#-------------------------------------------------------------------

# tarfile.py

#-------------------------------------------------------------------

# Copyright (C) 2002 Lars Gustaebel <lars@gustaebel.de>

# All rights reserved.

#

# Permission is hereby granted, free of charge, to any person

# obtaining a copy of this software and associated documentation

# files (the "Software"), to deal in the Software without

# restriction, including without limitation the rights to use,

# copy, modify, merge, publish, distribute, sublicense, and/or sell

# copies of the Software, and to permit persons to whom the

# Software is furnished to do so, subject to the following

# conditions:

#

# The above copyright notice and this permission notice shall be

# included in all copies or substantial portions of the Software.

#

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,

# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES

# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND

# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT

# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,

# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING

# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR

# OTHER DEALINGS IN THE SOFTWARE.

#

"""Read from and write to tar format archives.

"""

__author__ = "Lars Gust\u00e4bel (lars@gustaebel.de)"

__credits__ = "Gustavo Niemeyer, Niels Gust\u00e4bel, Richard Townsend."

#---------

# Imports

#---------

from builtins import open as bltn_open

import sys

import os

import io

import shutil

import stat

import time

import struct

import copy

import re

try:

import pwd

except ImportError:

pwd = None

try:

import grp

except ImportError:

grp = None

# os.symlink on Windows prior to 6.0 raises NotImplementedError

# OSError (winerror=1314) will be raised if the caller does not hold the

# SeCreateSymbolicLinkPrivilege privilege

symlink_exception = (AttributeError, NotImplementedError, OSError)

# from tarfile import *

__all__ = ["TarFile", "TarInfo", "is_tarfile", "TarError", "ReadError",

"CompressionError", "StreamError", "ExtractError", "HeaderError",

"ENCODING", "USTAR_FORMAT", "GNU_FORMAT", "PAX_FORMAT",

"DEFAULT_FORMAT", "open","fully_trusted_filter", "data_filter",

"tar_filter", "FilterError", "AbsoluteLinkError",

"OutsideDestinationError", "SpecialFileError", "AbsolutePathError",

"LinkOutsideDestinationError", "LinkFallbackError"]

#---------------------------------------------------------

# tar constants

#---------------------------------------------------------

NUL = b"\0" # the null character

BLOCKSIZE = 512 # length of processing blocks

RECORDSIZE = BLOCKSIZE * 20 # length of records

GNU_MAGIC = b"ustar \0" # magic gnu tar string

POSIX_MAGIC = b"ustar\x0000" # magic posix tar string

LENGTH_NAME = 100 # maximum length of a filename

LENGTH_LINK = 100 # maximum length of a linkname

LENGTH_PREFIX = 155 # maximum length of the prefix field

REGTYPE = b"0" # regular file

AREGTYPE = b"\0" # regular file

LNKTYPE = b"1" # link (inside tarfile)

SYMTYPE = b"2" # symbolic link

CHRTYPE = b"3" # character special device

BLKTYPE = b"4" # block special device

DIRTYPE = b"5" # directory

FIFOTYPE = b"6" # fifo special device

CONTTYPE = b"7" # contiguous file

GNUTYPE_LONGNAME = b"L" # GNU tar longname

GNUTYPE_LONGLINK = b"K" # GNU tar longlink

GNUTYPE_SPARSE = b"S" # GNU tar sparse file

XHDTYPE = b"x" # POSIX.1-2001 extended header

XGLTYPE = b"g" # POSIX.1-2001 global header

SOLARIS_XHDTYPE = b"X" # Solaris extended header

USTAR_FORMAT = 0 # POSIX.1-1988 (ustar) format

GNU_FORMAT = 1 # GNU tar format

PAX_FORMAT = 2 # POSIX.1-2001 (pax) format

DEFAULT_FORMAT = PAX_FORMAT

#---------------------------------------------------------

# tarfile constants

#---------------------------------------------------------

# File types that tarfile supports:

SUPPORTED_TYPES = (REGTYPE, AREGTYPE, LNKTYPE,

SYMTYPE, DIRTYPE, FIFOTYPE,

CONTTYPE, CHRTYPE, BLKTYPE,

GNUTYPE_LONGNAME, GNUTYPE_LONGLINK,

GNUTYPE_SPARSE)

# File types that will be treated as a regular file.

REGULAR_TYPES = (REGTYPE, AREGTYPE,

CONTTYPE, GNUTYPE_SPARSE)

# File types that are part of the GNU tar format.

GNU_TYPES = (GNUTYPE_LONGNAME, GNUTYPE_LONGLINK,

GNUTYPE_SPARSE)

# Fields from a pax header that override a TarInfo attribute.

PAX_FIELDS = ("path", "linkpath", "size", "mtime",

"uid", "gid", "uname", "gname")

# Fields from a pax header that are affected by hdrcharset.

PAX_NAME_FIELDS = {"path", "linkpath", "uname", "gname"}

# Fields in a pax header that are numbers, all other fields

# are treated as strings.

PAX_NUMBER_FIELDS = {

"atime": float,

"ctime": float,

"mtime": float,

"uid": int,

"gid": int,

"size": int

}

#---------------------------------------------------------

# initialization

#---------------------------------------------------------

if os.name == "nt":

ENCODING = "utf-8"

else:

ENCODING = sys.getfilesystemencoding()

#---------------------------------------------------------

# Some useful functions

#---------------------------------------------------------

def stn(s, length, encoding, errors):

"""Convert a string to a null-terminated bytes object.

"""

if s is None:

raise ValueError("metadata cannot contain None")

s = s.encode(encoding, errors)

return s[:length] + (length - len(s)) * NUL

def nts(s, encoding, errors):

"""Convert a null-terminated bytes object to a string.

"""

p = s.find(b"\0")

if p != -1:

s = s[:p]

return s.decode(encoding, errors)

def nti(s):

"""Convert a number field to a python number.

"""

# There are two possible encodings for a number field, see

# itn() below.

if s[0] in (0o200, 0o377):

n = 0

for i in range(len(s) - 1):

n <<= 8

n += s[i + 1]

if s[0] == 0o377:

n = -(256 ** (len(s) - 1) - n)

else:

try:

s = nts(s, "ascii", "strict")

n = int(s.strip() or "0", 8)

except ValueError:

raise InvalidHeaderError("invalid header")

return n

def itn(n, digits=8, format=DEFAULT_FORMAT):

"""Convert a python number to a number field.

"""

# POSIX 1003.1-1988 requires numbers to be encoded as a string of

# octal digits followed by a null-byte, this allows values up to

# (8**(digits-1))-1. GNU tar allows storing numbers greater than

# that if necessary. A leading 0o200 or 0o377 byte indicate this

# particular encoding, the following digits-1 bytes are a big-endian

# base-256 representation. This allows values up to (256**(digits-1))-1.

# A 0o200 byte indicates a positive number, a 0o377 byte a negative

# number.

n = int(n)

if 0 <= n < 8 ** (digits - 1):

s = bytes("%0*o" % (digits - 1, n), "ascii") + NUL

elif format == GNU_FORMAT and -256 ** (digits - 1) <= n < 256 ** (digits - 1):

if n >= 0:

s = bytearray([0o200])

else:

s = bytearray([0o377])

n = 256 ** digits + n

for i in range(digits - 1):

s.insert(1, n & 0o377)

n >>= 8

else:

raise ValueError("overflow in number field")

return s

def calc_chksums(buf):

"""Calculate the checksum for a member's header by summing up all

characters except for the chksum field which is treated as if

it was filled with spaces. According to the GNU tar sources,

some tars (Sun and NeXT) calculate chksum with signed char,

which will be different if there are chars in the buffer with

the high bit set. So we calculate two checksums, unsigned and

signed.

"""

unsigned_chksum = 256 + sum(struct.unpack_from("148B8x356B", buf))

signed_chksum = 256 + sum(struct.unpack_from("148b8x356b", buf))

return unsigned_chksum, signed_chksum

def copyfileobj(src, dst, length=None, exception=OSError, bufsize=None):

"""Copy length bytes from fileobj src to fileobj dst.

If length is None, copy the entire content.

"""

bufsize = bufsize or 16 * 1024

if length == 0:

return

if length is None:

shutil.copyfileobj(src, dst, bufsize)

return

blocks, remainder = divmod(length, bufsize)

for b in range(blocks):

buf = src.read(bufsize)

if len(buf) < bufsize:

raise exception("unexpected end of data")

dst.write(buf)

if remainder != 0:

buf = src.read(remainder)

if len(buf) < remainder:

raise exception("unexpected end of data")

dst.write(buf)

return

# Maximum number of bytes read in a single call when reading a member's

# extended header (a GNU long name/link or a pax header). The size of such

# a header is taken from the archive and is not trustworthy, so it is read in

# bounded chunks to avoid a huge up-front allocation when a crafted or

# truncated archive claims far more data than the file actually contains

# (gh-151497).

_EXTHEADER_READ_CHUNK = 1024 * 1024 # 1 MiB

def _safe_read(fileobj, size):

"""Read up to *size* bytes from *fileobj* in bounded chunks.

Returns the same bytes as ``fileobj.read(size)`` would (including a short

result at end of file), but limits pre-allocation, so an

oversized size field in a crafted header cannot force a huge allocation.

"""

if size <= _EXTHEADER_READ_CHUNK:

return fileobj.read(size)

chunks = []

while size > 0:

chunk = fileobj.read(min(size, _EXTHEADER_READ_CHUNK))

if not chunk:

break

chunks.append(chunk)

size -= len(chunk)

return b"".join(chunks)

def _safe_print(s):

encoding = getattr(sys.stdout, 'encoding', None)

if encoding is not None:

s = s.encode(encoding, 'backslashreplace').decode(encoding)

print(s, end=' ')

class TarError(Exception):

"""Base exception."""

pass

class ExtractError(TarError):

"""General exception for extract errors."""

pass

class ReadError(TarError):

"""Exception for unreadable tar archives."""

pass

class CompressionError(TarError):

"""Exception for unavailable compression methods."""

pass

class StreamError(TarError):

"""Exception for unsupported operations on stream-like TarFiles."""

pass

class HeaderError(TarError):

"""Base exception for header errors."""

pass

class EmptyHeaderError(HeaderError):

"""Exception for empty headers."""

pass

class TruncatedHeaderError(HeaderError):

"""Exception for truncated headers."""

pass

class EOFHeaderError(HeaderError):

"""Exception for end of file headers."""

pass

class InvalidHeaderError(HeaderError):

"""Exception for invalid headers."""

pass

class SubsequentHeaderError(HeaderError):

"""Exception for missing and invalid extended headers."""

pass

#---------------------------

# internal stream interface

#---------------------------

class _LowLevelFile:

"""Low-level file object. Supports reading and writing.

It is used instead of a regular file object for streaming

access.

"""

def __init__(self, name, mode):

mode = {

"r": os.O_RDONLY,

"w": os.O_WRONLY | os.O_CREAT | os.O_TRUNC,

}[mode]

if hasattr(os, "O_BINARY"):

mode |= os.O_BINARY

self.fd = os.open(name, mode, 0o666)

def close(self):

os.close(self.fd)

def read(self, size):

return os.read(self.fd, size)

def write(self, s):

os.write(self.fd, s)

class _Stream:

"""Class that serves as an adapter between TarFile and

a stream-like object. The stream-like object only

needs to have a read() or write() method that works with bytes,

and the method is accessed blockwise.

Use of gzip or bzip2 compression is possible.

A stream-like object could be for example: sys.stdin.buffer,

sys.stdout.buffer, a socket, a tape device etc.

_Stream is intended to be used only internally.

"""

def __init__(self, name, mode, comptype, fileobj, bufsize,

compresslevel, preset, mtime):

"""Construct a _Stream object.

