tok.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/>.


source cyrillic_alphabet.foma
source latin_alphabet.foma

define VowelLetter  LVowelLetter | CVowelLetter ;
define ConsonantLetter  LConsonantLetter | CConsonantLetter ;
define ucLetter  ucLLetter | ucCLetter ;
define lcLetter  lcLLetter | lcCLetter ;

define Letter VowelLetter | ConsonantLetter ; 

define Word [Letter+] ; 

define vocalicR [R | r | Р | р ];
define LetterSequence ConsonantLetter+ - [ConsonantLetter+ vocalicR ConsonantLetter+] -[В|в|V|v];
#  The word B must not be named as a letter. However, its Latin equivalent, follwoed by a dot, is an abbev. ...

define NZDigit 1|2|3|4|5|6|7|8|9;
define Digit %0|NZDigit;

define FormattedNumber NZDigit Digit^<3 [%. Digit^3]^{1,4} ; 
define Decimal  FormattedNumber %, Digit+;  # 0.1 2.0000
# foreign decimal of form 0.12, 0.1234 ...  but NOT 01.23
define ForeignDecimal  [[NZDigit Digit*] | %0] %. [Digit^{1,2} | Digit^>3];  # 0.1 2.0000

source romans.foma
source ordinals.foma
source abbrevs.foma 

define BasicTokenizer 
Abbreviation @-> ... word || _   \[Letter|num|%.] | [ %. [\num|.#.]] | .#. ,,  
Word @-> ... word || _   \[Letter|num|%.] | [ %. [\num|.#.]] | .#. ,,  # Roman Number might have been here first, so do not mess with labelled Num
[FormattedNumber (OrdSuffix)] @-> ... num || _ [.#. | \[Digit|Letter]]   ,, 
Decimal  @-> ... num || _ .#. | \Digit ,, 
ForeignDecimal  @-> ... num || _ .#. | \Digit ,, 
NZDigit Digit* OrdSuffix @-> ... num || _ [.#. | \[Digit|Letter]]   ,, 
NZDigit Digit* @-> ... num  ,, 
%0 Digit+ @-> ... dig ,, 
%0 @-> ... num ,, 
\[Letter | Digit | num] @-> ... sym  || _ [\num | .#.]   # again, protect Roman Numerals like V. with a dot 
; 


define UntagLargeNumbers 
num -> dig || Digit^16 _ ; 

define CamelCase 
ucLetter lcLetter* @-> ...word || [.#.|word|num|dig|sym] _ ucLetter lcLetter ; 

source acronyms.foma

define TagLetterSequences 
word -> lseq || [.#.|word|num|dig|sym] [Acronym | LetterSequence] _ ; 

define TagLetterSequenceAbbreviations 
lseq -> word || [.#.|word|lseq|num|dig|sym] Abbreviation _ ; 

# retrieve decimals
define DecimalNumbers  
[num %, sym] -> %,  || .#. Digit+  _ Digit+ num .#. ;  # pass 12,34 as a number



define GeneralTokenizer 
[[\eos]+ (eos)] .o. # Define what we expect as input, so the priority union works properly
[ eos -> 0 || _ ] .o. 
[ RomanNumeral @-> ... num || .#. _ .#.  .o.  BasicTokenizer ] 
 .o. 
DecimalNumbers  .o.
CamelCase .o.
TagLetterSequences .o. 
TagLetterSequenceAbbreviations .o. 
UntagLargeNumbers 
; 

define SingleLetterException Letter [eos : lseq] ; 
define Exception SingleLetterException ; 

define Tokenizer Exception .P. GeneralTokenizer ; 

define TokenTypeTag num|dig|sym|word|lseq ; 
define TokenOfType(tag) [[[\[eos | TokenTypeTag]]+ (eos)] .o. Tokenizer .o. [[\TokenTypeTag]+ [tag:0]]].l ;
define NumberToken TokenOfType(num);
define WordToken TokenOfType(word);
define LSeqToken TokenOfType(lseq);

regex Tokenizer ;