def test_lookup_compound_transfer_casing(self):
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.load_bigram_dictionary(self.bigram_path, 0, 2)
typo = ("Whereis th elove hehaD Dated forImuch of thepast who "
"couqdn'tread in sixthgrade AND ins pired him")
correction = ("Where is the love he haD Dated for much of the past "
"who couldn't read in sixth grade AND inspired him")
results = sym_spell.lookup_compound(typo,
edit_distance_max,
transfer_casing=True)
self.assertEqual(correction, results[0].term)
def test_load_bigram_dictionary_bad_dict(self):
dictionary_path = os.path.join(self.fortests_path, "bad_dict.txt")
edit_distance_max = 2
prefix_length = 7
sym_spell = SymSpell(edit_distance_max, prefix_length)
self.assertEqual(
True, sym_spell.load_bigram_dictionary(dictionary_path, 0, 2))
def test_load_bigram_dictionary_invalid_path(self):
edit_distance_max = 2
prefix_length = 7
sym_spell = SymSpell(edit_distance_max, prefix_length)
self.assertEqual(
False,
sym_spell.load_bigram_dictionary("invalid/dictionary/path.txt", 0,
2))
def test_lookup_compound(self):
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.load_bigram_dictionary(self.bigram_path, 0, 2)
typo = "whereis th elove"
correction = "where is the love"
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(2, results[0].distance)
self.assertEqual(585, results[0].count)
typo = "the bigjest playrs"
correction = "the biggest players"
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(2, results[0].distance)
self.assertEqual(34, results[0].count)
typo = "can yu readthis"
correction = "can you read this"
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(2, results[0].distance)
self.assertEqual(11440, results[0].count)
typo = ("whereis th elove hehad dated forImuch of thepast who "
"couqdn'tread in sixthgrade and ins pired him")
correction = ("where is the love he had dated for much of the past "
"who couldn't read in sixth grade and inspired him")
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(9, results[0].distance)
self.assertEqual(0, results[0].count)
typo = "in te dhird qarter oflast jear he hadlearned ofca sekretplan"
correction = ("in the third quarter of last year he had learned of a "
"secret plan")
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(9, results[0].distance)
self.assertEqual(0, results[0].count)
typo = ("the bigjest playrs in te strogsommer film slatew ith plety "
"of funn")
correction = ("the biggest players in the strong summer film slate "
"with plenty of fun")
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(9, results[0].distance)
self.assertEqual(0, results[0].count)
typo = ("can yu readthis messa ge despite thehorible sppelingmsitakes")
correction = ("can you read this message despite the horrible "
"spelling mistakes")
results = sym_spell.lookup_compound(typo, edit_distance_max)
self.assertEqual(1, len(results))
self.assertEqual(correction, results[0].term)
self.assertEqual(9, results[0].distance)
self.assertEqual(0, results[0].count)