"""

self._extfileobj = True

if fileobj is None:

fileobj = _LowLevelFile(name, mode)

self._extfileobj = False

if comptype == '*':

# Enable transparent compression detection for the

# stream interface

fileobj = _StreamProxy(fileobj)

comptype = fileobj.getcomptype()

self.name = os.fspath(name) if name is not None else ""

self.mode = mode

self.comptype = comptype

self.fileobj = fileobj

self.bufsize = bufsize

self.buf = b""

self.pos = 0

self.closed = False

try:

if comptype == "gz":

try:

import zlib

except ImportError:

raise CompressionError("zlib module is not available") from None

self.zlib = zlib

self.crc = zlib.crc32(b"")

if mode == "r":

self.exception = zlib.error

self._init_read_gz()

else:

self._init_write_gz(compresslevel, mtime)

elif comptype == "bz2":

try:

import bz2

except ImportError:

raise CompressionError("bz2 module is not available") from None

if mode == "r":

self.cmp = bz2.BZ2Decompressor()

self.exception = OSError

else:

self.cmp = bz2.BZ2Compressor(compresslevel)

elif comptype == "xz":

try:

import lzma

except ImportError:

raise CompressionError("lzma module is not available") from None

if mode == "r":

self.cmp = lzma.LZMADecompressor()

self.exception = lzma.LZMAError

else:

self.cmp = lzma.LZMACompressor(preset=preset)

elif comptype == "zst":

try:

from compression import zstd

except ImportError:

raise CompressionError("compression.zstd module is not available") from None

if mode == "r":

self.cmp = zstd.ZstdDecompressor()

self.exception = zstd.ZstdError

else:

self.cmp = zstd.ZstdCompressor()

elif comptype != "tar":

raise CompressionError("unknown compression type %r" % comptype)

except:

if not self._extfileobj:

self.fileobj.close()

self.closed = True

raise

def __del__(self):

if hasattr(self, "closed") and not self.closed:

self.close()

def _init_write_gz(self, compresslevel, mtime):

"""Initialize for writing with gzip compression.

"""

self.cmp = self.zlib.compressobj(compresslevel,

self.zlib.DEFLATED,

-self.zlib.MAX_WBITS,

self.zlib.DEF_MEM_LEVEL,

0)

if mtime is None:

mtime = time.time()

# gh-133998: substitute 0 for an out-of-range mtime and coerce to int,

# mirroring gzip (RFC 1952), so struct.pack cannot raise struct.error.

if not 0 <= mtime < 2**32:

mtime = 0

timestamp = struct.pack("<L", int(mtime))

self.__write(b"\037\213\010\010" + timestamp + b"\002\377")

if self.name.endswith(".gz"):

self.name = self.name[:-3]

# Honor "directory components removed" from RFC1952

self.name = os.path.basename(self.name)

# RFC1952 says we must use ISO-8859-1 for the FNAME field.

self.__write(self.name.encode("iso-8859-1", "replace") + NUL)

def write(self, s):

"""Write string s to the stream.

"""

if self.comptype == "gz":

self.crc = self.zlib.crc32(s, self.crc)

self.pos += len(s)

if self.comptype != "tar":

s = self.cmp.compress(s)

self.__write(s)

def __write(self, s):

"""Write string s to the stream if a whole new block

is ready to be written.

"""

self.buf += s

while len(self.buf) > self.bufsize:

self.fileobj.write(self.buf[:self.bufsize])

self.buf = self.buf[self.bufsize:]

def close(self):

"""Close the _Stream object. No operation should be

done on it afterwards.

"""

if self.closed:

return

self.closed = True

try:

if self.mode == "w" and self.comptype != "tar":

self.buf += self.cmp.flush()

if self.mode == "w" and self.buf:

self.fileobj.write(self.buf)

self.buf = b""

if self.comptype == "gz":

self.fileobj.write(struct.pack("<L", self.crc))

self.fileobj.write(struct.pack("<L", self.pos & 0xffffFFFF))

finally:

if not self._extfileobj:

self.fileobj.close()

def _init_read_gz(self):

"""Initialize for reading a gzip compressed fileobj.

