWARD"} + } } - Telugu-Tamil { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Tamil;NFC"} + + Telugu-InterIndic { + internal { + resource:process(transliterator) {"Telugu_InterIndic.txt"} + direction {"FORWARD"} + } } + Telugu-Kannada { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Kannada;NFC"} - } - Telugu-Malayalam { - alias {"[\u0C01-\u0C03\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55-\u0C56\u0C60-\u0C61\u0C66-\u0C6F];NFD;Telugu-InterIndic;InterIndic-Malayalam;NFC"} + file { + resource:process(transliterator) {"Telugu_Kannada.txt"} + direction {"FORWARD"} + } } - Kannada-Devanagari { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Devanagari;NFC"} - } - Kannada-Bengali { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Bengali;NFC"} - } - Kannada-Gurmukhi { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Gurmukhi;NFC"} + Telugu-Latin { + file { + resource:process(transliterator) {"Telugu_Latin.txt"} + direction {"FORWARD"} + } } - Kannada-Gujarati { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Gujarati;NFC"} + + Telugu-Malayalam { + file { + resource:process(transliterator) {"Telugu_Malayalam.txt"} + direction {"FORWARD"} + } } - Kannada-Oriya { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Oriya;NFC"} + + Telugu-Oriya { + file { + resource:process(transliterator) {"Telugu_Oriya.txt"} + direction {"FORWARD"} + } } - Kannada-Tamil { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Tamil;NFC"} + + Telugu-Tamil { + file { + resource:process(transliterator) {"Telugu_Tamil.txt"} + direction {"FORWARD"} + } } - Kannada-Telugu { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Telugu;NFC"} + + Thaana-Latin { + file { + resource:process(transliterator) {"Thaana_Latin.txt"} + direction {"FORWARD"} + } } - Kannada-Malayalam { - alias {"[\u0C82-\u0C83\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBC\u0CBD\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5-\u0CD6\u0CDE\u0CE0-\u0CE1\u0CE6-\u0CEF];NFD;Kannada-InterIndic;InterIndic-Malayalam;NFC"} + Latin-Thaana { + file { + resource:process(transliterator) {"Thaana_Latin.txt"} + direction {"REVERSE"} + } } - Malayalam-Devanagari { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Devanagari;NFC"} + Thai-Latin { + file { + resource:process(transliterator) {"Thai_Latin.txt"} + direction {"FORWARD"} + } } - Malayalam-Bengali { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Bengali;NFC"} + + Thai-ThaiLogical { + internal { + resource:process(transliterator) {"Thai_ThaiLogical.txt"} + direction {"FORWARD"} + } } - Malayalam-Gurmukhi { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Gurmukhi;NFC"} + ThaiLogical-Thai { + internal { + resource:process(transliterator) {"Thai_ThaiLogical.txt"} + direction {"REVERSE"} + } } - Malayalam-Gujarati { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Gujarati;NFC"} + + Thai-ThaiSemi { + internal { + resource:process(transliterator) {"Thai_ThaiSemi.txt"} + direction {"FORWARD"} + } } - Malayalam-Oriya { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Oriya;NFC"} + ThaiSemi-Thai { + internal { + resource:process(transliterator) {"Thai_ThaiSemi.txt"} + direction {"REVERSE"} + } } - Malayalam-Tamil { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Tamil;NFC"} + + ThaiLogical-Latin { + internal { + resource:process(transliterator) {"ThaiLogical_Latin.txt"} + direction {"FORWARD"} + } } - Malayalam-Telugu { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Telugu;NFC"} + Latin-ThaiLogical { + internal { + resource:process(transliterator) {"ThaiLogical_Latin.txt"} + direction {"REVERSE"} + } } - Malayalam-Kannada { - alias {"[\u0D02-\u0D03\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D28\u0D2A-\u0D39\u0D3E-\u0D43\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D60-\u0D61\u0D66-\u0D6F];NFD;Malayalam-InterIndic;InterIndic-Kannada;NFC"} - } - /* - # Comment these out; they are only for testing - Latin-Han/definition{ - file { - resource:process(transliterator){"Han_Latin_Definition.txt"} - direction{"REVERSE"} - } - } - Han-Latin/definition{ - file { - resource:process(transliterator){"Han_Latin_Definition.txt"} - direction{"FORWARD"} - } - } - Latin-Han/EDICT{ - file { - resource:process(transliterator){"Han_Latin_EDICT.txt"} - direction{"REVERSE"} - } - } - Han-Latin/EDICT{ - file { - resource:process(transliterator){"Han_Latin_EDICT.txt"} - direction{"FORWARD"} - } - } - */ -// eof + } TransliteratorNamePattern { // Format for the display name of a Transliterator. // This is the language-neutral form of this resource. "{0,choice,0#|1#{1}|2#{1}-{2}}" // Display name } - // Transliterator display names // This is the English form of this resource. "%Translit%Hex" { "%Translit%Hex" } "%Translit%UnicodeName" { "%Translit%UnicodeName" } "%Translit%UnicodeChar" { "%Translit%UnicodeChar" } - TransliterateLATIN{ - "", - "" + "", + "" } - } diff --git a/Build/source/libs/icu-xetex/data/translit/trnsfiles.mk b/Build/source/libs/icu-xetex/data/translit/trnsfiles.mk index fedaa43e1cb..81078b44ea3 100644 --- a/Build/source/libs/icu-xetex/data/translit/trnsfiles.mk +++ b/Build/source/libs/icu-xetex/data/translit/trnsfiles.mk @@ -1,4 +1,4 @@ -# * Copyright (C) 1997-2005, International Business Machines +# * Copyright (C) 1997-2006, International Business Machines # * Corporation and others. All Rights Reserved. # A list of txt's to build # Note: @@ -23,6 +23,4 @@ # # -TRANSLIT_ALIAS_SOURCE=root.txt - -TRANSLIT_SOURCE=el.txt en.txt +TRANSLIT_SOURCE=root.txt en.txt el.txt diff --git a/Build/source/libs/icu-xetex/data/translit/trnslocal.mk b/Build/source/libs/icu-xetex/data/translit/trnslocal.mk index ad11619c5e6..c3d990fea6c 100644 --- a/Build/source/libs/icu-xetex/data/translit/trnslocal.mk +++ b/Build/source/libs/icu-xetex/data/translit/trnslocal.mk @@ -1,4 +1,4 @@ -# * Copyright (C) 1997-2005, International Business Machines +# * Copyright (C) 1997-2006, International Business Machines # * Corporation and others. All Rights Reserved. # A list of txt's to build # Note: @@ -23,8 +23,4 @@ # # -TRANSLIT_ALIAS_SOURCE= - - TRANSLIT_SOURCE= - |