Fix file encoding when file has unicode code points written as strings (eg: "a string with u00e1 or \u00d1 code point as string in it")

unicode_code_point_fix.py

from re import compile, findall, split

with open('original_file', 'r') as of:
    with open('fixed_file', 'w') as ff:
        for line in of:
            # looks for substrings that are either 'u00fo' or '\u00fo'
            pattern = compile(r'\\?u00..')
            code_points = findall(pattern, line)
            pieces = split(pattern, line)
            res = ''
            for idx, cp in enumerate(code_points):
                res += pieces[idx] + chr(int(cp[1::] if cp[0] == 'u' else cp[2::], 16))
            else:
                res += pieces[-1]
                ff.write(res)