"""

self.cmp = self.zlib.decompressobj(-self.zlib.MAX_WBITS)

# taken from gzip.GzipFile with some alterations

if self.__read(2) != b"\037\213":

raise ReadError("not a gzip file")

if self.__read(1) != b"\010":

raise CompressionError("unsupported compression method")

flag = ord(self.__read(1))

self.__read(6)

if flag & 4:

xlen = ord(self.__read(1)) + 256 * ord(self.__read(1))

self.__read(xlen)

if flag & 8:

while True:

s = self.__read(1)

if not s or s == NUL:

break

if flag & 16:

while True:

s = self.__read(1)

if not s or s == NUL:

break

if flag & 2:

self.__read(2)

def tell(self):

"""Return the stream's file pointer position.

"""

return self.pos

def seek(self, pos=0):

"""Set the stream's file pointer to pos. Negative seeking

is forbidden.

"""

if pos - self.pos >= 0:

blocks, remainder = divmod(pos - self.pos, self.bufsize)

for i in range(blocks):

data = self.read(self.bufsize)

if not data:

break

self.read(remainder)

else:

raise StreamError("seeking backwards is not allowed")

return self.pos

def read(self, size):

"""Return the next size number of bytes from the stream."""

assert size is not None

buf = self._read(size)

self.pos += len(buf)

return buf

def _read(self, size):

"""Return size bytes from the stream.

"""

if self.comptype == "tar":

return self.__read(size)

c = 0

t = []

while c < size:

if self.comptype == "gz":

# zlib interface is different than others.

# It returns data in unconsumed_tail.

if self.buf:

cbuf = self.buf

self.buf = b""

else:

cbuf = self.fileobj.read(self.bufsize)

if not cbuf:

break

try:

dbuf = self.cmp.decompress(cbuf, size - c)

self.buf = self.cmp.unconsumed_tail

except self.exception as e:

raise ReadError("invalid compressed data") from e

else:

# Other decompressors have needs_input.

# decompress() can buffer data internally.

if self.cmp.needs_input:

cbuf = self.fileobj.read(self.bufsize)

if not cbuf:

break

else:

cbuf = b""

try:

dbuf = self.cmp.decompress(cbuf, size - c)

except self.exception as e:

raise ReadError("invalid compressed data") from e

t.append(dbuf)

c += len(dbuf)

return b"".join(t)

def __read(self, size):

"""Return size bytes from stream. If internal buffer is empty,

read another block from the stream.

"""

c = len(self.buf)

t = [self.buf]

while c < size:

buf = self.fileobj.read(self.bufsize)

if not buf:

break

t.append(buf)

c += len(buf)

t = b"".join(t)

self.buf = t[size:]

return t[:size]

# class _Stream

class _StreamProxy(object):

"""Small proxy class that enables transparent compression

detection for the Stream interface (mode 'r|*').

"""

def __init__(self, fileobj):

self.fileobj = fileobj

self.buf = self.fileobj.read(BLOCKSIZE)

def read(self, size):

self.read = self.fileobj.read

return self.buf

def getcomptype(self):

if self.buf.startswith(b"\x1f\x8b\x08"):

return "gz"

elif self.buf[0:3] == b"BZh" and self.buf[4:10] == b"1AY&SY":

return "bz2"

elif self.buf.startswith((b"\x5d\x00\x00\x80", b"\xfd7zXZ")):

return "xz"

elif self.buf.startswith(b"\x28\xb5\x2f\xfd"):

return "zst"

else:

return "tar"

def close(self):

self.fileobj.close()

# class StreamProxy

#------------------------

# Extraction file object

#------------------------

class _FileInFile(object):

"""A thin wrapper around an existing file object that

provides a part of its data as an individual file

object.

"""

def __init__(self, fileobj, offset, size, name, blockinfo=None):

self.fileobj = fileobj

self.offset = offset

self.size = size

self.position = 0

self.name = name

self.closed = False

if blockinfo is None:

blockinfo = [(0, size)]

# Construct a map with data and zero blocks.

self.map_index = 0

self.map = []

lastpos = 0

realpos = self.offset

for offset, size in blockinfo:

if offset > lastpos:

self.map.append((False, lastpos, offset, None))

self.map.append((True, offset, offset + size, realpos))

realpos += size

lastpos = offset + size

if lastpos < self.size:

self.map.append((False, lastpos, self.size, None))

def flush(self):

pass

@property

def mode(self):

return 'rb'

def readable(self):

return True

def writable(self):

return False

def seekable(self):

return self.fileobj.seekable()

def tell(self):

"""Return the current file position.

"""

return self.position

def seek(self, position, whence=io.SEEK_SET):

"""Seek to a position in the file.

"""

if whence == io.SEEK_SET:

self.position = min(max(position, 0), self.size)

elif whence == io.SEEK_CUR:

if position < 0:

self.position = max(self.position + position, 0)

else:

self.position = min(self.position + position, self.size)

elif whence == io.SEEK_END:

self.position = max(min(self.size + position, self.size), 0)

else:

raise ValueError("Invalid argument")

return self.position

def read(self, size=None):

"""Read data from the file.

"""

if size is None:

size = self.size - self.position

else:

size = min(size, self.size - self.position)

buf = b""

while size > 0:

while True:

data, start, stop, offset = self.map[self.map_index]

if start <= self.position < stop:

break

else:

self.map_index += 1

if self.map_index == len(self.map):

self.map_index = 0

length = min(size, stop - self.position)

if data:

self.fileobj.seek(offset + (self.position - start))

b = self.fileobj.read(length)

if len(b) != length:

raise ReadError("unexpected end of data")

buf += b

else:

buf += NUL * length

size -= length

self.position += length

return buf

def readinto(self, b):

buf = self.read(len(b))

b[:len(buf)] = buf

return len(buf)

def close(self):

self.closed = True

#class _FileInFile

class ExFileObject(io.BufferedReader):

def __init__(self, tarfile, tarinfo):

fileobj = _FileInFile(tarfile.fileobj, tarinfo.offset_data,

tarinfo.size, tarinfo.name, tarinfo.sparse)

super().__init__(fileobj)

#class ExFileObject

#-----------------------------

# extraction filters (PEP 706)

#-----------------------------

class FilterError(TarError):

pass

class AbsolutePathError(FilterError):

def __init__(self, tarinfo):

self.tarinfo = tarinfo

super().__init__(f'member {tarinfo.name!r} has an absolute path')

class OutsideDestinationError(FilterError):

def __init__(self, tarinfo, path):

self.tarinfo = tarinfo

self._path = path

super().__init__(f'{tarinfo.name!r} would be extracted to {path!r}, '

+ 'which is outside the destination')

class SpecialFileError(FilterError):

def __init__(self, tarinfo):

self.tarinfo = tarinfo

super().__init__(f'{tarinfo.name!r} is a special file')

class AbsoluteLinkError(FilterError):

def __init__(self, tarinfo):

self.tarinfo = tarinfo

super().__init__(f'{tarinfo.name!r} is a link to an absolute path')

class LinkOutsideDestinationError(FilterError):

def __init__(self, tarinfo, path):

self.tarinfo = tarinfo

self._path = path

super().__init__(f'{tarinfo.name!r} would link to {path!r}, '

+ 'which is outside the destination')

class LinkFallbackError(FilterError):

def __init__(self, tarinfo, path):

self.tarinfo = tarinfo

self._path = path

super().__init__(f'link {tarinfo.name!r} would be extracted as a '

+ f'copy of {path!r}, which was rejected')

# Errors caused by filters -- both "fatal" and "non-fatal" -- that

# we consider to be issues with the argument, rather than a bug in the

# filter function

_FILTER_ERRORS = (FilterError, OSError, ExtractError)

def _get_filtered_attrs(member, dest_path, for_data=True):

new_attrs = {}

name = member.name

dest_path = os.path.realpath(dest_path, strict=os.path.ALLOW_MISSING)

