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/build-icu-data.xml 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. 31e $lengthMarker → эй ; 32# 33# 34# Turn long /i:/ into two vowels /ii/. 35i $lengthMarker → | i i ; 36# 37# 38# Ignore vowel length everywhere else. 39$lengthMarker → ; 40# 41# 42# Vowels. 43# 44# TODO(mjansche): Enable diphthongs once we have Kanji boundaries. 45## ai → ай ; 46a → а ; 47i\~e → | ye ; 48i → и ; 49u\~ → в ; # ウィ etc. 50# 51## ui → уй ; 52u → у ; 53e → э ; 54o → о ; 55# 56# 57# Consonants. 58# 59k → к ; 60# 61# 62sh → | sy ; 63s → с ; 64# 65# 66ch → | ty ; 67c } ch → t ; 68te\~ → | t ; # テュ 69to\~ → | t ; # トゥ 70tsu\~ → | ts ; # ツァ, ツィ, etc. 71ts → ц ; 72t → т ; 73# 74# 75\~tsu → | tsu ; 76# 77# 78n } [bpm] → м ; # 群馬 → Гумма 79n\' → нъ ; 80n → н ; 81# 82# 83h → х ; 84fu\~ → | f ; # フュ 85f → ф ; 86# 87# 88m → м ; 89# 90# 91ya → я ; 92yi → и ; # Added for convenience, after sh, ch, j. 93yu → ю ; 94ye → е ; # ?? unobserved 95yo → ё ; 96# 97# 98r → р ; 99# 100# 101wa → ва ; 102w → ; 103# 104# 105g → г ; 106# 107# 108j → | zy ; 109z → дз ; 110# 111# 112de\~ → | d ; # デュ 113dji\~ → | z ; # ヂャ, ヂュ, etc. 114dj → | j ; # ヂ 115do\~ → | d ; # ドゥ 116dzu\~ → | z ; # ヅァ, ヅィ, etc. 117dz → | z ; # ヅ 118d → д ; 119# 120# 121b → б ; 122vu\~ → | v ; # ヴァ, etc. 123v → в ; # ?? unobserved 124# 125# 126p → п ; 127# 128# 129::NFC(NFD); 130 131