Created
February 2, 2018 17:01
-
-
Save Yutsa/7ed3c8c5c45ae75053b0f3b37941212b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import os | |
import argparse | |
import chardet | |
import codecs | |
from threading import Thread | |
parser = argparse.ArgumentParser( | |
description='Reencode every file in this directory with the right extension.') | |
parser.add_argument("-i", | |
required=True, | |
help='The path of the directory to process.', | |
dest="dirPath") | |
parser.add_argument("-e", | |
required=True, | |
help='The file extension of the files to process', | |
dest="extension") | |
def reencodeFile(file, oldCodec, newCodec): | |
with codecs.open(file, "r", oldCodec) as sourceFile: | |
with codecs.open("temp", "w", newCodec) as targetFile: | |
while True: | |
contents = sourceFile.read(65000) | |
if not contents: | |
break | |
targetFile.write(contents) | |
os.remove(file) | |
os.rename("temp", file) | |
def getCodec(file): | |
with open(file, 'r') as current_file: | |
oldCodec = chardet.detect(current_file.read())["encoding"] | |
return oldCodec | |
def convertDirectory(fullPath): | |
for root, dirs, files in os.walk(fullPath): | |
for dir in dirs: | |
dirPath = os.path.join(root, dir) | |
convertDirectory(dirPath) | |
for file in files: | |
file = os.path.join(root, file) | |
if (os.path.splitext(file)[1] == "." + args.extension): | |
oldCodec = getCodec(file) | |
if oldCodec != "utf-8": | |
print("Reencoding {} from {} to UTF-8".format(file, oldCodec)) | |
reencodeFile(file, oldCodec, "utf-8") | |
if __name__ == "__main__": | |
args = parser.parse_args() | |
fullPath = os.path.abspath(args.dirPath) | |
convertDirectory(fullPath) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment