Commit c9187f32 authored by Simon Will's avatar Simon Will
Browse files

Make scanner able to to parse verse

parent ce8dd4f5

allzweckmesser/scanner.py

+8 −30
Original line number Diff line number Diff line
@@ -9,13 +9,6 @@ from .db import FormAnalysis 
from .model import Reading, Syllable, Token, Verse, Phenomenon

from .wordlist import WordList



verses = [

    'nunc dum tibi lubet licetque pota perde rem',

    'antehac est habitus parcus nec magis continens',

    "clamavit moriens lingua: 'Corinna, vale!'",

    'an, quod ubique, tuum est? tua sunt Heliconia Tempe?',

]



CLITICS = ['que', 'qve', 'ue', 've', 'ne']
@@ -177,9 +170,9 @@ def get_syllables_for_token(token: Token): 
    syllables = []

    if token.accented:

        regex = (

            r'((?:ua|ue|ae|oe|au|eu|yi|[aeiouy])[_^]?)'

            r'((?:ua|ui|ue|ae|oe|au|eu|yi|[aeiouy])[_^]?)'

            if token.text[0].isupper()

            else r'((?:ua|ue|ae|oe|au|[aeiouy])[_^]?)'

            else r'((?:ua|ui|ue|ae|oe|au|[aeiouy])[_^]?)'

        )

        accented = (token.accented + token.clitic

                    if token.clitic
@@ -228,15 +221,13 @@ def get_syllables_for_token(token: Token): 
                            syllable_length=syll_vowel_length)

            syllables.append(syll)

    else:

        syllables = None

        syllables = []

    return syllables





def get_syllables(reading):

    for token in reading.tokens:

        token.syllables = get_syllables_for_token(token)

    # TODO: Add positional_lengthening phenomena and adjust syllable

    # lengths accordingly.

    return reading
@@ -275,7 +266,6 @@ def parse_verse(verse): 
    """Annotates syllable lengths based on positional_lengthening and muta cum liquida 

    

    """

    

    positional_lengthening(verse)

    

    muta_cum_liquida(verse)
@@ -328,23 +318,8 @@ def parse_verse(verse): 
        else:

            new_readings.append(copy.deepcopy(reading))

             

        return new_readings

            



        #for reading in verse.readings:

            #for token in reading.tokens:

                #for syllable in token.syllables:



                    #if "muta cum liquida" in syllable.phenomena:

                        

                        #old_reading = copy.deepcopy(reading)

                        #all_readings_parsed = False

                        

                        #if syllable_length == 1:

                            

                        #elif syllable_length == 2:

                        

                    

        verse.readings = new_readings

        return verse





class Scanner:
@@ -353,6 +328,8 @@ class Scanner: 
        self.word_list = WordList()



    def scan_verses(self, plain_verses: List[str]):

        import pdb

        pdb.set_trace()

        base_readings = [Reading(tokens=tokenize(v)) for v in plain_verses]

        verses = [

            Verse(verse=v, readings=lemmatize(self.word_list, br))
@@ -361,4 +338,5 @@ class Scanner: 
        for verse in verses:

            for reading in verse.readings:

                get_syllables(reading)

            parse_verse(verse)

        return verses