def test_file_to_update_in_wrong_lang(self):
rus_text_info = l.TextInfo(self.alph_rus, ENCODING, self.big_rus_file)
rus_count_info = rus_text_info.find_info(100)
l.write_json_in_file(
OUTPUT_FILE,
rus_count_info.make_count_dict(),
ENCODING)
en_text_info = l.TextInfo(self.alph_en, ENCODING, self.first_file)
en_count_info = en_text_info.find_info(100)
en_count_info.update_count_info(
OUTPUT_FILE, en_text_info.alph, 100, ENCODING)
self.assertDictEqual(self.count_first, en_count_info.make_count_dict())
def test__frequency_updated(self):
text_info = l.TextInfo(self.alph_en, ENCODING, self.first_file)
count_info = text_info.find_info(100)
l.write_json_in_file(
OUTPUT_FILE,
count_info.make_count_dict(),
ENCODING)
new_text_info = l.TextInfo(self.alph_en, ENCODING, self.second_file)
new_count_info = new_text_info.find_info(100)
new_count_info.update_count_info(
OUTPUT_FILE, new_text_info.alph, 100, ENCODING)
frequency = new_count_info.make_frequency_dict()
self.assertDictEqual(frequency, self.frequency_updated)
def test_change_top_words(self):
text_info = l.TextInfo(self.alph_en, ENCODING, self.first_file)
count_info = text_info.find_info(10)
l.write_json_in_file(
OUTPUT_FILE,
count_info.make_count_dict(),
ENCODING)
new_text_info = l.TextInfo(self.alph_en, ENCODING, self.second_file)
new_count_info = new_text_info.find_info(10)
new_count_info.update_count_info(
OUTPUT_FILE, new_text_info.alph, 3, ENCODING)
self.assertEqual(3, len(new_count_info.words))
def test_count_updated(self):
text_info = learner.TextInfo(self.alph_en,
ENCODING,
input_text=self.first_file)
count_info = text_info.find_info(100)
learner.write_json_in_file(OUTPUT_FILE, count_info.make_count_dict(),
ENCODING)
new_text_info = learner.TextInfo(self.alph_en,
ENCODING,
input_text=self.second_file)
new_count_info = new_text_info.find_info(100)
new_count_info.update_count_info(OUTPUT_FILE, new_text_info.alph, 100,
ENCODING)
updated_dict = new_count_info.make_count_dict()
self.assertDictEqual(updated_dict, self.count_updated)
def test_count_frequency(self):
text_info = learner.TextInfo(self.alph_en,
ENCODING,
input_text=self.first_file)
count_info = text_info.find_info(100)
frequency = count_info.make_frequency_dict()
self.assertDictEqual(frequency, self.frequency_first)
def test_count_first(self):
text_info = learner.TextInfo(self.alph_en,
ENCODING,
input_text=self.first_file)
count_info = text_info.find_info(100)
count = count_info.make_count_dict()
self.assertDictEqual(count, self.count_first)
def test_top_words(self):
text_info = learner.TextInfo(self.alph_en,
ENCODING,
input_text=self.first_file)
count_info = text_info.find_info(3)
print(count_info.words)
self.assertEqual(3, len(count_info.words))
def test_ngramms(self):
text_info = l.TextInfo(self.alph_en, ENCODING, self.ngr_file)
count_info = text_info.find_info(100)
ngramms = count_info.make_ngramms_dict()
must_be = {"2": {"aa": 2, "ab": 2, "ba": 1},
"3": {"aaa": 1, "aba": 1, "bab": 1},
"4": {"abab": 1}}
self.assertDictEqual(must_be, ngramms)
def test_file_to_update_is_missing(self):
text_info = l.TextInfo(self.alph_en, ENCODING, self.first_file)
count_info = text_info.find_info(100)
count_info.update_count_info(
"this_file_does_not_exist",
text_info.alph,
100,
ENCODING)
self.assertDictEqual(self.count_first, count_info.make_count_dict())
def test_default_top_words(self):
text_info = learner.TextInfo(self.alph_en,
ENCODING,
input_text=self.big_en_file)
count_info = text_info.find_info(None)
self.assertEqual(100, len(count_info.words))
def test_top_words(self):
text_info = l.TextInfo(self.alph_en, ENCODING, self.first_file)
count_info = text_info.find_info(3)
self.assertEqual(3, len(count_info.words))