summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/data/translit/ja_Latn_ko.txt
blob: a123d810f0fcf4d7b34685d52d24f15c35052b84 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# © 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_ko.txt
# Generated from CLDR
#

# 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 = [\u0302\u0304];
#
#
# 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);