Last active
June 4, 2022 09:33
-
-
Save xflr6/5761d36b3db9a9b15970f974de416e59 to your computer and use it in GitHub Desktop.
Make Python regex search/replace functions from sed-like s/old/new/g strings
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
"""Search/replace func from string roughly like 'sed -r s/old/new/g'.""" | |
from collections.abc import Callable | |
import functools | |
def search_replace(cmd: str, *, _cache={}) -> Callable[[str], str]: | |
"""Return a callable from sed/Perl-style search-replace pattern string. | |
>>> search_replace('s/ham/spam/g')('ham-eggs-ham') | |
'spam-eggs-spam' | |
""" | |
try: | |
return _cache[cmd] | |
except KeyError: | |
pass | |
if not (cmd.startswith('s') and len(cmd) >= 6 and cmd.endswith('g')): | |
raise ValueError(f'{cmd!r}') | |
sep = cmd[1] | |
if cmd.count(sep) != 3: | |
raise ValueError(f'{cmd!r}') | |
search, _, rest = cmd[2:].partition(sep) | |
repl, _, rest = rest.partition(sep) | |
if not search or rest != 'g': | |
raise ValueError(f'{cmd!r}') | |
use_mrab = any(v in search for v in ('(?V0)', '(?V1)')) | |
if use_mrab: | |
import regex as re | |
else: | |
import re | |
regex = re.compile(search) | |
result = _cache[cmd] = functools.partial(regex.sub, repl) | |
result.cmd = cmd | |
return result | |
if __name__== '__main__': | |
import doctest | |
doctest.testmod(verbose=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment