• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
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 $"/>
10	<transforms>
11		<transform source="fa" target="fa_Latn" variant="BGN" direction="forward" draft="contributed" alias="Persian-Latin/BGN fa-Latn-t-fa-m0-bgn">
12			<tRule><![CDATA[
13#
14########################################################################
15# BGN/PCGN 1956 System
16#
17# This system was adopted by the BGN in 1946 and by the PCGN in 1958.
18# It is used for the romanization of geographic names in Iran and
19# for Persian-language names in Afghanistan.
20#
21# Originally prepared by Michael Everson <everson@evertype.com>
22########################################################################
23#
24# MINIMAL FILTER: Persian-Latin
25#
26
27:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویيَُِّْ٠١٢٣٤٥٦٧٨٩پچژگی]] ;
28:: NFKD (NFC) ;
29#
30#
31########################################################################
32
33
34#
35########################################################################
36#
37# Define All Transformation Variables
38#
39########################################################################
40#
41
42$alef = ’;
43$ayin = ‘;
44$disambig =  ̱ ;
45#
46#
47# Use this $wordBoundary until bug 2034 is fixed in ICU:
48# http://bugs.icu-project.org/cgi-bin/icu-bugs/transliterate?id=2034;expression=boundary;user=guest
49#
50
51$wordBoundary =  [^[:L:][:M:][:N:]] ;
52#
53#
54########################################################################
55
56# non-letters
57[:Nd:]{٫}[:Nd:] ↔ [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR
58[:Nd:]{٬}[:Nd:] ↔ [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR
59٫ ↔ ',' $disambig ; # ARABIC DECIMAL SEPARATOR
60٬ ↔ '.' $disambig ; # ARABIC THOUSANDS SEPARATOR
61#  ٭ ↔ ; # ARABIC FIVE POINTED STAR // no need to transliterate
62، ↔ ',' ; # ARABIC COMMA
63؛ ↔ ';' ; # ARABIC SEMICOLON
64؟ ↔ '?' ; # ARABIC QUESTION MARK
65٪ ↔ '%' ; # ARABIC PERCENT SIGN
66٠ ↔ 0 $disambig ; # ARABIC-INDIC DIGIT ZERO
67١ ↔ 1 $disambig ; # ARABIC-INDIC DIGIT ONE
68٢ ↔ 2 $disambig ; # ARABIC-INDIC DIGIT TWO
69٣ ↔ 3 $disambig ; # ARABIC-INDIC DIGIT THREE
70٤ ↔ 4 $disambig ; # ARABIC-INDIC DIGIT FOUR
71٥ ↔ 5 $disambig ; # ARABIC-INDIC DIGIT FIVE
72٦ ↔ 6 $disambig ; # ARABIC-INDIC DIGIT SIX
73٧ ↔ 7 $disambig ; # ARABIC-INDIC DIGIT SEVEN
74٨ ↔ 8 $disambig ; # ARABIC-INDIC DIGIT EIGHT
75٩ ↔ 9 $disambig ; # ARABIC-INDIC DIGIT NINE
76۰ ↔ 0 ; # EXTENDED ARABIC-INDIC DIGIT ZERO
77۱ ↔ 1 ; # EXTENDED ARABIC-INDIC DIGIT ONE
78۲ ↔ 2 ; # EXTENDED ARABIC-INDIC DIGIT TWO
79۳ ↔ 3 ; # EXTENDED ARABIC-INDIC DIGIT THREE
80۴ ↔ 4 ; # EXTENDED ARABIC-INDIC DIGIT FOUR
81۵ ↔ 5 ; # EXTENDED ARABIC-INDIC DIGIT FIVE
82۶ ↔ 6 ; # EXTENDED ARABIC-INDIC DIGIT SIX
83۷ ↔ 7 ; # EXTENDED ARABIC-INDIC DIGIT SEVEN
84۸ ↔ 8 ; # EXTENDED ARABIC-INDIC DIGIT EIGHT
85۹ ↔ 9 ; # EXTENDED ARABIC-INDIC DIGIT NINE
86
87#
88########################################################################
89#
90# Rules moved to front to avoid masking
91#
92########################################################################
93
94
95#
96########################################################################
97#
98# BGN Page 89 Rule 4
99#
100# The character sequences كه , زه , سه , and گه may be romanized k·h, z·h,
101# s·h, and g·h in order to differentiate those romanizations from the
102# digraphs kh, zh, sh, and gh.
103#
104########################################################################
105#
106
107كه → k·h ; # ARABIC LETTER KAF + HEH
108زه → z·h ; # ARABIC LETTER ZAIN + HEH
109سه → s·h ; # ARABIC LETTER SEEN + HEH
110گه → g·h ; # ARABIC LETTER GAF + HEH
111#
112#
113########################################################################
114#
115# End Rule 4
116#
117########################################################################
118
119
120
121#
122########################################################################
123#
124# BGN Page 91 Rule 7
125#
126# Doubles consonant sounds are represented in Arabic script by
127# placing a shaddah ( ّ ) over a consonant character. In romanization
128# the letter should be doubled. [The remainder of this rule deals with
129# the definite article and is lexical.]
130#
131########################################################################
132#
133
134بّ → bb ; # ARABIC LETTER BEH + SHADDA
135پّ → pp ; # ARABIC LETTER PEH + SHADDA
136تّ → tt ; # ARABIC LETTER TEH + SHADDA
137ثّ → s̄s̄ ; # ARABIC LETTER THEH + SHADDA
138جّ → jj ; # ARABIC LETTER JEEM + SHADDA
139چّ → chch ; # ARABIC LETTER TCHEH + SHADDA
140حّ → ḥḥ ; # ARABIC LETTER HAH + SHADDA
141خّ → khkh ; # ARABIC LETTER KHAH + SHADDA
142دّ → dd ; # ARABIC LETTER DAL + SHADDA
143ذّ → z̄z̄ ; # ARABIC LETTER THAL + SHADDA
144رّ → rr ; # ARABIC LETTER REH + SHADDA
145زّ → zz ; # ARABIC LETTER ZAIN + SHADDA
146ژّ → zhzh ; # ARABIC LETTER JEH + SHADDA
147سّ → ss ; # ARABIC LETTER SEEN + SHADDA
148شّ → shsh ; # ARABIC LETTER SHEEN + SHADDA
149صّ → ṣṣ ; # ARABIC LETTER SAD + SHADDA
150ضّ → ḍḍ ; # ARABIC LETTER DAD + SHADDA
151طّ → ṭṭ ; # ARABIC LETTER TAH + SHADDA
152ظّ → ẓẓ ; # ARABIC LETTER ZAH + SHADDA
153عّ → $ayin $ayin ; # ARABIC LETTER AIN + SHADDA
154غّ → ghgh ; # ARABIC LETTER GHAIN + SHADDA
155فّ → ff ; # ARABIC LETTER FEH + SHADDA
156قّ → qq ; # ARABIC LETTER QAF + SHADDA
157كّ → kk ; # ARABIC LETTER KAF + SHADDA
158لّ → ll ; # ARABIC LETTER LAM + SHADDA
159مّ → mm ; # ARABIC LETTER MEEM + SHADDA
160نّ → nn ; # ARABIC LETTER NOON + SHADDA
161هّ → hh ; # ARABIC LETTER HEH + SHADDA
162وّ → ww ; # ARABIC LETTER WAW + SHADDA
163یّ → yy ; # ARABIC LETTER FARSI YEH + SHADDA
164#
165#
166########################################################################
167#
168# End Rule 7
169#
170########################################################################
171
172
173
174#
175########################################################################
176#
177# Start of Transformations
178#
179########################################################################
180#
181
182$wordBoundary{ء →  ; # ARABIC LETTER HAMZA
183ء → $alef ; # ARABIC LETTER HAMZA
184$wordBoundary{ا →  ; # ARABIC LETTER ALEF
185آ → $alef ā ; # ARABIC FATHA ALEF WITH MADDA ABOVE
186ب → b ; # ARABIC LETTER BEH
187پ → p ; # ARABIC LETTER PEH
188ت → t ; # ARABIC LETTER TEH
189ة → h ; # ARABIC LETTER TEH MARBUTA
190ث → s̄ ; # ARABIC LETTER THEH
191ج → j ; # ARABIC LETTER JEEM
192چ → ch ; # ARABIC LETTER TCHEH
193ح → ḥ ; # ARABIC LETTER HAH
194خ → kh ; # ARABIC LETTER KHAH
195د → d ; # ARABIC LETTER DAL
196ذ → z̄ ; # ARABIC LETTER THAL
197ر → r ; # ARABIC LETTER REH
198ز → z ; # ARABIC LETTER ZAIN
199ژ → zh ; # ARABIC LETTER JEH
200س → s ; # ARABIC LETTER SEEN
201ش → sh ; # ARABIC LETTER SHEEN
202ص → ṣ ; # ARABIC LETTER SAD
203ض → ẕ ; # ARABIC LETTER DAD
204ط → ṭ ; # ARABIC LETTER TAH
205ظ → ẓ ; # ARABIC LETTER ZAH
206ع → $ayin ; # ARABIC LETTER AIN
207غ → gh ; # ARABIC LETTER GHAIN
208ف → f ; # ARABIC LETTER FEH
209ق → q ; # ARABIC LETTER QAF
210ک ↔ k ; # ARABIC LETTER KEHEH
211ك ↔ k $disambig ; # ARABIC LETTER KAF
212گ → g ; # ARABIC LETTER GAF
213ل → l ; # ARABIC LETTER LAM
214م → m ; # ARABIC LETTER MEEM
215ن → n ; # ARABIC LETTER NOON
216ه → h ; # ARABIC LETTER HEH
217و → v ; # ARABIC LETTER WAW
218ی → y ; # ARABIC LETTER FARSI YEH
219
220َا → ā ; # ARABIC FATHA + ALEF
221َی → á ; # ARABIC FATHA + FARSI YEH
222َوْ → ow ; # ARABIC FATHA + WAW + SUKUN
223َ → a ; # ARABIC FATHA
224
225ِي → ī ; # ARABIC KASRA + YEH
226ِ → e ; # ARABIC KASRA
227
228ُو → ū ; # ARABIC DAMMA + WAW
229ُ → o ; # ARABIC DAMMA
230
231ْ →  ; # ARABIC SUKUN
232::NFC (NFD) ;
233
234#
235#
236########################################################################
237
238			]]></tRule>
239		</transform>
240	</transforms>
241</supplementalData>
242