class Filterator(QtWidgets.QApplication):
def __init__(self, *args, **kwargs):
#Initialization
super().__init__(*args, **kwargs)
self.tree_model = TreeModel(self)
self.filter_list_model = FilterListModel(DEFAULTS)
self.main_window = FilteratorMainWindow(self)
self.manager = Manager(self)
self.processor = Processor()
self.main_window.setupMainWindow(self.manager)
self.manager.setupManager(self.main_window, self.processor)
self.processor.setupProcessor(self.manager)
#Multithreading
self.processor_thread = QtCore.QThread()
self.processor.moveToThread(self.processor_thread)
self.processor_thread.start()
def __call__(self):
#Show MainWindow
self.main_window.showMaximized()
self.main_window.raise_()
#Start event loop
self.exec_()
def _run_console_option(self) -> None:
usersInput = UserInterface.GetUserInput()
matches_list = Processor.SearchData(usersInput[0],
self.names_data_dict,
usersInput[1])
UserInterface.PrintSearchResults(matches_list)
matches_total = Processor.GetSearchTotals(matches_list)
UserInterface.PrintTotalBorn(matches_total)
class CompaFactory():
def __init__(self):
self.extractor = Extractor()
self.processor = Processor(lists=WORDLISTS)
self.spellcheck = SpellChecker()
self.repetition = RepetitionChecker()
def execute(self, word):
# Extrai os Tokens da Frase
extracted = self.extractor.extract(word)
# Faz a Checagem Gramatical e retorna os erros encontrados
spelling_errors = self.spellcheck.from_tokenizer(extracted)
# Atualiza os tokens extraidos com as correções
extracted = self.spellcheck.autocorrect(extracted)
# Atualiza os tokens removendo as duplicadas
repetitions, extracted = self.repetition.repetition(extracted)
# Processa a lista de tokens e adiciona as tags de parte-de-fala
tagged = self.processor.process(extracted)
# Parser Sintático
parsed = ReduceParser(tagged)
semantic_errors = parsed.get_errors()
reduced = parsed.sintagmas
#errors = spelling_errors + repetitions + semantic_errors
return spelling_errors, semantic_errors, repetitions, reduced, tagged, extracted
def __init__(self, *args, **kwargs):
#Initialization
super().__init__(*args, **kwargs)
self.tree_model = TreeModel(self)
self.filter_list_model = FilterListModel(DEFAULTS)
self.main_window = FilteratorMainWindow(self)
self.manager = Manager(self)
self.processor = Processor()
self.main_window.setupMainWindow(self.manager)
self.manager.setupManager(self.main_window, self.processor)
self.processor.setupProcessor(self.manager)
#Multithreading
self.processor_thread = QtCore.QThread()
self.processor.moveToThread(self.processor_thread)
self.processor_thread.start()
def main():
brain: Processor = Processor()
current_channel = Telegram()
while True:
input_request: str = current_channel.get_input()
if input_request == "/shutdown":
break
output: str = brain.process(input_request)
current_channel.output(output)
def write_comments(comments, attributes, file=sys.stdout):
"""
write the :param attributes of all :param comments to a csv :param file.
"""
writer = csv.writer(file, dialect='unix')
with Processor('en') as p:
for comment in comments:
row = []
for attribute in attributes:
try:
row.append(p.preprocess(comment[attribute]))
except TypeError:
row.append(comment[attribute])
writer.writerow(row)
def match(self, a, b, gap_length, match_length):
comparator = self.Comparator(a=a,
b=b,
name_a=self.name_a,
name_b=self.name_b,
gap_length=gap_length,
match_length=match_length)
singlet_pairs = comparator.compare()
alpha = Mock()
alpha.raw_body = a
alpha.pre_body = a
beta = Mock()
beta.raw_body = b
beta.pre_body = b
matches = Processor.singlet_pairs_to_matches(
alpha=alpha, beta=beta, singlet_pairs=singlet_pairs)
return MatchSet(None, None, matches=matches)
def match(self, a, b, gap_length, match_length):
comparator = self.Comparator(a=a,
b=b,
name_a=self.name_a,
name_b=self.name_b,
gap_length=gap_length,
match_length=match_length)
singlet_pairs = comparator.compare()
alpha = Mock()
alpha.raw_body = a
alpha.pre_body = a
beta = Mock()
beta.raw_body = b
beta.pre_body = b
matches = Processor.singlet_pairs_to_matches(alpha=alpha,
beta=beta,
singlet_pairs=singlet_pairs)
return MatchSet(None, None, matches=matches)
def setUp(self):
self.passages_a = [chr(i + ord('a')) for i in xrange(10)]
self.passages_b = [chr(i + ord('A')) for i in xrange(10)]
self.file_a = 'models/test_data/match_set_test.json'
self.document_a = Document.from_json(self.file_a)
self.file_b = 'models/test_data/match_set_test2.json'
self.document_b = Document.from_json(self.file_b)
self.matches = []
self.singlet_pairs = []
for i in xrange(len(self.passages_a)):
a = MatchHalf(passage=self.passages_a[i])
b = MatchHalf(passage=self.passages_b[i])
s_pair = (a, b)
self.singlet_pairs.append(s_pair)
# Alpha/beta need to be actual documents, not names
self.matches = Processor.singlet_pairs_to_matches(alpha=self.document_a,
beta=self.document_b,
singlet_pairs=self.singlet_pairs)
self.match_set = MatchSet(alpha_doc=self.document_a,
beta_doc=self.document_b,
matches=self.matches)
def setUp(self):
self.passages_a = [chr(i + ord('a')) for i in xrange(10)]
self.passages_b = [chr(i + ord('A')) for i in xrange(10)]
self.file_a = 'models/test_data/match_set_test.json'
self.document_a = Document.from_json(self.file_a)
self.file_b = 'models/test_data/match_set_test2.json'
self.document_b = Document.from_json(self.file_b)
self.matches = []
self.singlet_pairs = []
for i in xrange(len(self.passages_a)):
a = MatchHalf(passage=self.passages_a[i])
b = MatchHalf(passage=self.passages_b[i])
s_pair = (a, b)
self.singlet_pairs.append(s_pair)
# Alpha/beta need to be actual documents, not names
self.matches = Processor.singlet_pairs_to_matches(
alpha=self.document_a,
beta=self.document_b,
singlet_pairs=self.singlet_pairs)
self.match_set = MatchSet(alpha_doc=self.document_a,
beta_doc=self.document_b,
matches=self.matches)
def __init__(self):
names_path = "./names/"
self.names_data_dict = Processor.GetFilesTextData(names_path)
def _run_graph_option(self) -> None:
name_to_search = UserInterface.GetSearchName()
match_list = Processor.SearchData(name_to_search, self.names_data_dict)
DataGraph.display_graph("Year", "Number born", match_list)
def __init__(self):
self.extractor = Extractor()
self.processor = Processor(lists=WORDLISTS)
self.spellcheck = SpellChecker()
self.repetition = RepetitionChecker()