pg2p.foma

# Copyright (C) 2023 Darko Milosevic  <daremc86@gmail.com>

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, version 3.0 of the License.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.

# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

define PB %- | .#. ; 

# # will separate the words in the same phrase.
define WB %# | PB ; 

define StressVowel 
a0 : a1 | e0 : e1 | ii0 : ii1 | o0 : o1 | u0 : u1 | i0 : i1 | ax0 : ax1 ; 

define Vowel StressVowel.u | StressVowel.l ; 

define fixVowelLetters 
StressVowel -> || PB _ PB ; 

define FixV 
v -> ... ax1 || PB _ PB ; 

define StressSingleMonosyllabicWord 
s e0 @-> ... || PB _ PB ,, 
StressVowel @-> || PB [\[Vowel | %#]]* _ [\[Vowel | %#]]* PB ; 

# Voiced/unvoiced pairs
define VUPair 
b:p|g:k|dj:tj|d:t|dzh:tsh|zh:sh|z:s|v:f;

#Voiced obstruents, extracting the domain of the pair fst.
define VObs VUPair.u;

#Voiceless obstruents, extracting the range of the pair fst.
define UObs VUPair.l | h;

define Obs VObs | UObs ; 

# Unvoiced become voiced before these.
define VContext VObs - v ; 

define ObsSeq Obs [[%#]* Obs]* ; 

define Voicing ObsSeq .o. [VUPair.i ->] ; 

define Assimilation 
Voicing [%#]* VContext @-> || _  ; 

define Rules 
fixVowelLetters 
.o. FixV 
.o.  StressSingleMonosyllabicWord 
.o. Assimilation 
 ; 

regex Rules ;