Created
January 25, 2017 06:44
-
-
Save bibby/b4bec314983522e96ab9cc38faba798f to your computer and use it in GitHub Desktop.
ass UTF-16 subfile to UTF-8 plain text
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
# rfw/python-ass does the heavy lifting, | |
# but I needed to hack around UTF-16 encoded files, | |
# saving them back as UTF-8 | |
import ass | |
import re | |
import sys | |
in_file = sys.argv[1] | |
out_file = re.sub('[as]+$', 'txt', in_file) | |
tmp_file = '/tmp/ass' | |
font_pattern = '\{[^\}]+\}' | |
with open(in_file, 'rb') as source_file: | |
with open(tmp_file, 'w+b') as dest_file: | |
contents = source_file.read() | |
dest_file.write(contents.decode('utf-16').encode('utf-8')) | |
with open(tmp_file, "r") as f: | |
with open(out_file, 'w') as final_file: | |
doc = ass.parse(f) | |
for e in doc.events: | |
t = e.text | |
t = t.replace('\N', "\n") | |
t = re.sub(font_pattern, '' , t) | |
t = re.sub(' ', ' ' , t).strip() | |
final_file.write(t) | |
final_file.write("\n") | |
print t |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment