def test_percentage_punctuation(self):
test_sentences = [
("The cat sat on the hat.", float(1)/18),
(".", 1),
(" ", 0),
("", 0),
(test_text, 20.0/147)
]
for test_sentence, result in test_sentences:
analyse_result_dict = compute_fingerprint.analyze_text(util.tokenize_sentences(test_sentence))
percent_punctuation = analyse_result_dict['percentage_punctuation']
self.assertEquals(percent_punctuation, result, msg=(test_sentence, percent_punctuation, '!=', result))
def test_lexical_diversity(self):
test_sentences = [
("The quick brown cat jumped over the lazy dog.", float(8)/9),
("", 0),
(".", 0),
(" ", 0),
(test_text, 13.0/48)
]
for test_sentence, result in test_sentences:
analyse_result_dict = compute_fingerprint.analyze_text(util.tokenize_sentences(test_sentence))
lexical_diversity = analyse_result_dict['lexical_diversity']
self.assertEquals(lexical_diversity, result, msg=(test_sentence, lexical_diversity, '!=', result))
def test_average_word_length(self):
avg_word_length_cases = [
("The quick brown fox jumped over the lazy dog", 4),
("", 0),
(" ", 0),
(",", 0),
(test_text, 127.0/48)
]
for test_sentence, result in avg_word_length_cases:
analyse_result_dict = compute_fingerprint.analyze_text(util.tokenize_sentences(test_sentence))
avg_word_length = analyse_result_dict['avg_word_length']
self.assertEquals(avg_word_length, result, msg=(test_sentence, avg_word_length, '!=', result))
def test_average_sentence_length(self):
avg_sentence_length_cases = [
("The cat sat on the hat. The fox jumped.", 4.5),
("", 0),
("Alice.", 1),
("Mr. Smith went to work.", 5),
("'hi,' said Katie.", 3),
(test_text, 48.0/9)
]
for test_sentence, result in avg_sentence_length_cases:
analyse_result_dict = compute_fingerprint.analyze_text(util.tokenize_sentences(test_sentence))
avg_sentence_length = analyse_result_dict['avg_sentence_length']
self.assertEquals(avg_sentence_length, result, msg=(test_sentence, avg_sentence_length, '!=', result))
def test_fingerprint_text(self):
empty_result = {key: 0 for key in constants.CHUNK_MODEL_FINGERPRINT_FIELDS}
test_texts = [
({'chunk': ' '},
empty_result),
({'chunk': test_text},
seuss_result_dictionary)
]
for argument_dictionary, result_dictionary in test_texts:
result_list = []
fingerprint_list=[]
fingerprint = compute_fingerprint.fingerprint_text(util.tokenize_sentences(argument_dictionary['chunk']))
for field in constants.CHUNK_MODEL_FINGERPRINT_FIELDS:
result_list.append(result_dictionary[field])
fingerprint_list.append(fingerprint[field])
self.assertEquals(fingerprint_list, result_list)
