def test_zajtso(self):
word = run_through_module(
TextPhonotypes('zajtšo',
[CONS, VOWEL, SONOR, SUBUNIT, CONS, VOWEL]))
self.assertEqual(word.get_syllables(), ['zaj', 'tšo'])
self.assertEqual(word.get_phonotypes(),
[[CONS, VOWEL, SONOR], [SUBUNIT, CONS, VOWEL]])
def test_sahac(self):
word = run_through_module(
TextPhonotypes('sahać', [CONS, VOWEL, CONS, VOWEL, CONS]))
self.assertEqual(word.get_syllables(), ['sa', 'hać'])
self.assertEqual(word.get_phonotypes(), [[
CONS,
VOWEL,
], [CONS, VOWEL, CONS]])
def test_neurcity(self):
word = run_through_module(
TextPhonotypes(
'neurčitý',
[SONOR, VOWEL, VOWEL, SONOR, CONS, VOWEL, CONS, VOWEL]))
self.assertEqual(word.get_syllables(), ['ne', 'ur', 'či', 'tý'])
self.assertEqual(
word.get_phonotypes(),
[[SONOR, VOWEL], [VOWEL, SONOR], [CONS, VOWEL], [CONS, VOWEL]])
def test_агульным(self):
word = run_through_module(
TextPhonotypes(
'агульным',
[VOWEL, CONS, VOWEL, SONOR, SPEC, SONOR, VOWEL, SONOR]))
self.assertEqual(word.get_syllables(), ['а', 'гу', 'льным'])
self.assertEqual(
word.get_phonotypes(),
[[VOWEL], [CONS, VOWEL], [SONOR, SPEC, SONOR, VOWEL, SONOR]])
def test_колькасць(self):
word = run_through_module(
TextPhonotypes(
'колькасць',
[CONS, VOWEL, SONOR, SPEC, CONS, VOWEL, CONS, CONS, SPEC]))
self.assertEqual(word.get_syllables(), ['коль', 'касць'])
self.assertEqual(
word.get_phonotypes(),
[[CONS, VOWEL, SONOR, SPEC], [CONS, VOWEL, CONS, CONS, SPEC]])
def test_srozpadem(self):
word = run_through_module(
TextPhonotypes(
'srozpadem',
[CONS, SONOR, VOWEL, CONS, CONS, VOWEL, CONS, VOWEL, SONOR]))
self.assertEqual(word.get_syllables(), ['sro', 'zpa', 'dem'])
self.assertEqual(
word.get_phonotypes(),
[[CONS, SONOR, VOWEL], [CONS, CONS, VOWEL], [CONS, VOWEL, SONOR]])
def test_automaticky(self):
word = run_through_module(
TextPhonotypes('automatický', [
SUBUNIT, VOWEL, CONS, VOWEL, SONOR, VOWEL, CONS, VOWEL, CONS,
CONS, VOWEL
]))
self.assertEqual(word.get_syllables(), ['au', 'to', 'ma', 'ti', 'cký'])
self.assertEqual(word.get_phonotypes(),
[[SUBUNIT, VOWEL], [CONS, VOWEL], [SONOR, VOWEL],
[CONS, VOWEL], [CONS, CONS, VOWEL]])
def test_bijologije(self):
word = run_through_module(
TextPhonotypes('bijologije', [
CONS, VOWEL, SONOR, VOWEL, SONOR, VOWEL, CONS, VOWEL, SONOR,
VOWEL
]))
self.assertEqual(word.get_syllables(), ['bi', 'jo', 'lo', 'gi', 'je'])
self.assertEqual(word.get_phonotypes(),
[[CONS, VOWEL], [SONOR, VOWEL], [SONOR, VOWEL],
[CONS, VOWEL], [SONOR, VOWEL]])
def test_зяўляецца(self):
word = run_through_module(
TextPhonotypes('з’яўляецца', [
CONS, SPEC, VOWEL, SONOR, SONOR, VOWEL, VOWEL, CONS, CONS,
VOWEL
]))
self.assertEqual(word.get_syllables(), ['з’я', 'ўля', 'е', 'цца'])
self.assertEqual(word.get_phonotypes(),
[[CONS, SPEC, VOWEL], [SONOR, SONOR, VOWEL], [VOWEL],
[CONS, CONS, VOWEL]])
def set_phonotypes(self, word) -> TextPhonotypes:
cluster_letters = self.cluster_letters
phono_changes = self.phono_changes
signs = self.signs
word_text = self.text_changes_func(word.get_text()) # TEXT CHANGES
word_length = len(word_text)
cluster_exception = False
cluster_croatian_exception = False
for i in range(word_length):
if cluster_exception:
cluster_exception = False
continue
if cluster_croatian_exception:
cluster_croatian_exception = False
continue
current_to_subunit_next_unchanged = phonotype_exception = False
previous_letter = word_text[i - 1] if i - 1 >= 0 else ""
current_letter = word_text[i]
next_letter = word_text[i + 1] if i + 1 < word_length else ""
exception_next_letter = word_text[
i +
