Index: source/data/translit/ru_zh.txt |
diff --git a/source/data/translit/ru_zh.txt b/source/data/translit/ru_zh.txt |
index a89dbb4331f92cf91e124eb86fa930a25fb23139..694fd17b440e9296f28b8650d2650f5a66f3c651 100644 |
--- a/source/data/translit/ru_zh.txt |
+++ b/source/data/translit/ru_zh.txt |
@@ -1,17 +1,23 @@ |
-# *************************************************************************** |
-# * |
-# * 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: ru_zh.txt |
-# Generated from CLDR |
+# Generated from CLDR |
+# |
+ |
+# Transliteration of Russian into Mandarin written in simplified Chinese. |
# |
+# TODO(mjansche): Implement exception rules from GB/T 17693.4-2009 section 5.3. |
+# TODO(anyone): Simplify. |
$bow = [-\ $]; # Word boundary. |
$vowel = [аеийоуыьэюяё]; |
$not_vowel = [^$vowel]; |
+# |
+# |
::NFC; |
::Lower; |
+# |
+# |
аа → а; |
бб → б; |
вв → в; |
@@ -36,11 +42,20 @@ $vowel { нь → н; |
чч → ч; |
шш → ш; |
щщ → щ; |
+# |
+# |
+## иа → я; ## TODO: Figure out if/when this applies. |
+# |
::Null; |
+# |
+# |
+# Special exceptions, per GB/T 17693.4-2009 表 1, 注 8: |
бург } $bow → 堡 ; |
град } $bow → 格勒 ; |
город } $bow → 哥罗德 ; |
цов } $bow → 佐夫 ; |
+# |
+# |
аи → 艾 ; |
ай → 艾 ; |
ан } $not_vowel → 安 ; |
@@ -448,6 +463,8 @@ $vowel { нь → н; |
лян } $not_vowel → 良 ; |
ля → 利亚 ; |
лё → 廖 ; |
+# |
+## $not_vowel { л → 勒 ; ## FIXME: Figure out if/when this applies. |
л → 尔 ; |
маи → 迈 ; |
май → 迈 ; |
@@ -574,6 +591,8 @@ $vowel { нь → н; |
рян } $not_vowel → 良 ; |
ря → 里亚 ; |
рё → 廖 ; |
+# |
+## $not_vowel { р → 勒 ; ## FIXME: Figure out if/when this applies. |
р → 尔 ; |
саи → 赛 ; |
сай → 赛 ; |
@@ -965,6 +984,10 @@ $vowel { нь → н; |
ян } $not_vowel → 扬 ; |
я → 亚 ; |
ё → 约 ; |
+# |
+# |
+# Dong-nan-xi-hai pass. Per GB/T 17693.4-2009 表 1, 注 4, replace confusing |
+# characters at the beginning and end of a word. |
:: Null (); |
$bow { 耶 → 叶 ; |
$bow { 夫 → 弗 ; |
@@ -973,4 +996,7 @@ $bow { 南 → 楠 ; |
$bow { 西 → 锡 ; |
江 } $bow → 姜 ; |
海 } $bow → 亥 ; |
+# |
+# |
::NFC; |
+ |