def test_delete_dictionary_entry(self):
sym_spell = SymSpell()
sym_spell.create_dictionary_entry("stea", 1)
sym_spell.create_dictionary_entry("steama", 2)
sym_spell.create_dictionary_entry("steem", 3)
result = sym_spell.lookup("steama", Verbosity.TOP, 2)
self.assertEqual(1, len(result))
self.assertEqual("steama", result[0].term)
self.assertEqual(len("steama"), sym_spell.max_length())
self.assertEqual(3, sym_spell.word_count())
self.assertTrue(sym_spell.delete_dictionary_entry("steama"))
self.assertEqual(len("steem"), sym_spell.max_length())
self.assertEqual(2, sym_spell.word_count())
result = sym_spell.lookup("steama", Verbosity.TOP, 2)
self.assertEqual(1, len(result))
self.assertEqual("steem", result[0].term)
self.assertTrue(sym_spell.delete_dictionary_entry("stea"))
self.assertEqual(len("steem"), sym_spell.max_length())
self.assertEqual(1, sym_spell.word_count())
result = sym_spell.lookup("steama", Verbosity.TOP, 2)
self.assertEqual(1, len(result))
self.assertEqual("steem", result[0].term)
def test_pickle_compressed(self):
pickle_path = os.path.join(self.fortests_path, "dictionary.pickle")
edit_distance_max = 2
prefix_length = 7
sym_spell = SymSpell(edit_distance_max, prefix_length)
sym_spell.load_dictionary(self.dictionary_path, 0, 1)
sym_spell.save_pickle(pickle_path)
sym_spell_2 = SymSpell(edit_distance_max, prefix_length)
sym_spell_2.load_pickle(pickle_path)
self.assertEqual(sym_spell.max_length(), sym_spell_2.max_length())
self.assertEqual(
sym_spell.lookup("flam", Verbosity.TOP, 0, True)[0].term,
sym_spell_2.lookup("flam", Verbosity.TOP, 0, True)[0].term)
os.remove(pickle_path)
def test_create_dictionary(self):
corpus_path = os.path.join(self.fortests_path, "big_modified.txt")
big_words_path = os.path.join(self.fortests_path, "big_words.txt")
edit_distance_max = 2
prefix_length = 7
sym_spell = SymSpell(edit_distance_max, prefix_length)
sym_spell.create_dictionary(corpus_path)
self.assertEqual(68, sym_spell.max_length())
def test_save_pickle_symspellcpppy(benchmark):
sym_spell = SymSpellCpp(max_dictionary_edit_distance=2, prefix_length=7)
sym_spell.load_dictionary(dict_path,
term_index=0,
count_index=1,
separator=" ")
os.makedirs("temp_cpppy", exist_ok=True)
result = benchmark(sym_spell.save_pickle, "temp_cpppy/temp.bin")
assert (sym_spell.max_length() == 28)
def test_save_load(self):
before_save = self.symSpell.lookup("tke", Verbosity.CLOSEST)[0].term
before_max_length = self.symSpell.max_length()
os.makedirs("temp", exist_ok=True)
self.symSpell.save_pickle("temp/temp.bin")
load_sym_spell = SymSpell()
load_sym_spell.load_pickle("temp/temp.bin")
after_load = load_sym_spell.lookup("tke", Verbosity.CLOSEST)[0].term
after_max_length = load_sym_spell.max_length()
os.remove("temp/temp.bin")
os.rmdir("temp")
assert (before_save == after_load)
assert (before_max_length == after_max_length)