2] if i + 2 < word_length else "" # used because of exception in croatian language (ije -> [SUBUNIT, SUBUNIT, VOWEL])
if current_letter in cluster_letters: # CLUSTERS
if exception_next_letter != "" and next_letter + exception_next_letter in cluster_letters[
current_letter]:
cluster_exception, current_to_subunit_next_unchanged = \
self.clusters_func(word_text, current_letter, next_letter, exception_next_letter)
cluster_croatian_exception = True
if next_letter in cluster_letters[current_letter]:
cluster_exception, current_to_subunit_next_unchanged = \
self.clusters_func(word_text, current_letter, next_letter, "")
elif current_letter in phono_changes: # PHONOTYPE CHANGES
phonotype_exception = self.phonotype_changes_func(
word_text, previous_letter, current_letter, next_letter)
no_exceptions = not current_to_subunit_next_unchanged and not cluster_exception and not phonotype_exception
if no_exceptions:
self.phonotypes.append(signs[current_letter])
phonotypes = self.phonotypes
self.phonotypes = []
return TextPhonotypes(word_text, phonotypes)
def test_українськогож(self):
word = run_through_module(
TextPhonotypes('українськогож', [
VOWEL, CONS, SONOR, VOWEL, VOWEL, SONOR, CONS, SPEC, CONS,
VOWEL, CONS, VOWEL, CONS
]))
self.assertEqual(word.get_syllables(),
['у', 'кра', 'їн', 'сько', 'гож'])
self.assertEqual(word.get_phonotypes(),
[[VOWEL], [CONS, SONOR, VOWEL], [VOWEL, SONOR],
[CONS, SPEC, CONS, VOWEL], [CONS, VOWEL, CONS]])
def test_farmaceuticky(self):
word = run_through_module(
TextPhonotypes('farmaceutický', [
CONS, VOWEL, SONOR, SONOR, VOWEL, CONS, SUBUNIT, VOWEL, CONS,
VOWEL, CONS, CONS, VOWEL
]))
self.assertEqual(word.get_syllables(),
['fa', 'rma', 'ceu', 'ti', 'cký'])
self.assertEqual(
word.get_phonotypes(),
[[CONS, VOWEL], [SONOR, SONOR, VOWEL], [CONS, SUBUNIT, VOWEL],
[CONS, VOWEL], [CONS, CONS, VOWEL]])
def set_phonotypes(self, word) -> TextPhonotypes:
cluster_letters = self.cluster_letters
phono_changes = self.phono_changes
signs = self.signs
word_text = self.text_changes_func(word.get_text()) # TEXT CHANGES
word_length = len(word_text)
cluster_exception = False
for i in range(word_length):
if cluster_exception:
cluster_exception = False
continue
current_to_subunit_next_unchanged = phonotype_exception = False
previous_sign = word_text[i - 1] if i - 1 >= 0 else None
current_sign = word_text[i]
next_sign = word_text[i + 1] if i + 1 < word_length else None
if current_sign in cluster_letters and next_sign in cluster_letters[
current_sign]: # CLUSTERS
cluster_exception, current_to_subunit_next_unchanged = \
self.clusters_func(word_text, current_sign, next_sign)
elif current_sign in phono_changes: # PHONOTYPE CHANGES
phonotype_exception = self.phonotype_changes_func(
word_text, previous_sign, current_sign, next_sign)
no_exceptions = not current_to_subunit_next_unchanged and \
not cluster_exception and not phonotype_exception
if no_exceptions:
self.phonotypes.append(signs[current_sign])
phonotypes = self.phonotypes
self.phonotypes = []
return TextPhonotypes(word_text, phonotypes)
def test_sneh(self):
word = run_through_module(
TextPhonotypes('sněh', [CONS, SONOR, VOWEL, CONS]))
self.assertEqual(word.get_syllables(), ['sněh'])
self.assertEqual(word.get_phonotypes(), [[CONS, SONOR, VOWEL, CONS]])
def test_osm(self):
word = run_through_module(TextPhonotypes('osm', [VOWEL, CONS, VOWEL]))
self.assertEqual(word.get_syllables(), ['o', 'sm'])
self.assertEqual(word.get_phonotypes(), [[VOWEL], [CONS, VOWEL]])
def test_rz(self):
word = run_through_module(TextPhonotypes('rž', [VOWEL, CONS]))
self.assertEqual(word.get_syllables(), ['rž'])
