def get(self, threshold):
scanner = Services.DirectoryScanner(config.DIRECTORIES_TO_SCAN)
interesting_service = Services.InterestingService(config.DEFAULT_INTERESTING_WEIGHT)
document_parser = Services.DocumentParser()
repo = Repositories.TxtRepository()
counting_service = Services.WordCountingService(document_parser, interesting_service, threshold)
for file in scanner.scan_files():
for line in repo.read_file(file):
for sentence in document_parser.split_to_sentences(line):
counting_service.populate(sentence, file)
return counting_service.get_word_count()
def main():
scanner = Services.DirectoryScanner(config.DIRECTORIES_TO_SCAN, Services.CompanyRegistry())
repo = Repositories.CsvRepository()
file_validator = Services.FileValidator()
new_files = []
for new_file in scanner.scan_new_files():
file, company = new_file
metadata = repo.get_metadata(file)
headers = repo.get_headers(file)
statement_type = file_validator.get_statement_type(metadata)
is_file_structure_valid = file_validator.is_file_structure_valid(headers)
is_file_in_good_dir = file_validator.is_file_in_good_dir(statement_type[0], file)
new_files.append(Entities.ScannedFileResult(file, statement_type, company, is_file_in_good_dir,
is_file_structure_valid))
print(f'new files of unseen companies: {len(new_files)}')
for new_file in new_files:
print(f'\n'
f'company: {new_file.company}\n'
f'file path: {new_file.path}\n'
f'statement type: {new_file.statement_type[1]}\n'
f'is file in good dir: {new_file.is_file_in_good_dir}\n'
f'is file valid: {new_file.is_valid}')