|
|
<?xml version="1.0" encoding="UTF-8" ?>
|
|
|
<!DOCTYPE supplementalData SYSTEM "../../common/dtd/ldmlSupplemental.dtd">
|
|
|
<!--
|
|
|
Copyright © 1991-2013 Unicode, Inc.
|
|
|
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
|
|
|
For terms of use, see http://www.unicode.org/copyright.html
|
|
|
-->
|
|
|
<supplementalData>
|
|
|
<version number="$Revision$"/>
|
|
|
<transforms>
|
|
|
<transform source="dv" target="dv_Latn" variant="BGN" direction="forward" draft="contributed" alias="Maldivian-Latin/BGN dv-Latn-t-dv-m0-bgn">
|
|
|
<tRule><![CDATA[
|
|
|
# BGN/PCGN 1988 Agreement, with modifications 2009
|
|
|
#
|
|
|
# This romanization system supersedes the one which was approved by
|
|
|
# the BGN and the PCGN in 1972. This official system was submitted
|
|
|
# to the PCGN by the Maldivian government in 1987 and approved by BGN
|
|
|
# and PCGN in 1988. The system presented here reflects the 1988 Agreement
|
|
|
# with minor modifications introduced by the government of the Maldives
|
|
|
# in 2009.
|
|
|
#
|
|
|
# In our rules, we also convert Arabic punctuation characters to Latin.
|
|
|
# These appears to be used in Maldivian text, for example in the Universal
|
|
|
# Declaration of Human Rights.
|
|
|
|
|
|
::[[:block=thaana:][،؛؟٪٫٬]\uFDF2] ;
|
|
|
::NFD;
|
|
|
|
|
|
$wordBoundary = [^[:L:][:M:][:N:]] ;
|
|
|
$vowel = [\u07A6-\u07AF] ;
|
|
|
$sukun = \u07B0 ;
|
|
|
$sign = [$sukun $vowel] ;
|
|
|
$rule4 = [އށ] $sukun ; # see note 4
|
|
|
|
|
|
### Consonants
|
|
|
# HAA
|
|
|
$rule4 ހ → hh ;
|
|
|
ހ → h ;
|
|
|
|
|
|
# NOONU
|
|
|
# See note 5: "romanized n’ when appearing without any vowel or auxiliary sign"
|
|
|
$rule4 ނ } $sign → nn ;
|
|
|
$rule4 ނ → nn\' ;
|
|
|
ނ } $sign → n ;
|
|
|
ނ → n\' ;
|
|
|
|
|
|
# RAA
|
|
|
$rule4 ރ → rr ;
|
|
|
ރ → r ;
|
|
|
|
|
|
# BAA
|
|
|
$rule4 ބ → bb ;
|
|
|
ބ → b ;
|
|
|
|
|
|
# LHAVIYANI
|
|
|
$rule4 ޅ → hlh ;
|
|
|
ޅ → lh;
|
|
|
|
|
|
# KAAFU
|
|
|
$rule4 ކ → kk ;
|
|
|
ކ → k ;
|
|
|
|
|
|
# VAAVU
|
|
|
$rule4 ވ → vv ;
|
|
|
ވ → v ;
|
|
|
|
|
|
# MEEMU
|
|
|
$rule4 މ → mm ;
|
|
|
މ → m ;
|
|
|
|
|
|
# FAAFU
|
|
|
$rule4 ފ → ff ;
|
|
|
ފ → f;
|
|
|
|
|
|
# DHAALU
|
|
|
$rule4 ދ → hdh ;
|
|
|
ދ → dh;
|
|
|
|
|
|
# THAA
|
|
|
# See note 6: "romanized iy when appearing in combination with a supercircle"
|
|
|
$rule4 ތ $sukun → hiy ;
|
|
|
$rule4 ތ → hth ;
|
|
|
ި ތ $sukun → iy ;
|
|
|
ތ $sukun → iy ;
|
|
|
ތ → th ;
|
|
|
|
|
|
# LAAMU
|
|
|
$rule4 ލ → ll ;
|
|
|
ލ → l ;
|
|
|
|
|
|
# GAAFU
|
|
|
$rule4 ގ → gg ;
|
|
|
ގ → g ;
|
|
|
|
