ICU-62107.0.1.tar.gz

[apple/icu.git] / icuSources / data / translit / ja_Latn_ko.txt

diff --git a/icuSources/data/translit/ja_Latn_ko.txt b/icuSources/data/translit/ja_Latn_ko.txt
index af01222f7755560bf20f4116f87b806d7a0323e1..9c0024ffb8faad4efc83d721617fcbe7881dcf11 100644 (file)
--- a/icuSources/data/translit/ja_Latn_ko.txt
+++ b/icuSources/data/translit/ja_Latn_ko.txt
@@ -1,30 +1,51 @@
-# ***************************************************************************
-# *
-# *  Copyright (C) 2004-2012, 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.
 $lengthMarker → ;
-[^$consonant] { ( [aiueoyw] ) → ᄋ | $1 ; # Supply a required null initial.
+#
+#
+# Vowels.
+#
+[^$consonant] { ( [aiueoyw] ) → ᄋ | $1 ;  # Supply a required null initial.
 a → ᅡ ;
-i\~e → | ie ; # イェ
+i\~e → | ie ;  # イェ
 i → ᅵ ;
-u\~a → | wa ; # クァ, グァ
-u\~i → ᅱ ; # ウィ, クィ, etc.
-u\~e → ᅰ ; # ウェ
-u\~o → ᅯ ; # ウォ
+u\~a → | wa ;  # クァ, グァ
+u\~i → ᅱ ;     # ウィ, クィ, etc.
+u\~e → ᅰ ;     # ウェ
+u\~o → ᅯ ;     # ウォ
 u → ᅮ ;
 e → ᅦ ;
 o → ᅩ ;
+#
+#
+# Geminates.
+#
 kk → ᆺ | k ;
 ss → ᆺ | s ;
 tt → ᆺ | t ;
@@ -40,54 +61,87 @@ dd → ᆺ | d ;
 bb → ᆺ | b ;
 vv → ᆺ | v ;
 pp → ᆺ | p ;
-' ' { k → | g ; # Beginning of a word (after space).
-^k → | g ; # Beginning of the string.
+#
+#
+# Consonants.
+#
+' ' { k → | g ;   # Beginning of a word (after space).
+^k      → | g ;   # Beginning of the string.
 k → ᄏ ;
+#
+#
 sh → | sy ;
 su → 스 ;
 s → ᄉ ;
-te\~ → | t ; # テュ
-to\~ → | t ; # トゥ
-tsu\~ → | ch ; # ツァ, ツィ, etc.
+#
+#
+te\~     → | t ;   # テュ
+to\~     → | t ;   # トゥ
+tsu\~    → | ch ;  # ツァ, ツィ, etc.
 tsu → 쓰 ;
-ts → | ch ;
-' ' { t → | d ;
-^t → | d ;
+ts       → | ch ;
+' ' { t  → | d ;
+^t       → | d ;
 t → ᄐ ;
 ' ' { ch → | j ;
-^ch → | j ;
+^ch      → | j ;
 ch → ᄎ ;
+#
+#
 n } [\ \'bcdfghjkmnprstwz] → ᆫ ;
 n$ → ᆫ ;
 n → ᄂ ;
+#
+#
 h → ᄒ ;
-fu\~ → | p ; # フュ
-fu → | hu ;
-f → | p ;
+fu\~ → | p ;   # フュ
+fu   → | hu ;
+f    → | p ;
+#
+#
 m } [bmp] → ᆫ ;
 m → ᄆ ;
+#
+#
 ya → ᅣ ;
-yi → ᅵ ; # Added for convenience, after shi.
+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 ;
+#
+#
+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 ;
+vu\~ → | b ;  # ヴァ, etc.
+v    → | b ;
+#
+#
 p → ᄑ ;
+#
+#
 ::NFC(NFD);
+