borg/attic/helpers.py

625 lines
19 KiB
Python
Raw Normal View History

2010-10-15 18:46:17 +00:00
import argparse
import binascii
import grp
import msgpack
2010-10-31 19:12:32 +00:00
import os
import pwd
import re
import sys
import time
from datetime import datetime, timezone, timedelta
from fnmatch import translate
from operator import attrgetter
import fcntl
import attic.hashindex
import attic.chunker
import attic.crypto
class Error(Exception):
"""Error base class"""
exit_code = 1
def get_message(self):
return 'Error: ' + type(self).__doc__.format(*self.args)
class ExtensionModuleError(Error):
"""The Borg binary extension modules do not seem to be properly installed"""
class UpgradableLock:
class ReadLockFailed(Error):
"""Failed to acquire read lock on {}"""
class WriteLockFailed(Error):
"""Failed to acquire write lock on {}"""
def __init__(self, path, exclusive=False):
self.path = path
try:
self.fd = open(path, 'r+')
except IOError:
self.fd = open(path, 'r')
try:
if exclusive:
fcntl.lockf(self.fd, fcntl.LOCK_EX)
else:
fcntl.lockf(self.fd, fcntl.LOCK_SH)
# Python 3.2 raises IOError, Python3.3+ raises OSError
except (IOError, OSError):
if exclusive:
raise self.WriteLockFailed(self.path)
else:
raise self.ReadLockFailed(self.path)
self.is_exclusive = exclusive
def upgrade(self):
try:
fcntl.lockf(self.fd, fcntl.LOCK_EX)
# Python 3.2 raises IOError, Python3.3+ raises OSError
2014-05-31 13:17:06 +00:00
except (IOError, OSError):
raise self.WriteLockFailed(self.path)
self.is_exclusive = True
def release(self):
fcntl.lockf(self.fd, fcntl.LOCK_UN)
self.fd.close()
2011-10-27 20:17:47 +00:00
def check_extension_modules():
2014-04-13 18:26:46 +00:00
import attic.platform
if (attic.hashindex.API_VERSION != 2 or
2014-08-03 13:04:41 +00:00
attic.chunker.API_VERSION != 2 or
attic.crypto.API_VERSION != 2 or
attic.platform.API_VERSION != 2):
raise ExtensionModuleError
class Manifest:
2013-06-03 11:45:48 +00:00
MANIFEST_ID = b'\0' * 32
def __init__(self, key, repository):
self.archives = {}
self.config = {}
self.key = key
self.repository = repository
@classmethod
def load(cls, repository, key=None):
from .key import key_factory
cdata = repository.get(cls.MANIFEST_ID)
if not key:
key = key_factory(repository, cdata)
manifest = cls(key, repository)
data = key.decrypt(None, cdata)
manifest.id = key.id_hash(data)
m = msgpack.unpackb(data)
2013-06-03 11:45:48 +00:00
if not m.get(b'version') == 1:
raise ValueError('Invalid manifest version')
2015-03-17 22:47:21 +00:00
manifest.archives = dict((k.decode('utf-8'), v) for k, v in m[b'archives'].items())
manifest.timestamp = m.get(b'timestamp')
if manifest.timestamp:
manifest.timestamp = manifest.timestamp.decode('ascii')
2013-06-03 11:45:48 +00:00
manifest.config = m[b'config']
return manifest, key
def write(self):
self.timestamp = datetime.utcnow().isoformat()
2014-02-18 22:09:12 +00:00
data = msgpack.packb(StableDict({
'version': 1,
'archives': self.archives,
'timestamp': self.timestamp,
'config': self.config,
2014-02-18 22:09:12 +00:00
}))
self.id = self.key.id_hash(data)
2013-06-20 10:44:58 +00:00
self.repository.put(self.MANIFEST_ID, self.key.encrypt(data))
def prune_within(archives, within):
multiplier = {'H': 1, 'd': 24, 'w': 24*7, 'm': 24*31, 'y': 24*365}
try:
hours = int(within[:-1]) * multiplier[within[-1]]
except (KeyError, ValueError):
# I don't like how this displays the original exception too:
raise argparse.ArgumentTypeError('Unable to parse --within option: "%s"' % within)
if hours <= 0:
raise argparse.ArgumentTypeError('Number specified using --within option must be positive')
target = datetime.now(timezone.utc) - timedelta(seconds=hours*60*60)
return [a for a in archives if a.ts > target]
2011-11-22 20:47:17 +00:00
def prune_split(archives, pattern, n, skip=[]):
2014-02-03 04:45:53 +00:00
last = None
2011-08-12 06:49:01 +00:00
keep = []
2014-02-03 04:45:53 +00:00
if n == 0:
return keep
for a in sorted(archives, key=attrgetter('ts'), reverse=True):
period = to_localtime(a.ts).strftime(pattern)
2014-02-03 04:45:53 +00:00
if period != last:
last = period
if a not in skip:
keep.append(a)
2015-03-17 22:47:21 +00:00
if len(keep) == n:
break
return keep
2011-08-11 19:18:13 +00:00
class Statistics:
def __init__(self):
self.osize = self.csize = self.usize = self.nfiles = 0
def update(self, size, csize, unique):
self.osize += size
self.csize += csize
if unique:
self.usize += csize
def print_(self, label, cache):
total_size, total_csize, unique_size, unique_csize = cache.chunks.summarize()
print()
2014-03-19 20:52:49 +00:00
print(' Original size Compressed size Deduplicated size')
print('%-15s %20s %20s %20s' % (label, format_file_size(self.osize), format_file_size(self.csize), format_file_size(self.usize)))
2014-03-19 20:52:49 +00:00
print('All archives: %20s %20s %20s' % (format_file_size(total_size), format_file_size(total_csize), format_file_size(unique_csize)))
def show_progress(self, item=None, final=False):
if not final:
path = remove_surrogates(item[b'path']) if item else ''
if len(path) > 43:
path = '%s...%s' % (path[:20], path[-20:])
msg = '%9s O %9s C %9s D %-43s' % (
format_file_size(self.osize), format_file_size(self.csize), format_file_size(self.usize), path)
else:
msg = ' ' * 79
print(msg, end='\r')
sys.stdout.flush()
2010-12-19 11:46:42 +00:00
2011-08-06 11:01:58 +00:00
def get_keys_dir():
2013-06-20 10:44:58 +00:00
"""Determine where to repository keys and cache"""
return os.environ.get('BORG_KEYS_DIR',
os.path.join(os.path.expanduser('~'), '.borg', 'keys'))
2011-08-06 11:01:58 +00:00
2011-08-06 11:01:58 +00:00
def get_cache_dir():
2013-06-20 10:44:58 +00:00
"""Determine where to repository keys and cache"""
return os.environ.get('BORG_CACHE_DIR',
os.path.join(os.path.expanduser('~'), '.cache', 'borg'))
2011-08-06 11:01:58 +00:00
def to_localtime(ts):
"""Convert datetime object from UTC to local time zone"""
2013-12-15 20:36:20 +00:00
return datetime(*time.localtime((ts - datetime(1970, 1, 1, tzinfo=timezone.utc)).total_seconds())[:6])
2010-12-19 11:46:42 +00:00
def parse_timestamp(timestamp):
"""Parse a ISO 8601 timestamp string"""
if '.' in timestamp: # microseconds might not be pressent
return datetime.strptime(timestamp, '%Y-%m-%dT%H:%M:%S.%f').replace(tzinfo=timezone.utc)
else:
return datetime.strptime(timestamp, '%Y-%m-%dT%H:%M:%S').replace(tzinfo=timezone.utc)
2014-02-08 17:44:48 +00:00
def update_excludes(args):
"""Merge exclude patterns from files with those on command line.
Empty lines and lines starting with '#' are ignored, but whitespace
is not stripped."""
if hasattr(args, 'exclude_files') and args.exclude_files:
if not hasattr(args, 'excludes') or args.excludes is None:
args.excludes = []
for file in args.exclude_files:
patterns = [line.rstrip('\r\n') for line in file if not line.startswith('#')]
args.excludes += [ExcludePattern(pattern) for pattern in patterns if pattern]
file.close()
2013-06-30 20:32:27 +00:00
def adjust_patterns(paths, excludes):
if paths:
return (excludes or []) + [IncludePattern(path) for path in paths] + [ExcludePattern('*')]
else:
return excludes
2010-11-02 21:47:39 +00:00
def exclude_path(path, patterns):
"""Used by create and extract sub-commands to determine
whether or not an item should be processed.
2010-11-02 21:47:39 +00:00
"""
for pattern in (patterns or []):
if pattern.match(path):
return isinstance(pattern, ExcludePattern)
return False
# For both IncludePattern and ExcludePattern, we require that
# the pattern either match the whole path or an initial segment
# of the path up to but not including a path separator. To
# unify the two cases, we add a path separator to the end of
# the path before matching.
class IncludePattern:
"""Literal files or directories listed on the command line
2014-02-07 23:10:52 +00:00
for some operations (e.g. extract, but not create).
If a directory is specified, all paths that start with that
path match as well. A trailing slash makes no difference.
2010-11-02 21:47:39 +00:00
"""
def __init__(self, pattern):
self.pattern = os.path.normpath(pattern).rstrip(os.path.sep)+os.path.sep
2010-11-02 21:47:39 +00:00
def match(self, path):
return (path+os.path.sep).startswith(self.pattern)
2010-11-02 21:47:39 +00:00
def __repr__(self):
return '%s(%s)' % (type(self), self.pattern)
class ExcludePattern(IncludePattern):
"""Shell glob patterns to exclude. A trailing slash means to
exclude the contents of a directory, but not the directory itself.
2010-11-02 21:47:39 +00:00
"""
2013-06-30 20:32:27 +00:00
def __init__(self, pattern):
if pattern.endswith(os.path.sep):
self.pattern = os.path.normpath(pattern).rstrip(os.path.sep)+os.path.sep+'*'+os.path.sep
else:
self.pattern = os.path.normpath(pattern)+os.path.sep+'*'
# fnmatch and re.match both cache compiled regular expressions.
# Nevertheless, this is about 10 times faster.
self.regex = re.compile(translate(self.pattern))
2013-06-30 20:32:27 +00:00
def match(self, path):
return self.regex.match(path+os.path.sep) is not None
2013-06-30 20:32:27 +00:00
def __repr__(self):
return '%s(%s)' % (type(self), self.pattern)
2010-11-02 21:47:39 +00:00
def timestamp(s):
"""Convert a --timestamp=s argument to a datetime object"""
try:
# is it pointing to a file / directory?
ts = os.stat(s).st_mtime
return datetime.utcfromtimestamp(ts)
except OSError:
# didn't work, try parsing as timestamp. UTC, no TZ, no microsecs support.
for format in ('%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%dT%H:%M:%S+00:00',
'%Y-%m-%dT%H:%M:%S', '%Y-%m-%d %H:%M:%S',
'%Y-%m-%dT%H:%M', '%Y-%m-%d %H:%M',
'%Y-%m-%d', '%Y-%j',
):
try:
return datetime.strptime(s, format)
except ValueError:
continue
raise ValueError
def is_cachedir(path):
"""Determines whether the specified path is a cache directory (and
therefore should potentially be excluded from the backup) according to
the CACHEDIR.TAG protocol
(http://www.brynosaurus.com/cachedir/spec.html).
"""
tag_contents = b'Signature: 8a477f597d28d172789f06886806bc55'
tag_path = os.path.join(path, 'CACHEDIR.TAG')
try:
if os.path.exists(tag_path):
with open(tag_path, 'rb') as tag_file:
tag_data = tag_file.read(len(tag_contents))
if tag_data == tag_contents:
return True
except OSError:
pass
return False
2010-11-02 21:47:39 +00:00
2010-10-27 17:30:21 +00:00
def format_time(t):
"""Format datetime suitable for fixed length list output
"""
if abs((datetime.now() - t).days) < 365:
2010-10-27 17:30:21 +00:00
return t.strftime('%b %d %H:%M')
else:
return t.strftime('%b %d %Y')
2010-10-27 17:30:21 +00:00
def format_timedelta(td):
"""Format timedelta in a human friendly format
"""
# Since td.total_seconds() requires python 2.7
2011-10-31 20:18:28 +00:00
ts = (td.microseconds + (td.seconds + td.days * 24 * 3600) * 10 ** 6) / float(10 ** 6)
s = ts % 60
m = int(ts / 60) % 60
h = int(ts / 3600) % 24
txt = '%.2f seconds' % s
if m:
txt = '%d minutes %s' % (m, txt)
if h:
txt = '%d hours %s' % (h, txt)
