def test_contains_extractor_with_list():
text = ["Simple", "is", "better", "than", "complex"]
features = contains_extractor(text)
assert_true(features['contains(Simple)'])
assert_false(features.get("contains(simple)", False))
assert_true(features['contains(complex)'])
assert_false(features.get("contains(derp)", False))
def test_contains_extractor_with_string():
text = "Simple is better than complex"
features = contains_extractor(text)
assert_true(features["contains(Simple)"])
assert_false(features.get('contains(simple)', False))
assert_true(features['contains(complex)'])
assert_false(features.get("contains(derp)", False))
def extractor_base(document, train_set=None):
""" Renvoyer des propriétés du texte """
features = contains_extractor(document, train_set)
features['has_digit_sequence(7)'] = bool(re.search(REGEX_DIGIT_SEQUENCE_7, document))
features['has_digit_sequence(4)'] = bool(re.search(REGEX_DIGIT_SEQUENCE_4, document))
features['has_digit_sequence(2)'] = bool(re.search(REGEX_DIGIT_SEQUENCE_2, document))
features['has_digits(7)'] = bool(re.search(REGEX_DIGIT_PRESENCE_7, document))
features['has_curency()'] = bool(re.search(REGEX_CURRENCY_PRESENCE, document))
features['has_email_markers()'] = bool(re.search(REGEX_EMAIL_MARKERS, document))
features['has_hyperlink()'] = bool(re.search(REGEX_HYPERLINK_MARKER, document))
return features
