Compare commits
53 Commits
Author | SHA1 | Date | |
---|---|---|---|
df4668754d | |||
08d6f83b2e | |||
c58f510054 | |||
c2879d054a | |||
f821d2c909 | |||
1ef2218919 | |||
177c958572 | |||
b5ab1ff0cd | |||
70a978b83d | |||
2037810c6b | |||
de304f83de | |||
5752373009 | |||
fecae39fcd | |||
38bc4fbfe2 | |||
92ed7573d4 | |||
80f0e92462 | |||
5f10b1b2ca | |||
4f83b1e6b3 | |||
15d5a687fb | |||
eb1fce3787 | |||
7f735cbe59 | |||
a690ea4016 | |||
7a110c7acd | |||
407bb33359 | |||
4b7f7bba04 | |||
cfdc0a1f2a | |||
f926055e67 | |||
058af95d70 | |||
54facdc391 | |||
2e4c0cc7e7 | |||
cb2fd7c5e8 | |||
94133cc8b1 | |||
dcec89be90 | |||
fefd5d1d0e | |||
163c37d77f | |||
b0e49ebce0 | |||
7e51c41ebf | |||
f9182514d8 | |||
7700b87b60 | |||
75bdbe6087 | |||
d243a8c836 | |||
4c2eb2bfe3 | |||
89ce060dbd | |||
ad7dcb4615 | |||
6680aece5a | |||
57eb93760f | |||
f21a2c06e3 | |||
2212539cb0 | |||
36d10fecb1 | |||
3ecd0e731e | |||
ecf5a7e294 | |||
893fbcf9ff | |||
f8f6560502 |
36
NEWS
36
NEWS
|
@ -1,3 +1,39 @@
|
|||
1.8.12.dev0
|
||||
* #860: Fix interaction between environment variable interpolation in constants and shell escaping.
|
||||
* #863: When color output is disabled (explicitly or implicitly), don't prefix each log line with
|
||||
the log level.
|
||||
* #866: Fix "Argument list too long" error in the "spot" check when checking hundreds of thousands
|
||||
of files at once.
|
||||
* #874: Add the configured repository label as "repository_label" to the interpolated variables
|
||||
passed to before/after command hooks.
|
||||
* In the "spot" check, don't try to hash symlinked directories.
|
||||
|
||||
1.8.11
|
||||
* #815: Add optional Healthchecks auto-provisioning via "create_slug" option.
|
||||
* #851: Fix lack of file extraction when using "extract --strip-components all" on a path with a
|
||||
leading slash.
|
||||
* #854: Fix a traceback when the "data" consistency check is used.
|
||||
* #857: Fix a traceback with "check --only spot" when the "spot" check is unconfigured.
|
||||
|
||||
1.8.10
|
||||
* #656 (beta): Add a "spot" consistency check that compares file counts and contents between your
|
||||
source files and the latest archive, ensuring they fall within configured tolerances. This can
|
||||
catch problems like incorrect excludes, inadvertent deletes, files changed by malware, etc. See
|
||||
the documentation for more information:
|
||||
https://torsion.org/borgmatic/docs/how-to/deal-with-very-large-backups/#spot-check
|
||||
* #779: When "--match-archives *" is used with "check" action, don't skip Borg's orphaned objects
|
||||
check.
|
||||
* #842: When a command hook exits with a soft failure, ping the log and finish states for any
|
||||
configured monitoring hooks.
|
||||
* #843: Add documentation link to Loki dashboard for borgmatic:
|
||||
https://torsion.org/borgmatic/docs/how-to/monitor-your-backups/#loki-hook
|
||||
* #847: Fix "--json" error when Borg includes non-JSON warnings in JSON output.
|
||||
* #848: SECURITY: Mask the password when logging a MongoDB dump or restore command.
|
||||
* Fix handling of the NO_COLOR environment variable to ignore an empty value.
|
||||
* Add documentation about backing up containerized databases by configuring borgmatic to exec into
|
||||
a container to run a dump command:
|
||||
https://torsion.org/borgmatic/docs/how-to/backup-your-databases/#containers
|
||||
|
||||
1.8.9
|
||||
* #311: Add custom dump/restore command options for MySQL and MariaDB.
|
||||
* #811: Add an "access_token" option to the ntfy monitoring hook for authenticating
|
||||
|
|
|
@ -1,12 +1,602 @@
|
|||
import datetime
|
||||
import hashlib
|
||||
import itertools
|
||||
import logging
|
||||
import os
|
||||
import pathlib
|
||||
import random
|
||||
|
||||
import borgmatic.borg.check
|
||||
import borgmatic.borg.create
|
||||
import borgmatic.borg.environment
|
||||
import borgmatic.borg.extract
|
||||
import borgmatic.borg.list
|
||||
import borgmatic.borg.rlist
|
||||
import borgmatic.borg.state
|
||||
import borgmatic.config.validate
|
||||
import borgmatic.execute
|
||||
import borgmatic.hooks.command
|
||||
|
||||
DEFAULT_CHECKS = (
|
||||
{'name': 'repository', 'frequency': '1 month'},
|
||||
{'name': 'archives', 'frequency': '1 month'},
|
||||
)
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def parse_checks(config, only_checks=None):
|
||||
'''
|
||||
Given a configuration dict with a "checks" sequence of dicts and an optional list of override
|
||||
checks, return a tuple of named checks to run.
|
||||
|
||||
For example, given a config of:
|
||||
|
||||
{'checks': ({'name': 'repository'}, {'name': 'archives'})}
|
||||
|
||||
This will be returned as:
|
||||
|
||||
('repository', 'archives')
|
||||
|
||||
If no "checks" option is present in the config, return the DEFAULT_CHECKS. If a checks value
|
||||
has a name of "disabled", return an empty tuple, meaning that no checks should be run.
|
||||
'''
|
||||
checks = only_checks or tuple(
|
||||
check_config['name'] for check_config in (config.get('checks', None) or DEFAULT_CHECKS)
|
||||
)
|
||||
checks = tuple(check.lower() for check in checks)
|
||||
|
||||
if 'disabled' in checks:
|
||||
logger.warning(
|
||||
'The "disabled" value for the "checks" option is deprecated and will be removed from a future release; use "skip_actions" instead'
|
||||
)
|
||||
if len(checks) > 1:
|
||||
logger.warning(
|
||||
'Multiple checks are configured, but one of them is "disabled"; not running any checks'
|
||||
)
|
||||
return ()
|
||||
|
||||
return checks
|
||||
|
||||
|
||||
def parse_frequency(frequency):
|
||||
'''
|
||||
Given a frequency string with a number and a unit of time, return a corresponding
|
||||
datetime.timedelta instance or None if the frequency is None or "always".
|
||||
|
||||
For instance, given "3 weeks", return datetime.timedelta(weeks=3)
|
||||
|
||||
Raise ValueError if the given frequency cannot be parsed.
|
||||
'''
|
||||
if not frequency:
|
||||
return None
|
||||
|
||||
frequency = frequency.strip().lower()
|
||||
|
||||
if frequency == 'always':
|
||||
return None
|
||||
|
||||
try:
|
||||
number, time_unit = frequency.split(' ')
|
||||
number = int(number)
|
||||
except ValueError:
|
||||
raise ValueError(f"Could not parse consistency check frequency '{frequency}'")
|
||||
|
||||
if not time_unit.endswith('s'):
|
||||
time_unit += 's'
|
||||
|
||||
if time_unit == 'months':
|
||||
number *= 30
|
||||
time_unit = 'days'
|
||||
elif time_unit == 'years':
|
||||
number *= 365
|
||||
time_unit = 'days'
|
||||
|
||||
try:
|
||||
return datetime.timedelta(**{time_unit: number})
|
||||
except TypeError:
|
||||
raise ValueError(f"Could not parse consistency check frequency '{frequency}'")
|
||||
|
||||
|
||||
def filter_checks_on_frequency(
|
||||
config,
|
||||
borg_repository_id,
|
||||
checks,
|
||||
force,
|
||||
archives_check_id=None,
|
||||
):
|
||||
'''
|
||||
Given a configuration dict with a "checks" sequence of dicts, a Borg repository ID, a sequence
|
||||
of checks, whether to force checks to run, and an ID for the archives check potentially being
|
||||
run (if any), filter down those checks based on the configured "frequency" for each check as
|
||||
compared to its check time file.
|
||||
|
||||
In other words, a check whose check time file's timestamp is too new (based on the configured
|
||||
frequency) will get cut from the returned sequence of checks. Example:
|
||||
|
||||
config = {
|
||||
'checks': [
|
||||
{
|
||||
'name': 'archives',
|
||||
'frequency': '2 weeks',
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
When this function is called with that config and "archives" in checks, "archives" will get
|
||||
filtered out of the returned result if its check time file is newer than 2 weeks old, indicating
|
||||
that it's not yet time to run that check again.
|
||||
|
||||
Raise ValueError if a frequency cannot be parsed.
|
||||
'''
|
||||
if not checks:
|
||||
return checks
|
||||
|
||||
filtered_checks = list(checks)
|
||||
|
||||
if force:
|
||||
return tuple(filtered_checks)
|
||||
|
||||
for check_config in config.get('checks', DEFAULT_CHECKS):
|
||||
check = check_config['name']
|
||||
if checks and check not in checks:
|
||||
continue
|
||||
|
||||
frequency_delta = parse_frequency(check_config.get('frequency'))
|
||||
if not frequency_delta:
|
||||
continue
|
||||
|
||||
check_time = probe_for_check_time(config, borg_repository_id, check, archives_check_id)
|
||||
if not check_time:
|
||||
continue
|
||||
|
||||
# If we've not yet reached the time when the frequency dictates we're ready for another
|
||||
# check, skip this check.
|
||||
if datetime.datetime.now() < check_time + frequency_delta:
|
||||
remaining = check_time + frequency_delta - datetime.datetime.now()
|
||||
logger.info(
|
||||
f'Skipping {check} check due to configured frequency; {remaining} until next check (use --force to check anyway)'
|
||||
)
|
||||
filtered_checks.remove(check)
|
||||
|
||||
return tuple(filtered_checks)
|
||||
|
||||
|
||||
def make_archives_check_id(archive_filter_flags):
|
||||
'''
|
||||
Given a sequence of flags to filter archives, return a unique hash corresponding to those
|
||||
particular flags. If there are no flags, return None.
|
||||
'''
|
||||
if not archive_filter_flags:
|
||||
return None
|
||||
|
||||
return hashlib.sha256(' '.join(archive_filter_flags).encode()).hexdigest()
|
||||
|
||||
|
||||
def make_check_time_path(config, borg_repository_id, check_type, archives_check_id=None):
|
||||
'''
|
||||
Given a configuration dict, a Borg repository ID, the name of a check type ("repository",
|
||||
"archives", etc.), and a unique hash of the archives filter flags, return a path for recording
|
||||
that check's time (the time of that check last occurring).
|
||||
'''
|
||||
borgmatic_source_directory = os.path.expanduser(
|
||||
config.get(
|
||||
'borgmatic_source_directory', borgmatic.borg.state.DEFAULT_BORGMATIC_SOURCE_DIRECTORY
|
||||
)
|
||||
)
|
||||
|
||||
if check_type in ('archives', 'data'):
|
||||
return os.path.join(
|
||||
borgmatic_source_directory,
|
||||
'checks',
|
||||
borg_repository_id,
|
||||
check_type,
|
||||
archives_check_id if archives_check_id else 'all',
|
||||
)
|
||||
|
||||
return os.path.join(
|
||||
borgmatic_source_directory,
|
||||
'checks',
|
||||
borg_repository_id,
|
||||
check_type,
|
||||
)
|
||||
|
||||
|
||||
def write_check_time(path): # pragma: no cover
|
||||
'''
|
||||
Record a check time of now as the modification time of the given path.
|
||||
'''
|
||||
logger.debug(f'Writing check time at {path}')
|
||||
|
||||
os.makedirs(os.path.dirname(path), mode=0o700, exist_ok=True)
|
||||
pathlib.Path(path, mode=0o600).touch()
|
||||
|
||||
|
||||
def read_check_time(path):
|
||||
'''
|
||||
Return the check time based on the modification time of the given path. Return None if the path
|
||||
doesn't exist.
|
||||
'''
|
||||
logger.debug(f'Reading check time from {path}')
|
||||
|
||||
try:
|
||||
return datetime.datetime.fromtimestamp(os.stat(path).st_mtime)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
|
||||
|
||||
def probe_for_check_time(config, borg_repository_id, check, archives_check_id):
|
||||
'''
|
||||
Given a configuration dict, a Borg repository ID, the name of a check type ("repository",
|
||||
"archives", etc.), and a unique hash of the archives filter flags, return a the corresponding
|
||||
check time or None if such a check time does not exist.
|
||||
|
||||
When the check type is "archives" or "data", this function probes two different paths to find
|
||||
the check time, e.g.:
|
||||
|
||||
~/.borgmatic/checks/1234567890/archives/9876543210
|
||||
~/.borgmatic/checks/1234567890/archives/all
|
||||
|
||||
... and returns the maximum modification time of the files found (if any). The first path
|
||||
represents a more specific archives check time (a check on a subset of archives), and the second
|
||||
is a fallback to the last "all" archives check.
|
||||
|
||||
For other check types, this function reads from a single check time path, e.g.:
|
||||
|
||||
~/.borgmatic/checks/1234567890/repository
|
||||
'''
|
||||
check_times = (
|
||||
read_check_time(group[0])
|
||||
for group in itertools.groupby(
|
||||
(
|
||||
make_check_time_path(config, borg_repository_id, check, archives_check_id),
|
||||
make_check_time_path(config, borg_repository_id, check),
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
try:
|
||||
return max(check_time for check_time in check_times if check_time)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def upgrade_check_times(config, borg_repository_id):
|
||||
'''
|
||||
Given a configuration dict and a Borg repository ID, upgrade any corresponding check times on
|
||||
disk from old-style paths to new-style paths.
|
||||
|
||||
Currently, the only upgrade performed is renaming an archive or data check path that looks like:
|
||||
|
||||
~/.borgmatic/checks/1234567890/archives
|
||||
|
||||
to:
|
||||
|
||||
~/.borgmatic/checks/1234567890/archives/all
|
||||
'''
|
||||
for check_type in ('archives', 'data'):
|
||||
new_path = make_check_time_path(config, borg_repository_id, check_type, 'all')
|
||||
old_path = os.path.dirname(new_path)
|
||||
temporary_path = f'{old_path}.temp'
|
||||
|
||||
if not os.path.isfile(old_path) and not os.path.isfile(temporary_path):
|
||||
continue
|
||||
|
||||
logger.debug(f'Upgrading archives check time from {old_path} to {new_path}')
|
||||
|
||||
try:
|
||||
os.rename(old_path, temporary_path)
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
|
||||
os.mkdir(old_path)
|
||||
os.rename(temporary_path, new_path)
|
||||
|
||||
|
||||
def collect_spot_check_source_paths(
|
||||
repository, config, local_borg_version, global_arguments, local_path, remote_path
|
||||
):
|
||||
'''
|
||||
Given a repository configuration dict, a configuration dict, the local Borg version, global
|
||||
arguments as an argparse.Namespace instance, the local Borg path, and the remote Borg path,
|
||||
collect the source paths that Borg would use in an actual create (but only include files).
|
||||
'''
|
||||
stream_processes = any(
|
||||
borgmatic.hooks.dispatch.call_hooks(
|
||||
'use_streaming',
|
||||
config,
|
||||
repository['path'],
|
||||
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
|
||||
).values()
|
||||
)
|
||||
|
||||
(create_flags, create_positional_arguments, pattern_file, exclude_file) = (
|
||||
borgmatic.borg.create.make_base_create_command(
|
||||
dry_run=True,
|
||||
repository_path=repository['path'],
|
||||
config=config,
|
||||
config_paths=(),
|
||||
local_borg_version=local_borg_version,
|
||||
global_arguments=global_arguments,
|
||||
borgmatic_source_directories=(),
|
||||
local_path=local_path,
|
||||
remote_path=remote_path,
|
||||
list_files=True,
|
||||
stream_processes=stream_processes,
|
||||
)
|
||||
)
|
||||
borg_environment = borgmatic.borg.environment.make_environment(config)
|
||||
|
||||
try:
|
||||
working_directory = os.path.expanduser(config.get('working_directory'))
|
||||
except TypeError:
|
||||
working_directory = None
|
||||
|
||||
paths_output = borgmatic.execute.execute_command_and_capture_output(
|
||||
create_flags + create_positional_arguments,
|
||||
capture_stderr=True,
|
||||
working_directory=working_directory,
|
||||
extra_environment=borg_environment,
|
||||
borg_local_path=local_path,
|
||||
borg_exit_codes=config.get('borg_exit_codes'),
|
||||
)
|
||||
|
||||
paths = tuple(
|
||||
path_line.split(' ', 1)[1]
|
||||
for path_line in paths_output.split('\n')
|
||||
if path_line and path_line.startswith('- ') or path_line.startswith('+ ')
|
||||
)
|
||||
|
||||
return tuple(path for path in paths if os.path.isfile(path))
|
||||
|
||||
|
||||
BORG_DIRECTORY_FILE_TYPE = 'd'
|
||||
|
||||
|
||||
def collect_spot_check_archive_paths(
|
||||
repository, archive, config, local_borg_version, global_arguments, local_path, remote_path
|
||||
):
|
||||
'''
|
||||
Given a repository configuration dict, the name of the latest archive, a configuration dict, the
|
||||
local Borg version, global arguments as an argparse.Namespace instance, the local Borg path, and
|
||||
the remote Borg path, collect the paths from the given archive (but only include files and
|
||||
symlinks).
|
||||
'''
|
||||
borgmatic_source_directory = os.path.expanduser(
|
||||
config.get(
|
||||
'borgmatic_source_directory', borgmatic.borg.state.DEFAULT_BORGMATIC_SOURCE_DIRECTORY
|
||||
)
|
||||
)
|
||||
|
||||
return tuple(
|
||||
path
|
||||
for line in borgmatic.borg.list.capture_archive_listing(
|
||||
repository['path'],
|
||||
archive,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
path_format='{type} /{path}{NL}', # noqa: FS003
|
||||
local_path=local_path,
|
||||
remote_path=remote_path,
|
||||
)
|
||||
for (file_type, path) in (line.split(' ', 1),)
|
||||
if file_type != BORG_DIRECTORY_FILE_TYPE
|
||||
if pathlib.Path(borgmatic_source_directory) not in pathlib.Path(path).parents
|
||||
)
|
||||
|
||||
|
||||
SAMPLE_PATHS_SUBSET_COUNT = 10000
|
||||
|
||||
|
||||
def compare_spot_check_hashes(
|
||||
repository,
|
||||
archive,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
log_label,
|
||||
source_paths,
|
||||
):
|
||||
'''
|
||||
Given a repository configuration dict, the name of the latest archive, a configuration dict, the
|
||||
local Borg version, global arguments as an argparse.Namespace instance, the local Borg path, the
|
||||
remote Borg path, a log label, and spot check source paths, compare the hashes for a sampling of
|
||||
the source paths with hashes from corresponding paths in the given archive. Return a sequence of
|
||||
the paths that fail that hash comparison.
|
||||
'''
|
||||
# Based on the configured sample percentage, come up with a list of random sample files from the
|
||||
# source directories.
|
||||
spot_check_config = next(check for check in config['checks'] if check['name'] == 'spot')
|
||||
sample_count = max(
|
||||
int(len(source_paths) * (min(spot_check_config['data_sample_percentage'], 100) / 100)), 1
|
||||
)
|
||||
source_sample_paths = tuple(random.sample(source_paths, sample_count))
|
||||
existing_source_sample_paths = {
|
||||
source_path for source_path in source_sample_paths if os.path.exists(source_path)
|
||||
}
|
||||
logger.debug(
|
||||
f'{log_label}: Sampling {sample_count} source paths (~{spot_check_config["data_sample_percentage"]}%) for spot check'
|
||||
)
|
||||
|
||||
source_sample_paths_iterator = iter(source_sample_paths)
|
||||
source_hashes = {}
|
||||
archive_hashes = {}
|
||||
|
||||
# Only hash a few thousand files at a time (a subset of the total paths) to avoid an "Argument
|
||||
# list too long" shell error.
|
||||
while True:
|
||||
# Hash each file in the sample paths (if it exists).
|
||||
source_sample_paths_subset = tuple(
|
||||
itertools.islice(source_sample_paths_iterator, SAMPLE_PATHS_SUBSET_COUNT)
|
||||
)
|
||||
if not source_sample_paths_subset:
|
||||
break
|
||||
|
||||
hash_output = borgmatic.execute.execute_command_and_capture_output(
|
||||
(spot_check_config.get('xxh64sum_command', 'xxh64sum'),)
|
||||
+ tuple(
|
||||
path for path in source_sample_paths_subset if path in existing_source_sample_paths
|
||||
)
|
||||
)
|
||||
|
||||
source_hashes.update(
|
||||
**dict(
|
||||
(reversed(line.split(' ', 1)) for line in hash_output.splitlines()),
|
||||
# Represent non-existent files as having empty hashes so the comparison below still works.
|
||||
**{
|
||||
path: ''
|
||||
for path in source_sample_paths_subset
|
||||
if path not in existing_source_sample_paths
|
||||
},
|
||||
)
|
||||
)
|
||||
|
||||
# Get the hash for each file in the archive.
|
||||
archive_hashes.update(
|
||||
**dict(
|
||||
reversed(line.split(' ', 1))
|
||||
for line in borgmatic.borg.list.capture_archive_listing(
|
||||
repository['path'],
|
||||
archive,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
list_paths=source_sample_paths_subset,
|
||||
path_format='{xxh64} /{path}{NL}', # noqa: FS003
|
||||
local_path=local_path,
|
||||
remote_path=remote_path,
|
||||
)
|
||||
if line
|
||||
)
|
||||
)
|
||||
|
||||
# Compare the source hashes with the archive hashes to see how many match.
|
||||
failing_paths = []
|
||||
|
||||
for path, source_hash in source_hashes.items():
|
||||
archive_hash = archive_hashes.get(path)
|
||||
|
||||
if archive_hash is not None and archive_hash == source_hash:
|
||||
continue
|
||||
|
||||
failing_paths.append(path)
|
||||
|
||||
return tuple(failing_paths)
|
||||
|
||||
|
||||
def spot_check(
|
||||
repository,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
):
|
||||
'''
|
||||
Given a repository dict, a loaded configuration dict, the local Borg version, global arguments
|
||||
as an argparse.Namespace instance, the local Borg path, and the remote Borg path, perform a spot
|
||||
check for the latest archive in the given repository.
|
||||
|
||||
A spot check compares file counts and also the hashes for a random sampling of source files on
|
||||
disk to those stored in the latest archive. If any differences are beyond configured tolerances,
|
||||
then the check fails.
|
||||
'''
|
||||
log_label = f'{repository.get("label", repository["path"])}'
|
||||
logger.debug(f'{log_label}: Running spot check')
|
||||
|
||||
try:
|
||||
spot_check_config = next(
|
||||
check for check in config.get('checks', ()) if check.get('name') == 'spot'
|
||||
)
|
||||
except StopIteration:
|
||||
raise ValueError('Cannot run spot check because it is unconfigured')
|
||||
|
||||
if spot_check_config['data_tolerance_percentage'] > spot_check_config['data_sample_percentage']:
|
||||
raise ValueError(
|
||||
'The data_tolerance_percentage must be less than or equal to the data_sample_percentage'
|
||||
)
|
||||
|
||||
source_paths = collect_spot_check_source_paths(
|
||||
repository,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
)
|
||||
logger.debug(f'{log_label}: {len(source_paths)} total source paths for spot check')
|
||||
|
||||
archive = borgmatic.borg.rlist.resolve_archive_name(
|
||||
repository['path'],
|
||||
'latest',
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
)
|
||||
logger.debug(f'{log_label}: Using archive {archive} for spot check')
|
||||
|
||||
archive_paths = collect_spot_check_archive_paths(
|
||||
repository,
|
||||
archive,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
)
|
||||
logger.debug(f'{log_label}: {len(archive_paths)} total archive paths for spot check')
|
||||
|
||||
# Calculate the percentage delta between the source paths count and the archive paths count, and
|
||||
# compare that delta to the configured count tolerance percentage.
|
||||
count_delta_percentage = abs(len(source_paths) - len(archive_paths)) / len(source_paths) * 100
|
||||
|
||||
if count_delta_percentage > spot_check_config['count_tolerance_percentage']:
|
||||
logger.debug(
|
||||
f'{log_label}: Paths in source paths but not latest archive: {", ".join(set(source_paths) - set(archive_paths)) or "none"}'
|
||||
)
|
||||
logger.debug(
|
||||
f'{log_label}: Paths in latest archive but not source paths: {", ".join(set(archive_paths) - set(source_paths)) or "none"}'
|
||||
)
|
||||
raise ValueError(
|
||||
f'Spot check failed: {count_delta_percentage:.2f}% file count delta between source paths and latest archive (tolerance is {spot_check_config["count_tolerance_percentage"]}%)'
|
||||
)
|
||||
|
||||
failing_paths = compare_spot_check_hashes(
|
||||
repository,
|
||||
archive,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
log_label,
|
||||
source_paths,
|
||||
)
|
||||
|
||||
# Error if the percentage of failing hashes exceeds the configured tolerance percentage.
|
||||
logger.debug(f'{log_label}: {len(failing_paths)} non-matching spot check hashes')
|
||||
data_tolerance_percentage = spot_check_config['data_tolerance_percentage']
|
||||
failing_percentage = (len(failing_paths) / len(source_paths)) * 100
|
||||
|
||||
if failing_percentage > data_tolerance_percentage:
|
||||
logger.debug(
|
||||
f'{log_label}: Source paths with data not matching the latest archive: {", ".join(failing_paths)}'
|
||||
)
|
||||
raise ValueError(
|
||||
f'Spot check failed: {failing_percentage:.2f}% of source paths with data not matching the latest archive (tolerance is {data_tolerance_percentage}%)'
|
||||
)
|
||||
|
||||
logger.info(
|
||||
f'{log_label}: Spot check passed with a {count_delta_percentage:.2f}% file count delta and a {failing_percentage:.2f}% file data delta'
|
||||
)
|
||||
|
||||
|
||||
def run_check(
|
||||
config_filename,
|
||||
repository,
|
||||
|
@ -20,6 +610,8 @@ def run_check(
|
|||
):
|
||||
'''
|
||||
Run the "check" action for the given repository.
|
||||
|
||||
Raise ValueError if the Borg repository ID cannot be determined.
|
||||
'''
|
||||
if check_arguments.repository and not borgmatic.config.validate.repositories_match(
|
||||
repository, check_arguments.repository
|
||||
|
@ -34,16 +626,69 @@ def run_check(
|
|||
global_arguments.dry_run,
|
||||
**hook_context,
|
||||
)
|
||||
|
||||
logger.info(f'{repository.get("label", repository["path"])}: Running consistency checks')
|
||||
repository_id = borgmatic.borg.check.get_repository_id(
|
||||
repository['path'],
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path=local_path,
|
||||
remote_path=remote_path,
|
||||
)
|
||||
upgrade_check_times(config, repository_id)
|
||||
configured_checks = parse_checks(config, check_arguments.only_checks)
|
||||
archive_filter_flags = borgmatic.borg.check.make_archive_filter_flags(
|
||||
local_borg_version, config, configured_checks, check_arguments
|
||||
)
|
||||
archives_check_id = make_archives_check_id(archive_filter_flags)
|
||||
checks = filter_checks_on_frequency(
|
||||
config,
|
||||
repository_id,
|
||||
configured_checks,
|
||||
check_arguments.force,
|
||||
archives_check_id,
|
||||
)
|
||||
borg_specific_checks = set(checks).intersection({'repository', 'archives', 'data'})
|
||||
|
||||
if borg_specific_checks:
|
||||
borgmatic.borg.check.check_archives(
|
||||
repository['path'],
|
||||
config,
|
||||
local_borg_version,
|
||||
check_arguments,
|
||||
global_arguments,
|
||||
borg_specific_checks,
|
||||
archive_filter_flags,
|
||||
local_path=local_path,
|
||||
remote_path=remote_path,
|
||||
)
|
||||
for check in borg_specific_checks:
|
||||
write_check_time(make_check_time_path(config, repository_id, check, archives_check_id))
|
||||
|
||||
if 'extract' in checks:
|
||||
borgmatic.borg.extract.extract_last_archive_dry_run(
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
repository['path'],
|
||||
config.get('lock_wait'),
|
||||
local_path,
|
||||
remote_path,
|
||||
)
|
||||
write_check_time(make_check_time_path(config, repository_id, 'extract'))
|
||||
|
||||
if 'spot' in checks:
|
||||
spot_check(
|
||||
repository,
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path,
|
||||
remote_path,
|
||||
)
|
||||
write_check_time(make_check_time_path(config, repository_id, 'spot'))
|
||||
|
||||
borgmatic.hooks.command.execute_hook(
|
||||
config.get('after_check'),
|
||||
config.get('umask'),
|
||||
|
|
|
@ -1,12 +1,26 @@
|
|||
import json
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def parse_json(borg_json_output, label):
|
||||
'''
|
||||
Given a Borg JSON output string, parse it as JSON into a dict. Inject the given borgmatic
|
||||
repository label into it and return the dict.
|
||||
|
||||
Raise JSONDecodeError if the JSON output cannot be parsed.
|
||||
'''
|
||||
json_data = json.loads(borg_json_output)
|
||||
lines = borg_json_output.splitlines()
|
||||
start_line_index = 0
|
||||
|
||||
# Scan forward to find the first line starting with "{" and assume that's where the JSON starts.
|
||||
for line_index, line in enumerate(lines):
|
||||
if line.startswith('{'):
|
||||
start_line_index = line_index
|
||||
break
|
||||
|
||||
json_data = json.loads('\n'.join(lines[start_line_index:]))
|
||||
|
||||
if 'repository' not in json_data:
|
||||
return json_data
|
||||
|
|
|
@ -1,172 +1,26 @@
|
|||
import argparse
|
||||
import datetime
|
||||
import hashlib
|
||||
import itertools
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import pathlib
|
||||
|
||||
from borgmatic.borg import environment, extract, feature, flags, rinfo, state
|
||||
from borgmatic.borg import environment, feature, flags, rinfo
|
||||
from borgmatic.execute import DO_NOT_CAPTURE, execute_command
|
||||
|
||||
DEFAULT_CHECKS = (
|
||||
{'name': 'repository', 'frequency': '1 month'},
|
||||
{'name': 'archives', 'frequency': '1 month'},
|
||||
)
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def parse_checks(config, only_checks=None):
|
||||
def make_archive_filter_flags(local_borg_version, config, checks, check_arguments):
|
||||
'''
|
||||
Given a configuration dict with a "checks" sequence of dicts and an optional list of override
|
||||
checks, return a tuple of named checks to run.
|
||||
Given the local Borg version, a configuration dict, a parsed sequence of checks, and check
|
||||
arguments as an argparse.Namespace instance, transform the checks into tuple of command-line
|
||||
flags for filtering archives in a check command.
|
||||
|
||||
For example, given a config of:
|
||||
|
||||
{'checks': ({'name': 'repository'}, {'name': 'archives'})}
|
||||
|
||||
This will be returned as:
|
||||
|
||||
('repository', 'archives')
|
||||
|
||||
If no "checks" option is present in the config, return the DEFAULT_CHECKS. If a checks value
|
||||
has a name of "disabled", return an empty tuple, meaning that no checks should be run.
|
||||
If "check_last" is set in the configuration and "archives" is in checks, then include a "--last"
|
||||
flag. And if "prefix" is set in configuration and "archives" is in checks, then include a
|
||||
"--match-archives" flag.
|
||||
'''
|
||||
checks = only_checks or tuple(
|
||||
check_config['name'] for check_config in (config.get('checks', None) or DEFAULT_CHECKS)
|
||||
)
|
||||
checks = tuple(check.lower() for check in checks)
|
||||
check_last = config.get('check_last', None)
|
||||
prefix = config.get('prefix')
|
||||
|
||||
if 'disabled' in checks:
|
||||
logger.warning(
|
||||
'The "disabled" value for the "checks" option is deprecated and will be removed from a future release; use "skip_actions" instead'
|
||||
)
|
||||
if len(checks) > 1:
|
||||
logger.warning(
|
||||
'Multiple checks are configured, but one of them is "disabled"; not running any checks'
|
||||
)
|
||||
return ()
|
||||
|
||||
return checks
|
||||
|
||||
|
||||
def parse_frequency(frequency):
|
||||
'''
|
||||
Given a frequency string with a number and a unit of time, return a corresponding
|
||||
datetime.timedelta instance or None if the frequency is None or "always".
