def test_read_from_line_handles_multiple_columns(self): index = 23 tuple_string = "this###is###a triple" label = True line = "%d\t%s\t%d" % (index, tuple_string, int(label)) instance = TupleInstance.read_from_line(line) assert instance.text == ["this", "is", "a triple"] assert instance.label is label assert instance.index == index
def test_words_tokenizes_the_tuple_correctly(self): t = TupleInstance(["This", "is", "a triple"]) assert t.words() == {'words': ['this', 'is', 'a', 'triple']}
def test_read_from_line_splits_correctly(self): line = "this###is###a triple" instance = TupleInstance.read_from_line(line) assert instance.text == ["this", "is", "a triple"]