1<?xml version="1.0" encoding="UTF-8" ?>
2<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
3<!--
4Copyright © 1991-2013 Unicode, Inc.
5CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
6For terms of use, see http://www.unicode.org/copyright.html
7-->
8<supplementalData>
9	<version number="$Revision: 13787 $"/>
10	<transforms>
11		<transform source="ru" target="ru_Latn" variant="BGN" direction="forward" draft="contributed" alias="Russian-Latin/BGN ru-Latn-t-ru-m0-bgn">
12			<tRule><![CDATA[
13# BGN/PCGN 1947 System
14#
15# The BGN/PCGN system for Russian was adopted by the BGN in 1944 and
16# by the PCGN in 1947 for use in romanizing names written in the
17# Russian Cyrillic alphabet.
18#
19# The Russian Alphabet as defined by the BGN (Page 93):
20#     АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ
21#     абвгдеёжзийклмнопрстуфхцчшщъыьэюя
22#
23# Originally prepared by Michael Everson everson@evertype.com
24# Fixed by Frank Yung-Fong Tang ftang@google.com
25#
26# Test Data from http://en.wikipedia.org/wiki/BGN/PCGN_romanization_of_Russian
27
28########################################################################
29# MINIMAL FILTER: Russian-Latin
30
31::[АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюя];
32
33::NFC;
34
35########################################################################
36# Define All Transformation Variables
37########################################################################
38
39$prime = ʹ ;
40$doublePrime = ʺ ;
41$wordBoundary = [^[:L:][:M:][:N:]] ;
42$upperVowels = [АЕЁЭИОУЫЮЯ] ;
43$lowerVowels = [аеёэиоуыюя] ;
44$vowels = [$upperVowels $lowerVowels] ;
45$upperConsonants = [[:Uppercase:]-$vowels] ;
46$lowerConsonants = [[:Lowercase:]-$vowels] ;
47$consonants = [$upperConsonants $lowerConsonants] ;
48$upper = [:Uppercase:];
49$lower = [:Lowercase:];
50
51
52########################################################################
53# Rules moved to front to avoid masking
54########################################################################
55
56$lowerVowels { ы → ·y ;
57$upperVowels { [Ыы] } $lower → ·y ;
58$upperVowels { [Ыы] } → ·Y ;
59
60
61[$consonants - [Йй]]{Э → ·E ;
62[$consonants - [Йй]]{э → ·e ;
63
64[$upperVowels [ЙЪЬ]] { Е } $upper → YE ; # CYRILLIC CAPITAL LETTER IE
65[$upperVowels [ЙЪЬ]] { Е → Ye ; # CYRILLIC CAPITAL LETTER IE
66[$upperVowels $lowerVowels [ЙйЪъЬь]] { е → ye ; # CYRILLIC SMALL LETTER IE
67[$upperVowels [ЙЪЬ]] { Ё } $upper → YË ; # CYRILLIC CAPITAL LETTER IO
68[$upperVowels [ЙЪЬ]] { Ё → Yë ; # CYRILLIC CAPITAL LETTER IO
69[$upperVowels $lowerVowels [ЙйЪъЬь]] { ё → yë ; # CYRILLIC SMALL LETTER IO
70
71# Since in the above rule we look at the Cyrillic context before the E/Ё/ё,
72# we have to transform these in a separate pass before we change the vowels.
73# The ::Null forces a separate pass.
74
75::Null;
76
77
78########################################################################
79# Start of Alphabetic Transformations
80########################################################################
81
82А → A ; # CYRILLIC CAPITAL LETTER A
83а → a ; # CYRILLIC SMALL LETTER A
84Б → B ; # CYRILLIC CAPITAL LETTER BE
85б → b ; # CYRILLIC SMALL LETTER BE
86В → V ; # CYRILLIC CAPITAL LETTER VE
87в → v ; # CYRILLIC SMALL LETTER VE
88Г → G ; # CYRILLIC CAPITAL LETTER GHE
89г → g ; # CYRILLIC SMALL LETTER GHE
90Д → D ; # CYRILLIC CAPITAL LETTER DE
91д → d ; # CYRILLIC SMALL LETTER DE
92
93
94########################################################################
95# BGN Page 94 Rule 1:
96# # The character e should be romanized ye
97# initially, after the vowel # characters a, e, ё, и, о, у, ы, э, ю,
98# and я, and after й, ъ, and ь.
99# In all other instances, it should
100# be romanized e.
101########################################################################
102
103# BUG(ftang)- the following two lines said BEFORE the vowels, instead of AFTER
104# Е}[$upperVowels [ЙЪЬ]] → YE ; # CYRILLIC CAPITAL LETTER IE
105# Е}[$lowerVowels [йъь]] → Ye ; # CYRILLIC CAPITAL LETTER IE
106
107$wordBoundary{Е} $upper → YE ; # CYRILLIC CAPITAL LETTER IE
108$wordBoundary{Е → Ye ; # CYRILLIC CAPITAL LETTER IE
109Е → E ; # CYRILLIC CAPITAL LETTER IE
110#
111# BUG(ftang)- the following line said BEFORE the vowels, instead of AFTER
112# е}[$upperVowels $lowerVowels [ЙйЪъЬь]] → ye ; # CYRILLIC SMALL LETTER IE
113
114$wordBoundary{е → ye ; # CYRILLIC SMALL LETTER IE
115е → e ; # CYRILLIC SMALL LETTER IE
116
117
118########################################################################
119# End of Rule 1
120########################################################################
121
122########################################################################
123# BGN Page 94 Rule 2:
124#
125# The character ё is not considered a separate character of the
126# Russian alphabet and the dieresis is generally not shown. When the
127# dieresis is shown, the character should be romanized yë initially,
128# after the vowel characters a, e, ё, и, о, у, ы, э, ю, and я, and
129# after й, ъ, and ь, In all other instances, it should be romanized
130# ё. When the dieresis is not shown, the character may still be
131# romanized in the preceding manner or, alternatively, in accordance
132# with note 1.
133
134########################################################################
135# BUG(ftang)- the following two lines said BEFORE the vowels, instead of AFTER
136# Ё}[$upperVowels [ЙЪЬ]] → YË ; # CYRILLIC CAPITAL LETTER IO
137# Ё}[$lowerVowels [йъь]] → Yë ; # CYRILLIC CAPITAL LETTER IO
138
139$wordBoundary {Ё} [·]? $upper → YË ; # CYRILLIC CAPITAL LETTER IO
140$wordBoundary {Ё} [·]? $lower → Yë ; # CYRILLIC CAPITAL LETTER IO
141Ё → Ë ; # CYRILLIC CAPITAL LETTER IO
142
143# BUG(ftang)- the following line said BEFORE the vowels, instead of AFTER
144# ё}[$upperVowels $lowerVowels [ЙйЪъЬь]] → yë ; # CYRILLIC SMALL LETTER IO
145
146$wordBoundary{ё → yë ; # CYRILLIC SMALL LETTER IO
147ё → ë ; # CYRILLIC SMALL LETTER IO
148
149
150########################################################################
151# End of Rule 2
152########################################################################
153
154Ж} $lower → Zh ; # CYRILLIC CAPITAL LETTER ZHE
155Ж → ZH ; # CYRILLIC CAPITAL LETTER ZHE
156ж → zh ; # CYRILLIC SMALL LETTER ZHE
157
158
159########################################################################
160# BGN Page 94 Rule 3.4
161# э after any consonant character except
162# й becomes ·е
163########################################################################
164
165З → Z ; # CYRILLIC CAPITAL LETTER ZE
166з → z ; # CYRILLIC SMALL LETTER ZE
167
168# BUG(ftang) The following two lines said those consonant becomes ·е
169# [$consonants - [Йй]]}Э → ·Е ;
170# [$consonants - [Йй]]}э → ·е ;
171
172########################################################################
173# End of Rule 3.4
174########################################################################
175
176И → I ; # CYRILLIC CAPITAL LETTER I
177и → i ; # CYRILLIC SMALL LETTER I
178
179
180########################################################################
181# BGN Page 94 Rule 3:
182#
183# Unusual Russian character sequences occurring primarily in
184# non-Russian-language names may be romanized as shown below in order
185# to provide differentiation from regularly-occurring digraphs and
186# character sequences.
187#
188# BGN Page 94 Rule 3.1
189# й before а, у, ы, or э becomes у·
190########################################################################
191
192Й}[АаУуЫыЭэ] → Y· ; # CYRILLIC CAPITAL LETTER I
193й}[АаУуЫыЭэ] → y· ; # CYRILLIC SMALL LETTER I
194
195Й → Y ; # CYRILLIC CAPITAL LETTER I
196й → y ; # CYRILLIC SMALL LETTER I
197
198
199########################################################################
200# End Rule 3.1
201########################################################################
202
203К → K ; # CYRILLIC CAPITAL LETTER KA
204к → k ; # CYRILLIC SMALL LETTER KA
205Л → L ; # CYRILLIC CAPITAL LETTER EL
206л → l ; # CYRILLIC SMALL LETTER EL
207М → M ; # CYRILLIC CAPITAL LETTER EM
208м → m ; # CYRILLIC SMALL LETTER EM
209Н → N ; # CYRILLIC CAPITAL LETTER EN
210н → n ; # CYRILLIC SMALL LETTER EN
211О → O ; # CYRILLIC CAPITAL LETTER O
212о → o ; # CYRILLIC SMALL LETTER O
213П → P ; # CYRILLIC CAPITAL LETTER PE
214п → p ; # CYRILLIC SMALL LETTER PE
215Р → R ; # CYRILLIC CAPITAL LETTER ER
216р → r ; # CYRILLIC SMALL LETTER ER
217С → S ; # CYRILLIC CAPITAL LETTER ES
218с → s ; # CYRILLIC SMALL LETTER ES
219
220
221########################################################################
222# BGN Page 94 Rule 3.5
223# тс becomes t·s
224########################################################################
225
226ТС → T·S ; # CYRILLIC CAPITAL LETTER TE
227Тс → T·s ; # CYRILLIC CAPITAL LETTER TE
228тс → t·s ; # CYRILLIC SMALL LETTER TE
229
230Т → T ; # CYRILLIC CAPITAL LETTER TE
231т → t ; # CYRILLIC SMALL LETTER TE
232
233
234########################################################################
235# End Rule 3.5
236########################################################################
237
238У → U ; # CYRILLIC CAPITAL LETTER U
239у → u ; # CYRILLIC SMALL LETTER U
240Ф → F ; # CYRILLIC CAPITAL LETTER EF
241ф → f ; # CYRILLIC SMALL LETTER EF
242Х} $lower → Kh ; # CYRILLIC CAPITAL LETTER HA
243Х → KH ; # CYRILLIC CAPITAL LETTER HA
244х → kh ; # CYRILLIC SMALL LETTER HA
245Ц} $lower → Ts ; # CYRILLIC CAPITAL LETTER TSE
246Ц → TS ; # CYRILLIC CAPITAL LETTER TSE
247ц → ts ; # CYRILLIC SMALL LETTER TSE
248Ч} $lower → Ch ; # CYRILLIC CAPITAL LETTER CHE
249Ч → CH ; # CYRILLIC CAPITAL LETTER CHE
250ч → ch ; # CYRILLIC SMALL LETTER CHE
251
252
253########################################################################
254# BGN Page 94 Rule 3.6
255# шч becomes sh·ch
256########################################################################
257
258ШЧ → SH·CH ; # CYRILLIC CAPITAL LETTER SHA
259Шч → Sh·ch ; # CYRILLIC CAPITAL LETTER SHA
260шч → sh·ch ; # CYRILLIC SMALL LETTER SHA
261
262Ш} $lower → Sh ; # CYRILLIC CAPITAL LETTER SHA
263Ш → SH ; # CYRILLIC CAPITAL LETTER SHA
264ш → sh ; # CYRILLIC SMALL LETTER SHA
265Щ} $lower → Shch ; # CYRILLIC CAPITAL LETTER SHCHA
266Щ → SHCH ; # CYRILLIC CAPITAL LETTER SHCHA
267щ → shch ; # CYRILLIC SMALL LETTER SHCHA
268
269
270########################################################################
271# End Rule 3.6
272########################################################################
273
274Ъ → $doublePrime ; # CYRILLIC CAPITAL LETTER HARD SIGN
275ъ → $doublePrime ; # CYRILLIC SMALL LETTER HARD SIGN
276
277
278########################################################################
279# BGN Page 94 Rule 3.2
280# ы before а, у, ы, or э becomes у·
281#
282# BGN Page 94 Rule 3.3
283# ы after any vowel character becomes ·у
284########################################################################
285#
286# BUG(ftang) the following line said the vowels will change
287# $vowels}Ы → ·Y ; # CYRILLIC CAPITAL LETTER I
288# $vowels}ы → ·y ; # CYRILLIC CAPITAL LETTER I
289
290Ы}[АаУуЫыЭэ] → Y· ; # CYRILLIC CAPITAL LETTER YERU
291ы}[ауыэ] → y· ; # CYRILLIC SMALL LETTER YERU
292
293Ы → Y ; # CYRILLIC CAPITAL LETTER YERU
294ы → y ; # CYRILLIC SMALL LETTER YERU
295
296
297########################################################################
298# End Rule 3.2 and 3.3
299########################################################################
300
301Ь → $prime ; # CYRILLIC CAPITAL LETTER SOFT SIGN
302ь → $prime ; # CYRILLIC SMALL LETTER SOFT SIGN
303Э → E ; # CYRILLIC CAPITAL LETTER E
304э → e ; # CYRILLIC SMALL LETTER E
305Ю} $lower → Yu ; # CYRILLIC CAPITAL LETTER YU
306Ю → YU ; # CYRILLIC CAPITAL LETTER YU
307ю → yu ; # CYRILLIC SMALL LETTER YU
308Я} $lower → Ya ; # CYRILLIC CAPITAL LETTER YA
309Я → YA ; # CYRILLIC CAPITAL LETTER YA
310я → ya ; # CYRILLIC SMALL LETTER YA
311			]]></tRule>
312		</transform>
313	</transforms>
314</supplementalData>
315