def test_word_segmentation_apostrophe(self): edit_distance_max = 0 prefix_length = 7 sym_spell = SymSpell(edit_distance_max, prefix_length) sym_spell.load_dictionary(self.dictionary_path, 0, 1) typo = "There'resomewords" correction = ("There' re some words") result = sym_spell.word_segmentation(typo) self.assertEqual(correction, result.corrected_string)
def test_word_segmentation_capitalize(self): edit_distance_max = 0 prefix_length = 7 sym_spell = SymSpell(edit_distance_max, prefix_length) sym_spell.load_dictionary(self.dictionary_path, 0, 1) typo = "Thequickbrownfoxjumpsoverthelazydog" correction = "The quick brown fox jumps over the lazy dog" result = sym_spell.word_segmentation(typo) self.assertEqual(correction, result.corrected_string) typo = "Itwasabrightcolddayinaprilandtheclockswerestrikingthirteen" correction = ("It was a bright cold day in april and the clocks " "were striking thirteen") result = sym_spell.word_segmentation(typo) self.assertEqual(correction, result.segmented_string) typo = ("Itwasthebestoftimesitwastheworstoftimesitwastheageofwisdom" "itwastheageoffoolishness") correction = ("It was the best of times it was the worst of times " "it was the age of wisdom it was the age of foolishness") result = sym_spell.word_segmentation(typo) self.assertEqual(correction, result.segmented_string)