Files
cura-te-ipsum/curateipsum/cli.py
T
72a8fe2b59 Validate topology and destructive path boundaries (#7)
* Validate topology and destructive path boundaries

- Canonicalize sources/backups_dir and reject overlap in either direction
- Reject duplicate sources and destination basename collisions
- Reject non-normalized relative paths in nest_hardlink
- Give each backup repository a persistent identity, recorded in every
  snapshot's completion manifest
- Verify repo identity, directory type (no symlinks), containment, and
  device before any recursive snapshot/staging-dir deletion, refusing to
  cross mount points

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

* Address Copilot review: root-path check, symlink/TOCTOU-safe writes, legacy marker adoption

- _is_same_or_within: drop the redundant, root-mishandling startswith
  check; commonpath() alone is already component-aware
- _ensure_repo_id/_write_manifest: write via temp-file + atomic rename
  (O_NOFOLLOW, O_EXCL on the temp file) instead of open+write in place,
  so writes can never go through a pre-existing symlink and are never
  left half-written
- _verify_safe_to_delete: distinguish a legacy empty marker (pre-dates
  the manifest format, can only be a pre-migration artifact) from a
  non-empty-but-invalid one (corrupt or forged); adopt the former into
  the repository instead of refusing to delete it forever

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

---------

Co-authored-by: Maxim Shulga <maxim.shulga@alludo.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-03 22:26:51 +00:00

132 lines
4.5 KiB
Python
Executable File

#!/usr/bin/env python
import argparse
import logging
import os.path
import shutil
import sys
import time
from datetime import timedelta
from curateipsum import backup
from curateipsum._version import version
_lg = logging.getLogger("curateipsum")
SUPPORTED_PLATFORMS = ("linux", "darwin")
def main():
formatter = logging.Formatter("{asctime}|{levelname}|{message}", style="{")
console_handler = logging.StreamHandler()
console_handler.setFormatter(formatter)
parser = argparse.ArgumentParser(
prog="cura-te-ipsum",
description="cura-te-ipsum, my personal backup software.",
)
parser.add_argument("-V", "--version",
action="version",
version=f"%(prog)s v{version}")
parser.add_argument("-v", "--verbose",
action="store_true",
default=False,
help="print verbose information")
parser.add_argument("-b",
dest="backups_dir",
metavar="BACKUPS_DIR",
type=str,
required=True,
help="directory, where all backups will be stored")
parser.add_argument("-n", "--dry-run",
action="store_true",
default=False,
help="Do not do create backup")
parser.add_argument("-f", "--force",
action="store_true",
default=False,
help="Wait for previous backup to finish instead of "
"exiting immediately if one is still running")
parser.add_argument("--external-rsync",
action="store_true",
default=False,
help="Use external rsync for copying")
parser.add_argument("--external-hardlink",
action="store_true",
default=False,
help="Use cp command for creating hardlink copies")
parser.add_argument("sources",
nargs="+",
metavar="SOURCE",
type=str,
help="backup source (file/dir/smth else)")
args = parser.parse_args()
loglevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig(level=loglevel, handlers=[console_handler])
_lg.info("Starting %s: %s", parser.prog, args)
if sys.platform not in SUPPORTED_PLATFORMS:
_lg.error("Not supported platform: %s. Supported platforms: %s",
sys.platform, SUPPORTED_PLATFORMS)
return 1
if args.external_rsync and not shutil.which("rsync"):
_lg.error("rsync should be installed to use --external-rsync option.")
return 1
cp_program = "gcp" if sys.platform == "darwin" else "cp"
if args.external_hardlink and not shutil.which(cp_program):
_lg.error("%s should be installed to use --external-hardlink option.",
cp_program)
return 1
backups_dir_abs = os.path.abspath(args.backups_dir)
if not os.path.isdir(backups_dir_abs):
_lg.error("Backup directory %s does not exist, exiting",
args.backups_dir)
return 1
for src_dir in args.sources:
if not os.path.isdir(src_dir):
_lg.error("Source directory %s does not exist", src_dir)
return 1
try:
backup.validate_topology(args.sources, backups_dir_abs)
except backup.BackupFailedError as err:
_lg.error("Unsafe source/backups layout: %s", err)
return 1
start_time = time.time()
if not backup.set_backups_lock(backups_dir_abs, args.force):
return 1
exit_code = 0
try:
backup.cleanup_old_backups(backups_dir=backups_dir_abs,
dry_run=args.dry_run)
backup.initiate_backup(
sources=args.sources,
backups_dir=backups_dir_abs,
dry_run=args.dry_run,
external_rsync=args.external_rsync,
external_hardlink=args.external_hardlink,
)
except backup.BackupFailedError as err:
_lg.error("Backup failed: %s", err)
exit_code = 1
finally:
backup.release_backups_lock(backups_dir_abs)
end_time = time.time()
spent_time = end_time - start_time
_lg.info("Finished, time spent: %s", str(timedelta(seconds=spent_time)))
return exit_code
if __name__ == "__main__":
sys.exit(main())