Fix malformed CSVs

fix-csv.py

import csv
import sys

def escape_field(field):
    if any(c in field for c in ['"', ',', '\n', '\r']):
        field = field.replace('"', '""')
        return f'"{field}"'
    return field

def fix_row(fields, expected_columns):
    if len(fields) == expected_columns:
        return [escape_field(f) for f in fields]
    elif len(fields) > expected_columns:
        # assume last column is valid; merge the rest
        merged = ','.join(fields[:-1])
        return [escape_field(merged), escape_field(fields[-1])]
    else:
        # too few fields — pad with empty strings
        return [escape_field(f) for f in fields] + [''] * (expected_columns - len(fields))

def main():
    input_path = sys.argv[1]
    output_path = sys.argv[2] if len(sys.argv) > 2 else None

    with open(input_path, newline='', encoding='utf-8') as infile:
        lines = infile.readlines()

    with (open(output_path, 'w', newline='', encoding='utf-8') if output_path else sys.stdout) as outfile:
        writer = csv.writer(outfile)

        header = lines[0].strip().split(',')
        expected_columns = len(header)
        writer.writerow(header)

        for line in lines[1:]:
            if not line.strip():
                continue
            fields = [f.strip() for f in line.strip().split(',')]
            fixed = fix_row(fields, expected_columns)
            writer.writerow(fixed)

if __name__ == "__main__":
    main()