blob: 12ab8f4abc3beaec7230c613e22365cf66f03d1f [file] [log] [blame]
# © 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html#License
#
# File: Cyrl_Latn.txt
# Generated from CLDR
#
# 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 ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:]] ;
### WARNING, \u0308 must be added to the generated filters, in both directions ###
# MINIMAL FILTER
:: [Ққ\u0308Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ\u0306Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ;
:: NFD (NFC) ;
$modprime = ʹ;
$modprime2 = ʺ;
$grave = \u0300;
$acute = \u0301;
$hat = \u0302;
$breve = \u0306 ;
$dot = \u0307 ;
$caron = \u030C ;
$comma = \u0326 ;
$under = \u0331 ;
$descender = ˌ;
# move up so not masked
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 ↔ 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
Ғ ↔ G $dot; # CYRILLIC CAPITAL LETTER GHE WITH STROKE
ҕ ↔ g $breve; # CYRILLIC SMALL LETTER GHE WITH MIDDLE HOOK
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
Ђ ↔ Đ ; # CYRILLIC CAPITAL LETTER DJE
ҙ ↔ z $comma ; # CYRILLIC SMALL LETTER ZE WITH DESCENDER
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
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
# 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
### а\u0306 ↔ XXX ; # CYRILLIC SMALL LETTER A
### А\u0306 ↔ XXX ; # CYRILLIC CAPITAL LETTER A
### а\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER A
### А\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER A
### ә\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER SCHWA
### Ә\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER SCHWA
### г\u0301 ↔ XXX ; # CYRILLIC SMALL LETTER GHE
### Г\u0301 ↔ XXX ; # CYRILLIC CAPITAL LETTER GHE
### е\u0300 ↔ XXX ; # CYRILLIC SMALL LETTER IE
### Е\u0300 ↔ XXX ; # CYRILLIC CAPITAL LETTER IE
### е\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER IE
### Е\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER IE
### е\u0306 ↔ XXX ; # CYRILLIC SMALL LETTER IE
### Е\u0306 ↔ XXX ; # CYRILLIC CAPITAL LETTER IE
### ж\u0306 ↔ XXX ; # CYRILLIC SMALL LETTER ZHE
### Ж\u0306 ↔ XXX ; # CYRILLIC CAPITAL LETTER ZHE
### ж\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER ZHE
### Ж\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER ZHE
### з\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER ZE
### З\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER ZE
### и\u0300 ↔ XXX ; # CYRILLIC SMALL LETTER I
### И\u0300 ↔ XXX ; # CYRILLIC CAPITAL LETTER I
### и\u0304 ↔ XXX ; # CYRILLIC SMALL LETTER I
### И\u0304 ↔ XXX ; # CYRILLIC CAPITAL LETTER I
### и\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER I
### И\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER I
### і\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
### І\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
### о\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER O
### О\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER O
### ө\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER BARRED O
### Ө\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER BARRED O
### к\u0301 ↔ XXX ; # CYRILLIC SMALL LETTER KA
### К\u0301 ↔ XXX ; # CYRILLIC CAPITAL LETTER KA
### у\u0304 ↔ XXX ; # CYRILLIC SMALL LETTER U
### У\u0304 ↔ XXX ; # CYRILLIC CAPITAL LETTER U
### у\u0306 ↔ XXX ; # CYRILLIC SMALL LETTER U
### У\u0306 ↔ XXX ; # CYRILLIC CAPITAL LETTER U
### у\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER U
### У\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER U
### у\u030B ↔ XXX ; # CYRILLIC SMALL LETTER U
### У\u030B ↔ XXX ; # CYRILLIC CAPITAL LETTER U
### ч\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER CHE
### Ч\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER CHE
### ы\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER YERU
### Ы\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER YERU
### э\u0308 ↔ XXX ; # CYRILLIC SMALL LETTER E
### Э\u0308 ↔ XXX ; # CYRILLIC CAPITAL LETTER E
### ѵ\u030F ↔ XXX ; # CYRILLIC SMALL LETTER IZHITSA
### Ѵ\u030F ↔ XXX ; # CYRILLIC CAPITAL LETTER IZHITSA
# Completeness
$ignore = [[:Mark:]''] * ;
| k ← q ;
| K ← Q ;
| u ← w ;
| U ← W ;
| KS ← X } $ignore [:UppercaseLetter:] ;
| 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 ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:]]);
# MINIMAL FILTER: Latin-Cyrillic
:: ( [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] ) ;