Compare commits
3 Commits
get-tracks
...
master
Author | SHA1 | Date |
---|---|---|
Karchnu | 13dd38ed56 | |
Karchnu | 1bb2b97760 | |
Karchnu | 51538fd5c3 |
54
README.md
54
README.md
|
@ -4,13 +4,9 @@
|
|||
|
||||
# Required applications
|
||||
|
||||
`get-tracks.sh` is a simple shell script based around `ffmpeg`, using `xxd` and `awk`.
|
||||
`get-tracks.sh` is a simple shell script based around `ffmpeg`, using only POSIX tools.
|
||||
|
||||
* ffmpeg
|
||||
* xxd (with '-r' and '-p' options)
|
||||
* awk
|
||||
|
||||
It was tested on both OpenBSD and Linux.
|
||||
It was tested on both OpenBSD and Linux (Ubuntu, Alpine).
|
||||
|
||||
# Usage
|
||||
|
||||
|
@ -36,22 +32,58 @@ The *time-file* must have this format:
|
|||
|
||||
# Environment variables
|
||||
|
||||
The behavior of the script can be changed by several environment variables.
|
||||
|
||||
* **SIMULATION** [empty or not]\
|
||||
do not invoke ffmpeg
|
||||
* **NONUMBER** [empty or 1]\
|
||||
do not write song numbers
|
||||
|
||||
* **FORMAT** [mp3,ogg,opus,…]\
|
||||
see the ffmpeg documentation for the output formats available
|
||||
* **SEPARATOR** [separator] (default: ' - ')\
|
||||
* **FFOPTS** [any ffmpeg options] *(default: '-c:a copy')*\
|
||||
ffmpeg options, can be used to change audio quality\
|
||||
can be **required** to change in case input and output file formats differ\
|
||||
see the ffmpeg documentation for available parameters
|
||||
|
||||
* **NONUMBER** [empty or 1]\
|
||||
do not write song numbers
|
||||
* **SEPARATOR** [separator] *(default: ' - ')*\
|
||||
separator between number and name\
|
||||
example with SEPARATOR='_': 01_intro.opus 02_blah.opus…
|
||||
|
||||
* **HEADERS** [empty or 1]\
|
||||
print environment parameters (verbosity, simulation, etc.)
|
||||
* **VERBOSITY** [0-3] (default: 1)\
|
||||
* **VERBOSITY** [0-3] *(default: 1)*\
|
||||
0: no output except errors from ffmpeg\
|
||||
1: simple indications on the current track being extracted\
|
||||
2: print actual ffmpeg commands the script currently runs
|
||||
|
||||
# Different input and output file formats
|
||||
|
||||
In case you want to change the file format, let's say from `flac` to `opus`, you need to override the default ffmpeg options provided by `get-tracks.sh`.
|
||||
This is done through the `FFOPTS` environment variable, **which needs to NOT be empty** in order to replace the default `get-tracks.sh` behavior (which is `-c:a copy`).
|
||||
By default, `ffmpeg` performs re-encoding by itself.
|
||||
|
||||
```Bash
|
||||
FORMAT=opus FFOPTS=" " get-tracks.sh cd.flac cd.txt
|
||||
```
|
||||
|
||||
### Warning: sometimes you don't even need to
|
||||
|
||||
You may encounter files in some format like `webm` and you want to convert the output files in `opus`.
|
||||
But, inside the `webm` format, you **may** have `opus`-encoded audio.
|
||||
In these cases, no re-encoding is necessary, and you can do something like:
|
||||
|
||||
```Bash
|
||||
FORMAT=opus get-tracks.sh cd.webm cd.txt
|
||||
```
|
||||
|
||||
You'll have a warning mentionning FFOPTS (based on different formats).
|
||||
But the generated audio files won't have any quality loss.
|
||||
This happens sometimes with the `youtube-dl` utility.
|
||||
|
||||
In case there are actual `ffmpeg` errors, and you don't have output audio files, then the contained audio hadn't the right format.
|
||||
You'll have to re-encode.
|
||||
|
||||
# More
|
||||
|
||||
Run `get-track.sh` without arguments.
|
||||
You can get some help by running `get-track.sh` without arguments.
|
||||
|
|
131
get-tracks.sh
131
get-tracks.sh
|
@ -1,7 +1,8 @@
|
|||
#!/usr/bin/env sh
|
||||
|
||||
# From a single byte in hexadecimal per line
|
||||
# to lines ending with 0a (hex for '\n').
|
||||
# From a single byte in hexadecimal per line to lines ending with 0a
|
||||
# (hex for '\n'). Ex: 61 62 63 0a
|
||||
# Required to easily match (and remove) multi-byte characters.
|
||||
regroup_lines() awk '
|
||||
BEGIN {
|
||||
line_start=1
|
||||
|
@ -32,25 +33,40 @@ simple_quote() sed "s/e2 80 99/27/g"
|
|||
# From / to '-'
|
||||
replace_slashes() sed "s/2f/2d/g"
|
||||
|
||||
remove_backslashes() sed "s/5c//g"
|
||||
|
||||
remove_multibyte_characters() sed "s/e2 80 .. //g"
|
||||
|
||||
uppercase() tr "[a-z]" "[A-Z]"
|
||||
|
||||
# One column decimal to plain text.
|
||||
from_dec() awk '{ printf ("%c", $1 + 0) }'
|
||||
|
||||
# Replace spaces by line returns, outputs a single column.
|
||||
spaces_to_line_returns() tr " " "\n"
|
||||
|
||||
# Convert input into hexadecimal and a single byte per line.
|
||||
to_hex_one_column() xxd -p -c 1
|
||||
to_hex_one_column() { od -An -tx1 | awk '{for(i=1;i<=NF;i++){ print $i }}'; }
|
||||
|
||||
# Reverse hexadecimal to original value.
|
||||
from_hex() xxd -p -r
|
||||
# One column hexa to one column decimal.
|
||||
hex_to_dec() { { echo "obase=10;ibase=16;" ; cat ; } | bc ; }
|
||||
|
||||
# Remove non ascii characters, convert "’" to "'", or remove invalid filename characters.
|
||||
# Reverse hexadecimal (with space separators) to original value.
|
||||
from_hex() { spaces_to_line_returns | uppercase | hex_to_dec | from_dec; }
|
||||
|
||||
# Remove non ascii, backslashes and invalid filename characters,
|
||||
# convert "’" to "'", "/" to " - ".
|
||||
to_ascii(){
|
||||
to_hex_one_column | # Convert input into hexadecimal and a single byte per line.
|
||||
regroup_lines | # Required to easily match multi-byte characters.
|
||||
simple_quote | # Convert "’" to "'".
|
||||
replace_slashes | # Replace / by ' - ', since it isn't a valid filename character.
|
||||
to_hex_one_column | # Input to hexadecimal, 1-byte representation per line.
|
||||
regroup_lines | # From 1-byte to x-byte lines with space separators.
|
||||
simple_quote | # From "’" to "'".
|
||||
replace_slashes | # From / to '-'.
|
||||
remove_multibyte_characters | # Remove non ascii values.
|
||||
from_hex # Convert back from hex.
|
||||
remove_backslashes | # Can mess with the script.
|
||||
from_hex # Convert back from hex (x-byte per line, space separator).
|
||||
}
|
||||
|
||||
process_end_of_songs() awk -v NONUMBER="$NONUMBER" -v SEPARATOR="$SEPARATOR" '
|
||||
comp_end_of_tracks() awk -v NONUMBER="$NONUMBER" -v SEPARATOR="$SEPARATOR" '
|
||||
BEGIN {
|
||||
OFS=" "
|
||||
}
|
||||
|
@ -106,7 +122,7 @@ first_column_to_seconds() awk '
|
|||
'
|
||||
|
||||
# Get a more usable time representation for the beginning and the end of songs.
|
||||
process_time_file(){ to_ascii | first_column_to_seconds | process_end_of_songs ; }
|
||||
get_timestamps(){ to_ascii | first_column_to_seconds | comp_end_of_tracks; }
|
||||
|
||||
run_ffmpeg(){
|
||||
file=$1
|
||||
|
@ -130,7 +146,7 @@ run_ffmpeg(){
|
|||
echo "extracting '$final_title'"
|
||||
;;
|
||||
v2)
|
||||
echo "ffmpeg $LOG_LEVEL $FROM $TO -i $INPUT_FILE '$OUTPUT_FILE'"
|
||||
echo "ffmpeg $LOG_LEVEL $FROM $TO -i $INPUT_FILE $FFOPTS '$OUTPUT_FILE'"
|
||||
;;
|
||||
*)
|
||||
echo "verbosity is not set properly" >&2
|
||||
|
@ -139,15 +155,15 @@ run_ffmpeg(){
|
|||
esac
|
||||
|
||||
if [ "$SIMULATION" = "" ]; then
|
||||
$(< /dev/null ffmpeg $LOG_LEVEL $FROM $TO -i "$INPUT_FILE" "$OUTPUT_FILE")
|
||||
ffmpeg $LOG_LEVEL $FROM $TO -i "$INPUT_FILE" $FFOPTS "$OUTPUT_FILE"
|
||||
fi
|
||||
}
|
||||
|
||||
rip(){
|
||||
extraction(){
|
||||
audio_file="$1"
|
||||
time_file="$2"
|
||||
|
||||
process_time_file < "$time_file" | while read LINE; do
|
||||
get_timestamps < "$time_file" | while read LINE; do
|
||||
track_start=$(echo $LINE | cut -d ' ' -f 1)
|
||||
track_end=$(echo $LINE | cut -d ' ' -f 2)
|
||||
track_title=$(echo $LINE | cut -d ' ' -f 3-)
|
||||
|
@ -156,7 +172,12 @@ rip(){
|
|||
track_end=""
|
||||
fi
|
||||
|
||||
run_ffmpeg "${audio_file}" "${track_start}" "${track_end}" "${track_title}.${FORMAT}"
|
||||
# Input is /dev/null, otherwise subshells will take the output
|
||||
# of "get_timestamps" as input.
|
||||
# Be careful: "while read X" is a dangerous shell design.
|
||||
< /dev/null run_ffmpeg "${audio_file}" \
|
||||
"${track_start}" "${track_end}" \
|
||||
"${track_title}.${FORMAT}"
|
||||
done
|
||||
}
|
||||
|
||||
|
@ -174,17 +195,17 @@ Format for <song-list>:
|
|||
1:30 Second track
|
||||
|
||||
Environment variables:
|
||||
- SIMULATION [empty or not]
|
||||
do not invoke ffmpeg
|
||||
- NONUMBER [empty or 1]
|
||||
do not write song numbers
|
||||
- FORMAT [mp3,ogg,opus,…]
|
||||
see the ffmpeg documentation
|
||||
- SIMULATION [empty or not] do not invoke ffmpeg
|
||||
|
||||
- FORMAT [mp3,ogg,opus,…] see ffmpeg documentation
|
||||
- FFOPTS (default: '-c:a copy') see ffmpeg documentation
|
||||
|
||||
- NONUMBER [empty or 1] do not write song numbers
|
||||
- SEPARATOR [separator] (default: ' - ')
|
||||
separator between number and name
|
||||
example with SEPARATOR='_': 01_intro.opus 02_blah.opus…
|
||||
- HEADERS [empty or 1]
|
||||
print environment parameters (verbosity, simulation, etc.)
|
||||
|
||||
- HEADERS [empty or 1] print env params (verbosity, quality, etc.)
|
||||
- VERBOSITY [0-3] (default: 1)
|
||||
0: no output except errors from ffmpeg
|
||||
1: simple indications on the current track being extracted
|
||||
|
@ -192,24 +213,42 @@ Environment variables:
|
|||
END
|
||||
}
|
||||
|
||||
if [ $# -lt 1 ]; then
|
||||
usage
|
||||
exit 0
|
||||
fi
|
||||
|
||||
header(){
|
||||
if [ "$HEADERS" = "1" ]; then
|
||||
echo $*
|
||||
fi
|
||||
}
|
||||
|
||||
warning(){
|
||||
echo "WARNING: $*"
|
||||
}
|
||||
|
||||
# Default output format is based on the extension of the input audio file.
|
||||
if [ $# -eq 2 ]; then
|
||||
DEFAULT_FORMAT="$(echo $1 | awk -F . '{print $NF}')"
|
||||
else
|
||||
header "no default FORMAT selected"
|
||||
fi
|
||||
|
||||
if [ "$FORMAT" = "" ]; then
|
||||
header "default FORMAT: opus"
|
||||
FORMAT="opus"
|
||||
FORMAT="$DEFAULT_FORMAT"
|
||||
header "default FORMAT: ${FORMAT}"
|
||||
else
|
||||
header "FORMAT: $FORMAT"
|
||||
fi
|
||||
|
||||
# For unexperienced users, print a warning when input and output formats differ.
|
||||
# In case FFOPTS is set, encoding is expected to be handled, drop the warning.
|
||||
# Example (remove the get-tracks.sh default behavior, perform re-encoding):
|
||||
# FFOPTS=" "
|
||||
if [ "$FFOPTS" = "" ] && [ "$FORMAT" != "$DEFAULT_FORMAT" ]; then
|
||||
warning "input and output formats seem to differ"
|
||||
warning "1. re-encoding may be required (through the FFOPTS envvar)"
|
||||
warning "2. FFOPTS represents ffmpeg options, directly given to ffmpeg"
|
||||
warning ' (default: "-c:a copy" = copy without re-encoding)'
|
||||
warning ' You can put FFOPTS=" " if you want to perform re-encoding.'
|
||||
fi
|
||||
|
||||
if [ "$VERBOSITY" = "" ]; then
|
||||
header "default VERBOSITY: 1"
|
||||
VERBOSITY=1
|
||||
|
@ -233,24 +272,20 @@ else
|
|||
SEPARATOR=""
|
||||
fi
|
||||
|
||||
if [ "$FFOPTS" != "" ]; then
|
||||
header "FFOPTS envvar is set: ${FFOPTS}."
|
||||
else
|
||||
FFOPTS="-c:a copy"
|
||||
header "default FFOPTS: ${FFOPTS}"
|
||||
fi
|
||||
|
||||
if [ "$SIMULATION" != "" ]; then
|
||||
header "SIMULATION envvar is set: this is a simulation."
|
||||
fi
|
||||
|
||||
</dev/null xxd -p >/dev/null 2>/dev/null
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "xxd: you don't have an xxd program with '-p' option." 1>&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
</dev/null xxd -r >/dev/null 2>/dev/null
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "xxd: you don't have an xxd program with '-r' option." 1>&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
case $# in
|
||||
1) process_time_file < "$1" ;;
|
||||
2) rip "$1" "$2" ;;
|
||||
*) usage 1>&2 ; exit 1 ;;
|
||||
0) usage; exit 0;;
|
||||
1) get_timestamps < "$1";;
|
||||
2) extraction "$1" "$2";;
|
||||
*) usage 1>&2; exit 1;;
|
||||
esac
|
||||
|
|
Loading…
Reference in New Issue