135 lines
2.3 KiB
XML
135 lines
2.3 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="pl" target="pl_FONIPA" direction="forward" alias="pl-fonipa-t-pl">
|
||
<tRule>
|
||
# Polish orthography to phonemic transcription.
|
||
# http://en.wikipedia.org/wiki/Polish_phonology
|
||
#
|
||
# Transform input to normalized form NFC, and to lowercase.
|
||
|
||
:: NFC () ;
|
||
:: Lower () ;
|
||
#
|
||
#
|
||
# Definitions.
|
||
|
||
$voiceless = [cfhkpst];
|
||
$vowel = [ aąeęioóuy ];
|
||
#
|
||
#
|
||
# Digraphs and Trigraphs.
|
||
#
|
||
|
||
ch } i → ç ;
|
||
ch → x ;
|
||
ci } $vowel → t \u0361 ɕ ;
|
||
ci → t \u0361 ɕ i ;
|
||
cz → t \u0361 ʂ ;
|
||
dzi } $vowel → d \u0361 ʑ ;
|
||
dzi → d \u0361 ʑ i ;
|
||
dz } $voiceless → t \u0361 s ;
|
||
dz → d \u0361 z ;
|
||
dź } $voiceless → t \u0361 ɕ ;
|
||
dź → d \u0361 ʑ ;
|
||
dż } $voiceless → t \u0361 ʂ ;
|
||
dż → d \u0361 ʐ ;
|
||
kw → kf ;
|
||
krw → krf ;
|
||
ni } $vowel → ɲ ;
|
||
ni → ɲ i ;
|
||
$voiceless { rz → ʂ ;
|
||
rz } $voiceless → ʂ ;
|
||
rz → ʐ ;
|
||
sz → ʂ ;
|
||
trw → trf ;
|
||
tw → tf ;
|
||
zi } $vowel → ʑ ;
|
||
zi → ʑ i ;
|
||
#
|
||
#
|
||
|
||
a → a ;
|
||
ą } [bp] → ɔm ;
|
||
ą } [kg] → ɔŋ ;
|
||
ą } [cdt] → ɔn ;
|
||
ą → ɔ̃ ;
|
||
b } $voiceless → p ;
|
||
b → b ;
|
||
c → t \u0361 s ;
|
||
ć → t \u0361 ɕ ;
|
||
d } $voiceless → t ;
|
||
d → d ;
|
||
e → ɛ ;
|
||
ę } [bp] → ɛm ;
|
||
ę } [dt] → ɛn ;
|
||
ę } [gk] → ɛŋ ;
|
||
ę → ɛ̃;
|
||
f → f ;
|
||
g } $voiceless → k ;
|
||
g → ɡ ;
|
||
h } i → ç ;
|
||
h → x ;
|
||
i } $vowel → ʲ ;
|
||
i → i ;
|
||
j → j ;
|
||
k } [bdzż] → ɡ ;
|
||
k → k ;
|
||
l } i → ʎ ;
|
||
l → l ;
|
||
ł → w ;
|
||
m → m ;
|
||
n → n ;
|
||
ń → ɲ ;
|
||
o → ɔ ;
|
||
ó → u ;
|
||
r → r ;
|
||
si } $vowel → ɕ ;
|
||
si → ɕi ;
|
||
s → s ;
|
||
ś → ɕ ;
|
||
t → t ;
|
||
u → u ;
|
||
w } $voiceless → f ;
|
||
w → v ;
|
||
y → ɨ ;
|
||
ź } $voiceless → ɕ ;
|
||
ź → ʑ ;
|
||
ż } $voiceless → ʂ ;
|
||
ż → ʐ ;
|
||
#
|
||
#
|
||
# Second pass: Phoneme-to-phone rules.
|
||
|
||
:: Null ;
|
||
#
|
||
#
|
||
|
||
tʐ → tʂ ;
|
||
pʐ → pʂ ;
|
||
xʐ → xʂ ;
|
||
ʐt͡ʂ → ʂt͡ʂ ;
|
||
#
|
||
#
|
||
# Final de-voicing.
|
||
|
||
b } [$] → p ;
|
||
d \u0361 z } [$] → t \u0361 s ; # rydz → rɨt͡s
|
||
d } [$] → t ;
|
||
ɡ } [$] → k ;
|
||
v } [$] → f ;
|
||
ʐ } [$] → ʂ ;
|
||
ʑ } [$] → ɕ ;
|
||
z } [$] → s ;
|
||
</tRule>
|
||
</transform>
|
||
</transforms>
|
||
</supplementalData>
|