|
|
# GNAVIYANI
|
|
|
$rule4 ޏ → hgn ;
|
|
|
ޏ → gn ;
|
|
|
|
|
|
# SEENU
|
|
|
$rule4 ސ → ss ;
|
|
|
ސ → s ;
|
|
|
|
|
|
# DAVIYANI
|
|
|
$rule4 ޑ → dd ;
|
|
|
ޑ → d ;
|
|
|
|
|
|
# ZAVIYANI
|
|
|
$rule4 ޒ → zz ;
|
|
|
ޒ → z ;
|
|
|
|
|
|
# TAVIYANI
|
|
|
$rule4 ޓ → tt ;
|
|
|
ޓ → t ;
|
|
|
|
|
|
# YAA
|
|
|
$rule4 ޔ → yy ;
|
|
|
ޔ → y ;
|
|
|
|
|
|
# PAVIYANI
|
|
|
$rule4 ޕ → pp ;
|
|
|
ޕ → p ;
|
|
|
|
|
|
# JAVIYANI
|
|
|
$rule4 ޖ → jj ;
|
|
|
ޖ → j ;
|
|
|
|
|
|
# CHAVIYANI
|
|
|
$rule4 ޗ → hch ;
|
|
|
ޗ → ch ;
|
|
|
|
|
|
### Borrowed Consonants (See Rule 7)
|
|
|
# SAADHU
|
|
|
$rule4 ޞ → şş ;
|
|
|
ޞ → ş ;
|
|
|
|
|
|
# SHEENU
|
|
|
$rule4 ޝ → hsh ;
|
|
|
ޝ → sh ;
|
|
|
|
|
|
# ZAA
|
|
|
$rule4 ޜ → zz ;
|
|
|
ޜ → z;
|
|
|
|
|
|
# KHAA
|
|
|
$rule4 ޚ → hkh ;
|
|
|
ޚ → kh;
|
|
|
|
|
|
# HHAA
|
|
|
$rule4 ޙ → ḩḩ ;
|
|
|
ޙ → ḩ ;
|
|
|
|
|
|
# THAALU
|
|
|
$rule4 ޛ → hdh ;
|
|
|
ޛ → dh ;
|
|
|
|
|
|
# TTAA
|
|
|
$rule4 ޘ → hth ;
|
|
|
ޘ → th ;
|
|
|
|
|
|
# WAAVU
|
|
|
$rule4 ޥ → ww ;
|
|
|
ޥ → w ;
|
|
|
|
|
|
# QAAFU
|
|
|
$rule4 ޤ → qq ;
|
|
|
ޤ → q ;
|
|
|
|
|
|
# GHAINU
|
|
|
$rule4 ޣ → hgh ;
|
|
|
ޣ → gh ;
|
|
|
|
|
|
# AINU
|
|
|
$rule4 ޢ → \'\' ;
|
|
|
ޢ → \' ;
|
|
|
|
|
|
# ZO
|
|
|
$rule4 ޡ → z̧z̧ ;
|
|
|
ޡ → z̧ ;
|
|
|
|
|
|
# TO
|
|
|
$rule4 ޠ → ţţ ;
|
|
|
ޠ → ţ ;
|
|
|
|
|
|
# DAADHU
|
|
|
$rule4 ޟ → ḑḑ ;
|
|
|
ޟ → ḑ ;
|
|
|
|
|
|
# NOTE: not in Maldivian BGN system, but for completeness of Thaana block
|
|
|
# NAA
|
|
|
$rule4 ޱ → n̲n̲ ;
|
|
|
ޱ → n̲ ;
|
|
|
|
|
|
# Rule 4 in word-final position
|
|
|
$rule4 } $wordBoundary → h;
|
|
|
|
|
|
# SHAVIYANI (placed last to avoid masking)
|
|
|
$rule4 ށ → hsh;
|
|
|
ށ → sh;
|
|
|
|
|
|
# Otherwise, these signs are not romanized elsewhere
|
|
|
$rule4 → ;
|
|
|
ް → ;
|
|
|
އ → ;
|
|
|
|
|
|
# NOTE: not in Maldivian BGN system, but common in names (e.g. Abdullah)
|
|
|
($vowel) \uFDF2 → | $1 llāh ;
|
|
|
\uFDF2 → allāh;
|
|
|
|
|
|
### Vowels
|
|
|
ަ → a; # ABAFILI
|
|
|
ާ → aa; # AABAAFILI
|
|
|
ެ → e; # EBEFILI
|
|
|
ޭ → ey; # EYBEYFILI
|
|
|
ި → i; # IBIFILI
|
|
|
ީ → ee; # EEBEEFILI
|
|
|
ޮ → o; # OBOFILI
|
|
|
ޯ → oa; # OABOAFILI
|
|
|
ު → u; # UBUFILI
|
|
|
ޫ → oo; # OOBOOFILI
|
|
|
|
|
|
، → ','; # U+060C ARABIC COMMA
|
|
|
؛ → ';'; # U+061B ARABIC SEMICOLON
|
|
|
؟ → '?'; # U+061F ARABIC QUESTION MARK
|
|
|
٪ → '%'; # U+066A ARABIC PERCENT SIGN
|
|
|
٫ → '.'; # U+066B ARABIC DECIMAL SEPARATOR
|
|
|
٬ → ','; # U+066C ARABIC THOUSANDS SEPARATOR
|
|
|
]]></tRule>
|
|
|
</transform>
|
|
|
</transforms>
|
|
|
</supplementalData>
|