if td.days:
txt = '%d days %s' % (td.days, txt)
return txt
2010-10-27 17:30:21 +00:00
def format_file_mode(mod):
"""Format file mode bits for list output
2010-10-23 19:38:42 +00:00
"""
2010-10-27 17:30:21 +00:00
def x(v):
return ''.join(v & m and s or '-'
for m, s in ((4, 'r'), (2, 'w'), (1, 'x')))
2013-06-03 11:45:48 +00:00
return '%s%s%s' % (x(mod // 64), x(mod // 8), x(mod))
2010-10-27 17:30:21 +00:00
2011-10-31 20:18:28 +00:00
2010-10-27 17:30:21 +00:00
def format_file_size(v):
"""Format file size into a human friendly format
2010-10-23 19:38:42 +00:00
"""
if abs(v) > 10**12:
return '%.2f TB' % (v / 10**12)
elif abs(v) > 10**9:
return '%.2f GB' % (v / 10**9)
elif abs(v) > 10**6:
return '%.2f MB' % (v / 10**6)
elif abs(v) > 10**3:
return '%.2f kB' % (v / 10**3)
2010-10-27 17:30:21 +00:00
else:
return '%d B' % v
2010-10-23 19:38:42 +00:00
2011-10-31 20:18:28 +00:00
def format_archive(archive):
return '%-36s %s' % (archive.name, to_localtime(archive.ts).strftime('%c'))
class IntegrityError(Error):
"""Data integrity error"""
2010-10-23 19:38:42 +00:00
2011-10-31 20:18:28 +00:00
def memoize(function):
cache = {}
2011-10-31 20:18:28 +00:00
def decorated_function(*args):
try:
return cache[args]
except KeyError:
val = function(*args)
cache[args] = val
return val
return decorated_function
2010-10-15 18:46:17 +00:00
2011-10-31 20:18:28 +00:00
@memoize
2014-04-13 18:26:46 +00:00
def uid2user(uid, default=None):
try:
return pwd.getpwuid(uid).pw_name
except KeyError:
2014-04-13 18:26:46 +00:00
return default
2011-10-31 20:18:28 +00:00
@memoize
2014-04-13 18:26:46 +00:00
def user2uid(user, default=None):
try:
2012-03-03 13:02:22 +00:00
return user and pwd.getpwnam(user).pw_uid
except KeyError:
2014-04-13 18:26:46 +00:00
return default
2011-10-31 20:18:28 +00:00
@memoize
2014-04-13 18:26:46 +00:00
def gid2group(gid, default=None):
try:
return grp.getgrgid(gid).gr_name
except KeyError:
2014-04-13 18:26:46 +00:00
return default
2010-10-19 19:12:12 +00:00
2011-10-31 20:18:28 +00:00
@memoize
2014-04-13 18:26:46 +00:00
def group2gid(group, default=None):
try:
2012-03-03 13:02:22 +00:00
return group and grp.getgrnam(group).gr_gid
except KeyError:
2014-04-13 18:26:46 +00:00
return default
def posix_acl_use_stored_uid_gid(acl):
2014-04-13 18:26:46 +00:00
"""Replace the user/group field with the stored uid/gid
"""
entries = []
for entry in acl.decode('ascii').split('\n'):
if entry:
fields = entry.split(':')
if len(fields) == 4:
entries.append(':'.join([fields[0], fields[3], fields[2]]))
else:
entries.append(entry)
return ('\n'.join(entries)).encode('ascii')
2010-10-27 17:30:21 +00:00
class Location:
2013-06-20 10:44:58 +00:00
"""Object representing a repository / archive location
"""
proto = user = host = port = path = archive = None
ssh_re = re.compile(r'(?P<proto>ssh)://(?:(?P<user>[^@]+)@)?'
r'(?P<host>[^:/#]+)(?::(?P<port>\d+))?'
r'(?P<path>[^:]+)(?:::(?P<archive>.+))?$')
file_re = re.compile(r'(?P<proto>file)://'
r'(?P<path>[^:]+)(?:::(?P<archive>.+))?$')
scp_re = re.compile(r'((?:(?P<user>[^@]+)@)?(?P<host>[^:/]+):)?'
