def test_tokenize_fr(self): test_file = get_test_file('fr') self._test_tokenize(test_file=test_file, language='fr')
def test_tokenize_it(self): test_file = get_test_file('it') self._test_tokenize(test_file=test_file, language='it')
def test_tokenize_en(self): test_file = get_test_file('en') self._test_tokenize(test_file=test_file, language='en')
def test_tokenize_de(self): test_file = get_test_file('de') self._test_tokenize(test_file=test_file, language='de')
def test_normalize_it(self): test_file = get_test_file('it') self._test_normalize(test_file=test_file, language='it', penn=False)
def test_normalize_it_penn(self): test_file = get_test_file('it') self._test_normalize(test_file=test_file, language='it', penn=True)
def test_normalize_fr_penn(self): test_file = get_test_file('fr') self._test_normalize(test_file=test_file, language='fr', penn=True)
def test_normalize_fr(self): test_file = get_test_file('fr') self._test_normalize(test_file=test_file, language='fr', penn=False)
def test_normalize_de_penn(self): test_file = get_test_file('de') self._test_normalize(test_file=test_file, language='de', penn=True)
def test_normalize_de(self): test_file = get_test_file('de') self._test_normalize(test_file=test_file, language='de', penn=False)
def test_normalize_en_penn(self): test_file = get_test_file('en') self._test_normalize(test_file=test_file, language='en', penn=True)