forked from HPR/hpr-tools
31eb5d200f
InternetArchive/recover_transcripts: Bash script to be run on 'borg'
which collects files missing on the IA ready for upload as part of
the missing asset repair process.
InternetArchive/repair_assets: Bash script to take assets from the IA
(after they had been repaired on 'borg') and copy them to the HPR
server for the notes to access. The local machine, where this was
run, was used to store files being uploaded. The planned script to
modify the notes to reflect the new file locations was never
finished. Notes were edited with Vim using a few macros.
InternetArchive/repair_item: Bash script which is best run on 'borg',
which repairs an IA item by comparing the files on the IA with the
files on 'borg' (or a local machine). These files are either in
'/data/IA/uploads/' or in the temporary file hierarchy used by
'recover_transcripts' (which calls it). Used after a normal IA
upload to check for and make good any missed file uploads (due to
timeouts, etc). Also used during asset repairs, but that project is
now finished.
InternetArchive/snapshot_metadata: Bash script which collects detailed
metadata from the IA in JSON format and saves it locally (run on
a local PC). Older shows on the IA often contained derivative files
which were identified by the script 'view_derivatives'. These files
were never needed, they were IA artefacts, so can be deleted (see
the script header for how).
InternetArchive/view_derivatives: Perl script to interpret a file of
JSON metadata from the IA for an HPR show in order to determine the
parent-child hierarchy of files where there may be derivatives. We
don't want IA-generated derivatives, but this process was hard to
turn off in earlier times. Generates a hierarchical report and
a list of unwanted derivatives (see 'snapshot_metadata' for more
details of how this was used).
205 lines
5.7 KiB
Bash
Executable File
205 lines
5.7 KiB
Bash
Executable File
#!/bin/bash -
|
|
#===============================================================================
|
|
#
|
|
# FILE: snapshot_metadata
|
|
#
|
|
# USAGE: ./snapshot_metadata episode_number
|
|
#
|
|
# DESCRIPTION: Collects JSON metadata from the IA for a given show and stores
|
|
# it in the cache. Runs 'view_derivatives' on the JSON to
|
|
# display the derivatives if any, and to save their names if
|
|
# found, for deletion.
|
|
# Deletion is performed thus (external to this script):
|
|
#
|
|
# cat assets/hpr$(./next_repair)/derived.lis | xargs ia delete hpr$(./next_repair) --no-backup
|
|
#
|
|
# OPTIONS: ---
|
|
# REQUIREMENTS: ---
|
|
# BUGS: ---
|
|
# NOTES: ---
|
|
# AUTHOR: Dave Morriss (djm), Dave.Morriss@gmail.com
|
|
# VERSION: 0.0.3
|
|
# CREATED: 2024-08-16 20:36:51
|
|
# REVISION: 2024-10-02 17:40:13
|
|
#
|
|
#===============================================================================
|
|
|
|
set -o nounset # Treat unset variables as an error
|
|
|
|
VERSION="0.0.3"
|
|
|
|
SCRIPT=${0##*/}
|
|
# DIR=${0%/*}
|
|
|
|
STDOUT="/dev/fd/2"
|
|
|
|
#
|
|
# Select the appropriate working directory for the host
|
|
#
|
|
case $(hostname) in
|
|
i7-desktop)
|
|
BASEDIR="$HOME/HPR/InternetArchive"
|
|
;;
|
|
borg)
|
|
BASEDIR="$HOME/IA"
|
|
;;
|
|
*)
|
|
echo "Wrong host!"
|
|
exit 1
|
|
;;
|
|
esac
|
|
|
|
cd "$BASEDIR" || { echo "Failed to cd to $BASEDIR"; exit 1; }
|
|
|
|
#
|
|
# Load library functions
|
|
#
|
|
LIB="$HOME/HPR/function_lib.sh"
|
|
[ -e "$LIB" ] || { echo "Unable to source functions"; exit; }
|
|
# shellcheck disable=SC1090
|
|
source "$LIB"
|
|
|
|
#
|
|
# Enable coloured messages
|
|
#
|
|
define_colours
|
|
|
|
#
|
|
# Sanity checks
|
|
#
|
|
IA=$(command -v ia)
|
|
[ -n "$IA" ] || { echo "Program 'ia' was not found"; exit 1; }
|
|
VIEWD="$BASEDIR/view_derivatives"
