Python split string without splitting escaped character

Question

Is there a way to split a string without splitting escaped character? For example, I have a string and want to split by \':\' and not by \'\\:\'

http\\://ww         


        

Answer 1

I have created this method, which is inspired by Henry Keiter's answer, but has the following advantages:

• Variable escape character and delimiter
• Do not remove the escape character if it is actually not escaping something

This is the code:

def _split_string(self, string: str, delimiter: str, escape: str) -> [str]:
    result = []
    current_element = []
    iterator = iter(string)
    for character in iterator:
        if character == self.release_indicator:
            try:
                next_character = next(iterator)
                if next_character != delimiter and next_character != escape:
                    # Do not copy the escape character if it is inteded to escape either the delimiter or the
                    # escape character itself. Copy the escape character if it is not in use to escape one of these
                    # characters.
                    current_element.append(escape)
                current_element.append(next_character)
            except StopIteration:
                current_element.append(escape)
        elif character == delimiter:
            # split! (add current to the list and reset it)
            result.append(''.join(current_element))
            current_element = []
        else:
            current_element.append(character)
    result.append(''.join(current_element))
    return result

This is test code indicating the behavior:

def test_split_string(self):
    # Verify normal behavior
    self.assertListEqual(['A', 'B'], list(self.sut._split_string('A+B', '+', '?')))

    # Verify that escape character escapes the delimiter
    self.assertListEqual(['A+B'], list(self.sut._split_string('A?+B', '+', '?')))

    # Verify that the escape character escapes the escape character
    self.assertListEqual(['A?', 'B'], list(self.sut._split_string('A??+B', '+', '?')))

    # Verify that the escape character is just copied if it doesn't escape the delimiter or escape character
    self.assertListEqual(['A?+B'], list(self.sut._split_string('A?+B', '\'', '?')))