self.assertEqual(word.get_phonotypes(), [[VOWEL, CONS]])
def test_maria(self):
word = run_through_module(
TextPhonotypes('maria', [SONOR, VOWEL, SONOR, SUBUNIT, VOWEL]))
self.assertEqual(word.get_syllables(), ['ma', 'ria'])
self.assertEqual(word.get_phonotypes(),
[[SONOR, VOWEL], [SONOR, SUBUNIT, VOWEL]])
def test_vlna(self):
word = run_through_module(
TextPhonotypes('vlna', [CONS, VOWEL, SONOR, VOWEL]))
self.assertEqual(word.get_syllables(), ['vl', 'na'])
self.assertEqual(word.get_phonotypes(),
[[CONS, VOWEL], [SONOR, VOWEL]])
def test_późniejszy(self):
word = run_through_module(
TextPhonotypes('późniejszy', [0, 2, 0, 1, 4, 2, 1, 4, 0, 2]))
self.assertEqual(word.get_syllables(), ['pó', 'źniej', 'szy'])
self.assertEqual(word.get_phonotypes(),
[[0, 2], [0, 1, 4, 2, 1], [4, 0, 2]])
def test_pouzil(self):
word = run_through_module(
TextPhonotypes('použil', [CONS, VOWEL, VOWEL, CONS, VOWEL, SONOR]))
self.assertEqual(word.get_syllables(), ['po', 'u', 'žil'])
self.assertEqual(word.get_phonotypes(),
[[CONS, VOWEL], [VOWEL], [CONS, VOWEL, SONOR]])
def test_pouze(self):
word = run_through_module(
TextPhonotypes('pouze', [CONS, SUBUNIT, VOWEL, CONS, VOWEL]))
self.assertEqual(word.get_syllables(), ['pou', 'ze'])
self.assertEqual(word.get_phonotypes(),
[[CONS, SUBUNIT, VOWEL], [CONS, VOWEL]])
from config_data import ConfigData
from pipe import Pipe
from queue import Queue
from threading import Condition
from count_module import CountModule
from syllabify_module import SyllabifyModule
from word import TextPhonotypes, SyllablesLengths
from constants import SONOR, CONS, VOWEL, SPEC, SUBUNIT
from end import End
import unittest
import time
words_to_do = [
TextPhonotypes('farmaceutický', [CONS, VOWEL, SONOR, SONOR, VOWEL, CONS,
SUBUNIT, VOWEL, CONS, VOWEL, CONS, CONS, VOWEL]),
TextPhonotypes('pouze', [CONS, SUBUNIT, VOWEL, CONS, VOWEL]),
TextPhonotypes('použil', [CONS, VOWEL, VOWEL, CONS, VOWEL, SONOR]),
TextPhonotypes('neurčitý', [SONOR, VOWEL, VOWEL, SONOR, CONS, VOWEL, CONS, VOWEL]),
TextPhonotypes('automatický', [SUBUNIT, VOWEL, CONS, VOWEL, SONOR, VOWEL, CONS, VOWEL, CONS, CONS, VOWEL]),
TextPhonotypes('vlna', [CONS, VOWEL, SONOR, VOWEL]),
TextPhonotypes('osm', [VOWEL, CONS, VOWEL]),
TextPhonotypes('bijologije', [CONS, VOWEL, SONOR, VOWEL, SONOR, VOWEL, CONS, VOWEL, SONOR, VOWEL]),
TextPhonotypes('srozpadem', [CONS, SONOR, VOWEL, CONS, CONS, VOWEL, CONS, VOWEL, SONOR]),
TextPhonotypes('vědomí', [CONS, VOWEL, CONS, VOWEL, SONOR, VOWEL]),
TextPhonotypes('sex', [CONS, VOWEL, CONS])
]
syllables = [['fa', 'rma', 'ceu', 'ti', 'cký'], ['pou', 'ze'], ['po', 'u', 'žil'], ['ne', 'ur', 'či', 'tý'],
['au', 'to', 'ma', 'ti', 'cký'], ['vl', 'na'], ['o', 'sm'], ['bi', 'jo', 'lo', 'gi', 'je'],
['sro', 'zpa', 'dem'], ['vě', 'do', 'mí'], ['sex']]
def test_wrobl(self):
word = run_through_module(
TextPhonotypes('wrobl', [SONOR, SONOR, VOWEL, CONS, VOWEL]))
self.assertEqual(word.get_syllables(), ['wro', 'bl'])
self.assertEqual(word.get_phonotypes(),
[[SONOR, SONOR, VOWEL], [CONS, VOWEL]])
def text_zastojnstwa(self):
word = run_through_module(
TextPhonotypes('zastojnstwa', [0, 2, 0, 1, 4, 2, 1, 4, 0, 2]))
self.assertEqual(word.get_syllables(), ['za', 'stojn', 'stwa'])
self.assertEqual(word.get_phonotypes(),
[[0, 2], [0, 0, 2, 1, 1], [0, 0, 1, 2]])
def test_vedomi(self):
word = run_through_module(
TextPhonotypes('vědomí', [CONS, VOWEL, CONS, VOWEL, SONOR, VOWEL]))
self.assertEqual(word.get_syllables(), ['vě', 'do', 'mí'])
self.assertEqual(word.get_phonotypes(),
[[CONS, VOWEL], [CONS, VOWEL], [SONOR, VOWEL]])