Created
May 27, 2022 09:49
-
-
Save kbridge/157f164de01d30f33ab45950cc418e05 to your computer and use it in GitHub Desktop.
A line-oriented non-ascii byte finder, with unnecessary elegance
This file contains hidden or 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 sys | |
from typing import Iterator, Optional | |
ascii_range = range(32, 128) | |
def is_non_ascii(b): | |
return b not in ascii_range | |
def non_ascii_iter(bs): | |
return (b for b in bs if is_non_ascii(b)) | |
def first_non_ascii_byte(bs): | |
return next(non_ascii_iter(bs), None) | |
def contains_non_ascii(bs): | |
return first_non_ascii_byte(bs) is not None | |
if __name__ == '__main__': | |
if len(sys.argv) != 2: | |
program = sys.argv[0] | |
print(f'usage: python {program} PATH') | |
sys.exit(1) | |
path = sys.argv[1] | |
with open(path, mode='rb') as f: | |
for (line_index, line) in enumerate(f): | |
line_without_lf = line.rstrip(b'\n') | |
if contains_non_ascii(line_without_lf): | |
line_number = line_index + 1 | |
line_representaion = repr(line_without_lf) | |
line_representaion_without_quotes = line_representaion[2:-1] | |
print(f'{path}:{line_number}: {line_representaion_without_quotes}') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment