mirror of
https://github.com/pre-commit/pre-commit-hooks.git
synced 2026-06-28 21:50:46 +00:00
aba8a7597a
New fixer hook that replaces UTF-8 em-dashes (U+2014) with a plain hyphen (-), modeled on the trailing-whitespace hook. - pre_commit_hooks/remove_em_dash.py: the fixer (binary-safe, UTF-8 only) - tests/remove_em_dash_test.py: full coverage of fix and no-op cases - registered in setup.cfg, .pre-commit-hooks.yaml, and README.md Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
34 lines
832 B
Python
34 lines
832 B
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
from collections.abc import Sequence
|
|
|
|
EM_DASH = '\N{EM DASH}'.encode()
|
|
|
|
|
|
def _fix_file(filename: str) -> bool:
|
|
with open(filename, 'rb') as f:
|
|
contents = f.read()
|
|
new_contents = contents.replace(EM_DASH, b'-')
|
|
if new_contents == contents:
|
|
return False
|
|
with open(filename, 'wb') as f:
|
|
f.write(new_contents)
|
|
return True
|
|
|
|
|
|
def main(argv: Sequence[str] | None = None) -> int:
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('filenames', nargs='*', help='Filenames to fix')
|
|
args = parser.parse_args(argv)
|
|
|
|
retv = 0
|
|
for filename in args.filenames:
|
|
if _fix_file(filename):
|
|
print(f'Fixing {filename}')
|
|
retv = 1
|
|
return retv
|
|
|
|
|
|
if __name__ == '__main__':
|
|
raise SystemExit(main())
|