Newer
Older
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
def addfile(self, tarinfo, fileobj=None):
"""Add the TarInfo object `tarinfo' to the archive. If `fileobj' is
given, tarinfo.size bytes are read from it and added to the archive.
You can create TarInfo objects using gettarinfo().
On Windows platforms, `fileobj' should always be opened with mode
'rb' to avoid irritation about the file size.
"""
self._check("aw")
tarinfo = copy.copy(tarinfo)
buf = tarinfo.tobuf(self.format, self.encoding, self.errors)
self.fileobj.write(buf)
self.offset += len(buf)
# If there's data to follow, append it.
if fileobj is not None:
copyfileobj(fileobj, self.fileobj, tarinfo.size)
blocks, remainder = divmod(tarinfo.size, BLOCKSIZE)
if remainder > 0:
self.fileobj.write(NUL * (BLOCKSIZE - remainder))
blocks += 1
self.offset += blocks * BLOCKSIZE
self.members.append(tarinfo)
def extractall(self, path=".", members=None):
"""Extract all members from the archive to the current working
directory and set owner, modification time and permissions on
directories afterwards. `path' specifies a different directory
to extract to. `members' is optional and must be a subset of the
list returned by getmembers().
"""
directories = []
if members is None:
members = self
for tarinfo in members:
if tarinfo.isdir():
# Extract directories with a safe mode.
directories.append(tarinfo)
tarinfo = copy.copy(tarinfo)
tarinfo.mode = 0700
self.extract(tarinfo, path)
# Reverse sort directories.
directories.sort(key=operator.attrgetter('name'))
directories.reverse()
# Set correct owner, mtime and filemode on directories.
for tarinfo in directories:
dirpath = os.path.join(path, tarinfo.name)
try:
self.chown(tarinfo, dirpath)
self.utime(tarinfo, dirpath)
self.chmod(tarinfo, dirpath)
except ExtractError, e:
if self.errorlevel > 1:
raise
else:
self._dbg(1, "tarfile: %s" % e)
def extract(self, member, path=""):
"""Extract a member from the archive to the current working directory,
using its full name. Its file information is extracted as accurately
as possible. `member' may be a filename or a TarInfo object. You can
specify a different directory using `path'.
"""
self._check("r")
if isinstance(member, basestring):
tarinfo = self.getmember(member)
else:
tarinfo = member
# Prepare the link target for makelink().
if tarinfo.islnk():
tarinfo._link_target = os.path.join(path, tarinfo.linkname)
try:
self._extract_member(tarinfo, os.path.join(path, tarinfo.name))
except EnvironmentError, e:
if self.errorlevel > 0:
raise
else:
if e.filename is None:
self._dbg(1, "tarfile: %s" % e.strerror)
else:
self._dbg(1, "tarfile: %s %r" % (e.strerror, e.filename))
except ExtractError, e:
if self.errorlevel > 1:
raise
else:
self._dbg(1, "tarfile: %s" % e)
def extractfile(self, member):
"""Extract a member from the archive as a file object. `member' may be
a filename or a TarInfo object. If `member' is a regular file, a
file-like object is returned. If `member' is a link, a file-like
object is constructed from the link's target. If `member' is none of
the above, None is returned.
The file-like object is read-only and provides the following
methods: read(), readline(), readlines(), seek() and tell()
"""
self._check("r")
if isinstance(member, basestring):
tarinfo = self.getmember(member)
else:
tarinfo = member
if tarinfo.isreg():
return self.fileobject(self, tarinfo)
elif tarinfo.type not in SUPPORTED_TYPES:
# If a member's type is unknown, it is treated as a
# regular file.
return self.fileobject(self, tarinfo)
elif tarinfo.islnk() or tarinfo.issym():
if isinstance(self.fileobj, _Stream):
# A small but ugly workaround for the case that someone tries
# to extract a (sym)link as a file-object from a non-seekable
# stream of tar blocks.
raise StreamError("cannot extract (sym)link as file object")
else:
# A (sym)link's file object is its target's file object.
return self.extractfile(self._find_link_target(tarinfo))
else:
# If there's no data associated with the member (directory, chrdev,
# blkdev, etc.), return None instead of a file object.
return None
def _extract_member(self, tarinfo, targetpath):
"""Extract the TarInfo object tarinfo to a physical
file called targetpath.
"""
# Fetch the TarInfo object for the given name
# and build the destination pathname, replacing
# forward slashes to platform specific separators.
targetpath = targetpath.rstrip("/")
targetpath = targetpath.replace("/", os.sep)
# Create all upper directories.
upperdirs = os.path.dirname(targetpath)
if upperdirs and not os.path.exists(upperdirs):
# Create directories that are not part of the archive with
# default permissions.
os.makedirs(upperdirs)
if tarinfo.islnk() or tarinfo.issym():
self._dbg(1, "%s -> %s" % (tarinfo.name, tarinfo.linkname))
else:
self._dbg(1, tarinfo.name)
if tarinfo.isreg():
self.makefile(tarinfo, targetpath)
elif tarinfo.isdir():
self.makedir(tarinfo, targetpath)
elif tarinfo.isfifo():
self.makefifo(tarinfo, targetpath)
elif tarinfo.ischr() or tarinfo.isblk():
self.makedev(tarinfo, targetpath)
elif tarinfo.islnk() or tarinfo.issym():
self.makelink(tarinfo, targetpath)
elif tarinfo.type not in SUPPORTED_TYPES:
self.makeunknown(tarinfo, targetpath)
else:
self.makefile(tarinfo, targetpath)
self.chown(tarinfo, targetpath)
if not tarinfo.issym():
self.chmod(tarinfo, targetpath)
self.utime(tarinfo, targetpath)
#--------------------------------------------------------------------------
# Below are the different file methods. They are called via
# _extract_member() when extract() is called. They can be replaced in a
# subclass to implement other functionality.
def makedir(self, tarinfo, targetpath):
"""Make a directory called targetpath.
"""
try:
# Use a safe mode for the directory, the real mode is set
# later in _extract_member().
os.mkdir(targetpath, 0700)
except EnvironmentError, e:
if e.errno != errno.EEXIST:
raise
def makefile(self, tarinfo, targetpath):
"""Make a file called targetpath.
"""
source = self.extractfile(tarinfo)
target = bltn_open(targetpath, "wb")
copyfileobj(source, target)
source.close()
target.close()
def makeunknown(self, tarinfo, targetpath):
"""Make a file from a TarInfo object with an unknown type
at targetpath.
"""
self.makefile(tarinfo, targetpath)
self._dbg(1, "tarfile: Unknown file type %r, " \
"extracted as regular file." % tarinfo.type)
def makefifo(self, tarinfo, targetpath):
"""Make a fifo called targetpath.
"""
if hasattr(os, "mkfifo"):
os.mkfifo(targetpath)
else:
raise ExtractError("fifo not supported by system")
def makedev(self, tarinfo, targetpath):
"""Make a character or block device called targetpath.
"""
if not hasattr(os, "mknod") or not hasattr(os, "makedev"):
raise ExtractError("special devices not supported by system")
mode = tarinfo.mode
if tarinfo.isblk():
mode |= stat.S_IFBLK
else:
mode |= stat.S_IFCHR
os.mknod(targetpath, mode,
os.makedev(tarinfo.devmajor, tarinfo.devminor))
def makelink(self, tarinfo, targetpath):
"""Make a (symbolic) link called targetpath. If it cannot be created
(platform limitation), we try to make a copy of the referenced file
instead of a link.
"""
if hasattr(os, "symlink") and hasattr(os, "link"):
# For systems that support symbolic and hard links.
if tarinfo.issym():
if os.path.lexists(targetpath):
os.unlink(targetpath)
os.symlink(tarinfo.linkname, targetpath)
else:
# See extract().
if os.path.exists(tarinfo._link_target):
if os.path.lexists(targetpath):
os.unlink(targetpath)
os.link(tarinfo._link_target, targetpath)
else:
self._extract_member(self._find_link_target(tarinfo), targetpath)
else:
try:
self._extract_member(self._find_link_target(tarinfo), targetpath)
except KeyError:
raise ExtractError("unable to resolve link inside archive")
def chown(self, tarinfo, targetpath):
"""Set owner of targetpath according to tarinfo.
"""
if pwd and hasattr(os, "geteuid") and os.geteuid() == 0:
# We have to be root to do so.
try:
g = grp.getgrnam(tarinfo.gname)[2]
except KeyError:
try:
g = grp.getgrgid(tarinfo.gid)[2]
except KeyError:
g = os.getgid()
try:
u = pwd.getpwnam(tarinfo.uname)[2]
except KeyError:
try:
u = pwd.getpwuid(tarinfo.uid)[2]
except KeyError:
u = os.getuid()
try:
if tarinfo.issym() and hasattr(os, "lchown"):
os.lchown(targetpath, u, g)
else:
if sys.platform != "os2emx":
os.chown(targetpath, u, g)
except EnvironmentError, e:
raise ExtractError("could not change owner")
def chmod(self, tarinfo, targetpath):
"""Set file permissions of targetpath according to tarinfo.
"""
if hasattr(os, 'chmod'):
try:
os.chmod(targetpath, tarinfo.mode)
except EnvironmentError, e:
raise ExtractError("could not change mode")
def utime(self, tarinfo, targetpath):
"""Set modification time of targetpath according to tarinfo.
"""
if not hasattr(os, 'utime'):
return
try:
os.utime(targetpath, (tarinfo.mtime, tarinfo.mtime))
except EnvironmentError, e:
raise ExtractError("could not change modification time")
#--------------------------------------------------------------------------
def next(self):
"""Return the next member of the archive as a TarInfo object, when
TarFile is opened for reading. Return None if there is no more
available.
"""
self._check("ra")
if self.firstmember is not None:
m = self.firstmember
self.firstmember = None
return m
# Read the next block.
self.fileobj.seek(self.offset)
tarinfo = None
while True:
try:
tarinfo = self.tarinfo.fromtarfile(self)
except EOFHeaderError, e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
except InvalidHeaderError, e:
if self.ignore_zeros:
self._dbg(2, "0x%X: %s" % (self.offset, e))
self.offset += BLOCKSIZE
continue
elif self.offset == 0:
raise ReadError(str(e))
except EmptyHeaderError:
if self.offset == 0:
raise ReadError("empty file")
except TruncatedHeaderError, e:
if self.offset == 0:
raise ReadError(str(e))
except SubsequentHeaderError, e:
raise ReadError(str(e))
break
if tarinfo is not None:
self.members.append(tarinfo)
else:
self._loaded = True
return tarinfo
#--------------------------------------------------------------------------
# Little helper methods:
def _getmember(self, name, tarinfo=None, normalize=False):
"""Find an archive member by name from bottom to top.
If tarinfo is given, it is used as the starting point.
"""
# Ensure that all members have been loaded.
members = self.getmembers()
# Limit the member search list up to tarinfo.
if tarinfo is not None:
members = members[:members.index(tarinfo)]
if normalize:
name = os.path.normpath(name)
for member in reversed(members):
if normalize:
member_name = os.path.normpath(member.name)
else:
member_name = member.name
if name == member_name:
return member
def _load(self):
"""Read through the entire archive file and look for readable
members.
"""
while True:
tarinfo = self.next()
if tarinfo is None:
break
self._loaded = True
def _check(self, mode=None):
"""Check if TarFile is still open, and if the operation's mode
corresponds to TarFile's mode.
"""
if self.closed:
raise IOError("%s is closed" % self.__class__.__name__)
if mode is not None and self.mode not in mode:
raise IOError("bad operation for mode %r" % self.mode)
def _find_link_target(self, tarinfo):
"""Find the target member of a symlink or hardlink member in the
archive.
"""
if tarinfo.issym():
# Always search the entire archive.
linkname = os.path.dirname(tarinfo.name) + "/" + tarinfo.linkname
limit = None
else:
# Search the archive before the link, because a hard link is
# just a reference to an already archived file.
linkname = tarinfo.linkname
limit = tarinfo
member = self._getmember(linkname, tarinfo=limit, normalize=True)
if member is None:
raise KeyError("linkname %r not found" % linkname)
return member
def __iter__(self):
"""Provide an iterator object.
"""
if self._loaded:
return iter(self.members)
else:
return TarIter(self)
def _dbg(self, level, msg):
"""Write debugging output to sys.stderr.
