Convert Latin 1 encoding to UTF-8

latin1_to_utf8.py

from __future__ import print_function
import codecs
import os
import fnmatch


def delete_if_exists(filename):
    if os.path.exists(filename):
        os.remove(filename)


def find_files(root_folder, filter_pattern):
    for root, dirs, files in os.walk(root_directory):
        for basename in filter(lambda n: fnmatch(n, filter_pattern), files):
            yield os.path.join(root, basename)


def normalize_single_file(filename):
    filename_bak = os.path.splitext(filename)[0] + ".bak"
    delete_if_exists(filename_bak)
    os.rename(filename, filename_bak)
    with codecs.open(filename_bak, "r", encoding="latin_1") as f_in, \
            codecs.open(filename, "w", encoding="utf-8") as f_out:
        for line in f_in:
            f_out.write(line)
            f_out.write(preferred_linesep)


def normalize_in_all_subfolders(root_folder, filter_pattern):
    for filename in find_files(root_folder, filter_pattern):
        print("Processing '{:s}'...".format(filename))
        normalize_single_file(filename)


preferred_linesep = "\n"
normalize_in_all_subfolders(r".", "*.txt")