|
|
[ -e "$VIEWD" ] || { echo "Program '$VIEWD' was not found"; exit 1; }
|
|
|
|
# {{{ -- Functions -- _usage
|
|
|
|
#=== FUNCTION ================================================================
|
|
# NAME: make_dir
|
|
# DESCRIPTION: Make a directory if it doesn't exist, failing gracefully on
|
|
# errors.
|
|
# PARAMETERS: $1 directory path
|
|
# RETURNS: True if success, otherwise exits the caller script
|
|
#===============================================================================
|
|
make_dir () {
|
|
local dir="${1}"
|
|
|
|
if [[ ! -d $dir ]]; then
|
|
mkdir -p "$dir" || {
|
|
coloured 'red' "Failed to create $dir"
|
|
exit 1
|
|
}
|
|
fi
|
|
}
|
|
|
|
#=== FUNCTION ================================================================
|
|
# NAME: _usage
|
|
# DESCRIPTION: Reports usage; always exits the script after doing so
|
|
# PARAMETERS: 1 - the integer to pass to the 'exit' command
|
|
# RETURNS: Nothing
|
|
#===============================================================================
|
|
_usage () {
|
|
local -i result=${1:-0}
|
|
|
|
cat >$STDOUT <<-endusage
|
|
${SCRIPT} - version: ${VERSION}
|
|
|
|
Usage: ./${SCRIPT} showid
|
|
|
|
Collects notes for a show and adds them to the cache directory
|
|
|
|
Arguments:
|
|
showid The show id in the form 'hpr1234'
|
|
|
|
endusage
|
|
exit "$result"
|
|
}
|
|
|
|
# }}}
|
|
|
|
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
#-------------------------------------------------------------------------------
|
|
# Argument check
|
|
#-------------------------------------------------------------------------------
|
|
# Should have one argument
|
|
#
|
|
if [[ $# != 1 ]]; then
|
|
coloured 'red' "Missing argument"
|
|
_usage 1
|
|
fi
|
|
show="${1,,}"
|
|
|
|
#
|
|
# Ensure show id is correctly formatted. We want it to be 'hpr1234' but we
|
|
# allow the 'hpr' bit to be omitted, as well as any leading zeroes. We need to
|
|
# handle the weirdness of "leading zero means octal" though, but we always
|
|
# store it as 'hpr1234' once processed.
|
|
#
|
|
if [[ $show =~ (hpr)?([0-9]+) ]]; then
|
|
printf -v show 'hpr%04d' "$((10#${BASH_REMATCH[2]}))"
|
|
else
|
|
coloured 'red' "Incorrect show specification: $show"
|
|
coloured 'yellow' "Use 'hpr9999' or '9999' format"
|
|
exit 1
|
|
fi
|
|
|
|
#-------------------------------------------------------------------------------
|
|
# Setting up paths
|
|
#-------------------------------------------------------------------------------
|
|
#
|
|
# CACHEDIR is where we store asset details and files
|
|
#
|
|
CACHEDIR="$BASEDIR/assets"
|
|
[ ! -d "$CACHEDIR" ] && {
|
|
coloured 'red' "Creating cache directory"
|
|
make_dir "$CACHEDIR"
|
|
}
|
|
|
|
#
|
|
# Pointers into the cache:
|
|
# LOCAL_ASSETDIR - where the cache for this show lives
|
|
#
|
|
LOCAL_ASSETDIR="$CACHEDIR/${show}"
|
|
[ ! -d "$LOCAL_ASSETDIR" ] && {
|
|
coloured 'green' "Creating cache directory for $show"
|
|
make_dir "$LOCAL_ASSETDIR"
|
|
}
|
|
|
|
METADATA="$CACHEDIR/$show/metadata.json"
|
|
DERIVED="$CACHEDIR/$show/derived.lis"
|
|
|
|
#-------------------------------------------------------------------------------
|
|
# Save the IA metadata unless we already have the file
|
|
#-------------------------------------------------------------------------------
|
|
if [[ ! -e $METADATA ]]; then
|
|
if ia metadata "$show" > "$METADATA"; then
|
|
coloured 'green' "Created metadata file"
|
|
if [[ ! -s $METADATA ]]; then
|
|
coloured 'red' "Metadata file is empty"
|
|
fi
|
|
else
|
|
coloured 'red' "Creation of metadata file failed"
|
|
exit 1
|
|
fi
|
|
else
|
|
coloured 'yellow' "Metadata already exists, not replacing it"
|
|
fi
|
|
|
|
#-------------------------------------------------------------------------------
|
|
# Use the collected metadata to view the state of the IA, and collect the derived file names
|
|
#-------------------------------------------------------------------------------
|
|
coloured 'blue' "Viewing IA files"
|
|
"$VIEWD" -verb "$METADATA"
|
|
|
|
if "$VIEWD" -list "$METADATA" > "$DERIVED"; then
|
|
nfiles="$(wc -l < "$DERIVED")"
|
|
coloured 'green' "Saved 'derived' files for show $show ($nfiles)"
|
|
else
|
|
coloured 'red' "Creation of $DERIVED file failed"
|
|
fi
|
|
|
|
exit
|
|
|
|
# vim: syntax=sh:ts=8:sw=4:ai:et:tw=78:fo=tcrqn21:fdm=marker
|