remove_nbsp: script that replaces non-breaking space charaters

remove_nbsp

#!/usr/bin/env python3

# This script replaces each non-breaking space charaters with a space character
# in the given files.
#
# Usage: remove_nbsp <files>
#
# Examples:
#
# Replace NBSPs in two files:
#
#     $ remove_nbsp file1.txt file2.txt
#
# Replace NBSPs in each Erlang source file and header file that is
# (recursively) inside the 'apps' directory:
#
#     $ remove_nbsp $(git ls-files 'apps/*.[eh]rl')
#     File fixed: apps/wo_plugins/include/wo_plugins.hrl


import re
import sys


if len(sys.argv) == 1:
    print('Usage: remove_nbsp <files>')
    sys.exit(1)
    
NBSP = '\u00a0' # char code for non-breaking space

for fname in sys.argv[1:]:
    with open(fname) as f:
        try:
            contents = f.read()
            if NBSP not in contents:
                continue
        except Exception:
            print('Warning: Cannot read file:', fname)
            continue
    with open(fname, 'w') as f:
        contents = re.sub(NBSP, ' ', contents)
        f.write(contents)
        print('File fixed:', fname)