#!/usr/bin/python3
# coding: utf-8

# Run: python3 fix.py
# See:
# https://github.com/rspeer/python-ftfy
# https://stackoverflow.com/questions/7861358/strange-characters-in-database-text-%C3%83-%C3%83-%C2%A2-%C3%A2-%E2%82%AC

import ftfy

# Set input_file
input_file = open('bad.sql', 'r', encoding="utf-8")
# Set output file
output_file = open ('good.sql', 'w')

# Create fixed output stream
stream = ftfy.fix_file(
    input_file,
    encoding=None,
    fix_entities='auto',
    remove_terminal_escapes=False,
    fix_encoding=True,
    fix_latin_ligatures=False,
    fix_character_width=False,
    uncurl_quotes=False,
    fix_line_breaks=False,
    fix_surrogates=False,
    remove_control_chars=False,
    # remove_bom=False,
    normalization='NFC'
)

# Save stream to output file
stream_iterator = iter(stream)
while stream_iterator:
    try:
        line = next(stream_iterator)
        output_file.write(line)
    except StopIteration:
        break