- 2019-11-19 22_43_17.jpg (48.49 KiB) Viewed 24431 times
Everytime the script is executed it processes the next MKV file. So you need to restart it by cronjob or task schedulers. You can copy & paste this script directly into the command line as well.
P.S. Please vote for auto-naming of forced subtitles.
Settings
- movies_path: The path to your movie collection
- docker_config_path: Compare with your docker configuration
- sub_langs: "all" exports all subtitle languages or "ger,eng,tur" exports these specific languages
- sub_forced_max_size maybe you want to reduce the subtitle filesize for TV shows episodes
Requirements
- Linux
- Docker
- MKVToolNix Container
- Movie collection in sub folders like "/volume1/movies/Ben Hur (1959)/Ben Hur (1959).mkv"
Script
Code: Select all
#!/bin/bash
# #####################################
# mkv2sup v0.5
#
# Notes:
# mkv2sup automatically exports all subtitles of all MKV files in a specific folder.
# After that it determines the forced subtitles. MKVs without (compatible) subtitles will be skipped.
# It works only with MKVs in subfolders like /volume1/movies/Ben Hur/Ben Hur.mkv
#
# Changelog:
# 0.5
# - "bin/bash" added to the head of the script to force the usage of the correct interpreter
# 0.4
# - check mkv modification filetime to ensure its not currently written through an other app
# 0.3
# - Docker is now optional
# - No exported SUP will be deleted if the new option <preserve_sup_files> is enabled
# - Check if mkvtoolnix docker container is in use by other bash script before killing it
# 0.2
# - Bug fix: Changed some exit status codes
# - Bug fix: Some file names containing dots were cut
# - Bug fix: Now all <sub_langs> of forced subtitles are renamed and not only those with <default_lang>
# - Bug fix: Named SUP files that were only skipped, will now be deleted, too
# 0.1
# - first release
#
# Todo:
# - update subtitle track names in mkv file
# - set forced track as default in mkv file
# - how to solve doubles (two forced subtitle tracks in the same language, at the moment those will be tried to be renamed, but this fails as there already exists one)
# - add support for DVDs S_VOBSUB subtitles
# - determine all SRT subtitles (Regular, SDH, etc.) by using word/char matching
# - while writing SUP files check if one contains the word "Forced" and is <default_lang>
# - skip MKV files that are currently written
# #####################################
#
# ######### Settings ##################
movies_path="/volume1/Movies/"
docker_config_path="/volume1/docker"
sub_langs="ger,eng,tur" # Use "all" to preserve all subtitle languages. Note: The first language is set as default.
sub_forced_max_size="3MB"
preserve_sup_files=true
# #####################################
#
# ######### Script ####################
# check user settings
movies_path=$([[ "${movies_path: -1}" == "/" ]] && echo "${movies_path%?}" || echo "$movies_path")
docker_config_path=$([[ "${docker_config_path: -1}" != "/" ]] && echo "${docker_config_path}/" || echo "$docker_config_path")
default_lang="${sub_langs:0:3}" # first language is used as default language
sub_forced_max_size="${sub_forced_max_size//[!0-9.]/}" # float filtering (https://stackoverflow.com/a/19724571/318765)
sub_forced_max_size=$(awk "BEGIN { print $sub_forced_max_size*1000000}") # convert MB to Bytes
mkv_path=""
function exitus() {
exit_status=$1
# check if container exists
if [[ -x "$(command -v docker)" ]] && [[ "$(docker ps -q -f name=mkvtoolnix_mkv2sub)" ]]; then
# stop container only if its not in use (by other shell script)
mkvtoolnix_cpu_usage="$(docker stats mkvtoolnix_mkv2sub --no-stream --format "{{.CPUPerc}}")"
# if [[ ${mkvtoolnix_cpu_usage%.*} -lt 1 ]]; then
# we do not stop the container as our script is not race-condition safe!
# echo "Stop mkvtoolnix container"
# docker stop mkvtoolnix_mkv2sub
# docker rm mkvtoolnix_mkv2sub
# fi
fi
exit $exit_status
}
function mkv_getinfo() {
# check if mkvtoolnix exists
if [[ -x "$(command -v mkvmerge)" ]]; then
echo "mkvtoolnix will be used to fetch tracks information"
mkv_info="$(mkvmerge -J "$mkv_path")"
return "$mkv_info"
# check if docker exists
elif [[ -x "$(command -v docker)" ]]; then
echo "Docker will be used to fetch tracks information"
# check if mkvtoolnix container exists
if [[ ! "$(docker ps -q -f name=mkvtoolnix_mkv2sub)" ]]; then # https://stackoverflow.com/a/38576401/318765
# check for blocking container
if [[ "$(docker ps -aq -f status=exited -f name=mkvtoolnix_mkv2sub)" ]]; then
docker rm mkvtoolnix_mkv2sub
fi
echo "mkvtoolnix container needs to be started"
# start mkvtoolnix container
docker_options=(
run -d
--name=mkvtoolnix_mkv2sub
-e TZ=Europe/Berlin
-v "${docker_config_path}mkvtoolnix_mkv2sub:/config:rw"
-v "${movies_path}:/storage:rw"
jlesage/mkvtoolnix
)
echo "docker ${docker_options[@]}"
docker "${docker_options[@]}"
fi
mkv_info="$(docker exec mkvtoolnix_mkv2sub /usr/bin/mkvmerge -J "$docker_mkv_path")"
return
fi
echo "mkvtoolnix and docker do not exist!"
exitus 1
}
function mkv_extract() {
# check if mkvtoolnix exists
if [[ -x "$(command -v mkvmerge)" ]]; then
echo "mkvtoolnix will be used to extract tracks"
mkv_info="$(mkvextract "$mkv_path" "${mkvextract_options[@]}")"
return
# check if docker exists
elif [[ -x "$(command -v docker)" ]]; then
echo "mkvtoolnix@docker will be used to extract tracks"
# check if mkvtoolnix container exists
if [[ ! "$(docker ps -q -f name=mkvtoolnix_mkv2sub)" ]]; then # https://stackoverflow.com/a/38576401/318765
# check for blocking container
if [[ ! "$(docker ps -aq -f status=exited -f name=mkvtoolnix_mkv2sub)" ]]; then
docker rm mkvtoolnix_mkv2sub
fi
echo "mkvtoolnixcontainer needs to be started"
# start mkvtoolnix container
docker_options=(
run -d
--name=mkvtoolnix_mkv2sub
-e TZ=Europe/Berlin
-v "${docker_config_path}mkvtoolnix_mkv2sub:/config:rw"
-v "${movies_path}:/storage:rw"
jlesage/mkvtoolnix
)
echo "docker ${docker_options[@]}"
docker "${docker_options[@]}"
fi
echo "docker exec mkvtoolnix_mkv2sub /usr/bin/mkvextract $docker_mkv_path ${mkvextract_options[@]}"
docker exec mkvtoolnix_mkv2sub /usr/bin/mkvextract "$docker_mkv_path" "${mkvextract_options[@]}"
return
fi
echo "mkvtoolnix and docker do not exist!"
exitus 1
}
# get next mkv file
shopt -s nullglob # avoid empty directory errors (https://unix.stackexchange.com/questions/56051/avoiding-errors-due-to-unexpanded-asterisk)
for movie_path in "$movies_path"/*; do
mkv_folder="$(basename "$movie_path")"
echo "Parsing '$mkv_folder'..."
for mkv_path in "$movie_path"/*.mkv; do
mkv_basename=$(basename "$mkv_path")
mkv_filename=${mkv_basename%.*}
file_time=$(stat -c %Y "$mkv_path") # file modification time
file_time=$(($file_time+120)) # the last modification of the file should be a few time ago
current_time=$(date +%s) # actual timestamp
if [[ $file_time -gt $current_time ]]; then
continue
fi
for sup_path in "$movie_path"/*.sup; do
sup_basename=$(basename "$sup_path")
if [[ $sup_basename == *"$mkv_filename."* ]]; then
# skip this mkv file because its sup subtitle has been found
continue 2
fi
done
for srt_path in "$movie_path"/*.srt; do
srt_basename=$(basename "$srt_path")
if [[ $srt_basename == *"$mkv_filename."* ]]; then
# skip this mkv file because its srt subtitle has been found
continue 2
fi
done
echo "'$mkv_path' has been found."
