# Copyright (C) 2009 Google, Inc. All Rights Reserved.
# Author: mjansche@google.com (Martin Jansche)
#
# Japanese (Rōmaji) to Korean (Hangul) transliteration table for ICU.
# Can be run in sequence after e.g. Katakana-Latin.
#
# Based on 문교부 고시 제85-11호 (1986. 1. 7.) 외래어 표기법
# For background info, see http://ko.wikisource.org/wiki/문교부_고시_제85-11호
# and http://ko.wikipedia.org/wiki/외래어_표기법 (外來語表記法)
#
::NFD(NFC);
::[:Latin:] Lower();
#
$consonant = [ᄀᄁᄂᄃᄄᄅᄆᄇᄈᄉᄊᄋᄌᄍᄎᄏᄐᄑᄒ];
$lengthMarker = [̂̄];
#
# Drop hyphens and apostrophes.
[\-\'] → ;
#
# Turn long /e:/ into diphthong /ei/.
e $lengthMarker → | e i ;
#
# Ignore vowel length everywhere else.
$lengthMarker → ;
#
# Vowels.
#
[^$consonant] { ( [aiueoyw] ) → ᄋ | $1 ; # Supply a required null initial.
a → ᅡ ;
i\~e → | ie ; # イェ
i → ᅵ ;
u\~a → | wa ; # クァ, グァ
u\~i → ᅱ ; # ウィ, クィ, etc.
u\~e → ᅰ ; # ウェ
u\~o → ᅯ ; # ウォ
u → ᅮ ;
e → ᅦ ;
o → ᅩ ;
#
# Geminates.
#
kk → ᆺ | k ;
ss → ᆺ | s ;
tt → ᆺ | t ;
tc → ᆺ | c ;
cc → ᆺ | c ;
hh → ᆺ | h ;
ff → ᆺ | f ;
rr → ᆺ | r ;
gg → ᆺ | g ;
zz → ᆺ | z ;
jj → ᆺ | j ;
dd → ᆺ | d ;
bb → ᆺ | b ;
vv → ᆺ | v ;
pp → ᆺ | p ;
#
# Consonants.
#
' ' { k → | g ; # Beginning of a word (after space).
^k → | g ; # Beginning of the string.
k → ᄏ ;
#
sh → | sy ;
su → 스 ;
s → ᄉ ;
#
te\~ → | t ; # テュ
to\~ → | t ; # トゥ
tsu\~ → | ch ; # ツァ, ツィ, etc.
tsu → 쓰 ;
ts → | ch ;
' ' { t → | d ;
^t → | d ;
t → ᄐ ;
' ' { ch → | j ;
^ch → | j ;
ch → ᄎ ;
#
n } [\ \'bcdfghjkmnprstwz] → ᆫ ;
n$ → ᆫ ;
n → ᄂ ;
#
h → ᄒ ;
fu\~ → | p ; # フュ
fu → | hu ;
f → | p ;
#
m } [bmp] → ᆫ ;
m → ᄆ ;
#
ya → ᅣ ;
yi → ᅵ ; # Added for convenience, after shi.
yu → ᅲ ;
ye → ᅨ ;
yo → ᅭ ;
#
r → ᄅ ;
#
wa → ᅪ ;
w → ;
#
g → ᄀ ;
#
zu → 즈 ;
z → | j ;
j → ᄌ ;
#
de\~ → | d ; # デュ
dji\~ → | j ; # ヂァ, ヂゥ, etc.
dji → | ji ; # ヂ
do\~ → | d ; # ドゥ
dzu\~ → | j ; # ヅァ, ヅィ, etc.
dzu → | zu ; # ヅ
dz → | j ;
d → ᄃ ;
#
b → ᄇ ;
vu\~ → | b ; # ヴァ, etc.
v → | b ;
#
p → ᄑ ;
#
::NFC(NFD);