148 lines
2.4 KiB
XML
148 lines
2.4 KiB
XML
|
<?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="ro" target="ro_FONIPA" direction="forward" alias="ro-fonipa-t-ro">
|
|||
|
|
<tRule><![CDATA[
|
|||
|
|
# Romanian orthography to phonemic transcription.
|
|||
|
|
# http://en.wikipedia.org/wiki/Romanian_phonology
|
|||
|
|
#
|
|||
|
|
# TODO: Currently this transform does not palatalize consonants.
|
|||
|
|
|
|||
|
|
$VowelEI = [e i î];
|
|||
|
|
$VowelAOU = [a â ă o u];
|
|||
|
|
$Vowel = [$VowelEI $VowelAOU];
|
|||
|
|
$Boundary = [^[:L:][:M:][:N:]];
|
|||
|
|
|
|||
|
|
:: NFC () ;
|
|||
|
|
:: Lower () ;
|
|||
|
|
|
|||
|
|
# Special cases.
|
|||
|
|
eoai → eo̯aj ; # eg. leoaică → /leo̯ajkə/, not /le̯o̯aikə/
|
|||
|
|
|
|||
|
|
# Triphthongs.
|
|||
|
|
eai → e̯aj ;
|
|||
|
|
eau → e̯aw ;
|
|||
|
|
eoa → e̯o̯a ;
|
|||
|
|
i\-ai → jaj ;
|
|||
|
|
ia\-i → jaj ;
|
|||
|
|
iau → jaw ;
|
|||
|
|
iei → jej ;
|
|||
|
|
ieu → jew ;
|
|||
|
|
$Boundary {eu} → jew ;
|
|||
|
|
ioa → jo̯a ;
|
|||
|
|
ioi → joj ;
|
|||
|
|
i\-oi → joj ;
|
|||
|
|
iou → jow ;
|
|||
|
|
oai → o̯aj ;
|
|||
|
|
uai → waj ;
|
|||
|
|
uau → waw ;
|
|||
|
|
uăi → wəj ;
|
|||
|
|
|
|||
|
|
# Diphthongs.
|
|||
|
|
ai → aj ;
|
|||
|
|
âi → ɨj ;
|
|||
|
|
ăi → əj ;
|
|||
|
|
au} r → au ;
|
|||
|
|
au → aw ;
|
|||
|
|
âu → ɨw ;
|
|||
|
|
ău → əw ;
|
|||
|
|
ea → e̯a ;
|
|||
|
|
ei → ej ;
|
|||
|
|
eo → e̯o ;
|
|||
|
|
e\-o → e̯o ;
|
|||
|
|
eu → ew ;
|
|||
|
|
e\-u → e̯u ;
|
|||
|
|
ia → ja ;
|
|||
|
|
i\-a → ja ;
|
|||
|
|
ie → je ;
|
|||
|
|
ii → ij ;
|
|||
|
|
io → jo ;
|
|||
|
|
iu} [$Vowel $Boundary] → iw ;
|
|||
|
|
iu → ju ;
|
|||
|
|
oa → o̯a ;
|
|||
|
|
oi → oj ;
|
|||
|
|
ou → ow ;
|
|||
|
|
ua → wa ;
|
|||
|
|
uâ → wɨ ;
|
|||
|
|
uă → wə ;
|
|||
|
|
ue → we ;
|
|||
|
|
ui → uj ;
|
|||
|
|
uu → uw ;
|
|||
|
|
|
|||
|
|
a → a ;
|
|||
|
|
â → ɨ ;
|
|||
|
|
ă → ə ;
|
|||
|
|
b → b ;
|
|||
|
|
ch → k ;
|
|||
|
|
{c} [ei] → t͡ʃ ;
|
|||
|
|
c → k ;
|
|||
|
|
d → d ;
|
|||
|
|
e → e ;
|
|||
|
|
f → f ;
|
|||
|
|
gh → ɡ ;
|
|||
|
|
{g} [ei] → d͡ʒ ;
|
|||
|
|
g → ɡ ;
|
|||
|
|
h → h ;
|
|||
|
|
i → i ;
|
|||
|
|
î → ɨ ;
|
|||
|
|
j → ʒ ;
|
|||
|
|
k → k ;
|
|||
|
|
l → l ;
|
|||
|
|
m → m ;
|
|||
|
|
ng → ŋ ;
|
|||
|
|
n → n ;
|
|||
|
|
o → o ;
|
|||
|
|
p → p ;
|
|||
|
|
q → k ;
|
|||
|
|
r → r ;
|
|||
|
|
s → s ;
|
|||
|
|
ş → ʃ ;
|
|||
|
|
ș → ʃ ;
|
|||
|
|
t → t ;
|
|||
|
|
ţ → t͡s ;
|
|||
|
|
ț → t͡s ;
|
|||
|
|
u → u ;
|
|||
|
|
v → v ;
|
|||
|
|
x → ks ;
|
|||
|
|
y → i ;
|
|||
|
|
z → z ;
|
|||
|
|
[:P:]+ → ' ';
|
|||
|
|
|
|||
|
|
# Romanian does not have any gemination.
|
|||
|
|
# https://en.wikipedia.org/wiki/Gemination#Latin_and_Romance_languages
|
|||
|
|
::null;
|
|||
|
|
pp+ → p;
|
|||
|
|
bb+ → b;
|
|||
|
|
tt+ → t;
|
|||
|
|
dd+ → d;
|
|||
|
|
kk+ → k;
|
|||
|
|
dd+ → d;
|
|||
|
|
ɡɡ+ → ɡ;
|
|||
|
|
|
|||
|
|
ff+ → f;
|
|||
|
|
vv+ → v;
|
|||
|
|
hh+ → h;
|
|||
|
|
|
|||
|
|
ss+ → s;
|
|||
|
|
zz+ → z;
|
|||
|
|
ʃʃ+ → ʃ;
|
|||
|
|
ʒʒ+ → ʒ;
|
|||
|
|
|
|||
|
|
rr+ → r;
|
|||
|
|
ll+ → l;
|
|||
|
|
|
|||
|
|
jj+ → j;
|
|||
|
|
ww+ → w;
|
|||
|
|
|
|||
|
|
]]></tRule>
|
|||
|
|
</transform>
|
|||
|
|
</transforms>
|
|||
|
|
</supplementalData>
|