"""
if level <= self.debug:
print >> sys.stderr, msg
def __enter__(self):
self._check()
return self
def __exit__(self, type, value, traceback):
if type is None:
self.close()
else:
# An exception occurred. We must not call close() because
# it would try to write end-of-archive blocks and padding.
if not self._extfileobj:
self.fileobj.close()
self.closed = True
# class TarFile
class TarIter:
"""Iterator Class.
for tarinfo in TarFile(...):
suite...
"""
def __init__(self, tarfile):
"""Construct a TarIter object.
"""
self.tarfile = tarfile
self.index = 0
def __iter__(self):
"""Return iterator object.
"""
return self
def next(self):
"""Return the next item using TarFile's next() method.
When all members have been read, set TarFile as _loaded.
"""
# Fix for SF #1100429: Under rare circumstances it can
# happen that getmembers() is called during iteration,
# which will cause TarIter to stop prematurely.
if not self.tarfile._loaded:
tarinfo = self.tarfile.next()
if not tarinfo:
self.tarfile._loaded = True
raise StopIteration
else:
try:
tarinfo = self.tarfile.members[self.index]
except IndexError:
raise StopIteration
self.index += 1
return tarinfo
# Helper classes for sparse file support
class _section:
"""Base class for _data and _hole.
"""
def __init__(self, offset, size):
self.offset = offset
self.size = size
def __contains__(self, offset):
return self.offset <= offset < self.offset + self.size
class _data(_section):
"""Represent a data section in a sparse file.
"""
def __init__(self, offset, size, realpos):
_section.__init__(self, offset, size)
self.realpos = realpos
class _hole(_section):
"""Represent a hole section in a sparse file.
"""
pass
class _ringbuffer(list):
"""Ringbuffer class which increases performance
over a regular list.
"""
def __init__(self):
self.idx = 0
def find(self, offset):
idx = self.idx
while True:
item = self[idx]
if offset in item:
break
idx += 1
if idx == len(self):
idx = 0
if idx == self.idx:
# End of File
return None
self.idx = idx
return item
#---------------------------------------------
# zipfile compatible TarFile class
#---------------------------------------------
TAR_PLAIN = 0 # zipfile.ZIP_STORED
TAR_GZIPPED = 8 # zipfile.ZIP_DEFLATED
class TarFileCompat:
"""TarFile class compatible with standard module zipfile's
ZipFile class.
"""
def __init__(self, file, mode="r", compression=TAR_PLAIN):
from warnings import warnpy3k
warnpy3k("the TarFileCompat class has been removed in Python 3.0",
stacklevel=2)
if compression == TAR_PLAIN:
self.tarfile = TarFile.taropen(file, mode)
elif compression == TAR_GZIPPED:
self.tarfile = TarFile.gzopen(file, mode)
else:
raise ValueError("unknown compression constant")
if mode[0:1] == "r":
members = self.tarfile.getmembers()
for m in members:
m.filename = m.name
m.file_size = m.size
m.date_time = time.gmtime(m.mtime)[:6]
def namelist(self):
return map(lambda m: m.name, self.infolist())
def infolist(self):
return filter(lambda m: m.type in REGULAR_TYPES,
self.tarfile.getmembers())
def printdir(self):
self.tarfile.list()
def testzip(self):
return
def getinfo(self, name):
return self.tarfile.getmember(name)
def read(self, name):
return self.tarfile.extractfile(self.tarfile.getmember(name)).read()
def write(self, filename, arcname=None, compress_type=None):
self.tarfile.add(filename, arcname)
def writestr(self, zinfo, bytes):
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
import calendar
tinfo = TarInfo(zinfo.filename)
tinfo.size = len(bytes)
tinfo.mtime = calendar.timegm(zinfo.date_time)
self.tarfile.addfile(tinfo, StringIO(bytes))
def close(self):
self.tarfile.close()
#class TarFileCompat
#--------------------
# exported functions
#--------------------
def is_tarfile(name):
"""Return True if name points to a tar archive that we
are able to handle, else return False.
"""
try:
t = open(name)
t.close()
return True
except TarError:
return False
bltn_open = open
open = TarFile.open