usage: destroy_nulls.py [-h] [--overwrite] input_filepath [output_filepath]
Process a file to remove BOM and NULL characters, re-encode as UTF8.
positional arguments:
input_filepath Path to the input file
output_filepath Path to the output result file
options:
-h, --help show this help message and exit
--overwrite If specified, overwrite the input file in place
python3 destroy_nulls.py airtable_output.csv --overwrite
| # MIT License | |
| # Sebastian Reategui <[email protected]> | |
| import argparse | |
| def process_file(input_filepath, output_filepath): | |
| # Read the file | |
| with open(input_filepath, 'rb') as f: | |
| content = f.read() | |
| # Remove BOM (Byte Order Mark) if present | |
| if content[:3] == b'\xef\xbb\xbf': | |
| content = content[3:] | |
| # Decode to UTF-8, ignoring errors | |
| content = content.decode('utf-8', errors='ignore') | |
| # Remove NULL characters | |
| content = content.replace('\x00', '') | |
| # Convert back to bytes | |
| content = content.encode('utf-8') | |
| # Write the processed content to the output file | |
| with open(output_filepath, 'wb') as f: | |
| f.write(content) | |
| if __name__ == '__main__': | |
| parser = argparse.ArgumentParser(description='Process a file to remove BOM and NULL characters, re-encode as UTF8.') | |
| parser.add_argument('input_filepath', type=str, help='Path to the input file') | |
| parser.add_argument('output_filepath', type=str, nargs='?', help='Path to the output result file') | |
| parser.add_argument('--overwrite', action='store_true', help='If specified, overwrite the input file in place') | |
| args = parser.parse_args() | |
| # When specified overwrite the original file | |
| if args.overwrite: | |
| args.output_filepath = args.input_filepath | |
| elif not args.output_filepath: | |
| parser.error('the following arguments are required: output_filepath') | |
| process_file(args.input_filepath, args.output_filepath) |