Index: source/data/translit/ps_ps_Latn_BGN.txt |
diff --git a/source/data/translit/Pashto_Latin_BGN.txt b/source/data/translit/ps_ps_Latn_BGN.txt |
similarity index 68% |
rename from source/data/translit/Pashto_Latin_BGN.txt |
rename to source/data/translit/ps_ps_Latn_BGN.txt |
index f6c0d2fddcf0ea37c323f766c9236cee120656ef..90f48df9ef7f6bc901240d0317e9eeef61ce5609 100644 |
--- a/source/data/translit/Pashto_Latin_BGN.txt |
+++ b/source/data/translit/ps_ps_Latn_BGN.txt |
@@ -1,22 +1,53 @@ |
-# *************************************************************************** |
-# * |
-# * Copyright (C) 2004-2015, International Business Machines |
-# * Corporation; Unicode, Inc.; and others. All Rights Reserved. |
-# * |
-# *************************************************************************** |
-# File: Pashto_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: ps_ps_Latn_BGN.txt |
+# Generated from CLDR |
+# |
+ |
+# |
+######################################################################## |
+# BGN/PCGN 1968 System |
+# |
+# This system was adopted in 1968 for the romanization of Pashto |
+# geographic names in Afghanistan. Persian names in Afghanistan are |
+# romanized in accordance with the Romanization System for Persian |
+# (BGN/PCGN 1958 System), shown on pages 87-92). |
+# |
+# Originally prepared by Michael Everson <everson@evertype.com> |
+######################################################################## |
+# |
+# MINIMAL FILTER: Pashto-Latin |
# |
:: [ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىي\u064E\u064F\u0650\u0651\u0652\u0654٠١٢٣٤٥٦٧٨٩ټپځڅچډړږژښگڰڼیۍې] ; |
:: NFD (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:]] ; |
+# |
+# |
+######################################################################## |
[: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 |
@@ -86,6 +153,20 @@ $wordBoundary = [^[:L:][:M:][:N:]] ; |
و\u0651 → ww ; # ARABIC LETTER WAW + SHADDA |
\u0651ی → yy ; # ARABIC LETTER FARSI YEH + SHADDA |
ى\u0651 → yy ; # ARABIC LETTER YEH + SHADDA |
+# |
+# |
+######################################################################## |
+# |
+# End Rule 7 |
+# |
+######################################################################## |
+# |
+######################################################################## |
+# |
+# Start of Transformations |
+# |
+######################################################################## |
+# |
$wordBoundary{ء → ; # ARABIC LETTER HAMZA |
ء → $alef ; # ARABIC LETTER HAMZA |
$wordBoundary{ا → ; # ARABIC LETTER ALEF |
@@ -135,7 +216,7 @@ $wordBoundary{ا → ; # ARABIC LETTER ALEF |
ى → y ; # ARABIC LETTER YEH |
ې → e ; # ARABIC LETTER E |
\u064Eا → ā ; # ARABIC FATHA + ALEF |
-\u064Eى\u0652 → ay ; # ARABIC FATHA + FARSI YEH + SUKUN |
+\u064Eى\u0652 → ay ; # ARABIC FATHA + FARSI YEH + SUKUN |
\u064Eى → á ; # ARABIC FATHA + ALEF MAKSURA |
\u064E\u0652ۍ → êy ; # ARABIC FATHA + SUKUN + YEH WITH TAIL |
\u064E\u0652 → ê ; # ARABIC FATHA + SUKUN |
@@ -150,3 +231,7 @@ $wordBoundary{ا → ; # ARABIC LETTER ALEF |
\u064Fو → ū ; # ARABIC DAMMA + WAW |
\u064F → u ; # ARABIC DAMMA |
\u0652 → ; # ARABIC SUKUN |
+# |
+# |
+######################################################################## |
+ |