|
||||
|
||||
For instance, given "3 weeks", return datetime.timedelta(weeks=3)
|
||||
|
||||
Raise ValueError if the given frequency cannot be parsed.
|
||||
'''
|
||||
if not frequency:
|
||||
return None
|
||||
|
||||
frequency = frequency.strip().lower()
|
||||
|
||||
if frequency == 'always':
|
||||
return None
|
||||
|
||||
try:
|
||||
number, time_unit = frequency.split(' ')
|
||||
number = int(number)
|
||||
except ValueError:
|
||||
raise ValueError(f"Could not parse consistency check frequency '{frequency}'")
|
||||
|
||||
if not time_unit.endswith('s'):
|
||||
time_unit += 's'
|
||||
|
||||
if time_unit == 'months':
|
||||
number *= 30
|
||||
time_unit = 'days'
|
||||
elif time_unit == 'years':
|
||||
number *= 365
|
||||
time_unit = 'days'
|
||||
|
||||
try:
|
||||
return datetime.timedelta(**{time_unit: number})
|
||||
except TypeError:
|
||||
raise ValueError(f"Could not parse consistency check frequency '{frequency}'")
|
||||
|
||||
|
||||
def filter_checks_on_frequency(
|
||||
config,
|
||||
borg_repository_id,
|
||||
checks,
|
||||
force,
|
||||
archives_check_id=None,
|
||||
):
|
||||
'''
|
||||
Given a configuration dict with a "checks" sequence of dicts, a Borg repository ID, a sequence
|
||||
of checks, whether to force checks to run, and an ID for the archives check potentially being
|
||||
run (if any), filter down those checks based on the configured "frequency" for each check as
|
||||
compared to its check time file.
|
||||
|
||||
In other words, a check whose check time file's timestamp is too new (based on the configured
|
||||
frequency) will get cut from the returned sequence of checks. Example:
|
||||
|
||||
config = {
|
||||
'checks': [
|
||||
{
|
||||
'name': 'archives',
|
||||
'frequency': '2 weeks',
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
When this function is called with that config and "archives" in checks, "archives" will get
|
||||
filtered out of the returned result if its check time file is newer than 2 weeks old, indicating
|
||||
that it's not yet time to run that check again.
|
||||
|
||||
Raise ValueError if a frequency cannot be parsed.
|
||||
'''
|
||||
if not checks:
|
||||
return checks
|
||||
|
||||
filtered_checks = list(checks)
|
||||
|
||||
if force:
|
||||
return tuple(filtered_checks)
|
||||
|
||||
for check_config in config.get('checks', DEFAULT_CHECKS):
|
||||
check = check_config['name']
|
||||
if checks and check not in checks:
|
||||
continue
|
||||
|
||||
frequency_delta = parse_frequency(check_config.get('frequency'))
|
||||
if not frequency_delta:
|
||||
continue
|
||||
|
||||
check_time = probe_for_check_time(config, borg_repository_id, check, archives_check_id)
|
||||
if not check_time:
|
||||
continue
|
||||
|
||||
# If we've not yet reached the time when the frequency dictates we're ready for another
|
||||
# check, skip this check.
|
||||
if datetime.datetime.now() < check_time + frequency_delta:
|
||||
remaining = check_time + frequency_delta - datetime.datetime.now()
|
||||
logger.info(
|
||||
f'Skipping {check} check due to configured frequency; {remaining} until next check (use --force to check anyway)'
|
||||
)
|
||||
filtered_checks.remove(check)
|
||||
|
||||
return tuple(filtered_checks)
|
||||
|
||||
|
||||
def make_archive_filter_flags(
|
||||
local_borg_version, config, checks, check_arguments, check_last=None, prefix=None
|
||||
):
|
||||
'''
|
||||
Given the local Borg version, a configuration dict, a parsed sequence of checks, check arguments
|
||||
as an argparse.Namespace instance, the check last value, and a consistency check prefix,
|
||||
transform the checks into tuple of command-line flags for filtering archives in a check command.
|
||||
|
||||
If a check_last value is given and "archives" is in checks, then include a "--last" flag. And if
|
||||
a prefix value is given and "archives" is in checks, then include a "--match-archives" flag.
|
||||
'''
|
||||
if 'archives' in checks or 'data' in checks:
|
||||
return (('--last', str(check_last)) if check_last else ()) + (
|
||||
(
|
||||
|
@ -196,21 +50,10 @@ def make_archive_filter_flags(
|
|||
return ()
|
||||
|
||||
|
||||
def make_archives_check_id(archive_filter_flags):
|
||||
'''
|
||||
Given a sequence of flags to filter archives, return a unique hash corresponding to those
|
||||
particular flags. If there are no flags, return None.
|
||||
'''
|
||||
if not archive_filter_flags:
|
||||
return None
|
||||
|
||||
return hashlib.sha256(' '.join(archive_filter_flags).encode()).hexdigest()
|
||||
|
||||
|
||||
def make_check_flags(checks, archive_filter_flags):
|
||||
'''
|
||||
Given a parsed sequence of checks and a sequence of flags to filter archives, transform the
|
||||
checks into tuple of command-line check flags.
|
||||
Given a parsed checks set and a sequence of flags to filter archives,
|
||||
transform the checks into tuple of command-line check flags.
|
||||
|
||||
For example, given parsed checks of:
|
||||
|
||||
|
@ -225,13 +68,13 @@ def make_check_flags(checks, archive_filter_flags):
|
|||
'''
|
||||
if 'data' in checks:
|
||||
data_flags = ('--verify-data',)
|
||||
checks += ('archives',)
|
||||
checks.update({'archives'})
|
||||
else:
|
||||
data_flags = ()
|
||||
|
||||
common_flags = (archive_filter_flags if 'archives' in checks else ()) + data_flags
|
||||
|
||||
if {'repository', 'archives'}.issubset(set(checks)):
|
||||
if {'repository', 'archives'}.issubset(checks):
|
||||
return common_flags
|
||||
|
||||
return (
|
||||
|
@ -240,144 +83,17 @@ def make_check_flags(checks, archive_filter_flags):
|
|||
)
|
||||
|
||||
|
||||
def make_check_time_path(config, borg_repository_id, check_type, archives_check_id=None):
|
||||
'''
|
||||
Given a configuration dict, a Borg repository ID, the name of a check type ("repository",
|
||||
"archives", etc.), and a unique hash of the archives filter flags, return a path for recording
|
||||
that check's time (the time of that check last occurring).
|
||||
'''
|
||||
borgmatic_source_directory = os.path.expanduser(
|
||||
config.get('borgmatic_source_directory', state.DEFAULT_BORGMATIC_SOURCE_DIRECTORY)
|
||||
)
|
||||
|
||||
if check_type in ('archives', 'data'):
|
||||
return os.path.join(
|
||||
borgmatic_source_directory,
|
||||
'checks',
|
||||
borg_repository_id,
|
||||
check_type,
|
||||
archives_check_id if archives_check_id else 'all',
|
||||
)
|
||||
|
||||
return os.path.join(
|
||||
borgmatic_source_directory,
|
||||
'checks',
|
||||
borg_repository_id,
|
||||
check_type,
|
||||
)
|
||||
|
||||
|
||||
def write_check_time(path): # pragma: no cover
|
||||
'''
|
||||
Record a check time of now as the modification time of the given path.
|
||||
'''
|
||||
logger.debug(f'Writing check time at {path}')
|
||||
|
||||
os.makedirs(os.path.dirname(path), mode=0o700, exist_ok=True)
|
||||
pathlib.Path(path, mode=0o600).touch()
|
||||
|
||||
|
||||
def read_check_time(path):
|
||||
'''
|
||||
Return the check time based on the modification time of the given path. Return None if the path
|
||||
doesn't exist.
|
||||
'''
|
||||
logger.debug(f'Reading check time from {path}')
|
||||
|
||||
try:
|
||||
return datetime.datetime.fromtimestamp(os.stat(path).st_mtime)
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
|
||||
|
||||
def probe_for_check_time(config, borg_repository_id, check, archives_check_id):
|
||||
'''
|
||||
Given a configuration dict, a Borg repository ID, the name of a check type ("repository",
|
||||
"archives", etc.), and a unique hash of the archives filter flags, return a the corresponding
|
||||
check time or None if such a check time does not exist.
|
||||
|
||||
When the check type is "archives" or "data", this function probes two different paths to find
|
||||
the check time, e.g.:
|
||||
|
||||
~/.borgmatic/checks/1234567890/archives/9876543210
|
||||
~/.borgmatic/checks/1234567890/archives/all
|
||||
|
||||
... and returns the maximum modification time of the files found (if any). The first path
|
||||
represents a more specific archives check time (a check on a subset of archives), and the second
|
||||
is a fallback to the last "all" archives check.
|
||||
|
||||
For other check types, this function reads from a single check time path, e.g.:
|
||||
|
||||
~/.borgmatic/checks/1234567890/repository
|
||||
'''
|
||||
check_times = (
|
||||
read_check_time(group[0])
|
||||
for group in itertools.groupby(
|
||||
(
|
||||
make_check_time_path(config, borg_repository_id, check, archives_check_id),
|
||||
make_check_time_path(config, borg_repository_id, check),
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
try:
|
||||
return max(check_time for check_time in check_times if check_time)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def upgrade_check_times(config, borg_repository_id):
|
||||
'''
|
||||
Given a configuration dict and a Borg repository ID, upgrade any corresponding check times on
|
||||
disk from old-style paths to new-style paths.
|
||||
|
||||
Currently, the only upgrade performed is renaming an archive or data check path that looks like:
|
||||
|
||||
~/.borgmatic/checks/1234567890/archives
|
||||
|
||||
to:
|
||||
|
||||
~/.borgmatic/checks/1234567890/archives/all
|
||||
'''
|
||||
for check_type in ('archives', 'data'):
|
||||
new_path = make_check_time_path(config, borg_repository_id, check_type, 'all')
|
||||
old_path = os.path.dirname(new_path)
|
||||
temporary_path = f'{old_path}.temp'
|
||||
|
||||
if not os.path.isfile(old_path) and not os.path.isfile(temporary_path):
|
||||
continue
|
||||
|
||||
logger.debug(f'Upgrading archives check time from {old_path} to {new_path}')
|
||||
|
||||
try:
|
||||
os.rename(old_path, temporary_path)
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
|
||||
os.mkdir(old_path)
|
||||
os.rename(temporary_path, new_path)
|
||||
|
||||
|
||||
def check_archives(
|
||||
repository_path,
|
||||
config,
|
||||
local_borg_version,
|
||||
check_arguments,
|
||||
global_arguments,
|
||||
local_path='borg',
|
||||
remote_path=None,
|
||||
def get_repository_id(
|
||||
repository_path, config, local_borg_version, global_arguments, local_path, remote_path
|
||||
):
|
||||
'''
|
||||
Given a local or remote repository path, a configuration dict, the local Borg version, check
|
||||
arguments as an argparse.Namespace instance, global arguments, and local/remote commands to run,
|
||||
check the contained Borg archives for consistency.
|
||||
Given a local or remote repository path, a configuration dict, the local Borg version, global
|
||||
arguments, and local/remote commands to run, return the corresponding Borg repository ID.
|
||||
|
||||
If there are no consistency checks to run, skip running them.
|
||||
|
||||
Raises ValueError if the Borg repository ID cannot be determined.
|
||||
Raise ValueError if the Borg repository ID cannot be determined.
|
||||
'''
|
||||
try:
|
||||
borg_repository_id = json.loads(
|
||||
return json.loads(
|
||||
rinfo.display_repository_info(
|
||||
repository_path,
|
||||
config,
|
||||
|
@ -391,28 +107,26 @@ def check_archives(
|
|||
except (json.JSONDecodeError, KeyError):
|
||||
raise ValueError(f'Cannot determine Borg repository ID for {repository_path}')
|
||||
|
||||
upgrade_check_times(config, borg_repository_id)
|
||||
|
||||
check_last = config.get('check_last', None)
|
||||
prefix = config.get('prefix')
|
||||
configured_checks = parse_checks(config, check_arguments.only_checks)
|
||||
lock_wait = None
|
||||
extra_borg_options = config.get('extra_borg_options', {}).get('check', '')
|
||||
archive_filter_flags = make_archive_filter_flags(
|
||||
local_borg_version, config, configured_checks, check_arguments, check_last, prefix
|
||||
)
|
||||
archives_check_id = make_archives_check_id(archive_filter_flags)
|
||||
|
||||
checks = filter_checks_on_frequency(
|
||||
def check_archives(
|
||||
repository_path,
|
||||
config,
|
||||
borg_repository_id,
|
||||
configured_checks,
|
||||
check_arguments.force,
|
||||
archives_check_id,
|
||||
)
|
||||
|
||||
if set(checks).intersection({'repository', 'archives', 'data'}):
|
||||
local_borg_version,
|
||||
check_arguments,
|
||||
global_arguments,
|
||||
checks,
|
||||
archive_filter_flags,
|
||||
local_path='borg',
|
||||
remote_path=None,
|
||||
):
|
||||
'''
|
||||
Given a local or remote repository path, a configuration dict, the local Borg version, check
|
||||
arguments as an argparse.Namespace instance, global arguments, a set of named Borg checks to run
|
||||
(some combination "repository", "archives", and/or "data"), archive filter flags, and
|
||||
local/remote commands to run, check the contained Borg archives for consistency.
|
||||
'''
|
||||
lock_wait = config.get('lock_wait')
|
||||
extra_borg_options = config.get('extra_borg_options', {}).get('check', '')
|
||||
|
||||
verbosity_flags = ()
|
||||
if logger.isEnabledFor(logging.INFO):
|
||||
|
@ -453,20 +167,3 @@ def check_archives(
|
|||
borg_local_path=local_path,
|
||||
borg_exit_codes=borg_exit_codes,
|
||||
)
|
||||
|
||||
for check in checks:
|
||||
write_check_time(
|
||||
make_check_time_path(config, borg_repository_id, check, archives_check_id)
|
||||
)
|
||||
|
||||
if 'extract' in checks:
|
||||
extract.extract_last_archive_dry_run(
|
||||
config,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
repository_path,
|
||||
lock_wait,
|
||||
local_path,
|
||||
remote_path,
|
||||
)
|
||||
write_check_time(make_check_time_path(config, borg_repository_id, 'extract'))
|
||||
|
|
|
@ -275,11 +275,11 @@ def collect_special_file_paths(
|
|||
create_command, config, local_path, working_directory, borg_environment, skip_directories
|
||||
):
|
||||
'''
|
||||
Given a Borg create command as a tuple, a local Borg path, a working directory, a dict of
|
||||
environment variables to pass to Borg, and a sequence of parent directories to skip, collect the
|
||||
paths for any special files (character devices, block devices, and named pipes / FIFOs) that
|
||||
Borg would encounter during a create. These are all paths that could cause Borg to hang if its
|
||||
--read-special flag is used.
|
||||
Given a Borg create command as a tuple, a configuration dict, a local Borg path, a working
|
||||
directory, a dict of environment variables to pass to Borg, and a sequence of parent directories
|
||||
to skip, collect the paths for any special files (character devices, block devices, and named
|
||||
pipes / FIFOs) that Borg would encounter during a create. These are all paths that could cause
|
||||
Borg to hang if its --read-special flag is used.
|
||||
'''
|
||||
# Omit "--exclude-nodump" from the Borg dry run command, because that flag causes Borg to open
|
||||
# files including any named pipe we've created.
|
||||
|
@ -320,35 +320,31 @@ def check_all_source_directories_exist(source_directories):
|
|||
raise ValueError(f"Source directories do not exist: {', '.join(missing_directories)}")
|
||||
|
||||
|
||||
def create_archive(
|
||||
def make_base_create_command(
|
||||
dry_run,
|
||||
repository_path,
|
||||
config,
|
||||
config_paths,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
borgmatic_source_directories,
|
||||
local_path='borg',
|
||||
remote_path=None,
|
||||
progress=False,
|
||||
stats=False,
|
||||
json=False,
|
||||
list_files=False,
|
||||
stream_processes=None,
|
||||
):
|
||||
'''
|
||||
Given vebosity/dry-run flags, a local or remote repository path, a configuration dict, a
|
||||
sequence of loaded configuration paths, the local Borg version, and global arguments as an
|
||||
argparse.Namespace instance, create a Borg archive and return Borg's JSON output (if any).
|
||||
|
||||
If a sequence of stream processes is given (instances of subprocess.Popen), then execute the
|
||||
create command while also triggering the given processes to produce output.
|
||||
sequence of loaded configuration paths, the local Borg version, global arguments as an
|
||||
argparse.Namespace instance, and a sequence of borgmatic source directories, return a tuple of
|
||||
(base Borg create command flags, Borg create command positional arguments, open pattern file
|
||||
handle, open exclude file handle).
|
||||
'''
|
||||
borgmatic.logger.add_custom_log_levels()
|
||||
borgmatic_source_directories = expand_directories(
|
||||
collect_borgmatic_source_directories(config.get('borgmatic_source_directory'))
|
||||
)
|
||||
if config.get('source_directories_must_exist', False):
|
||||
check_all_source_directories_exist(config.get('source_directories'))
|
||||
|
||||
sources = deduplicate_directories(
|
||||
map_directories_to_devices(
|
||||
expand_directories(
|
||||
|
@ -364,11 +360,6 @@ def create_archive(
|
|||
|
||||
ensure_files_readable(config.get('patterns_from'), config.get('exclude_from'))
|
||||
|
||||
try:
|
||||
working_directory = os.path.expanduser(config.get('working_directory'))
|
||||
except TypeError:
|
||||
working_directory = None
|
||||
|
||||
pattern_file = (
|
||||
write_pattern_file(config.get('patterns'), sources)
|
||||
if config.get('patterns') or config.get('patterns_from')
|
||||
|
@ -411,11 +402,6 @@ def create_archive(
|
|||
('--remote-ratelimit', str(upload_rate_limit)) if upload_rate_limit else ()
|
||||
)
|
||||
|
||||
if stream_processes and config.get('read_special') is False:
|
||||
logger.warning(
|
||||
f'{repository_path}: Ignoring configured "read_special" value of false, as true is needed for database hooks.'
|
||||
)
|
||||
|
||||
create_flags = (
|
||||
tuple(local_path.split(' '))
|
||||
+ ('create',)
|
||||
|
@ -451,22 +437,19 @@ def create_archive(
|
|||
repository_path, archive_name_format, local_borg_version
|
||||
) + (sources if not pattern_file else ())
|
||||
|
||||
if json:
|
||||
output_log_level = None
|
||||
elif list_files or (stats and not dry_run):
|
||||
output_log_level = logging.ANSWER
|
||||
else:
|
||||
output_log_level = logging.INFO
|
||||
|
||||
# The progress output isn't compatible with captured and logged output, as progress messes with
|
||||
# the terminal directly.
|
||||
output_file = DO_NOT_CAPTURE if progress else None
|
||||
|
||||
borg_environment = environment.make_environment(config)
|
||||
|
||||
# If database hooks are enabled (as indicated by streaming processes), exclude files that might
|
||||
# cause Borg to hang. But skip this if the user has explicitly set the "read_special" to True.
|
||||
if stream_processes and not config.get('read_special'):
|
||||
logger.warning(
|
||||
f'{repository_path}: Ignoring configured "read_special" value of false, as true is needed for database hooks.'
|
||||
)
|
||||
try:
|
||||
working_directory = os.path.expanduser(config.get('working_directory'))
|
||||
except TypeError:
|
||||
working_directory = None
|
||||
|
||||
borg_environment = environment.make_environment(config)
|
||||
|
||||
logger.debug(f'{repository_path}: Collecting special file paths')
|
||||
special_file_paths = collect_special_file_paths(
|
||||
create_flags + create_positional_arguments,
|
||||
|
@ -489,6 +472,73 @@ def create_archive(
|
|||
)
|
||||
create_flags += make_exclude_flags(config, exclude_file.name)
|
||||
|
||||
return (create_flags, create_positional_arguments, pattern_file, exclude_file)
|
||||
|
||||
|
||||
def create_archive(
|
||||
dry_run,
|
||||
repository_path,
|
||||
config,
|
||||
config_paths,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
local_path='borg',
|
||||
remote_path=None,
|
||||
progress=False,
|
||||
stats=False,
|
||||
json=False,
|
||||
list_files=False,
|
||||
stream_processes=None,
|
||||
):
|
||||
'''
|
||||
Given vebosity/dry-run flags, a local or remote repository path, a configuration dict, a
|
||||
sequence of loaded configuration paths, the local Borg version, and global arguments as an
|
||||
argparse.Namespace instance, create a Borg archive and return Borg's JSON output (if any).
|
||||
|
||||
If a sequence of stream processes is given (instances of subprocess.Popen), then execute the
|
||||
create command while also triggering the given processes to produce output.
|
||||
'''
|
||||
borgmatic.logger.add_custom_log_levels()
|
||||
borgmatic_source_directories = expand_directories(
|
||||
collect_borgmatic_source_directories(config.get('borgmatic_source_directory'))
|
||||
)
|
||||
|
||||
(create_flags, create_positional_arguments, pattern_file, exclude_file) = (
|
||||
make_base_create_command(
|
||||
dry_run,
|
||||
repository_path,
|
||||
config,
|
||||
config_paths,
|
||||
local_borg_version,
|
||||
global_arguments,
|
||||
borgmatic_source_directories,
|
||||
local_path,
|
||||
remote_path,
|
||||
progress,
|
||||
json,
|
||||
list_files,
|
||||
stream_processes,
|
||||
)
|
||||
)
|
||||
|
||||
if json:
|
||||
output_log_level = None
|
||||
elif list_files or (stats and not dry_run):
|
||||
output_log_level = logging.ANSWER
|
||||
else:
|
||||
output_log_level = logging.INFO
|
||||
|
||||
# The progress output isn't compatible with captured and logged output, as progress messes with
|
||||
# the terminal directly.
|
||||
output_file = DO_NOT_CAPTURE if progress else None
|
||||
|
||||
try:
|
||||
working_directory = os.path.expanduser(config.get('working_directory'))
|
||||
except TypeError:
|
||||
working_directory = None
|
||||
|
||||
borg_environment = environment.make_environment(config)
|
||||
|
||||
create_flags += (
|
||||
(('--info',) if logger.getEffectiveLevel() == logging.INFO and not json else ())
|
||||
+ (('--stats',) if stats and not json and not dry_run else ())
|
||||
|
|
|
@ -104,8 +104,13 @@ def extract_archive(
|
|||
if not paths:
|
||||
raise ValueError('The --strip-components flag with "all" requires at least one --path')
|
||||
|
||||
# Calculate the maximum number of leading path components of the given paths.
|
||||
strip_components = max(0, *(len(path.split(os.path.sep)) - 1 for path in paths))
|
||||
# Calculate the maximum number of leading path components of the given paths. "if piece"
|
||||
# ignores empty path components, e.g. those resulting from a leading slash. And the "- 1"
|
||||
# is so this doesn't count the final path component, e.g. the filename itself.
|
||||
strip_components = max(
|
||||
0,
|
||||
*(len(tuple(piece for piece in path.split(os.path.sep) if piece)) - 1 for path in paths)
|
||||
)
|
||||
|
||||
full_command = (
|
||||
(local_path, 'extract')
|
||||
|
|
|
@ -74,6 +74,9 @@ def make_match_archives_flags(match_archives, archive_name_format, local_borg_ve
|
|||
(like "{now}") with globs.
|
||||
'''
|
||||
if match_archives:
|
||||
if match_archives in {'*', 're:.*', 'sh:*'}:
|
||||
return ()
|
||||
|
||||
if feature.available(feature.Feature.MATCH_ARCHIVES, local_borg_version):
|
||||
return ('--match-archives', match_archives)
|
||||
else:
|
||||
|
|
|
@ -79,9 +79,11 @@ def make_find_paths(find_paths):
|
|||
return ()
|
||||
|
||||
return tuple(
|
||||
(
|
||||
find_path
|
||||
if re.compile(r'([-!+RrPp] )|(\w\w:)').match(find_path)
|
||||
else f'sh:**/*{find_path}*/**'
|
||||
)
|
||||
for find_path in find_paths
|
||||
)
|
||||
|
||||
|
@ -93,14 +95,15 @@ def capture_archive_listing(
|
|||
local_borg_version,
|
||||
global_arguments,
|
||||
list_paths=None,
|
||||
path_format=None,
|
||||
local_path='borg',
|
||||
remote_path=None,
|
||||
):
|
||||
'''
|
||||
Given a local or remote repository path, an archive name, a configuration dict, the local Borg
|
||||
version, global arguments as an argparse.Namespace, the archive paths in which to list files, and
|
||||
local and remote Borg paths, capture the output of listing that archive and return it as a list
|
||||
of file paths.
|
||||
version, global arguments as an argparse.Namespace, the archive paths in which to list files,
|
||||
the Borg path format to use for the output, and local and remote Borg paths, capture the output
|
||||
of listing that archive and return it as a list of file paths.
|
||||
'''
|
||||
borg_environment = environment.make_environment(config)
|
||||
|
||||
|
@ -116,7 +119,7 @@ def capture_archive_listing(
|
|||
paths=[f'sh:{path}' for path in list_paths] if list_paths else None,
|
||||
find_paths=None,
|
||||
json=None,
|
||||
format='{path}{NL}', # noqa: FS003
|
||||
format=path_format or '{path}{NL}', # noqa: FS003
|
||||
),
|
||||
global_arguments,
|
||||
local_path,
|
||||
|
|
|
@ -614,10 +614,10 @@ def make_parsers():
|
|||
check_group.add_argument(
|
||||
'--only',
|
||||
metavar='CHECK',
|
||||
choices=('repository', 'archives', 'data', 'extract'),
|
||||
choices=('repository', 'archives', 'data', 'extract', 'spot'),
|
||||
dest='only_checks',
|
||||
action='append',
|
||||
help='Run a particular consistency check (repository, archives, data, or extract) instead of configured checks (subject to configured frequency, can specify flag multiple times)',
|
||||
help='Run a particular consistency check (repository, archives, data, extract, or spot) instead of configured checks (subject to configured frequency, can specify flag multiple times)',
|
||||
)
|
||||
check_group.add_argument(
|
||||
'--force',
|
||||
|
|
|
@ -169,7 +169,7 @@ def run_configuration(config_filename, config, config_paths, arguments):
|
|||
continue
|
||||
|
||||
if command.considered_soft_failure(config_filename, error):
|
||||
return
|
||||
break
|
||||
|
||||
yield from log_error_records(
|
||||
f'{repository.get("label", repository["path"])}: Error running actions for repository',
|
||||
|
@ -191,9 +191,7 @@ def run_configuration(config_filename, config, config_paths, arguments):
|
|||
global_arguments.dry_run,
|
||||
)
|
||||
except (OSError, CalledProcessError) as error:
|
||||
if command.considered_soft_failure(config_filename, error):
|
||||
return
|
||||
|
||||
if not command.considered_soft_failure(config_filename, error):
|
||||
encountered_error = error
|
||||
yield from log_error_records(f'{repository["path"]}: Error pinging monitor', error)
|
||||
|
||||
|
@ -288,10 +286,11 @@ def run_actions(
|
|||
global_arguments = arguments['global']
|
||||
dry_run_label = ' (dry run; not making any changes)' if global_arguments.dry_run else ''
|
||||
hook_context = {
|
||||
'repository': repository_path,
|
||||
'repository_label': repository.get('label', ''),
|
||||
'log_file': global_arguments.log_file if global_arguments.log_file else '',
|
||||
# Deprecated: For backwards compatibility with borgmatic < 1.6.0.
|
||||
'repositories': ','.join([repo['path'] for repo in config['repositories']]),
|
||||
'log_file': global_arguments.log_file if global_arguments.log_file else '',
|
||||
'repository': repository_path,
|
||||
}
|
||||
skip_actions = set(get_skip_actions(config, arguments))
|
||||
|
||||
|
|
|
@ -50,12 +50,15 @@ def apply_constants(value, constants, shell_escape=False):
|
|||
value[index] = apply_constants(list_value, constants, shell_escape)
|
||||
elif isinstance(value, dict):
|
||||
for option_name, option_value in value.items():
|
||||
shell_escape = (
|
||||
value[option_name] = apply_constants(
|
||||
option_value,
|
||||
constants,
|
||||
shell_escape=(
|
||||
shell_escape
|
||||
or option_name.startswith('before_')
|
||||
or option_name.startswith('after_')
|
||||
or option_name == 'on_error'
|
||||
),
|
||||
)
|
||||
value[option_name] = apply_constants(option_value, constants, shell_escape)
|
||||
|
||||
return value
|
||||
|
|
|
@ -21,6 +21,19 @@ def insert_newline_before_comment(config, field_name):
|
|||
)
|
||||
|
||||
|
||||
def get_properties(schema):
|
||||
'''
|
||||
Given a schema dict, return its properties. But if it's got sub-schemas with multiple different
|
||||
potential properties, returned their merged properties instead.
|
||||
'''
|
||||
if 'oneOf' in schema:
|
||||
return dict(
|
||||
collections.ChainMap(*[sub_schema['properties'] for sub_schema in schema['oneOf']])
|
||||
)
|
||||
|
||||
return schema['properties']
|
||||
|
||||
|
||||
def schema_to_sample_configuration(schema, level=0, parent_is_sequence=False):
|
||||
'''
|
||||
Given a loaded configuration schema, generate and return sample config for it. Include comments
|
||||
|
@ -40,7 +53,7 @@ def schema_to_sample_configuration(schema, level=0, parent_is_sequence=False):
|
|||
config = ruamel.yaml.comments.CommentedMap(
|
||||
[
|
||||
(field_name, schema_to_sample_configuration(sub_schema, level + 1))
|
||||
for field_name, sub_schema in schema['properties'].items()
|
||||
for field_name, sub_schema in get_properties(schema).items()
|
||||
]
|
||||
)
|
||||
indent = (level * INDENT) + (SEQUENCE_INDENT if parent_is_sequence else 0)
|
||||
|
@ -151,7 +164,7 @@ def add_comments_to_configuration_sequence(config, schema, indent=0):
|
|||
return
|
||||
|
||||
for field_name in config[0].keys():
|
||||
field_schema = schema['items']['properties'].get(field_name, {})
|
||||
field_schema = get_properties(schema['items']).get(field_name, {})
|
||||
description = field_schema.get('description')
|
||||
|
||||
# No description to use? Skip it.
|
||||
|
@ -178,7 +191,7 @@ def add_comments_to_configuration_object(config, schema, indent=0, skip_first=Fa
|
|||
if skip_first and index == 0:
|
||||
continue
|
||||
|
||||
field_schema = schema['properties'].get(field_name, {})
|
||||
field_schema = get_properties(schema).get(field_name, {})
|
||||
description = field_schema.get('description', '').strip()
|
||||
|
||||
# If this is an optional key, add an indicator to the comment flagging it to be commented
|
||||
|
|
|
@ -269,7 +269,8 @@ properties:
|
|||
compression:
|
||||
type: string
|
||||
description: |
|
||||
Type of compression to use when creating archives. See
|
||||
Type of compression to use when creating archives. (Compression
|
||||
level can be added separated with a comma, like "zstd,7".) See
|
||||
http://borgbackup.readthedocs.io/en/stable/usage/create.html for
|
||||
details. Defaults to "lz4".
|
||||
example: lz4
|
||||
|
@ -503,7 +504,8 @@ properties:
|
|||
type: array
|
||||
items:
|
||||
type: object
|
||||
required: ['name']
|
||||
oneOf:
|
||||
- required: [name]
|
||||
additionalProperties: false
|
||||
properties:
|
||||
name:
|
||||
|
@ -516,24 +518,106 @@ properties:
|
|||
- disabled
|
||||
description: |
|
||||
Name of consistency check to run: "repository",
|
||||
"archives", "data", and/or "extract". "repository"
|
||||
checks the consistency of the repository, "archives"
|
||||
checks all of the archives, "data" verifies the
|
||||
integrity of the data within the archives, and "extract"
|
||||
does an extraction dry-run of the most recent archive.
|
||||
Note that "data" implies "archives". See "skip_actions"
|
||||
for disabling checks altogether.
|
||||
"archives", "data", "spot", and/or "extract".
|
||||
"repository" checks the consistency of the
|
||||
repository, "archives" checks all of the
|
||||
archives, "data" verifies the integrity of the
|
||||
data within the archives, "spot" checks that
|
||||
some percentage of source files are found in the
|
||||
most recent archive (with identical contents),
|
||||
and "extract" does an extraction dry-run of the
|
||||
most recent archive. Note that "data" implies
|
||||
"archives". See "skip_actions" for disabling
|
||||
checks altogether.
|
||||
example: spot
|
||||
frequency:
|
||||
type: string
|
||||
description: |
|
||||
How frequently to run this type of consistency
|
||||
check (as a best effort). The value is a number
|
||||
followed by a unit of time. E.g., "2 weeks" to
|
||||
run this consistency check no more than every
|
||||
two weeks for a given repository or "1 month" to
|
||||
run it no more than monthly. Defaults to
|
||||
"always": running this check every time checks
|
||||
are run.
|
||||
example: 2 weeks
|
||||
- required:
|
||||
- name
|
||||
- count_tolerance_percentage
|
||||
- data_sample_percentage
|
||||
- data_tolerance_percentage
|
||||
additionalProperties: false
|
||||
properties:
|
||||
name:
|
||||
type: string
|
||||
enum:
|
||||
- spot
|
||||
description: |
|
||||
Name of consistency check to run: "repository",
|
||||
"archives", "data", "spot", and/or "extract".
|
||||
"repository" checks the consistency of the
|
||||
repository, "archives" checks all of the
|
||||
archives, "data" verifies the integrity of the
|
||||
data within the archives, "spot" checks that
|
||||
some percentage of source files are found in the
|
||||
most recent archive (with identical contents),
|
||||
and "extract" does an extraction dry-run of the
|
||||
most recent archive. Note that "data" implies
|
||||
"archives". See "skip_actions" for disabling
|
||||
checks altogether.
|
||||
example: repository
|
||||
frequency:
|
||||
type: string
|
||||
description: |
|
||||
How frequently to run this type of consistency check (as
|
||||
a best effort). The value is a number followed by a unit
|
||||
of time. E.g., "2 weeks" to run this consistency check
|
||||
no more than every two weeks for a given repository or
|
||||
"1 month" to run it no more than monthly. Defaults to
|
||||
"always": running this check every time checks are run.
|
||||
How frequently to run this type of consistency
|
||||
check (as a best effort). The value is a number
|
||||
followed by a unit of time. E.g., "2 weeks" to
|
||||
run this consistency check no more than every
|
||||
two weeks for a given repository or "1 month" to
|
||||
run it no more than monthly. Defaults to
|
||||
"always": running this check every time checks
|
||||
are run.
|
||||
example: 2 weeks
|
||||
count_tolerance_percentage:
|
||||
type: number
|
||||
description: |
|
||||
The percentage delta between the source
|
||||
directories file count and the most recent backup
|
||||
archive file count that is allowed before the
|
||||
entire consistency check fails. This can catch
|
||||
problems like incorrect excludes, inadvertent
|
||||
deletes, etc. Only applies to the "spot" check.
|
||||
example: 10
|
||||
data_sample_percentage:
|
||||
type: number
|
||||
description: |
|
||||
The percentage of total files in the source
|
||||
directories to randomly sample and compare to
|
||||
their corresponding files in the most recent
|
||||
backup archive. Only applies to the "spot" check.
|
||||
example: 1
|
||||
data_tolerance_percentage:
|
||||
type: number
|
||||
description: |
|
||||
The percentage of total files in the source
|
||||
directories that can fail a spot check comparison
|
||||
without failing the entire consistency check. This
|
||||
can catch problems like source files that have
|
||||
been bulk-changed by malware, backups that have
|
||||
been tampered with, etc. The value must be lower
|
||||
than or equal to the "contents_sample_percentage".
|
||||
Only applies to the "spot" check.
|
||||
example: 0.5
|
||||
xxh64sum_command:
|
||||
type: string
|
||||
description: |
|
||||
Command to use instead of "xxh64sum" to hash
|
||||
source files, usually found in an OS package named
|
||||
"xxhash". Do not substitute with a different hash
|
||||
type (SHA, MD5, etc.) or the check will never
|
||||
succeed. Only applies to the "spot" check.
|
||||
example: /usr/local/bin/xxh64sum
|
||||
description: |
|
||||
List of one or more consistency checks to run on a periodic basis
|
||||
(if "frequency" is set) or every time borgmatic runs checks (if
|
||||
|
@ -1579,6 +1663,14 @@ properties:
|
|||
states.
|
||||
example:
|
||||
- finish
|
||||
create_slug:
|
||||
type: boolean
|
||||
description: |
|
||||
Create the check if it does not exist. Only works with
|
||||
the slug URL scheme (https://hc-ping.com/<ping-key>/<slug>
|
||||
as opposed to https://hc-ping.com/<uuid>).
|
||||
Defaults to false.
|
||||
example: true
|
||||
description: |
|
||||
Configuration for a monitoring integration with Healthchecks. Create
|
||||
an account at https://healthchecks.io (or self-host Healthchecks) if
|
||||
|
|
|
@ -4,6 +4,7 @@ import logging
|
|||
import os
|
||||
import select
|
||||
import subprocess
|
||||
import textwrap
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
@ -219,13 +220,41 @@ def log_outputs(processes, exclude_stdouts, output_log_level, borg_local_path, b
|
|||
}
|
||||
|
||||
|
||||
SECRET_COMMAND_FLAG_NAMES = {'--password'}
|
||||
|
||||
|
||||
def mask_command_secrets(full_command):
|
||||
'''
|
||||
Given a command as a sequence, mask secret values for flags like "--password" in preparation for
|
||||
logging.
|
||||
'''
|
||||
masked_command = []
|
||||
previous_piece = None
|
||||
|
||||
for piece in full_command:
|
||||
masked_command.append('***' if previous_piece in SECRET_COMMAND_FLAG_NAMES else piece)
|
||||
previous_piece = piece
|
||||
|
||||
return tuple(masked_command)
|
||||
|
||||
|
||||
MAX_LOGGED_COMMAND_LENGTH = 1000
|
||||
|
||||
|
||||
def log_command(full_command, input_file=None, output_file=None, environment=None):
|
||||
'''
|
||||
Log the given command (a sequence of command/argument strings), along with its input/output file
|
||||
paths and extra environment variables (with omitted values in case they contain passwords).
|
||||
'''
|
||||
logger.debug(
|
||||
' '.join(tuple(f'{key}=***' for key in (environment or {}).keys()) + tuple(full_command))
|
||||
textwrap.shorten(
|
||||
' '.join(
|
||||
tuple(f'{key}=***' for key in (environment or {}).keys())
|
||||
+ mask_command_secrets(full_command)
|
||||
),
|
||||
width=MAX_LOGGED_COMMAND_LENGTH,
|
||||
placeholder=' ...',
|
||||
)
|
||||
+ (f" < {getattr(input_file, 'name', '')}" if input_file else '')
|
||||
+ (f" > {getattr(output_file, 'name', '')}" if output_file else '')
|
||||
)
|
||||
|
@ -376,9 +405,9 @@ def execute_command_with_processes(
|
|||
command,
|
||||
stdin=input_file,
|
||||
stdout=None if do_not_capture else (output_file or subprocess.PIPE),
|
||||
stderr=None
|
||||
if do_not_capture
|
||||
else (subprocess.PIPE if output_file else subprocess.STDOUT),
|
||||
stderr=(
|
||||
None if do_not_capture else (subprocess.PIPE if output_file else subprocess.STDOUT)
|
||||
),
|
||||
shell=shell,
|
||||
env=environment,
|
||||
cwd=working_directory,
|
||||
|
|
|
@ -68,9 +68,9 @@ def execute_hook(commands, umask, config_filename, description, dry_run, **conte
|
|||
if not dry_run:
|
||||
execute.execute_command(
|
||||
[command],
|
||||
output_log_level=logging.ERROR
|
||||
if description == 'on-error'
|
||||
else logging.WARNING,
|
||||
output_log_level=(
|
||||
logging.ERROR if description == 'on-error' else logging.WARNING
|
||||
),
|
||||
shell=True,
|
||||
)
|
||||
finally:
|
||||
|
|
|
@ -1,4 +1,5 @@
|
|||
import logging
|
||||
import re
|
||||
|
||||
import requests
|
||||
|
||||
|
@ -59,10 +60,20 @@ def ping_monitor(hook_config, config, config_filename, state, monitoring_log_lev
|
|||
)
|
||||
return
|
||||
|
||||
ping_url_is_uuid = re.search(r'\w{8}-\w{4}-\w{4}-\w{4}-\w{12}$', ping_url)
|
||||
|
||||
healthchecks_state = MONITOR_STATE_TO_HEALTHCHECKS.get(state)
|
||||
if healthchecks_state:
|
||||
ping_url = f'{ping_url}/{healthchecks_state}'
|
||||
|
||||
if hook_config.get('create_slug'):
|
||||
if ping_url_is_uuid:
|
||||
logger.warning(
|
||||
f'{config_filename}: Healthchecks UUIDs do not support auto provisionning; ignoring'
|
||||
)
|
||||
else:
|
||||
ping_url = f'{ping_url}?create=1'
|
||||
|
||||
logger.info(f'{config_filename}: Pinging Healthchecks {state.name.lower()}{dry_run_label}')
|
||||
logger.debug(f'{config_filename}: Using Healthchecks ping URL {ping_url}')
|
||||
|
||||
|
|
|
@ -115,6 +115,14 @@ def execute_dump_command(
|
|||
)
|
||||
|
||||
|
||||
def use_streaming(databases, config, log_prefix):
|
||||
'''
|
||||
Given a sequence of MariaDB database configuration dicts, a configuration dict (ignored), and a
|
||||
log prefix (ignored), return whether streaming will be using during dumps.
|
||||
'''
|
||||
return any(databases)
|
||||
|
||||
|
||||
def dump_data_sources(databases, config, log_prefix, dry_run):
|
||||
'''
|
||||
Dump the given MariaDB databases to a named pipe. The databases are supplied as a sequence of
|
||||
|
|
|
@ -16,6 +16,14 @@ def make_dump_path(config): # pragma: no cover
|
|||
)
|
||||
|
||||
|
||||
def use_streaming(databases, config, log_prefix):
|
||||
'''
|
||||
Given a sequence of MongoDB database configuration dicts, a configuration dict (ignored), and a
|
||||
log prefix (ignored), return whether streaming will be using during dumps.
|
||||
'''
|
||||
return any(database.get('format') != 'directory' for database in databases)
|
||||
|
||||
|
||||
def dump_data_sources(databases, config, log_prefix, dry_run):
|
||||
'''
|
||||
Dump the given MongoDB databases to a named pipe. The databases are supplied as a sequence of
|
||||
|
|
|
@ -114,6 +114,14 @@ def execute_dump_command(
|
|||
)
|
||||
|
||||
|
||||
def use_streaming(databases, config, log_prefix):
|
||||
'''
|
||||
Given a sequence of MySQL database configuration dicts, a configuration dict (ignored), and a
|
||||
log prefix (ignored), return whether streaming will be using during dumps.
|
||||
'''
|
||||
return any(databases)
|
||||
|
||||
|
||||
def dump_data_sources(databases, config, log_prefix, dry_run):
|
||||
'''
|
||||
Dump the given MySQL/MariaDB databases to a named pipe. The databases are supplied as a sequence
|
||||
|
|
|
@ -96,6 +96,14 @@ def database_names_to_dump(database, extra_environment, log_prefix, dry_run):
|
|||
)
|
||||
|
||||
|
||||
def use_streaming(databases, config, log_prefix):
|
||||
'''
|
||||
Given a sequence of PostgreSQL database configuration dicts, a configuration dict (ignored), and
|
||||
a log prefix (ignored), return whether streaming will be using during dumps.
|
||||
'''
|
||||
return any(database.get('format') != 'directory' for database in databases)
|
||||
|
||||
|
||||
def dump_data_sources(databases, config, log_prefix, dry_run):
|
||||
'''
|
||||
Dump the given PostgreSQL databases to a named pipe. The databases are supplied as a sequence of
|
||||
|
|
|
@ -17,9 +17,17 @@ def make_dump_path(config): # pragma: no cover
|
|||
)
|
||||
|
||||
|
||||
def use_streaming(databases, config, log_prefix):
|
||||
'''
|
||||
Given a sequence of SQLite database configuration dicts, a configuration dict (ignored), and a
|
||||
log prefix (ignored), return whether streaming will be using during dumps.
|
||||
'''
|
||||
return any(databases)
|
||||
|
||||
|
||||
def dump_data_sources(databases, config, log_prefix, dry_run):
|
||||
'''
|
||||
Dump the given SQLite3 databases to a named pipe. The databases are supplied as a sequence of
|
||||
Dump the given SQLite databases to a named pipe. The databases are supplied as a sequence of
|
||||
configuration dicts, as per the configuration schema. Use the given configuration dict to
|
||||
construct the destination path and the given log prefix in any log entries.
|
||||
|
||||
|
@ -71,7 +79,7 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
|
|||
|
||||
def remove_data_source_dumps(databases, config, log_prefix, dry_run): # pragma: no cover
|
||||
'''
|
||||
Remove the given SQLite3 database dumps from the filesystem. The databases are supplied as a
|
||||
Remove the given SQLite database dumps from the filesystem. The databases are supplied as a
|
||||
sequence of configuration dicts, as per the configuration schema. Use the given configuration
|
||||
dict to construct the destination path and the given log prefix in any log entries. If this is a
|
||||
dry run, then don't actually remove anything.
|
||||
|
@ -81,8 +89,8 @@ def remove_data_source_dumps(databases, config, log_prefix, dry_run): # pragma:
|
|||
|
||||
def make_data_source_dump_pattern(databases, config, log_prefix, name=None): # pragma: no cover
|
||||
'''
|
||||
Make a pattern that matches the given SQLite3 databases. The databases are supplied as a
|
||||
sequence of configuration dicts, as per the configuration schema.
|
||||
Make a pattern that matches the given SQLite databases. The databases are supplied as a sequence
|
||||
of configuration dicts, as per the configuration schema.
|
||||
'''
|
||||
return dump.make_data_source_dump_filename(make_dump_path(config), name)
|
||||
|
||||
|
|
|
@ -41,8 +41,7 @@ def should_do_markup(no_color, configs):
|
|||
if any(config.get('output', {}).get('color') is False for config in configs.values()):
|
||||
return False
|
||||
|
||||
no_color_env = os.environ.get('NO_COLOR', None)
|
||||
if no_color_env is not None:
|
||||
if os.environ.get('NO_COLOR', None):
|
||||
return False
|
||||
|
||||
py_colors = os.environ.get('PY_COLORS', None)
|
||||
|
@ -89,6 +88,11 @@ class Multi_stream_handler(logging.Handler):
|
|||
handler.setLevel(level)
|
||||
|
||||
|
||||
class Console_no_color_formatter(logging.Formatter):
|
||||
def format(self, record):
|
||||
return record.msg
|
||||
|
||||
|
||||
class Console_color_formatter(logging.Formatter):
|
||||
def format(self, record):
|
||||
add_custom_log_levels()
|
||||
|
@ -199,6 +203,8 @@ def configure_logging(
|
|||
|
||||
if color_enabled:
|
||||
console_handler.setFormatter(Console_color_formatter())
|
||||
else:
|
||||
console_handler.setFormatter(Console_no_color_formatter())
|
||||
|
||||
console_handler.setLevel(console_log_level)
|
||||
|
||||
|
|
|
@ -1,4 +1,3 @@
|
|||
version: '3'
|
||||
services:
|
||||
docs:
|
||||
image: borgmatic-docs
|
||||
|
|
|
@ -84,6 +84,9 @@ variables you can use here:
|
|||
path of the borgmatic log file, only set when the `--log-file` flag is used
|
||||
* `repository`: path of the current repository as configured in the current
|
||||
borgmatic configuration file
|
||||
* `repository_label` <span class="minilink minilink-addedin">New in version
|
||||
1.8.12</span>: label of the current repository as configured in the current
|
||||
borgmatic configuration file
|
||||
|
||||
Note that you can also interpolate in [arbitrary environment
|
||||
variables](https://torsion.org/borgmatic/docs/how-to/provide-your-passwords/).
|
||||
|
|
|
@ -206,6 +206,36 @@ hooks:
|
|||
|
||||
Alter the ports in these examples to suit your particular database system.
|
||||
|
||||
Normally, borgmatic dumps a database by running a database dump command (e.g.
|
||||
`pg_dump`) on the host or wherever borgmatic is running, and this command
|
||||
connects to your containerized database via the given `hostname` and `port`.
|
||||
But if you don't have any database dump commands installed on your host and
|
||||
you'd rather use the commands inside your database container itself, borgmatic
|
||||
supports that too. Just configure borgmatic to `exec` into your container to
|
||||
run the dump command.
|
||||
|
||||
For instance, if using Docker and PostgreSQL, something like this might work:
|
||||
|
||||
```yaml
|
||||
hooks:
|
||||
postgresql_databases:
|
||||
- name: users
|
||||
hostname: 127.0.0.1
|
||||
port: 5433
|
||||
username: postgres
|
||||
password: trustsome1
|
||||
pg_dump_command: docker exec my_pg_container pg_dump
|
||||
```
|
||||
|
||||
... where `my_pg_container` is the name of your database container. In this
|
||||
example, you'd also need to set the `pg_restore_command` and `psql_command`
|
||||
options.
|
||||
|
||||
Similar command override options are available for (some of) the other
|
||||
supported database types as well. See the [configuration
|
||||
reference](https://torsion.org/borgmatic/docs/reference/configuration/) for
|
||||
details.
|
||||
|
||||
|
||||
### No source directories
|
||||
|
||||
|
@ -407,19 +437,28 @@ borgmatic's own configuration file. So include your configuration file in
|
|||
backups to avoid getting caught without a way to restore a database.
|
||||
3. borgmatic does not currently support backing up or restoring multiple
|
||||
databases that share the exact same name on different hosts.
|
||||
4. Because database hooks implicitly enable the `read_special` configuration,
|
||||
any special files are excluded from backups (named pipes, block devices,
|
||||
character devices, and sockets) to prevent hanging. Try a command like `find
|
||||
/your/source/path -type b -or -type c -or -type p -or -type s` to find such
|
||||
files. Common directories to exclude are `/dev` and `/run`, but that may not
|
||||
be exhaustive. <span class="minilink minilink-addedin">New in version
|
||||
1.7.3</span> When database hooks are enabled, borgmatic automatically excludes
|
||||
special files (and symlinks to special files) that may cause Borg to hang, so
|
||||
generally you no longer need to manually exclude them. There are potential
|
||||
edge cases though in which applications on your system create new special files
|
||||
*after* borgmatic constructs its exclude list, resulting in Borg hangs. If that
|
||||
occurs, you can resort to the manual excludes described above. And to opt out
|
||||
of the auto-exclude feature entirely, explicitly set `read_special` to true.
|
||||
4. When database hooks are enabled, borgmatic instructs Borg to consume
|
||||
special files (via `--read-special`) to support database dump
|
||||
streaming—regardless of the value of your `read_special` configuration option.
|
||||
And because this can cause Borg to hang, borgmatic also automatically excludes
|
||||
special files (and symlinks to them) that Borg may get stuck on. Even so,
|
||||
there are still potential edge cases in which applications on your system
|
||||
create new special files *after* borgmatic constructs its exclude list,
|
||||
resulting in Borg hangs. If that occurs, you can resort to manually excluding
|
||||
those files. And if you explicitly set the `read-special` option to `true`,
|
||||
borgmatic will opt you out of the auto-exclude feature entirely, but will
|
||||
still instruct Borg to consume special files—you will just be on your own to
|
||||
exclude them. <span class="minilink minilink-addedin">Prior to version
|
||||
1.7.3</span>Special files were not auto-excluded, and you were responsible for
|
||||
excluding them yourself. Common directories to exclude are `/dev` and `/run`,
|
||||
but that may not be exhaustive.
|
||||
5. Database hooks also implicitly enable the `one_file_system` option, which
|
||||
means Borg won't cross filesystem boundaries when looking for files to backup.
|
||||
This is especially important when running borgmatic in a container, as
|
||||
container volumes are mounted as separate filesystems. One work-around is to
|
||||
explicitly add each mounted volume you'd like to backup to
|
||||
`source_directories` instead of relying on Borg to include them implicitly via
|
||||
a parent directory.
|
||||
|
||||
|
||||
### Manual restoration
|
||||
|
|
|
@ -20,7 +20,7 @@ default action ordering was `prune`, `compact`, `create`, and `check`.
|
|||
### A la carte actions
|
||||
|
||||
If you find yourself wanting to customize the actions, you have some options.
|
||||
First, you can run borgmatic's `prune`, `compact`, `create`, or `check`
|
||||
First, you can run borgmatic's `create`, `prune`, `compact`, or `check`
|
||||
actions separately. For instance, the following optional actions are
|
||||
available (among others):
|
||||
|
||||
|
@ -91,8 +91,9 @@ Here are the available checks from fastest to slowest:
|
|||
|
||||
* `repository`: Checks the consistency of the repository itself.
|
||||
* `archives`: Checks all of the archives in the repository.
|
||||
* `extract`: Performs an extraction dry-run of the most recent archive.
|
||||
* `extract`: Performs an extraction dry-run of the latest archive.
|
||||
* `data`: Verifies the data integrity of all archives contents, decrypting and decompressing all data.
|
||||
* `spot`: Compares file counts and contents between your source files and the latest archive.
|
||||
|
||||
Note that the `data` check is a more thorough version of the `archives` check,
|
||||
so enabling the `data` check implicitly enables the `archives` check as well.
|
||||
|
@ -102,6 +103,89 @@ documentation](https://borgbackup.readthedocs.io/en/stable/usage/check.html)
|
|||
for more information.
|
||||
|
||||
|
||||
### Spot check
|
||||
|
||||
The various consistency checks all have trade-offs around speed and
|
||||
thoroughness, but most of them don't even look at your original source
|
||||
files—arguably one important way to ensure your backups contain the files
|
||||
you'll want to restore in the case of catastrophe (or just an accidentally
|
||||
deleted file). Because if something goes wrong with your source files, most
|
||||
consistency checks will still pass with flying colors and you won't discover
|
||||
there's a problem until you go to restore.
|
||||
|
||||
<span class="minilink minilink-addedin">New in version 1.8.10</span> <span
|
||||
class="minilink minilink-addedin">Beta feature</span> That's where the spot
|
||||
check comes in. This check actually compares your source file counts and data
|
||||
against those in the latest archive, potentially catching problems like
|
||||
incorrect excludes, inadvertent deletes, files changed by malware, etc.
|
||||
|
||||
However, because an exhaustive comparison of all source files against the
|
||||
latest archive might be too slow, the spot check supports *sampling* a
|
||||
percentage of your source files for the comparison, ensuring they fall within
|
||||
configured tolerances.
|
||||
|
||||
Here's how it works. Start by installing the `xxhash` OS package if you don't
|
||||
already have it, so the spot check can run the `xxh64sum` command and
|
||||
efficiently hash files for comparison. Then add something like the following
|
||||
to your borgmatic configuration:
|
||||
|
||||
```yaml
|
||||
checks:
|
||||
- name: spot
|
||||
count_tolerance_percentage: 10
|
||||
data_sample_percentage: 1
|
||||
data_tolerance_percentage: 0.5
|
||||
```
|
||||
|
||||
The `count_tolerance_percentage` is the percentage delta between the source
|
||||
directories file count and the latest backup archive file count that is
|
||||
allowed before the entire consistency check fails. For instance, if the spot
|
||||
check runs and finds 100 source files on disk and 105 files in the latest
|
||||
archive, that would be within the configured 10% count tolerance and the check
|
||||
would succeed. But if there were 100 source files and 200 archive files, the
|
||||
check would fail. (100 source files and only 50 archive files would also
|
||||
fail.)
|
||||
|
||||
The `data_sample_percentage` is the percentage of total files in the source
|
||||
directories to randomly sample and compare to their corresponding files in the
|
||||
latest backup archive. A higher value allows a more accurate check—and a
|
||||
slower one. The comparison is performed by hashing the selected source files
|
||||
and counting hashes that don't match the latest archive. For instance, if you
|
||||
have 1,000 source files and your sample percentage is 1%, then only 10 source
|
||||
files will be compared against the latest archive. These sampled files are
|
||||
selected randomly each time, so in effect the spot check is probabilistic.
|
||||
|
||||
The `data_tolerance_percentage` is the percentage of total files in the source
|
||||
directories that can fail a spot check data comparison without failing the
|
||||
entire consistency check. The value must be lower than or equal to the
|
||||
`data_sample_percentage`, because `data_tolerance_percentage` only looks at
|
||||
at the sampled files as determined by `data_sample_percentage`.
|
||||
|
||||
All three options are required when using the spot check. And because the
|
||||
check relies on these configured tolerances, it may not be a
|
||||
set-it-and-forget-it type of consistency check, at least until you get the
|
||||
tolerances dialed in so there are minimal false positives or negatives. It is
|
||||
recommended you run `borgmatic check` several times after configuring the spot
|
||||
check, tweaking your tolerances as needed. For certain workloads where your
|
||||
source files experience wild swings of file contents or counts, the spot check
|
||||
may not suitable at all.
|
||||
|
||||
What if you add, delete, or change a bunch of your source files and you don't
|
||||
want the spot check to fail the next time it's run? Run `borgmatic create` to
|
||||
create a new backup, thereby allowing the next spot check to run against an
|
||||
archive that contains your recent changes.
|
||||
|
||||
Because the spot check only looks at the most recent archive, you may not want
|
||||
to run it immediately after a `create` action (borgmatic's default behavior).
|
||||
Instead, it may make more sense to run the spot check on a separate schedule
|
||||
from `create`.
|
||||
|
||||
As long as the spot check feature is in beta, it may be subject to breaking
|
||||
changes. But feel free to use it in production if you're okay with that
|
||||
caveat, and please [provide any
|
||||
feedback](https://torsion.org/borgmatic/#issues) you have on this feature.
|
||||
|
||||
|
||||
### Check frequency
|
||||
|
||||
<span class="minilink minilink-addedin">New in version 1.6.2</span> You can
|
||||
|
|
|
@ -208,8 +208,8 @@ cronitor:
|
|||
this option in the `hooks:` section of your configuration.
|
||||
|
||||
With this configuration, borgmatic pings your Cronitor monitor when a backup
|
||||
begins, ends, or errors, but only when any of the `prune`, `compact`,
|
||||
`create`, or `check` actions are run. Then, if the actions complete
|
||||
begins, ends, or errors, but only when any of the `create`, `prune`,
|
||||
`compact`, or `check` actions are run. Then, if the actions complete
|
||||
successfully or errors, borgmatic notifies Cronitor accordingly.
|
||||
|
||||
You can configure Cronitor to notify you by a [variety of
|
||||
|
@ -235,8 +235,8 @@ cronhub:
|
|||
this option in the `hooks:` section of your configuration.
|
||||
|
||||
With this configuration, borgmatic pings your Cronhub monitor when a backup
|
||||
begins, ends, or errors, but only when any of the `prune`, `compact`,
|
||||
`create`, or `check` actions are run. Then, if the actions complete
|
||||
begins, ends, or errors, but only when any of the `create`, `prune`,
|
||||
`compact`, or `check` actions are run. Then, if the actions complete
|
||||
successfully or errors, borgmatic notifies Cronhub accordingly.
|
||||
|
||||
Note that even though you configure borgmatic with the "start" variant of the
|
||||
|
@ -368,7 +368,7 @@ loki:
|
|||
```
|
||||
|
||||
With this configuration, borgmatic sends its logs to your Loki instance as any
|
||||
of the `prune`, `compact`, `create`, or `check` actions are run. Then, after
|
||||
of the `create`, `prune`, `compact`, or `check` actions are run. Then, after
|
||||
the actions complete, borgmatic notifies Loki of success or failure.
|
||||
|
||||
This hook supports sending arbitrary labels to Loki. For instance:
|
||||
|
@ -401,6 +401,10 @@ loki:
|
|||
hostname: __hostname
|
||||
```
|
||||
|
||||
Also check out this [Loki dashboard for
|
||||
borgmatic](https://grafana.com/grafana/dashboards/20736-borgmatic-logs/) if
|
||||
you'd like to see your backup logs and statistics in one place.
|
||||
|
||||
|
||||
## Apprise hook
|
||||
|
||||
|
@ -416,7 +420,8 @@ pipx](https://torsion.org/borgmatic/docs/how-to/set-up-backups/#installation),
|
|||
run the following to install Apprise so borgmatic can use it:
|
||||
|
||||
```bash
|
||||
sudo pipx install --force borgmatic[Apprise]
|
||||
sudo pipx uninstall borgmatic
|
||||
sudo pipx install borgmatic[Apprise]
|
||||
```
|
||||
|
||||
Omit `sudo` if borgmatic is installed as a non-root user.
|
||||
|
@ -431,11 +436,16 @@ apprise:
|
|||
label: gotify
|
||||
- url: mastodons://access_key@hostname/@user
|
||||
label: mastodon
|
||||
states:
|
||||
- start
|
||||
- finish
|
||||
- fail
|
||||
```
|
||||
|
||||
With this configuration, borgmatic pings each of the configured Apprise
|
||||
services when a backup begins, ends, or errors, but only when any of the
|
||||
`prune`, `compact`, `create`, or `check` actions are run.
|
||||
`create`, `prune`, `compact`, or `check` actions are run. (By default, if
|
||||
`states` is not specified, Apprise services are only pinged on error.)
|
||||
|
||||
You can optionally customize the contents of the default messages sent to
|
||||
these services:
|
||||
|
|
2
setup.py
2
setup.py
|
@ -1,6 +1,6 @@
|
|||
from setuptools import find_packages, setup
|
||||
|
||||
VERSION = '1.8.9'
|
||||
VERSION = '1.8.12.dev0'
|
||||
|
||||
|
||||
setup(
|
||||
|
|
|
@ -1,34 +1,34 @@
|
|||
appdirs==1.4.4
|
||||
apprise==1.3.0
|
||||
attrs==22.2.0
|
||||
black==23.3.0
|
||||
certifi==2023.7.22
|
||||
chardet==5.1.0
|
||||
click==8.1.3
|
||||
codespell==2.2.4
|
||||
apprise==1.8.0
|
||||
attrs==23.2.0
|
||||
black==24.4.2
|
||||
certifi==2024.2.2
|
||||
chardet==5.2.0
|
||||
click==8.1.7
|
||||
codespell==2.2.6
|
||||
colorama==0.4.6
|
||||
coverage==7.2.3
|
||||
flake8==6.0.0
|
||||
flake8-quotes==3.3.2
|
||||
coverage==7.5.1
|
||||
flake8==7.0.0
|
||||
flake8-quotes==3.4.0
|
||||
flake8-use-fstring==1.4
|
||||
flake8-variables-names==0.0.5
|
||||
flexmock==0.11.3
|
||||
idna==3.4
|
||||
isort==5.12.0
|
||||
jsonschema==4.17.3
|
||||
Markdown==3.4.1
|
||||
flake8-variables-names==0.0.6
|
||||
flexmock==0.12.1
|
||||
idna==3.7
|
||||
isort==5.13.2
|
||||
jsonschema==4.22.0
|
||||
Markdown==3.6
|
||||
mccabe==0.7.0
|
||||
packaging==23.1
|
||||
pathspec==0.11.1
|
||||
pluggy==1.0.0
|
||||
packaging==24.0
|
||||
pathspec==0.12.1
|
||||
pluggy==1.5.0
|
||||
py==1.11.0
|
||||
pycodestyle==2.10.0
|
||||
pyflakes==3.0.1
|
||||
pytest==7.3.0
|
||||
pytest-cov==4.0.0
|
||||
pycodestyle==2.11.1
|
||||
pyflakes==3.2.0
|
||||
pytest==8.2.1
|
||||
pytest-cov==5.0.0
|
||||
PyYAML>5.0.0
|
||||
regex
|
||||
requests==2.31.0
|
||||
requests==2.32.2
|
||||
ruamel.yaml>0.15.0
|
||||
toml==0.10.2
|
||||
typed-ast
|
||||
|
|
|
@ -1,4 +1,3 @@
|
|||
version: '3'
|
||||
services:
|
||||
postgresql:
|
||||
image: docker.io/postgres:13.1-alpine
|
||||
|
|
File diff suppressed because it is too large
Load Diff
|
@ -1,25 +1,31 @@
|
|||
from flexmock import flexmock
|
||||
import pytest
|
||||
|
||||
from borgmatic.actions import json as module
|
||||
|
||||
|
||||
def test_parse_json_loads_json_from_string():
|
||||
flexmock(module.json).should_receive('loads').and_return({'repository': {'id': 'foo'}})
|
||||
|
||||
assert module.parse_json('{"repository": {"id": "foo"}}', label=None) == {
|
||||
'repository': {'id': 'foo', 'label': ''}
|
||||
}
|
||||
|
||||
|
||||
def test_parse_json_injects_label_into_parsed_data():
|
||||
flexmock(module.json).should_receive('loads').and_return({'repository': {'id': 'foo'}})
|
||||
def test_parse_json_skips_non_json_warnings_and_loads_subsequent_json():
|
||||
assert module.parse_json(
|
||||
'/non/existent/path: stat: [Errno 2] No such file or directory: /non/existent/path\n{"repository":\n{"id": "foo"}}',
|
||||
label=None,
|
||||
) == {'repository': {'id': 'foo', 'label': ''}}
|
||||
|
||||
|
||||
def test_parse_json_skips_with_invalid_json_raises():
|
||||
with pytest.raises(module.json.JSONDecodeError):
|
||||
module.parse_json('this is not valid JSON }', label=None)
|
||||
|
||||
|
||||
def test_parse_json_injects_label_into_parsed_data():
|
||||
assert module.parse_json('{"repository": {"id": "foo"}}', label='bar') == {
|
||||
'repository': {'id': 'foo', 'label': 'bar'}
|
||||
}
|
||||
|
||||
|
||||
def test_parse_json_injects_nothing_when_repository_missing():
|
||||
flexmock(module.json).should_receive('loads').and_return({'stuff': {'id': 'foo'}})
|
||||
|
||||
assert module.parse_json('{"stuff": {"id": "foo"}}', label='bar') == {'stuff': {'id': 'foo'}}
|
||||
|
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
@ -507,6 +507,39 @@ def test_extract_archive_calls_borg_with_strip_components_calculated_from_all():
|
|||
)
|
||||
|
||||
|
||||
def test_extract_archive_calls_borg_with_strip_components_calculated_from_all_with_leading_slash():
|
||||
flexmock(module.os.path).should_receive('abspath').and_return('repo')
|
||||
insert_execute_command_mock(
|
||||
(
|
||||
'borg',
|
||||
'extract',
|
||||
'--strip-components',
|
||||
'2',
|
||||
'repo::archive',
|
||||
'/foo/bar/baz.txt',
|
||||
'/foo/bar.txt',
|
||||
)
|
||||
)
|
||||
flexmock(module.feature).should_receive('available').and_return(True)
|
||||
flexmock(module.flags).should_receive('make_repository_archive_flags').and_return(
|
||||
('repo::archive',)
|
||||
)
|
||||
flexmock(module.borgmatic.config.validate).should_receive(
|
||||
'normalize_repository_path'
|
||||
).and_return('repo')
|
||||
|
||||
module.extract_archive(
|
||||
dry_run=False,
|
||||
repository='repo',
|
||||
archive='archive',
|
||||
paths=['/foo/bar/baz.txt', '/foo/bar.txt'],
|
||||
config={},
|
||||
local_borg_version='1.2.3',
|
||||
global_arguments=flexmock(log_json=False),
|
||||
strip_components='all',
|
||||
)
|
||||
|
||||
|
||||
def test_extract_archive_with_strip_components_all_and_no_paths_raises():
|
||||
flexmock(module.os.path).should_receive('abspath').and_return('repo')
|
||||
flexmock(module.feature).should_receive('available').and_return(True)
|
||||
|
|
|
@ -151,6 +151,30 @@ def test_make_repository_archive_flags_with_borg_features_joins_repository_and_a
|
|||
False,
|
||||
('--glob-archives', '*-docs-{user}'), # noqa: FS003
|
||||
),
|
||||
(
|
||||
'*',
|
||||
'{now}', # noqa: FS003
|
||||
True,
|
||||
(),
|
||||
),
|
||||
(
|
||||
'*',
|
||||
'{now}', # noqa: FS003
|
||||
False,
|
||||
(),
|
||||
),
|
||||
(
|
||||
're:.*',
|
||||
'{now}', # noqa: FS003
|
||||
True,
|
||||
(),
|
||||
),
|
||||
(
|
||||
'sh:*',
|
||||
'{now}', # noqa: FS003
|
||||
True,
|
||||
(),
|
||||
),
|
||||
),
|
||||
)
|
||||
def test_make_match_archives_flags_makes_flags_with_globs(
|
||||
|
|
|
@ -61,7 +61,7 @@ def test_run_configuration_with_invalid_borg_version_errors():
|
|||
flexmock(module.command).should_receive('execute_hook').never()
|
||||
flexmock(module.dispatch).should_receive('call_hooks').never()
|
||||
flexmock(module).should_receive('run_actions').never()
|
||||
config = {'repositories': ['foo']}
|
||||
config = {'repositories': [{'path': 'foo'}]}
|
||||
arguments = {'global': flexmock(monitoring_verbosity=1, dry_run=False), 'prune': flexmock()}
|
||||
|
||||
list(module.run_configuration('test.yaml', config, ['/tmp/test.yaml'], arguments))
|
||||
|
@ -77,7 +77,7 @@ def test_run_configuration_logs_monitor_start_error():
|
|||
expected_results = [flexmock()]
|
||||
flexmock(module).should_receive('log_error_records').and_return(expected_results)
|
||||
flexmock(module).should_receive('run_actions').never()
|
||||
config = {'repositories': ['foo']}
|
||||
config = {'repositories': [{'path': 'foo'}]}
|
||||
arguments = {'global': flexmock(monitoring_verbosity=1, dry_run=False), 'create': flexmock()}
|
||||
|
||||
results = list(module.run_configuration('test.yaml', config, ['/tmp/test.yaml'], arguments))
|
||||
|
@ -93,7 +93,7 @@ def test_run_configuration_bails_for_monitor_start_soft_failure():
|
|||
flexmock(module.dispatch).should_receive('call_hooks').and_raise(error)
|
||||
flexmock(module).should_receive('log_error_records').never()
|
||||
flexmock(module).should_receive('run_actions').never()
|
||||
config = {'repositories': ['foo']}
|
||||
config = {'repositories': [{'path': 'foo'}]}
|
||||
arguments = {'global': flexmock(monitoring_verbosity=1, dry_run=False), 'create': flexmock()}
|
||||
|
||||
results = list(module.run_configuration('test.yaml', config, ['/tmp/test.yaml'], arguments))
|
||||
|
@ -118,11 +118,11 @@ def test_run_configuration_logs_actions_error():
|
|||
assert results == expected_results
|
||||
|
||||
|
||||
def test_run_configuration_bails_for_actions_soft_failure():
|
||||
def test_run_configuration_skips_remaining_actions_for_actions_soft_failure_but_still_pings_monitor():
|
||||
flexmock(module).should_receive('verbosity_to_log_level').and_return(logging.INFO)
|
||||
flexmock(module).should_receive('get_skip_actions').and_return([])
|
||||
flexmock(module.borg_version).should_receive('local_borg_version').and_return(flexmock())
|
||||
flexmock(module.dispatch).should_receive('call_hooks')
|
||||
flexmock(module.dispatch).should_receive('call_hooks').times(5)
|
||||
error = subprocess.CalledProcessError(borgmatic.hooks.command.SOFT_FAIL_EXIT_CODE, 'try again')
|
||||
flexmock(module).should_receive('run_actions').and_raise(error)
|
||||
flexmock(module).should_receive('log_error_records').never()
|
||||
|
@ -153,14 +153,14 @@ def test_run_configuration_logs_monitor_log_error():
|
|||
assert results == expected_results
|
||||
|
||||
|
||||
def test_run_configuration_bails_for_monitor_log_soft_failure():
|
||||
def test_run_configuration_still_pings_monitor_for_monitor_log_soft_failure():
|
||||
flexmock(module).should_receive('verbosity_to_log_level').and_return(logging.INFO)
|
||||
flexmock(module).should_receive('get_skip_actions').and_return([])
|
||||
flexmock(module.borg_version).should_receive('local_borg_version').and_return(flexmock())
|
||||
error = subprocess.CalledProcessError(borgmatic.hooks.command.SOFT_FAIL_EXIT_CODE, 'try again')
|
||||
flexmock(module.dispatch).should_receive('call_hooks').and_return(None).and_return(
|
||||
None
|
||||
).and_raise(error)
|
||||
).and_raise(error).and_return(None).and_return(None).times(5)
|
||||
flexmock(module).should_receive('log_error_records').never()
|
||||
flexmock(module).should_receive('run_actions').and_return([])
|
||||
flexmock(module.command).should_receive('considered_soft_failure').and_return(True)
|
||||
|
@ -259,7 +259,7 @@ def test_run_configuration_bails_for_on_error_hook_soft_failure():
|
|||
|
||||
|
||||
def test_run_configuration_retries_soft_error():
|
||||
# Run action first fails, second passes
|
||||
# Run action first fails, second passes.
|
||||
flexmock(module).should_receive('verbosity_to_log_level').and_return(logging.INFO)
|
||||
flexmock(module).should_receive('get_skip_actions').and_return([])
|
||||
flexmock(module.borg_version).should_receive('local_borg_version').and_return(flexmock())
|
||||
|
@ -273,7 +273,7 @@ def test_run_configuration_retries_soft_error():
|
|||
|
||||
|
||||
def test_run_configuration_retries_hard_error():
|
||||
# Run action fails twice
|
||||
# Run action fails twice.
|
||||
flexmock(module).should_receive('verbosity_to_log_level').and_return(logging.INFO)
|
||||
flexmock(module).should_receive('get_skip_actions').and_return([])
|
||||
flexmock(module.borg_version).should_receive('local_borg_version').and_return(flexmock())
|
||||
|
@ -487,6 +487,45 @@ def test_run_actions_runs_rcreate():
|
|||
)
|
||||
|
||||
|
||||
def test_run_actions_adds_label_file_to_hook_context():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module).should_receive('get_skip_actions').and_return([])
|
||||
flexmock(module.command).should_receive('execute_hook')
|
||||
expected = flexmock()
|
||||
flexmock(borgmatic.actions.create).should_receive('run_create').with_args(
|
||||
config_filename=object,
|
||||
repository={'path': 'repo', 'label': 'my repo'},
|
||||
config={'repositories': []},
|
||||
config_paths=[],
|
||||
hook_context={
|
||||
'repository_label': 'my repo',
|
||||
'log_file': '',
|
||||
'repositories': '',
|
||||
'repository': 'repo',
|
||||
},
|
||||
local_borg_version=object,
|
||||
create_arguments=object,
|
||||
global_arguments=object,
|
||||
dry_run_label='',
|
||||
local_path=object,
|
||||
remote_path=object,
|
||||
).once().and_return(expected)
|
||||
|
||||
result = tuple(
|
||||
module.run_actions(
|
||||
arguments={'global': flexmock(dry_run=False, log_file=None), 'create': flexmock()},
|
||||
config_filename=flexmock(),
|
||||
config={'repositories': []},
|
||||
config_paths=[],
|
||||
local_path=flexmock(),
|
||||
remote_path=flexmock(),
|
||||
local_borg_version=flexmock(),
|
||||
repository={'path': 'repo', 'label': 'my repo'},
|
||||
)
|
||||
)
|
||||
assert result == (expected,)
|
||||
|
||||
|
||||
def test_run_actions_adds_log_file_to_hook_context():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module).should_receive('get_skip_actions').and_return([])
|
||||
|
@ -497,7 +536,12 @@ def test_run_actions_adds_log_file_to_hook_context():
|
|||
repository={'path': 'repo'},
|
||||
config={'repositories': []},
|
||||
config_paths=[],
|
||||
hook_context={'repository': 'repo', 'repositories': '', 'log_file': 'foo'},
|
||||
hook_context={
|
||||
'repository_label': '',
|
||||
'log_file': 'foo',
|
||||
'repositories': '',
|
||||
'repository': 'repo',
|
||||
},
|
||||
local_borg_version=object,
|
||||
create_arguments=object,
|
||||
global_arguments=object,
|
||||
|
|
|
@ -50,6 +50,16 @@ def test_apply_constants_with_empty_constants_passes_through_value():
|
|||
({'before_backup': '{inject}'}, {'before_backup': "'echo hi; naughty-command'"}),
|
||||
({'after_backup': '{inject}'}, {'after_backup': "'echo hi; naughty-command'"}),
|
||||
({'on_error': '{inject}'}, {'on_error': "'echo hi; naughty-command'"}),
|
||||
(
|
||||
{
|
||||
'before_backup': '{env_pass}',
|
||||
'postgresql_databases': [{'name': 'users', 'password': '{env_pass}'}],
|
||||
},
|
||||
{
|
||||
'before_backup': "'${PASS}'",
|
||||
'postgresql_databases': [{'name': 'users', 'password': '${PASS}'}],
|
||||
},
|
||||
),
|
||||
(3, 3),
|
||||
(True, True),
|
||||
(False, False),
|
||||
|
@ -63,6 +73,7 @@ def test_apply_constants_makes_string_substitutions(value, expected_value):
|
|||
'int': 3,
|
||||
'bool': True,
|
||||
'inject': 'echo hi; naughty-command',
|
||||
'env_pass': '${PASS}',
|
||||
}
|
||||
|
||||
assert module.apply_constants(value, constants) == expected_value
|
||||
|
|
|
@ -6,9 +6,48 @@ from flexmock import flexmock
|
|||
from borgmatic.config import generate as module
|
||||
|
||||
|
||||
def test_get_properties_with_simple_object():
|
||||
schema = {
|
||||
'type': 'object',
|
||||
'properties': OrderedDict(
|
||||
[
|
||||
('field1', {'example': 'Example'}),
|
||||
]
|
||||
),
|
||||
}
|
||||
|
||||
assert module.get_properties(schema) == schema['properties']
|
||||
|
||||
|
||||
def test_get_properties_merges_one_of_list_properties():
|
||||
schema = {
|
||||
'type': 'object',
|
||||
'oneOf': [
|
||||
{
|
||||
'properties': OrderedDict(
|
||||
[
|
||||
('field1', {'example': 'Example 1'}),
|
||||
('field2', {'example': 'Example 2'}),
|
||||
]
|
||||
),
|
||||
},
|
||||
{
|
||||
'properties': OrderedDict(
|
||||
[
|
||||
('field2', {'example': 'Example 2'}),
|
||||
('field3', {'example': 'Example 3'}),
|
||||
]
|
||||
),
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
assert module.get_properties(schema) == dict(
|
||||
schema['oneOf'][0]['properties'], **schema['oneOf'][1]['properties']
|
||||
)
|
||||
|
||||
|
||||
def test_schema_to_sample_configuration_generates_config_map_with_examples():
|
||||
flexmock(module.ruamel.yaml.comments).should_receive('CommentedMap').replace_with(OrderedDict)
|
||||
flexmock(module).should_receive('add_comments_to_configuration_object')
|
||||
schema = {
|
||||
'type': 'object',
|
||||
'properties': OrderedDict(
|
||||
|
@ -19,6 +58,9 @@ def test_schema_to_sample_configuration_generates_config_map_with_examples():
|
|||
]
|
||||
),
|
||||
}
|
||||
flexmock(module).should_receive('get_properties').and_return(schema['properties'])
|
||||
flexmock(module.ruamel.yaml.comments).should_receive('CommentedMap').replace_with(OrderedDict)
|
||||
flexmock(module).should_receive('add_comments_to_configuration_object')
|
||||
|
||||
config = module.schema_to_sample_configuration(schema)
|
||||
|
||||
|
@ -42,9 +84,6 @@ def test_schema_to_sample_configuration_generates_config_sequence_of_strings_wit
|
|||
|
||||
|
||||
def test_schema_to_sample_configuration_generates_config_sequence_of_maps_with_examples():
|
||||
flexmock(module.ruamel.yaml.comments).should_receive('CommentedSeq').replace_with(list)
|
||||
flexmock(module).should_receive('add_comments_to_configuration_sequence')
|
||||
flexmock(module).should_receive('add_comments_to_configuration_object')
|
||||
schema = {
|
||||
'type': 'array',
|
||||
'items': {
|
||||
|
@ -54,6 +93,10 @@ def test_schema_to_sample_configuration_generates_config_sequence_of_maps_with_e
|
|||
),
|
||||
},
|
||||
}
|
||||
flexmock(module).should_receive('get_properties').and_return(schema['items']['properties'])
|
||||
flexmock(module.ruamel.yaml.comments).should_receive('CommentedSeq').replace_with(list)
|
||||
flexmock(module).should_receive('add_comments_to_configuration_sequence')
|
||||
flexmock(module).should_receive('add_comments_to_configuration_object')
|
||||
|
||||
config = module.schema_to_sample_configuration(schema)
|
||||
|
||||
|
|
|
@ -264,6 +264,75 @@ def test_ping_monitor_hits_ping_url_when_states_matching():
|
|||
)
|
||||
|
||||
|
||||
def test_ping_monitor_adds_create_query_parameter_when_create_slug_true():
|
||||
flexmock(module.borgmatic.hooks.logs).should_receive('Forgetful_buffering_handler').never()
|
||||
hook_config = {'ping_url': 'https://example.com', 'create_slug': True}
|
||||
flexmock(module.requests).should_receive('post').with_args(
|
||||
'https://example.com/start?create=1', data=''.encode('utf-8'), verify=True
|
||||
).and_return(flexmock(ok=True))
|
||||
|
||||
module.ping_monitor(
|
||||
hook_config,
|
||||
{},
|
||||
'config.yaml',
|
||||
state=module.monitor.State.START,
|
||||
monitoring_log_level=1,
|
||||
dry_run=False,
|
||||
)
|
||||
|
||||
|
||||
def test_ping_monitor_does_not_add_create_query_parameter_when_create_slug_false():
|
||||
flexmock(module.borgmatic.hooks.logs).should_receive('Forgetful_buffering_handler').never()
|
||||
hook_config = {'ping_url': 'https://example.com', 'create_slug': False}
|
||||
flexmock(module.requests).should_receive('post').with_args(
|
||||
'https://example.com/start', data=''.encode('utf-8'), verify=True
|
||||
).and_return(flexmock(ok=True))
|
||||
|
||||
module.ping_monitor(
|
||||
hook_config,
|
||||
{},
|
||||
'config.yaml',
|
||||
state=module.monitor.State.START,
|
||||
monitoring_log_level=1,
|
||||
dry_run=False,
|
||||
)
|
||||
|
||||
|
||||
def test_ping_monitor_does_not_add_create_query_parameter_when_ping_url_is_uuid():
|
||||
hook_config = {'ping_url': 'b3611b24-df9c-4d36-9203-fa292820bf2a', 'create_slug': True}
|
||||
flexmock(module.requests).should_receive('post').with_args(
|
||||
f"https://hc-ping.com/{hook_config['ping_url']}",
|
||||
data=''.encode('utf-8'),
|
||||
verify=True,
|
||||
).and_return(flexmock(ok=True))
|
||||
|
||||
module.ping_monitor(
|
||||
hook_config,
|
||||
{},
|
||||
'config.yaml',
|
||||
state=module.monitor.State.FINISH,
|
||||
monitoring_log_level=1,
|
||||
dry_run=False,
|
||||
)
|
||||
|
||||
|
||||
def test_ping_monitor_issues_warning_when_ping_url_is_uuid_and_create_slug_true():
|
||||
hook_config = {'ping_url': 'b3611b24-df9c-4d36-9203-fa292820bf2a', 'create_slug': True}
|
||||
|
||||
flexmock(module.requests).should_receive('post').and_return(flexmock(ok=True))
|
||||
|
||||
flexmock(module.logger).should_receive('warning').once()
|
||||
|
||||
module.ping_monitor(
|
||||
hook_config,
|
||||
{},
|
||||
'config.yaml',
|
||||
state=module.monitor.State.FINISH,
|
||||
monitoring_log_level=1,
|
||||
dry_run=False,
|
||||
)
|
||||
|
||||
|
||||
def test_ping_monitor_with_connection_error_logs_warning():
|
||||
flexmock(module.borgmatic.hooks.logs).should_receive('Forgetful_buffering_handler').never()
|
||||
hook_config = {'ping_url': 'https://example.com'}
|
||||
|
|
|
@ -44,6 +44,16 @@ def test_database_names_to_dump_queries_mariadb_for_database_names():
|
|||
assert names == ('foo', 'bar')
|
||||
|
||||
|
||||
def test_use_streaming_true_for_any_databases():
|
||||
assert module.use_streaming(
|
||||
databases=[flexmock(), flexmock()], config=flexmock(), log_prefix=flexmock()
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_no_databases():
|
||||
assert not module.use_streaming(databases=[], config=flexmock(), log_prefix=flexmock())
|
||||
|
||||
|
||||
def test_dump_data_sources_dumps_each_database():
|
||||
databases = [{'name': 'foo'}, {'name': 'bar'}]
|
||||
processes = [flexmock(), flexmock()]
|
||||
|
|
|
@ -5,6 +5,26 @@ from flexmock import flexmock
|
|||
from borgmatic.hooks import mongodb as module
|
||||
|
||||
|
||||
def test_use_streaming_true_for_any_non_directory_format_databases():
|
||||
assert module.use_streaming(
|
||||
databases=[{'format': 'stuff'}, {'format': 'directory'}, {}],
|
||||
config=flexmock(),
|
||||
log_prefix=flexmock(),
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_all_directory_format_databases():
|
||||
assert not module.use_streaming(
|
||||
databases=[{'format': 'directory'}, {'format': 'directory'}],
|
||||
config=flexmock(),
|
||||
log_prefix=flexmock(),
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_no_databases():
|
||||
assert not module.use_streaming(databases=[], config=flexmock(), log_prefix=flexmock())
|
||||
|
||||
|
||||
def test_dump_data_sources_runs_mongodump_for_each_database():
|
||||
databases = [{'name': 'foo'}, {'name': 'bar'}]
|
||||
processes = [flexmock(), flexmock()]
|
||||
|
|
|
@ -44,6 +44,16 @@ def test_database_names_to_dump_queries_mysql_for_database_names():
|
|||
assert names == ('foo', 'bar')
|
||||
|
||||
|
||||
def test_use_streaming_true_for_any_databases():
|
||||
assert module.use_streaming(
|
||||
databases=[flexmock(), flexmock()], config=flexmock(), log_prefix=flexmock()
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_no_databases():
|
||||
assert not module.use_streaming(databases=[], config=flexmock(), log_prefix=flexmock())
|
||||
|
||||
|
||||
def test_dump_data_sources_dumps_each_database():
|
||||
databases = [{'name': 'foo'}, {'name': 'bar'}]
|
||||
processes = [flexmock(), flexmock()]
|
||||
|
|
|
@ -199,6 +199,26 @@ def test_database_names_to_dump_with_all_and_psql_command_uses_custom_command():
|
|||
)
|
||||
|
||||
|
||||
def test_use_streaming_true_for_any_non_directory_format_databases():
|
||||
assert module.use_streaming(
|
||||
databases=[{'format': 'stuff'}, {'format': 'directory'}, {}],
|
||||
config=flexmock(),
|
||||
log_prefix=flexmock(),
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_all_directory_format_databases():
|
||||
assert not module.use_streaming(
|
||||
databases=[{'format': 'directory'}, {'format': 'directory'}],
|
||||
config=flexmock(),
|
||||
log_prefix=flexmock(),
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_no_databases():
|
||||
assert not module.use_streaming(databases=[], config=flexmock(), log_prefix=flexmock())
|
||||
|
||||
|
||||
def test_dump_data_sources_runs_pg_dump_for_each_database():
|
||||
databases = [{'name': 'foo'}, {'name': 'bar'}]
|
||||
processes = [flexmock(), flexmock()]
|
||||
|
|
|
@ -5,6 +5,16 @@ from flexmock import flexmock
|
|||
from borgmatic.hooks import sqlite as module
|
||||
|
||||
|
||||
def test_use_streaming_true_for_any_databases():
|
||||
assert module.use_streaming(
|
||||
databases=[flexmock(), flexmock()], config=flexmock(), log_prefix=flexmock()
|
||||
)
|
||||
|
||||
|
||||
def test_use_streaming_false_for_no_databases():
|
||||
assert not module.use_streaming(databases=[], config=flexmock(), log_prefix=flexmock())
|
||||
|
||||
|
||||
def test_dump_data_sources_logs_and_skips_if_dump_already_exists():
|
||||
databases = [{'path': '/path/to/database', 'name': 'database'}]
|
||||
|
||||
|
|
|
@ -117,12 +117,37 @@ def test_append_last_lines_with_output_log_level_none_appends_captured_output():
|
|||
assert captured_output == ['captured', 'line']
|
||||
|
||||
|
||||
def test_mask_command_secrets_masks_password_flag_value():
|
||||
assert module.mask_command_secrets(('cooldb', '--username', 'bob', '--password', 'pass')) == (
|
||||
'cooldb',
|
||||
'--username',
|
||||
'bob',
|
||||
'--password',
|
||||
'***',
|
||||
)
|
||||
|
||||
|
||||
def test_mask_command_secrets_passes_through_other_commands():
|
||||
assert module.mask_command_secrets(('cooldb', '--username', 'bob')) == (
|
||||
'cooldb',
|
||||
'--username',
|
||||
'bob',
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
'full_command,input_file,output_file,environment,expected_result',
|
||||
(
|
||||
(('foo', 'bar'), None, None, None, 'foo bar'),
|
||||
(('foo', 'bar'), flexmock(name='input'), None, None, 'foo bar < input'),
|
||||
(('foo', 'bar'), None, flexmock(name='output'), None, 'foo bar > output'),
|
||||
(
|
||||
('A',) * module.MAX_LOGGED_COMMAND_LENGTH,
|
||||
None,
|
||||
None,
|
||||
None,
|
||||
'A ' * (module.MAX_LOGGED_COMMAND_LENGTH // 2 - 2) + '...',
|
||||
),
|
||||
(
|
||||
('foo', 'bar'),
|
||||
flexmock(name='input'),
|
||||
|
@ -142,6 +167,7 @@ def test_append_last_lines_with_output_log_level_none_appends_captured_output():
|
|||
def test_log_command_logs_command_constructed_from_arguments(
|
||||
full_command, input_file, output_file, environment, expected_result
|
||||
):
|
||||
flexmock(module).should_receive('mask_command_secrets').replace_with(lambda command: command)
|
||||
flexmock(module.logger).should_receive('debug').with_args(expected_result).once()
|
||||
|
||||
module.log_command(full_command, input_file, output_file, environment)
|
||||
|
|
|
@ -116,7 +116,7 @@ def test_should_do_markup_prefers_PY_COLORS_to_interactive_console_value():
|
|||
)
|
||||
flexmock(module.os.environ).should_receive('get').with_args('NO_COLOR', None).and_return(None)
|
||||
flexmock(module).should_receive('to_bool').and_return(True)
|
||||
flexmock(module).should_receive('interactive_console').and_return(False)
|
||||
flexmock(module).should_receive('interactive_console').never()
|
||||
|
||||
assert module.should_do_markup(no_color=False, configs={}) is True
|
||||
|
||||
|
@ -124,7 +124,6 @@ def test_should_do_markup_prefers_PY_COLORS_to_interactive_console_value():
|
|||
def test_should_do_markup_prefers_NO_COLOR_to_interactive_console_value():
|
||||
flexmock(module.os.environ).should_receive('get').with_args('PY_COLORS', None).and_return(None)
|
||||
flexmock(module.os.environ).should_receive('get').with_args('NO_COLOR', None).and_return('True')
|
||||
flexmock(module).should_receive('interactive_console').and_return(False)
|
||||
|
||||
assert module.should_do_markup(no_color=False, configs={}) is False
|
||||
|
||||
|
@ -136,6 +135,14 @@ def test_should_do_markup_respects_NO_COLOR_environment_variable():
|
|||
assert module.should_do_markup(no_color=False, configs={}) is False
|
||||
|
||||
|
||||
def test_should_do_markup_ignores_empty_NO_COLOR_environment_variable():
|
||||
flexmock(module.os.environ).should_receive('get').with_args('NO_COLOR', None).and_return('')
|
||||
flexmock(module.os.environ).should_receive('get').with_args('PY_COLORS', None).and_return(None)
|
||||
flexmock(module).should_receive('interactive_console').and_return(True)
|
||||
|
||||
assert module.should_do_markup(no_color=False, configs={}) is True
|
||||
|
||||
|
||||
def test_should_do_markup_prefers_NO_COLOR_to_PY_COLORS():
|
||||
flexmock(module.os.environ).should_receive('get').with_args('PY_COLORS', None).and_return(
|
||||
'True'
|
||||
|
@ -210,10 +217,11 @@ def test_add_logging_level_skips_global_setting_if_already_set():
|
|||
def test_configure_logging_with_syslog_log_level_probes_for_log_socket_on_linux():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
flexmock(module).should_receive('Console_color_formatter')
|
||||
flexmock(module).should_receive('interactive_console').and_return(False)
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
level=logging.DEBUG, handlers=list
|
||||
|
@ -230,10 +238,11 @@ def test_configure_logging_with_syslog_log_level_probes_for_log_socket_on_linux(
|
|||
def test_configure_logging_with_syslog_log_level_probes_for_log_socket_on_macos():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
flexmock(module).should_receive('Console_color_formatter')
|
||||
flexmock(module).should_receive('interactive_console').and_return(False)
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
level=logging.DEBUG, handlers=list
|
||||
|
@ -251,10 +260,11 @@ def test_configure_logging_with_syslog_log_level_probes_for_log_socket_on_macos(
|
|||
def test_configure_logging_with_syslog_log_level_probes_for_log_socket_on_freebsd():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
flexmock(module).should_receive('Console_color_formatter')
|
||||
flexmock(module).should_receive('interactive_console').and_return(False)
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
level=logging.DEBUG, handlers=list
|
||||
|
@ -273,10 +283,11 @@ def test_configure_logging_with_syslog_log_level_probes_for_log_socket_on_freebs
|
|||
def test_configure_logging_without_syslog_log_level_skips_syslog():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
flexmock(module).should_receive('Console_color_formatter')
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
level=logging.INFO, handlers=list
|
||||
)
|
||||
|
@ -289,10 +300,11 @@ def test_configure_logging_without_syslog_log_level_skips_syslog():
|
|||
def test_configure_logging_skips_syslog_if_not_found():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
flexmock(module).should_receive('Console_color_formatter')
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
level=logging.INFO, handlers=list
|
||||
)
|
||||
|
@ -305,8 +317,10 @@ def test_configure_logging_skips_syslog_if_not_found():
|
|||
def test_configure_logging_skips_log_file_if_log_file_logging_is_disabled():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).DISABLED = module.DISABLED
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
|
@ -324,8 +338,10 @@ def test_configure_logging_skips_log_file_if_log_file_logging_is_disabled():
|
|||
def test_configure_logging_to_log_file_instead_of_syslog():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
|
@ -349,8 +365,10 @@ def test_configure_logging_to_log_file_instead_of_syslog():
|
|||
def test_configure_logging_to_both_log_file_and_syslog():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
|
@ -380,8 +398,10 @@ def test_configure_logging_to_log_file_formats_with_custom_log_format():
|
|||
flexmock(module.logging).should_receive('Formatter').with_args(
|
||||
'{message}', style='{' # noqa: FS003
|
||||
).once()
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
|
||||
flexmock(module).should_receive('interactive_console').and_return(False)
|
||||
|
@ -406,8 +426,10 @@ def test_configure_logging_to_log_file_formats_with_custom_log_format():
|
|||
def test_configure_logging_skips_log_file_if_argument_is_none():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').once()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
|
@ -419,11 +441,14 @@ def test_configure_logging_skips_log_file_if_argument_is_none():
|
|||
module.configure_logging(console_log_level=logging.INFO, log_file=None)
|
||||
|
||||
|
||||
def test_configure_logging_skips_console_color_formatter_if_color_disabled():
|
||||
def test_configure_logging_uses_console_no_color_formatter_if_color_disabled():
|
||||
flexmock(module).should_receive('add_custom_log_levels')
|
||||
flexmock(module.logging).ANSWER = module.ANSWER
|
||||
fake_formatter = flexmock()
|
||||
flexmock(module).should_receive('Console_color_formatter').never()
|
||||
flexmock(module).should_receive('Console_no_color_formatter').and_return(fake_formatter)
|
||||
multi_stream_handler = flexmock(setLevel=lambda level: None, level=logging.INFO)
|
||||
multi_stream_handler.should_receive('setFormatter').never()
|
||||
multi_stream_handler.should_receive('setFormatter').with_args(fake_formatter).once()
|
||||
flexmock(module).should_receive('Multi_stream_handler').and_return(multi_stream_handler)
|
||||
|
||||
flexmock(module.logging).should_receive('basicConfig').with_args(
|
||||
|
|
Loading…
Reference in New Issue
Block a user