r'(?P<path>[^:]+)(?:::(?P<archive>.+))?$')
2010-10-15 18:46:17 +00:00
def __init__(self, text):
2011-10-27 20:17:47 +00:00
self.orig = text
if not self.parse(text):
2010-10-15 18:46:17 +00:00
raise ValueError
def parse(self, text):
m = self.ssh_re.match(text)
if m:
self.proto = m.group('proto')
self.user = m.group('user')
self.host = m.group('host')
self.port = m.group('port') and int(m.group('port')) or None
self.path = m.group('path')
self.archive = m.group('archive')
return True
m = self.file_re.match(text)
if m:
self.proto = m.group('proto')
self.path = m.group('path')
self.archive = m.group('archive')
return True
m = self.scp_re.match(text)
if m:
self.user = m.group('user')
self.host = m.group('host')
self.path = m.group('path')
self.archive = m.group('archive')
self.proto = self.host and 'ssh' or 'file'
return True
return False
2010-10-15 18:46:17 +00:00
def __str__(self):
items = []
items.append('proto=%r' % self.proto)
items.append('user=%r' % self.user)
items.append('host=%r' % self.host)
items.append('port=%r' % self.port)
2012-07-31 12:43:32 +00:00
items.append('path=%r' % self.path)
items.append('archive=%r' % self.archive)
return ', '.join(items)
2010-10-15 18:46:17 +00:00
2011-08-04 13:27:52 +00:00
def to_key_filename(self):
name = re.sub('[^\w]', '_', self.path).strip('_')
if self.proto != 'file':
name = self.host + '__' + name
2011-08-06 11:01:58 +00:00
return os.path.join(get_keys_dir(), name)
2011-08-04 13:27:52 +00:00
2010-10-15 18:46:17 +00:00
def __repr__(self):
return "Location(%s)" % self
2010-10-15 18:46:17 +00:00
def canonical_path(self):
if self.proto == 'file':
return self.path
else:
if self.path and self.path.startswith('~'):
path = '/' + self.path
elif self.path and not self.path.startswith('/'):
path = '/~/' + self.path
else:
path = self.path
return 'ssh://{}{}{}{}'.format('{}@'.format(self.user) if self.user else '',
self.host,
':{}'.format(self.port) if self.port else '',
path)
2010-10-15 18:46:17 +00:00
def location_validator(archive=None):
def validator(text):
try:
loc = Location(text)
except ValueError:
raise argparse.ArgumentTypeError('Invalid location format: "%s"' % text)
if archive is True and not loc.archive:
raise argparse.ArgumentTypeError('"%s": No archive specified' % text)
elif archive is False and loc.archive:
raise argparse.ArgumentTypeError('"%s" No archive can be specified' % text)
return loc
return validator
def read_msgpack(filename):
with open(filename, 'rb') as fd:
return msgpack.unpack(fd)
2012-07-31 12:43:32 +00:00
def write_msgpack(filename, d):
2012-07-31 12:43:32 +00:00
with open(filename + '.tmp', 'wb') as fd:
msgpack.pack(d, fd)
fd.flush()
os.fsync(fd.fileno())
2012-07-31 12:43:32 +00:00
os.rename(filename + '.tmp', filename)
2013-06-03 11:45:48 +00:00
def decode_dict(d, keys, encoding='utf-8', errors='surrogateescape'):
for key in keys:
if isinstance(d.get(key), bytes):
d[key] = d[key].decode(encoding, errors)
return d
def remove_surrogates(s, errors='replace'):
"""Replace surrogates generated by fsdecode with '?'
"""
2013-06-15 18:56:27 +00:00
return s.encode('utf-8', errors).decode('utf-8')
_safe_re = re.compile(r'^((\.\.)?/+)+')
def make_path_safe(path):
"""Make path safe by making it relative and local
"""
return _safe_re.sub('', path) or '.'
def daemonize():
"""Detach process from controlling terminal and run in background
"""
pid = os.fork()
if pid:
os._exit(0)
os.setsid()
pid = os.fork()
if pid:
os._exit(0)
os.chdir('/')
os.close(0)
os.close(1)
os.close(2)
fd = os.open('/dev/null', os.O_RDWR)
os.dup2(fd, 0)
os.dup2(fd, 1)
os.dup2(fd, 2)
class StableDict(dict):
"""A dict subclass with stable items() ordering"""
def items(self):
return sorted(super(StableDict, self).items())
2013-06-15 18:56:27 +00:00
if sys.version < '3.3':
# st_mtime_ns attribute only available in 3.3+
2013-06-15 18:56:27 +00:00
def st_mtime_ns(st):
2013-07-29 11:57:43 +00:00
return int(st.st_mtime * 1e9)
# unhexlify in < 3.3 incorrectly only accepts bytes input
def unhexlify(data):
if isinstance(data, str):
data = data.encode('ascii')
return binascii.unhexlify(data)
2013-06-15 18:56:27 +00:00
else:
def st_mtime_ns(st):
return st.st_mtime_ns
unhexlify = binascii.unhexlify
def bigint_to_int(mtime):
"""Convert bytearray to int
"""
if isinstance(mtime, bytes):
return int.from_bytes(mtime, 'little', signed=True)
return mtime
def int_to_bigint(value):
"""Convert integers larger than 64 bits to bytearray
Smaller integers are left alone
"""
if value.bit_length() > 63:
return value.to_bytes((value.bit_length() + 9) // 8, 'little', signed=True)
return value
2014-08-03 13:04:41 +00:00