Created
October 5, 2023 22:34
-
-
Save shner-elmo/7cd7c383fa882ab8cda743ec7a689b24 to your computer and use it in GitHub Desktop.
Regex split test cases (feel free to add more)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
lst = [ | |
( | |
r"(x)", | |
"1x2", | |
["1", "x", "2"], | |
), | |
( | |
r"([^\d]+)", | |
"1-2", | |
["1", "-", "2"], | |
), | |
( | |
r"(\s+)", | |
"this is a \n\ntest", | |
["this", " ", "is", " ", "a", " \n\n", "test"], | |
), | |
( | |
r"([^0-9a-zA-Z_])", | |
" C# is great! (not actually) :)", | |
["", " ", "C", "#", "", " ", "is", " ", "great", "!", "", " ", "", "(", "not", " ", "actually", ")", "", " ", "", ":", "", ")", ""], | |
), | |
( | |
r"([a-zA-Z](?:[a-zA-Z']*[a-zA-Z])?)", | |
'He said, "I\'d like to eat cake!"', | |
["", "He", " ", "said", ', "', "I'd", " ", "like", " ", "to", " ", "eat", " ", "cake", '!"'], | |
), | |
] | |
def main(): | |
for pattern, in_text, expected_out in lst: | |
out = re.split(pattern, in_text) | |
assert out == expected_out, (f'Regex: {pattern}, Text: {in_text}, \nOut: {out} ' | |
f'\nExpected out: {expected_out}') | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment