Index: source/data/translit/mn_mn_Latn_BGN.txt |
diff --git a/source/data/translit/Mongolian_Latin_BGN.txt b/source/data/translit/mn_mn_Latn_BGN.txt |
similarity index 56% |
rename from source/data/translit/Mongolian_Latin_BGN.txt |
rename to source/data/translit/mn_mn_Latn_BGN.txt |
index 9bb8e7405241692a7d862cb9df8b7cd26c11e92b..dbed925d0d6dee9e418bc8a99efe9f452374c723 100644 |
--- a/source/data/translit/Mongolian_Latin_BGN.txt |
+++ b/source/data/translit/mn_mn_Latn_BGN.txt |
@@ -1,14 +1,40 @@ |
-# *************************************************************************** |
-# * |
-# * Copyright (C) 2004-2015, International Business Machines |
-# * Corporation; Unicode, Inc.; and others. All Rights Reserved. |
-# * |
-# *************************************************************************** |
-# File: Mongolian_Latin_BGN.txt |
-# Generated from CLDR |
-# |
-:: [АБВГДЕЁЖЗИЙКЛМНОӨПРСТУҮФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмноөпрстуүфхцчшщъыьэюя] ; |
-:: NFD (NFC) ; |
+# © 2016 and later: Unicode, Inc. and others. |
+# License & terms of use: http://www.unicode.org/copyright.html#License |
+# |
+# File: mn_mn_Latn_BGN.txt |
+# Generated from CLDR |
+# |
+ |
+######################################################################## |
+# BGN/PCGN 1964 System |
+# |
+# The BGN/PCGN system for Mongolian was adopted by the BGN in 1957 |
+# and by the PCGN in 1964 for use in romanizing names written in |
+# the Mongolian Cyrillic alphabet. The Mongolian Cyrillic alphabet |
+# contains two letters not present in the Russian alphabet, Өө |
+# and Үү. Names written in the indigenous Mongolian alphabet, which |
+# is still utilized in the Inner Mongolia Autonomous Region of China, |
+# are not romanized by BGN and PCGN. Instead, for such names, |
+# BGN and PCGN utilize the Roman-script spellings appearing in |
+# official sources published by the People's Republic of China |
+# |
+# The Mongolian Alphabet as defined by the BGN (Page 73): |
+# |
+# АБВГДЕЁЖЗИЙКЛМНОӨПРСТУҮФХЦЧШЩЪЫЬЭЮЯ |
+# абвгдеёжзийклмноөпрстуүфхцчшщъыьэюя |
+# |
+# Originally prepared by Michael Everson <everson@evertype.com> |
+######################################################################## |
+# |
+# MINIMAL FILTER: Mongolian-Latin, works both in NFC and NFD |
+::[АБВГДЕЁЖЗИЙКЛМНОӨПРСТУҮФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмноөпрстуүфхцчшщъыьэюя\u0308]; |
+::NFC; |
+######################################################################## |
+# |
+# Define All Transformation Variables |
+# |
+######################################################################## |
+# |
$prime = ʹ ; |
$upperConsonants = [БВГДЖЙКЛМНПРСТФХЦЧШЩЭ] ; |
$lowerConsonants = [бвгджйклмнпрстфхцчшщэ] ; |
@@ -17,7 +43,12 @@ $upperVowels = [АЕЁЭИОУЫЮЯ] ; |
$lowerVowels = [аеёэиоуыюя] ; |
$vowels = [$upperVowels $lowerVowels] ; |
$lower = [$lowerConsonants $lowerVowels] ; |
+# Use this $wordBoundary until bug 2034 is fixed in ICU: |
+# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest |
$wordBoundary = [^[:L:][:M:][:N:]] ; |
+######################################################################## |
+# Start of Alphabetic Transformations |
+######################################################################## |
А → A ; # CYRILLIC CAPITAL LETTER A |
а → a ; # CYRILLIC SMALL LETTER A |
Б → B ; # CYRILLIC CAPITAL LETTER BE |
@@ -77,6 +108,10 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
Ч} $lower → Ch ; # CYRILLIC CAPITAL LETTER CHE |
Ч → CH ; # CYRILLIC CAPITAL LETTER CHE |
ч → ch ; # CYRILLIC SMALL LETTER CHE |
+######################################################################## |
+# Implied rule from BGN Russian-Latin transliteration (Page 94 Note 3.6). |
+# шч becomes sh·ch |
+######################################################################## |
ШЧ → SH·CH ; # CYRILLIC CAPITAL LETTER SHA |
Шч → Sh·ch ; # CYRILLIC CAPITAL LETTER SHA |
шч → sh·ch ; # CYRILLIC SMALL LETTER SHA |
@@ -86,6 +121,9 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
Щ} $lower → Shch ; # CYRILLIC CAPITAL LETTER SHCHA |
Щ → SHCH ; # CYRILLIC CAPITAL LETTER SHCHA |
щ → shch ; # CYRILLIC SMALL LETTER SHCHA |
+######################################################################## |
+# End Implied rule |
+######################################################################## |
Ъ → $prime ; # CYRILLIC CAPITAL LETTER HARD SIGN |
ъ → $prime ; # CYRILLIC SMALL LETTER HARD SIGN |
Ы → Ï ; # CYRILLIC CAPITAL LETTER YERU |
@@ -94,9 +132,26 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
ь → ĭ ; # CYRILLIC SMALL LETTER SOFT SIGN |
Э → E ; # CYRILLIC CAPITAL LETTER E |
э → e ; # CYRILLIC SMALL LETTER E |
+######################################################################## |
+# |
+# BGN Page 74 Rule 7 |
+# |
+# In monosyllables, the character ю is romanized yu or yü depending on |
+# pronunciation; in polysyllables, it is romanized yu when followed by |
+# a, o, or u, buy yü when followed by i, e, ö, or ü. |
+# |
+# This rule is lexical and has not been implemented in this file. |
+# |
+######################################################################## |
Ю} $lower → Yu ; # CYRILLIC CAPITAL LETTER YU |
Ю → YU ; # CYRILLIC CAPITAL LETTER YU |
ю → yu ; # CYRILLIC SMALL LETTER YU |
+######################################################################## |
+# |
+# End Rule 7 |
+# |
+######################################################################## |
Я} $lower → Ya ; # CYRILLIC CAPITAL LETTER YA |
Я → YA ; # CYRILLIC CAPITAL LETTER YA |
я → ya ; # CYRILLIC SMALL LETTER YA |
+ |