icu4c/source/data/translit/pl_pl_FONIPA.txt

# © 2016 and later: Unicode, Inc. and others.
# License & terms of use: http://www.unicode.org/copyright.html
# Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
#
# File: pl_pl_FONIPA.txt
# Generated from CLDR
#

# 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 → ɔ\u0303 ;
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 → ɛ\u0303;
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 } $voiceless → ʂ ;
ż → ʐ ;
#
#
# Second pass: Phoneme-to-phone rules.
:: Null ;
#
#
tʐ → tʂ ;
pʐ → pʂ ;
xʐ → xʂ ;
ʐt\u0361ʂ → ʂt\u0361ʂ ;
#
#
# Final de-voicing.
b } [$] → p ;
d \u0361 z } [$] → t \u0361 s ;  # rydz → rɨt\u0361s
d } [$] → t ;
ɡ } [$] → k ;
v } [$] → f ;
ʐ } [$] → ʂ ;
ʑ } [$] → ɕ ;
z } [$] → s ;