icu4c/source/data/translit/ja_Latn_ru.txt

# © 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
#
# File: ja_Latn_ru.txt
# Generated from CLDR
#

# Japanese (Rōmaji) to Russian (Cyrillic) Polivanov transliteration for ICU.
# Can be run in sequence after e.g. Katakana-Latin.
#
# These rules cannot be used to target Bulgarian, Serbian, Tajik, or Ukrainian.
#
# TODO: Cyrillization needs to respect morpheme/Kanji boundaries.
# 中井 becomes Накаи, but 北海道 becomes Хоккайдо.  We need boundary
# markup in the input in order to do that properly.
#
::NFD(NFC);
::[:Latin:] Lower();
#
#
$lengthMarker = [\u0302\u0304];
#
#
# Delete apostrophes.  Apostrophes after "n" are consumed below.
\' → ;
#
#
# Turn long /e:/ into diphthong /ei/.
# Note that /ei/ across a morpheme boundary (e.g. 武井 Takei) becomes эи.
e $lengthMarker → эй ;
#
#
# Turn long /i:/ into two vowels /ii/.
i $lengthMarker → | i i ;
#
#
# Ignore vowel length everywhere else.
$lengthMarker → ;
#
#
# Vowels.
#
# TODO(mjansche): Enable diphthongs once we have Kanji boundaries.
## ai → ай ;
a  → а ;
i\~e → | ye ;
i  → и ;
u\~ → в ;  # ウィ etc.
#
## ui → уй ;
u  → у ;
e  → э ;
o  → о ;
#
#
# Consonants.
#
k → к ;
#
#
sh → | sy ;
s → с ;
#
#
ch     → | ty ;
c } ch → t ;
te\~   → | t ;   # テュ
to\~   → | t ;   # トゥ
tsu\~  → | ts ;  # ツァ, ツィ, etc.
ts → ц ;
t  → т ;
#
#
\~tsu → | tsu ;
#
#
n } [bpm] → м ;  # 群馬 → Гумма
n\' → нъ ;
n → н ;
#
#
h → х ;
fu\~ → | f ;  # フュ
f → ф ;
#
#
m → м ;
#
#
ya → я ;
yi → и ;  # Added for convenience, after sh, ch, j.
yu → ю ;
ye → е ;  # ?? unobserved
yo → ё ;
#
#
r → р ;
#
#
wa → ва ;
w → ;
#
#
g → г ;
#
#
j → | zy ;
z → дз ;
#
#
de\~  → | d ;  # デュ
dji\~ → | z ;  # ヂャ, ヂュ, etc.
dj    → | j ;  # ヂ
do\~  → | d ;  # ドゥ
dzu\~ → | z ;  # ヅァ, ヅィ, etc.
dz    → | z ;  # ヅ
d → д ;
#
#
b → б ;
vu\~ → | v ;  # ヴァ, etc.
v → в ;  # ?? unobserved
#
#
p → п ;
#
#
::NFC(NFD);