Last active
September 22, 2016 16:20
-
-
Save Barlog951/69aceea68c38230c57d6658884e2349c to your computer and use it in GitHub Desktop.
Automated subtitles convert to UTF-8
This file contains hidden or 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
#!/bin/bash | |
LANGUAGE=czech | |
TO=utf8 | |
CONVERT="enca -L $LANGUAGE -x $TO" | |
# Find and onvert | |
find ./ -type f -name "*.srt" | while read fn; do | |
IS_TARGET=`enca "${fn}" | egrep -ow -m 1 'UTF-8|Unrecognized|KOI8-CS2|7bit ASCII|UCS-2|Macintosh Central European'` | |
if [ "$IS_TARGET" != "UTF-8" ] && | |
[ "$IS_TARGET" != "UCS-2" ] && | |
[ "$IS_TARGET" != "Macintosh Central European" ] && | |
[ "$IS_TARGET" != "Unrecognized" ] && | |
[ "$IS_TARGET" != "7bit ASCII" ] && | |
[ "$IS_TARGET" != "KOI8-CS2" ]; then | |
echo "${fn} ---- Will be converted!" | |
# optional backup of original srt | |
# cp "${fn}" "${fn}.bak" | |
$CONVERT "${fn}" | |
fi | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment