class TestScrapperGraph(unittest.TestCase):
out_text_file = "_.txt"
out_ttl_file = "_.ttl"
out_ttl_file_2 = "_2.ttl"
@classmethod
def setUpClass(cls):
cls.res = get_synonyms_from_scrappers(
cls.word, cls.lang, cls.depth, merge_graph=False
)
cls.scrapper_names = [scr.website for scr in scrappers[cls.lang]]
# print(cls.word)
# print(cls.res[0].to_text_file())
def setUp(self):
# self.res = get_synonyms_from_scrappers(
# "test", self.lang, self.depth, merge_graph=False
# )
self.merged_graph = Graph()
for g in self.res:
self.merged_graph += g
with open(self.out_ttl_file, "w") as f:
print(self.merged_graph, file=f)
self.words = []
for g in self.res:
self.words += g.to_list()
self.words = set(self.words)
touch(self.out_text_file)
touch(self.out_ttl_file)
touch(self.out_ttl_file_2)
def tearDown(self):
os.remove(self.out_text_file)
os.remove(self.out_ttl_file)
os.remove(self.out_ttl_file_2)
# return
def test_same_output(self):
for word in self.words:
self.assertTrue(word in self.merged_graph)
def test_not_loosing_word_in_output(self):
self.merged_graph.to_text_file(self.out_text_file)
words_in_file = []
with open(self.out_text_file) as f:
for line in f:
if line.strip():
self.assertTrue(
line.strip() in self.merged_graph, f"word is: {line.strip()}"
)
self.assertTrue(line.strip() in self.words)
words_in_file.append(line.strip())
self.assertEqual(len(words_in_file), len(self.words))
self.assertEqual(len(words_in_file), len(set(words_in_file)))
def test_delete_several_depth(self):
self.merged_graph.delete_several_depth()
self.test_not_loosing_word_in_output()
self.test_same_output()
# cheking if there are no tripple with seveal depth
q = ""
with open(self.out_ttl_file_2, "w") as f:
print(self.merged_graph, file=f)
def test_all_scrappers_return_results(self):
for graph, scrapper_name in zip(self.res, self.scrapper_names):
with self.subTest():
self.assertFalse(
graph.is_empty(),
msg=f"Error with scrapper of '{scrapper_name}'. lang is '{self.lang}'. word is '{self.word}'",
)
self.assertTrue(
graph.contains_synonyms(),
msg=f"Error with scrapper of '{scrapper_name}'. lang is '{self.lang}'. word is '{self.word}'",
)
def test_no_W_in_words(self):
for word in self.merged_graph.to_list():
with self.subTest(msg=f"test failed with word '{word}'"):
# no parenthesis
self.assertFalse(re.search(r"[\(\)]", word))
# htm escaped
self.assertEqual(html.unescape(word), word)
# no html tag
self.assertFalse(re.search(r"[<>]", word))
# no space
self.assertEqual(word.strip(), word)
