Fixes UTF-8 files that are wrongly encoded into Latin-1

fix_latin1_utf8_mojibake.py

import json, codecs, re
from functools import partial


input_filename = "message.json"
output_filename = "message_new.json"

fix_mojibake_escapes = partial(
  re.compile(rb'\\u00([\da-f]{2})').sub,
  lambda m: bytes.fromhex(m.group(1).decode()))


with open(input_filename, 'rb') as binary_data:
	repaired = fix_mojibake_escapes(binary_data.read())
	data = json.loads(repaired.decode('utf8'))
	with codecs.open(output_filename, 'w', encoding='utf-8') as outfile:
		json.dump(data, outfile, ensure_ascii=False)