mirror of
https://github.com/superseriousbusiness/gotosocial.git
synced 2024-12-28 18:16:31 +00:00
9ff4c20374
* [docs] Rework backups a bit This changes the existing backup documentation to: * Push a bit harder on people to perform backups, it's not really just a nice to have * Removes the language about migrating to/from GoToSocial and a different ActivityPub server since that's really not supported * Adds a section about using backup software and provides an example on how to do this using Borgmatic * [docs] Remove too much info in db section * [docs] Add docs on how to backup local media This adds documentation pointing people at the media list-local command in order to determine what media files they need to include as part of their backups. Provides a Python script that people can use to transform the media listing from the CLI into Borg patterns. It also includes a Borgmatic config.yaml in the repository so people can easily fetch it instead of copy-pasting from the docs. * [bugfix] Ensure we emit an absolute path prefix It works either way, as a pattern like data/files/<ID> would match a file on /data/files/<ID>. But it would potentially also match any path that happens to include data/files/<ID> but not rooted at the storage-local-base-path. * [docs] Add more links to media list CLI reference
52 lines
1.9 KiB
Python
Executable file
52 lines
1.9 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
import argparse
|
|
import os
|
|
import pathlib
|
|
import sys
|
|
|
|
def main():
|
|
cli = argparse.ArgumentParser(
|
|
prog="media-to-borg-patterns",
|
|
description="""Generate Borg patterns to backup media files belonging to
|
|
this instance. You can pass the output to Borg or Borgmatic as a patterns file.
|
|
For example: gotosocial admin media list-local | media-to-borg-patterns
|
|
<storage-local-base-path>. You can pass a second argument, the destination file, to
|
|
write the patterns in. If it's ommitted the patterns will be emitted on stdout
|
|
instead and you can redirect the output to a file yourself.
|
|
""",
|
|
epilog="Be gay, do backups. Trans rights!"
|
|
)
|
|
cli.add_argument("storageroot", type=pathlib.Path, help="same value as storage-local-base-path in your GoToSocial configuration")
|
|
cli.add_argument("destination", nargs="?", type=pathlib.Path, help="file to write patterns to, or stdout if ommitted")
|
|
args = cli.parse_args()
|
|
|
|
output = open(args.destination, 'w') if args.destination else sys.stdout
|
|
# Start recursing from the storage root, including the storage root itself
|
|
output.write("R "+str(args.storageroot)+"\n")
|
|
|
|
prefixes=set()
|
|
|
|
for line in sys.stdin:
|
|
# Skip any log lines
|
|
if "msg=" in line:
|
|
continue
|
|
# Reduce the path to the storage path plus the account ID. By
|
|
# doing this we can emit path-prefix patterns, one for each account,
|
|
# instead of a path-file pattern for each file.
|
|
prefixes.add(os.path.join(*line.split("/")[:-3]))
|
|
|
|
for prefix in prefixes:
|
|
# Add a path-prefix, pp:, for each path we want to include.
|
|
output.write("+ pp:"+os.path.join(os.path.sep, prefix)+"\n")
|
|
|
|
# Exclude every file and directory under the storage root. This excludes
|
|
# everything that wasn't matched by any of our prior patterns. This turns
|
|
# the emitted patterns into an "include only" list.
|
|
output.write("- "+os.path.join(args.storageroot, "*")+"\n")
|
|
|
|
if output is not sys.stdout:
|
|
output.close()
|
|
|
|
if __name__ == "__main__":
|
|
main()
|