def test_default_get_words_from_text(self):
with TempFiles(1) as files:
print_lines_to_file(['Hi baby', 'How are', 'you?'], files[0].name)
correct_result = {'hi', 'baby', 'how', 'are', 'you'}
with open(files[0].name, 'r') as f:
result = dic_cr.get_words_from_text(f)
self.assertSetEqual(correct_result, result)
def test_default_get_words_from_dict(self):
with TempFiles(1) as files:
print_lines_to_file(['apple', 'bobby', 'hello'], files[0].name)
correct_result = {'apple', 'bobby', 'hello'}
with open(files[0].name, 'r') as f:
result = dic_cr.get_words_from_dict(f)
self.assertSetEqual(correct_result, result)
def test_create_with_zero_length_text(self):
with TempFiles(2) as files:
output = files[1]
args = prepare_args(ArgsTypes.CREATE, files)
args.encoding = 'utf8'
dic_cr.create(args)
correct_result = []
assert_file_lines_with_list(self, output.name, correct_result)
def test_append_with_zero_length_dict(self):
with TempFiles(2) as files:
first_dict = files[0]
second_dict = files[1]
print_lines_to_file(['bobby'], second_dict.name)
args = prepare_args(ArgsTypes.APPEND, files)
dic_cr.append(args)
correct_result = ['bobby']
assert_file_lines_with_list(self, first_dict.name, correct_result)
def test_merge_with_zero_length_dict(self):
with TempFiles(3) as files:
first_dict = files[0]
print_lines_to_file(['apple', 'hello'], first_dict.name)
third_dict = files[2]
args = prepare_args(ArgsTypes.MERGE, files)
dic_cr.merge(args)
correct_result = ['apple', 'hello']
assert_file_lines_with_list(self, third_dict.name, correct_result)
def test_get_words_from_text_with_numbers(self):
with TempFiles(1) as files:
print_lines_to_file(
['Прив8ет', 'как', 'дела?', '8 9123 8-800-555-35-35'],
files[0].name)
correct_result = {'как', 'дела'}
with open(files[0].name, 'r', encoding='utf8') as f:
result = dic_cr.get_words_from_text(f)
self.assertSetEqual(correct_result, result)
def is_dictionary(filename):
dict_hash = md5(filename)
with TempFiles(1) as files:
args = Args
args.first_dict = files[0].name
args.second_dict = filename
dic_cr.append(args)
new_dict_hash = md5(files[0].name)
return new_dict_hash == dict_hash
def test_add_with_wrong_word(self):
with TempFiles(1) as files:
dictionary = files[0]
print_lines_to_file(['apple', 'hello'], dictionary.name)
args = Args
args.dict = dictionary.name
args.word = 'lsakdf====--://'
dic_cr.add(args)
correct_result = ['apple', 'hello']
assert_file_lines_with_list(self, dictionary.name, correct_result)
def test_default_add(self):
with TempFiles(1) as files:
dictionary = files[0]
print_lines_to_file(['apple', 'hello'], dictionary.name)
args = Args
args.dict = dictionary.name
args.word = 'mango'
dic_cr.add(args)
correct_result = sorted(['apple', 'mango', 'hello'])
assert_file_lines_with_list(self, dictionary.name, correct_result)
def test_get_words_from_text_with_encoding(self):
with TempFiles(1) as files:
with open(files[0].name, 'w', encoding='cp1251') as f:
print('Привет', file=f)
print('как', file=f)
print('дела?', file=f)
correct_result = {'привет', 'как', 'дела'}
with open(files[0].name, 'r', encoding='cp1251') as f:
result = dic_cr.get_words_from_text(f)
self.assertSetEqual(correct_result, result)
def test_default_load_dictionary(self):
with TempFiles(1) as files:
tmp = files[0]
with open(tmp.name, 'w') as f:
print('apple', file=f)
print('help', file=f)
trie = ldc.load_dictionary(f.name)
self.assertTrue(ldc.is_word_in_dictionary(trie, 'apple'))
self.assertTrue(ldc.is_word_in_dictionary(trie, 'help'))
self.assertFalse(ldc.is_word_in_dictionary(trie, 'hello'))
def test_default_get_words_from_text_with_line_breaks(self):
with TempFiles(1) as files:
text = files[0]
print_lines_to_file(['Hey Boys how are you do-', 'ing today?'],
text.name)
correct_result = {
'hey', 'boys', 'how', 'are', 'you', 'doing', 'today'
}
with open(files[0].name, 'r', encoding='utf8') as f:
result = dic_cr.get_words_from_text(f)
self.assertSetEqual(correct_result, result)
def test_default_create(self):
with TempFiles(2) as files:
text = files[0]
print_lines_to_file(["This is test text.", 'I like python!'],
text.name)
output = files[1]
args = prepare_args(ArgsTypes.CREATE, files)
args.encoding = 'utf8'
dic_cr.create(args)
correct_result = sorted(
['this', 'is', 'test', 'text', 'i', 'like', 'python'])
assert_file_lines_with_list(self, output.name, correct_result)
def test_get_words_from_text_with_dashes(self):
with TempFiles(1) as files:
text = files[0]
print_lines_to_file([
'Hey Boys bla-bla how are you do-', 'ing today? I fee-',
'l yourself very good. Hey -'
], text.name)
correct_result = {
'bla-bla', 'hey', 'boys', 'how', 'are', 'you', 'doing',
'today', 'i', 'feel', 'yourself', 'very', 'good'
}
with open(files[0].name, 'r', encoding='utf8') as f:
result = dic_cr.get_words_from_text(f)
self.assertSetEqual(correct_result, result)
def test_get_words_from_text_with_no_text(self):
with TempFiles(1) as files:
correct_result = set()
with open(files[0].name, 'r') as f:
result = dic_cr.get_words_from_text(f)
self.assertSetEqual(correct_result, result)
def test_load_dictionary_without_words(self):
with TempFiles(1) as files:
tmp = files[0]
trie = ldc.load_dictionary(tmp.name)
self.assertFalse(ldc.is_word_in_dictionary(trie, 'apple'))
self.assertFalse(ldc.is_word_in_dictionary(trie, 'help'))