# we found an mkv file without subtitle files
docker_mkv_path="/storage/${mkv_folder}/${mkv_basename}"
break 2;
done
done
shopt -u nullglob # its important to reset this setting (https://unix.stackexchange.com/questions/534858/why-does-shopt-s-nullglob-remove-a-string-with-question-mark-in-an-array-elemen)
# no mkv file found
if [[ -z $docker_mkv_path ]]; then
echo "No mkv files found or all subtitles have been exported!"
exitus 0
fi
mkv_getinfo # uses $mkv_path, fills $mkv_info
if [[ -z $mkv_info ]]; then
echo "Error while fetching tracks information with mkvmerge"
exitus 1
fi
echo "Informations of all tracks have been obtained."
# parse info
sub_track_ids=(); track_langs=(); track_names=(); track_codec_ids=();
while read -r line ; do
echo $line
# Note: we did not use "jq -r" to parse JSON as it needs installation
track_codec_name=$(echo $line | grep -oP '^.*?(?=\")')
track_id=$(echo $line | grep -oP '(?<="id": )[0-9]+')
track_bits=$(echo $line | grep -oP '(?<="audio_bits_per_sample": )[0-9]+')
track_channels=$(echo $line | grep -oP '(?<="audio_channels": )[0-9]+')
track_codec_id=$(echo $line | grep -oP '(?<="codec_id": ").*?[^\\](?=\",)')
track_lang=$(echo $line | grep -oP '(?<="language": ")[a-z]+')
track_name=$(echo $line | grep -oP '(?<="track_name": ").*?[^\\](?=\",)') # most flexible way of getting a JSON value (https://stackoverflow.com/a/6852427/318765)
track_default=$(echo $line | grep -oP '(?<="default_track": )(true|false)')
track_forced=$(echo $line | grep -oP '(?<="forced_track": )(true|false)')
track_type=$(echo $line | grep -oP '(?<=")[a-z]+$')
# collect track langs
if [[ -n $track_lang ]]; then
track_langs[$track_id]=$track_lang
else
track_langs[$track_id]='und' # und = undetermined
fi
# collect track names
if [[ -n $track_name ]]; then
track_names[$track_id]=$track_name
else
track_names[$track_id]='und'
fi
# collect codec ids
if [[ -n $track_codec_id ]]; then
track_codec_ids[$track_id]=$track_codec_id
else
track_codec_ids[$track_id]='und'
fi
# collect subtitles in prefered languages
if [[ $track_type == "subtitles" ]] && [[ $track_codec_id == "S_HDMV/PGS" ]]; then
if [[ $sub_langs == "all" ]] || [[ $sub_langs == *"$track_lang"* ]]; then
sub_track_ids+=("$track_id")
fi
fi
done < <(echo "$mkv_info" |
tr -d '\n' | # we need to remove line breaks with "tr" to force grep to return one-liners
grep -oP '(?<=codec": ").*?"type": "[a-z]+') # Regex is faster than looping through all lines
# create empty sup file if mkv file does not contain any subtitles (by that it will be skipped in next turn)
if [[ ${#sub_track_ids[@]} -eq 0 ]];then
empty_sup_filename="${movies_path}/${mkv_folder}/${mkv_filename}.nosubs.sup"
echo "The empty SUP file '${empty_sup_filename}' will be created to skip MKV file '${mkv_path}' in the next turn as it does not contain any (compatible) subtitles."
