| Index: source/data/translit/fa_fa_Latn_BGN.txt
|
| diff --git a/source/data/translit/Persian_Latin_BGN.txt b/source/data/translit/fa_fa_Latn_BGN.txt
|
| similarity index 63%
|
| rename from source/data/translit/Persian_Latin_BGN.txt
|
| rename to source/data/translit/fa_fa_Latn_BGN.txt
|
| index 6082a862d551128b2bb8575c38560f799d09f400..0fd2d1181ea9fcabe1e8084e39403e77023b328c 100644
|
| --- a/source/data/translit/Persian_Latin_BGN.txt
|
| +++ b/source/data/translit/fa_fa_Latn_BGN.txt
|
| @@ -1,22 +1,53 @@
|
| -# ***************************************************************************
|
| -# *
|
| -# * Copyright (C) 2004-2015, International Business Machines
|
| -# * Corporation; Unicode, Inc.; and others. All Rights Reserved.
|
| -# *
|
| -# ***************************************************************************
|
| -# File: Persian_Latin_BGN.txt
|
| -# Generated from CLDR
|
| +# © 2016 and later: Unicode, Inc. and others.
|
| +# License & terms of use: http://www.unicode.org/copyright.html#License
|
| +#
|
| +# File: fa_fa_Latn_BGN.txt
|
| +# Generated from CLDR
|
| +#
|
| +
|
| +#
|
| +########################################################################
|
| +# BGN/PCGN 1956 System
|
| +#
|
| +# This system was adopted by the BGN in 1946 and by the PCGN in 1958.
|
| +# It is used for the romanization of geographic names in Iran and
|
| +# for Persian-language names in Afghanistan.
|
| +#
|
| +# Originally prepared by Michael Everson <everson@evertype.com>
|
| +########################################################################
|
| +#
|
| +# MINIMAL FILTER: Persian-Latin
|
| #
|
| :: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویي\u064E\u064F\u0650\u0651\u0652٠١٢٣٤٥٦٧٨٩پچژگی]] ;
|
| :: NFKD (NFC) ;
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# Define All Transformation Variables
|
| +#
|
| +########################################################################
|
| +#
|
| $alef = ’;
|
| $ayin = ‘;
|
| $disambig = \u0331 ;
|
| +#
|
| +#
|
| +# 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:]] ;
|
| +#
|
| +#
|
| +########################################################################
|
| +# non-letters
|
| [:Nd:]{٫}[:Nd:] ↔ [:Nd:]{','}[:Nd:] ; # ARABIC DECIMAL SEPARATOR
|
| [:Nd:]{٬}[:Nd:] ↔ [:Nd:]{'.'}[:Nd:] ; # ARABIC THOUSANDS SEPARATOR
|
| ٫ ↔ ',' $disambig ; # ARABIC DECIMAL SEPARATOR
|
| ٬ ↔ '.' $disambig ; # ARABIC THOUSANDS SEPARATOR
|
| +# ٭ ↔ ; # ARABIC FIVE POINTED STAR // no need to transliterate
|
| ، ↔ ',' ; # ARABIC COMMA
|
| ؛ ↔ ';' ; # ARABIC SEMICOLON
|
| ؟ ↔ '?' ; # ARABIC QUESTION MARK
|
| @@ -41,10 +72,46 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| ۷ ↔ 7 ; # EXTENDED ARABIC-INDIC DIGIT SEVEN
|
| ۸ ↔ 8 ; # EXTENDED ARABIC-INDIC DIGIT EIGHT
|
| ۹ ↔ 9 ; # EXTENDED ARABIC-INDIC DIGIT NINE
|
| +#
|
| +########################################################################
|
| +#
|
| +# Rules moved to front to avoid masking
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 89 Rule 4
|
| +#
|
| +# The character sequences كه , زه , سه , and گه may be romanized k·h, z·h,
|
| +# s·h, and g·h in order to differentiate those romanizations from the
|
| +# digraphs kh, zh, sh, and gh.
|
| +#
|
| +########################################################################
|
| +#
|
| كه → k·h ; # ARABIC LETTER KAF + HEH
|
| زه → z·h ; # ARABIC LETTER ZAIN + HEH
|
| سه → s·h ; # ARABIC LETTER SEEN + HEH
|
| گه → g·h ; # ARABIC LETTER GAF + HEH
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 4
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# BGN Page 91 Rule 7
|
| +#
|
| +# Doubles consonant sounds are represented in Arabic script by
|
| +# placing a shaddah ( \u0651 ) over a consonant character. In romanization
|
| +# the letter should be doubled. [The remainder of this rule deals with
|
| +# the definite article and is lexical.]
|
| +#
|
| +########################################################################
|
| +#
|
| ب\u0651 → bb ; # ARABIC LETTER BEH + SHADDA
|
| پ\u0651 → pp ; # ARABIC LETTER PEH + SHADDA
|
| ت\u0651 → tt ; # ARABIC LETTER TEH + SHADDA
|
| @@ -75,6 +142,20 @@ $wordBoundary = [^[:L:][:M:][:N:]] ;
|
| ه\u0651 → hh ; # ARABIC LETTER HEH + SHADDA
|
| و\u0651 → ww ; # ARABIC LETTER WAW + SHADDA
|
| ی\u0651 → yy ; # ARABIC LETTER FARSI YEH + SHADDA
|
| +#
|
| +#
|
| +########################################################################
|
| +#
|
| +# End Rule 7
|
| +#
|
| +########################################################################
|
| +#
|
| +########################################################################
|
| +#
|
| +# Start of Transformations
|
| +#
|
| +########################################################################
|
| +#
|
| $wordBoundary{ء → ; # ARABIC LETTER HAMZA
|
| ء → $alef ; # ARABIC LETTER HAMZA
|
| $wordBoundary{ا → ; # ARABIC LETTER ALEF
|
| @@ -122,3 +203,7 @@ $wordBoundary{ا → ; # ARABIC LETTER ALEF
|
| \u064F → o ; # ARABIC DAMMA
|
| \u0652 → ; # ARABIC SUKUN
|
| ::NFC (NFD) ;
|
| +#
|
| +#
|
| +########################################################################
|
| +
|
|
|