larvitgeodata
Version:
Geo data, primarily ISO territories, languages etc. Data fetched mostly from CLDR.
137 lines (136 loc) • 4.3 kB
text/xml
<!--
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: 11914 $"/>
<transforms>
<transform source="pl" target="pl_FONIPA" direction="forward">
<comment>
# Copyright (C) 2010 Google, Inc. All Rights Reserved.
# Author: sascha@google.com (Sascha Brawer)
#
# Polish orthography to phonemic transcription.
# http://en.wikipedia.org/wiki/Polish_phonology
#
# Transform input to normalized form NFC, and to lowercase.
</comment>
<tRule>:: NFC () ;</tRule>
<tRule>:: Lower () ;</tRule>
<comment>
#
# Definitions.
</comment>
<tRule>$voiceless = [cfhkpst];</tRule>
<tRule>$vowel = [ aąeęioóuy ];</tRule>
<comment>
#
# Digraphs and Trigraphs.
#
</comment>
<tRule>ch } i → ç ;</tRule>
<tRule>ch → x ;</tRule>
<tRule>ci } $vowel → t \u0361 ɕ ;</tRule>
<tRule>ci → t \u0361 ɕ i ;</tRule>
<tRule>cz → t \u0361 ʂ ;</tRule>
<tRule>dzi } $vowel → d \u0361 ʑ ;</tRule>
<tRule>dzi → d \u0361 ʑ i ;</tRule>
<tRule>dz } $voiceless → t \u0361 s ;</tRule>
<tRule>dz → d \u0361 z ;</tRule>
<tRule>dź } $voiceless → t \u0361 ɕ ;</tRule>
<tRule>dź → d \u0361 ʑ ;</tRule>
<tRule>dż } $voiceless → t \u0361 ʂ ;</tRule>
<tRule>dż → d \u0361 ʐ ;</tRule>
<tRule>kw → kf ;</tRule>
<tRule>krw → krf ;</tRule>
<tRule>ni } $vowel → ɲ ;</tRule>
<tRule>ni → ɲ i ;</tRule>
<tRule>$voiceless { rz → ʂ ;</tRule>
<tRule>rz } $voiceless → ʂ ;</tRule>
<tRule>rz → ʐ ;</tRule>
<tRule>sz → ʂ ;</tRule>
<tRule>trw → trf ;</tRule>
<tRule>tw → tf ;</tRule>
<tRule>zi } $vowel → ʑ ;</tRule>
<tRule>zi → ʑ i ;</tRule>
<comment>
#
</comment>
<tRule>a → a ;</tRule>
<tRule>ą } [bp] → ɔm ;</tRule>
<tRule>ą } [kg] → ɔŋ ;</tRule>
<tRule>ą } [cdt] → ɔn ;</tRule>
<tRule>ą → ɔ̃ ;</tRule>
<tRule>b } $voiceless → p ;</tRule>
<tRule>b → b ;</tRule>
<tRule>c → t \u0361 s ;</tRule>
<tRule>ć → t \u0361 ɕ ;</tRule>
<tRule>d } $voiceless → t ;</tRule>
<tRule>d → d ;</tRule>
<tRule>e → ɛ ;</tRule>
<tRule>ę } [bp] → ɛm ;</tRule>
<tRule>ę } [dt] → ɛn ;</tRule>
<tRule>ę } [gk] → ɛŋ ;</tRule>
<tRule>ę → ɛ̃;</tRule>
<tRule>f → f ;</tRule>
<tRule>g } $voiceless → k ;</tRule>
<tRule>g → ɡ ;</tRule>
<tRule>h } i → ç ;</tRule>
<tRule>h → x ;</tRule>
<tRule>i } $vowel → ʲ ;</tRule>
<tRule>i → i ;</tRule>
<tRule>j → j ;</tRule>
<tRule>k } [bdzż] → ɡ ;</tRule>
<tRule>k → k ;</tRule>
<tRule>l } i → ʎ ;</tRule>
<tRule>l → l ;</tRule>
<tRule>ł → w ;</tRule>
<tRule>m → m ;</tRule>
<tRule>n → n ;</tRule>
<tRule>ń → ɲ ;</tRule>
<tRule>o → ɔ ;</tRule>
<tRule>ó → u ;</tRule>
<tRule>r → r ;</tRule>
<tRule>si } $vowel → ɕ ;</tRule>
<tRule>si → ɕi ;</tRule>
<tRule>s → s ;</tRule>
<tRule>ś → ɕ ;</tRule>
<tRule>t → t ;</tRule>
<tRule>u → u ;</tRule>
<tRule>w } $voiceless → f ;</tRule>
<tRule>w → v ;</tRule>
<tRule>y → ɨ ;</tRule>
<tRule>ź } $voiceless → ɕ ;</tRule>
<tRule>ź → ʑ ;</tRule>
<tRule>ż } $voiceless → ʂ ;</tRule>
<tRule>ż → ʐ ;</tRule>
<comment>
#
# Second pass: Phoneme-to-phone rules.
</comment>
<tRule>:: Null ;</tRule>
<comment>
#
</comment>
<tRule>tʐ → tʂ ;</tRule>
<tRule>pʐ → pʂ ;</tRule>
<tRule>xʐ → xʂ ;</tRule>
<tRule>ʐt͡ʂ → ʂt͡ʂ ;</tRule>
<comment>
#
# Final de-voicing.
</comment>
<tRule>b } [$] → p ;</tRule>
<tRule>d \u0361 z } [$] → t \u0361 s ; # rydz → rɨt͡s</tRule>
<tRule>d } [$] → t ;</tRule>
<tRule>ɡ } [$] → k ;</tRule>
<tRule>v } [$] → f ;</tRule>
<tRule>ʐ } [$] → ʂ ;</tRule>
<tRule>ʑ } [$] → ɕ ;</tRule>
<tRule>z } [$] → s ;</tRule>
</transform>
</transforms>
</supplementalData>