touch "$empty_sup_filename"
exitus 0
fi
# build mkvextract export parameter
mkvextract_options=(tracks)
for track_id in "${sub_track_ids[@]}"; do
# file naming scheme "Movie_Name.[Language_Code].forced.ext" adopted from Plex (https://support.plex.tv/articles/200471133-adding-local-subtitles-to-your-media/#toc-3)
mkvextract_options+=("${track_id}:/storage/${mkv_folder}/${mkv_filename}.track${track_id}.${track_langs[$track_id]}.${track_names[$track_id]}.sup")
done
# export all subtitles
mkv_extract # uses mkv_path, docker_mkv_path, mkvextract_options, movies_path
echo "Successfully extracted all subtitles"
# determine forced subtitle
shopt -s nullglob
shopt -s nocasematch # insensitive string comparison (https://stackoverflow.com/a/14138301/318765)
forced_found=false
for sup_path in "${movie_path}"/*.sup; do
# get path parts
sup_dirname=$(dirname "$sup_path")
sup_basename=$(basename "$sup_path")
sup_filename=${sup_basename%.*.*.*.*} # (filename).track[0-9].<lang>.<name>.sup
sup_extension=${sup_basename/#"$sup_filename"./} # filename.(track[0-9].<lang>.<name>.sup)
# fetch track data through filename
IFS='.' # set internal field separator to dot (default is whitespace)
read -ra track_data <<< "$sup_extension" # explode to array (https://stackoverflow.com/a/918931/318765)
unset IFS; # unset internal field separator
track_id=${track_data[0]}
track_id=${track_id/track/} # remove the word "track"
track_lang=${track_data[1]}
track_name=${track_data[2]}
# skip SUP files with wrong naming scheme
if [[ -n ${track_id//[0-9]/} ]]; then
echo "'$track_id' is not a track id"
continue
fi
if [[ ${#track_lang} -lt 2 ]] || [[ ${#track_lang} -gt 3 ]] || [[ -n "${track_lang//[a-zA-Z]/}" ]]; then
echo "'$track_lang' is not a track lang"
continue
fi
if [[ -n ${track_name//[a-zA-Z \']/} ]]; then
echo "'$track_name' is not a track name"
continue
fi
# set Plex compatible filename (https://support.plex.tv/articles/200471133-adding-local-subtitles-to-your-media/#toc-3)
sup_filename_new="${sup_dirname}/${sup_filename}.${track_lang}.forced.sup"
# determine by track name
if [[ $track_name == "forced" ]] && [[ $sub_langs == *"$track_lang"* ]] || [[ $default_lang == "all" ]]; then
forced_found=true
mv "$sup_path" "$sup_filename_new"
echo "'$sup_path' has been renamed to '$sup_filename_new'"
continue
fi
# skip subtitle tracks that already have names like "Regular", "SDH", etc.)
if [[ $track_name != "und" ]];then
if [[ $preserve_sup_files == "false" ]]; then
rm -rf "$sup_path"
echo "'$sup_path' has been deleted"
fi
continue
fi
# determine by filesize
filesize=$(stat -c%s "$sup_path")
if [ $sub_forced_max_size -ge $filesize ]; then
forced_found=true
echo "'$sup_path' is small enough to be a forced subtitle"
mv "$sup_path" "$sup_filename_new"
# cp --backup "$sup_path" "$sup_filename_new"
echo "'$sup_path' has been renamed to '$sup_filename_new'"
continue
fi
# delete all other exported subtitles
if [[ $preserve_sup_files == "false" ]]; then
rm -rf "$sup_path"
echo "'$sup_path' has been deleted"
fi
done
shopt -u nocasematch
shopt -u nullglob
# create empty sup file if mkv does not contain at least one forced subtitle (by that it will be skipped in next turn)
if [[ $preserve_sup_files != "true" ]] && [[ $forced_found != "true" ]]; then
empty_sup_filename="${movies_path}/${mkv_folder}/${mkv_filename}.noforced.sup"
echo "The empty SUP file '${empty_sup_filename}' has been created to skip MKV file '${mkv_path}' in the next turn as it does not contain forced subtitles."
touch "$empty_sup_filename"
exitus 0
fi
exitus 0