Created
March 17, 2022 20:36
-
-
Save tristanlatr/c6d02cb23b275ab8b674e5893fc95890 to your computer and use it in GitHub Desktop.
Utility function to unquote a string. It supports all kinds of python quotes.
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 | |
import ast | |
_QUOTED_STR_REGEX = re.compile(r'(^\"(?:\\.|[^\"\\])*\"$)|' | |
r'(^\'(?:\\.|[^\'\\])*\'$)') | |
# older version (not very strong): (^\'\'\'(\s+)?(((?!\'\'\').)*)?(\s+)?\'\'\'$) | |
_TRIPLE_QUOTED_STR_REGEX = re.compile(r'(^\"\"\"(\s+)?(([^\"]|\"([^\"]|\"[^\"]))*(\"\"?)?)?(\s+)?(?:\\.|[^\"\\])?\"\"\"$)|' | |
# Unescaped quotes at the end of a string generates | |
# "SyntaxError: EOL while scanning string literal", | |
# so we don't account for those kind of strings as quoted. | |
r'(^\'\'\'(\s+)?(([^\']|\'([^\']|\'[^\']))*(\'\'?)?)?(\s+)?(?:\\.|[^\'\\])?\'\'\'$)', flags=re.DOTALL) | |
def _is_quoted(text:str) -> bool: | |
return bool(_QUOTED_STR_REGEX.match(text)) or \ | |
bool(_TRIPLE_QUOTED_STR_REGEX.match(text)) | |
def unquote_str(text:str) -> str: | |
""" | |
Unquote a maybe quoted string representation. | |
If the string is not detected as being a quoted representation, it returns the same string as passed. | |
It supports all kinds of python quotes: C{\"\"\"}, C{'''}, C{"} and C{'}. | |
""" | |
if _is_quoted(text): | |
s = ast.literal_eval(text) | |
assert isinstance(s, str) | |
return s | |
return text |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment