Index: source/data/translit/ja_Latn_ko.txt |
diff --git a/source/data/translit/ja_Latn_ko.txt b/source/data/translit/ja_Latn_ko.txt |
index 11857253c0bd13a1e9b8af6d026450647e8be584..9c0024ffb8faad4efc83d721617fcbe7881dcf11 100644 |
--- a/source/data/translit/ja_Latn_ko.txt |
+++ b/source/data/translit/ja_Latn_ko.txt |
@@ -1,19 +1,36 @@ |
-# *************************************************************************** |
-# * |
-# * Copyright (C) 2004-2015, International Business Machines |
-# * Corporation; Unicode, Inc.; and others. All Rights Reserved. |
-# * |
-# *************************************************************************** |
+# © 2016 and later: Unicode, Inc. and others. |
+# License & terms of use: http://www.unicode.org/copyright.html#License |
+# |
# File: ja_Latn_ko.txt |
-# Generated from CLDR |
+# 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 | $1 ; # Supply a required null initial. |
a → ᅡ ; |
i\~e → | ie ; # イェ |
@@ -25,6 +42,10 @@ u\~o → ᅯ ; # ウォ |
u → ᅮ ; |
e → ᅦ ; |
o → ᅩ ; |
+# |
+# |
+# Geminates. |
+# |
kk → ᆺ | k ; |
ss → ᆺ | s ; |
tt → ᆺ | t ; |
@@ -40,12 +61,20 @@ dd → ᆺ | d ; |
bb → ᆺ | b ; |
vv → ᆺ | v ; |
pp → ᆺ | p ; |
+# |
+# |
+# Consonants. |
+# |
' ' { k → | g ; # Beginning of a word (after space). |
^k → | g ; # Beginning of the string. |
k → ᄏ ; |
+# |
+# |
sh → | sy ; |
su → 스 ; |
s → ᄉ ; |
+# |
+# |
te\~ → | t ; # テュ |
to\~ → | t ; # トゥ |
tsu\~ → | ch ; # ツァ, ツィ, etc. |
@@ -57,27 +86,45 @@ t → ᄐ ; |
' ' { ch → | j ; |
^ch → | j ; |
ch → ᄎ ; |
+# |
+# |
n } [\ \'bcdfghjkmnprstwz] → ᆫ ; |
n$ → 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 |
@@ -86,8 +133,15 @@ 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); |
+ |