Index: source/data/translit/zh_Latn_PINYIN_ru.txt |
diff --git a/source/data/translit/zh_Latn_PINYIN_ru.txt b/source/data/translit/zh_Latn_PINYIN_ru.txt |
index a4aaa397d91106940d73f9ad839234b0d3b84af6..ef543daad4b1f0f8daab1aa9acac365caca188ef 100644 |
--- a/source/data/translit/zh_Latn_PINYIN_ru.txt |
+++ b/source/data/translit/zh_Latn_PINYIN_ru.txt |
@@ -1,21 +1,41 @@ |
-# *************************************************************************** |
-# * |
-# * 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: zh_Latn_PINYIN_ru.txt |
-# Generated from CLDR |
+# Generated from CLDR |
+# |
+ |
+# Cyrillization of Mandarin Chinese from Pinyin into Russian (Palladius system). |
+# |
+# References: |
+# http://ru.wikipedia.org/wiki/Транскрипционная_система_Палладия |
+# http://www.omniglot.com/writing/mandarin_pts.htm |
+# http://www.pinyin.info/romanization/russian/index.html |
+# These differ in the treatment of some syllables (e.g. <jue>) from the rules |
+# below. |
# |
+# Further commentary: |
+# http://languagelog.ldc.upenn.edu/nll/?p=604 |
+# |
+# Remove tone marks. |
:: NFD (NFC); |
[\u0304\u0301\u030C\u0300\u0306] → ; |
:: NFC (NFD); |
+# |
+# |
+# Syllabify. Add apostrophes to disambiguate whether <n> and <g> belong to the |
+# coda or onset of a syllable. |
:: Null (); |
ng } [aeou] → n\'g; |
ng → ng\'; |
n } [aeiouü] → \'n; |
n → n\'; |
+# |
+# |
+# Main pass. |
:: Null (); |
+# |
+# |
Ai → Ай; |
A → А; |
B → Б; |
@@ -57,9 +77,13 @@ Yu → Ю | v; |
Zh → Чж; |
Zi → Цзы; |
Z → Цз; |
+# |
+# |
[$] { n → н; |
\'n → н; |
\' → ; |
+# |
+# |
ai → ай; |
a → а; |
b → б; |
@@ -100,7 +124,12 @@ ui → уй; |
uo → о; |
u → у; |
ü → ю | v; |
+# |
+# We use the dummy symbol <v> to signal that an <ü> or equivalent character has |
+# just been processed. |
ve → э; |
+# |
+#alternative: ve → е; |
v } [an] → ; |
v → й; |
wu → у; |
@@ -118,4 +147,8 @@ yu → ю | v; |
zh → чж; |
zi → цзы; |
z → цз; |
+# |
+# |
+# Final pass: Make sure that the output consists entirely of Cyrillic letters. |
:: NFC (); |
+ |