tor-browser

The Tor Browser
git clone https://git.dasho.dev/tor-browser.git
Log | Files | Refs | README | LICENSE

ja_Latn_ru.txt (2168B)


      1 # © 2016 and later: Unicode, Inc. and others.
      2 # License & terms of use: http://www.unicode.org/copyright.html
      3 # Generated using tools/cldr/cldr-to-icu/
      4 #
      5 # File: ja_Latn_ru.txt
      6 # Generated from CLDR
      7 #
      8 
      9 # Japanese (Rōmaji) to Russian (Cyrillic) Polivanov transliteration for ICU.
     10 # Can be run in sequence after e.g. Katakana-Latin.
     11 #
     12 # These rules cannot be used to target Bulgarian, Serbian, Tajik, or Ukrainian.
     13 #
     14 # TODO: Cyrillization needs to respect morpheme/Kanji boundaries.
     15 # 中井 becomes Накаи, but 北海道 becomes Хоккайдо.  We need boundary
     16 # markup in the input in order to do that properly.
     17 #
     18 ::NFD(NFC);
     19 ::[:Latin:] Lower();
     20 #
     21 #
     22 $lengthMarker = [\u0302\u0304];
     23 #
     24 #
     25 # Delete apostrophes.  Apostrophes after "n" are consumed below.
     26 \' → ;
     27 #
     28 #
     29 # Turn long /e:/ into diphthong /ei/.
     30 # Note that /ei/ across a morpheme boundary (e.g. 武井 Takei) becomes эи.
     31 e $lengthMarker → эй ;
     32 #
     33 #
     34 # Turn long /i:/ into two vowels /ii/.
     35 i $lengthMarker → | i i ;
     36 #
     37 #
     38 # Ignore vowel length everywhere else.
     39 $lengthMarker → ;
     40 #
     41 #
     42 # Vowels.
     43 #
     44 # TODO(mjansche): Enable diphthongs once we have Kanji boundaries.
     45 ## ai → ай ;
     46 a  → а ;
     47 i\~e → | ye ;
     48 i  → и ;
     49 u\~ → в ;  # ウィ etc.
     50 #
     51 ## ui → уй ;
     52 u  → у ;
     53 e  → э ;
     54 o  → о ;
     55 #
     56 #
     57 # Consonants.
     58 #
     59 k → к ;
     60 #
     61 #
     62 sh → | sy ;
     63 s → с ;
     64 #
     65 #
     66 ch     → | ty ;
     67 c } ch → t ;
     68 te\~   → | t ;   # テュ
     69 to\~   → | t ;   # トゥ
     70 tsu\~  → | ts ;  # ツァ, ツィ, etc.
     71 ts → ц ;
     72 t  → т ;
     73 #
     74 #
     75 \~tsu → | tsu ;
     76 #
     77 #
     78 n } [bpm] → м ;  # 群馬 → Гумма
     79 n\' → нъ ;
     80 n → н ;
     81 #
     82 #
     83 h → х ;
     84 fu\~ → | f ;  # フュ
     85 f → ф ;
     86 #
     87 #
     88 m → м ;
     89 #
     90 #
     91 ya → я ;
     92 yi → и ;  # Added for convenience, after sh, ch, j.
     93 yu → ю ;
     94 ye → е ;  # ?? unobserved
     95 yo → ё ;
     96 #
     97 #
     98 r → р ;
     99 #
    100 #
    101 wa → ва ;
    102 w → ;
    103 #
    104 #
    105 g → г ;
    106 #
    107 #
    108 j → | zy ;
    109 z → дз ;
    110 #
    111 #
    112 de\~  → | d ;  # デュ
    113 dji\~ → | z ;  # ヂャ, ヂュ, etc.
    114 dj    → | j ;  # ヂ
    115 do\~  → | d ;  # ドゥ
    116 dzu\~ → | z ;  # ヅァ, ヅィ, etc.
    117 dz    → | z ;  # ヅ
    118 d → д ;
    119 #
    120 #
    121 b → б ;
    122 vu\~ → | v ;  # ヴァ, etc.
    123 v → в ;  # ?? unobserved
    124 #
    125 #
    126 p → п ;
    127 #
    128 #
    129 ::NFC(NFD);