# Strip leading / (tar's directory separator) from filenames.

# Include os.sep (target OS directory separator) as well.

if name.startswith(('/', os.sep)):

name = new_attrs['name'] = member.path.lstrip('/' + os.sep)

if os.path.isabs(name):

# Path is absolute even after stripping.

# For example, 'C:/foo' on Windows.

raise AbsolutePathError(member)

# Ensure we stay in the destination

if '..' in name.replace(os.sep, '/').split('/'):

# Directories are created from the name as given, so a name that

# leaves the destination part-way through would create them

# outside it even if the resolved path stays inside.

normalized = os.path.normpath(name)

if normalized != name:

name = new_attrs['name'] = normalized

target_path = os.path.realpath(os.path.join(dest_path, name),

strict=os.path.ALLOW_MISSING)

if os.path.commonpath([target_path, dest_path]) != dest_path:

raise OutsideDestinationError(member, target_path)

# A link member named after the destination directory itself

# would replace it with a (sym)link, redirecting the destination

# for all subsequent members.

if ((member.islnk() or member.issym())

and os.path.normpath(name) == os.curdir):

raise OutsideDestinationError(member, target_path)

# Limit permissions (no high bits, and go-w)

mode = member.mode

if mode is not None:

# Strip high bits & group/other write bits

mode = mode & 0o755

if for_data:

# For data, handle permissions & file types

if member.isreg() or member.islnk():

if not mode & 0o100:

# Clear executable bits if not executable by user

mode &= ~0o111

# Ensure owner can read & write

mode |= 0o600

elif member.isdir() or member.issym():

# Ignore mode for directories & symlinks

mode = None

else:

# Reject special files

raise SpecialFileError(member)

if mode != member.mode:

new_attrs['mode'] = mode

if for_data:

# Ignore ownership for 'data'

if member.uid is not None:

new_attrs['uid'] = None

if member.gid is not None:

new_attrs['gid'] = None

if member.uname is not None:

new_attrs['uname'] = None

if member.gname is not None:

new_attrs['gname'] = None

# Check link destination for 'data'

if member.islnk() or member.issym():

if os.path.isabs(member.linkname):

raise AbsoluteLinkError(member)

normalized = os.path.normpath(member.linkname)

if normalized != member.linkname:

new_attrs['linkname'] = normalized

if member.issym():

# The symlink is created at `name` with trailing separators

# stripped, so its target is relative to the directory

# containing that path.

link_dir = os.path.dirname(name.rstrip('/' + os.sep))

target_path = os.path.join(dest_path, link_dir, normalized)

else:

target_path = os.path.join(dest_path, normalized)

target_path = os.path.realpath(target_path,

strict=os.path.ALLOW_MISSING)

if os.path.commonpath([target_path, dest_path]) != dest_path:

raise LinkOutsideDestinationError(member, target_path)

return new_attrs

def fully_trusted_filter(member, dest_path):

return member

def tar_filter(member, dest_path):

new_attrs = _get_filtered_attrs(member, dest_path, False)

if new_attrs:

return member.replace(**new_attrs, deep=False)

return member

def data_filter(member, dest_path):

new_attrs = _get_filtered_attrs(member, dest_path, True)

if new_attrs:

return member.replace(**new_attrs, deep=False)

return member

_NAMED_FILTERS = frozendict({

"fully_trusted": fully_trusted_filter,

"tar": tar_filter,

"data": data_filter,

})

#------------------

# Exported Classes

#------------------

# Sentinel for replace() defaults, meaning "don't change the attribute"

_KEEP = object()

# Header length is digits followed by a space.

_header_length_prefix_re = re.compile(br"([0-9]{1,20}) ")

class TarInfo(object):

"""Informational class which holds the details about an

archive member given by a tar header block.

TarInfo objects are returned by TarFile.getmember(),

TarFile.getmembers() and TarFile.gettarinfo() and are

usually created internally.

"""

__slots__ = dict(

name = 'Name of the archive member.',

mode = 'Permission bits.',

uid = 'User ID of the user who originally stored this member.',

gid = 'Group ID of the user who originally stored this member.',

size = 'Size in bytes.',

mtime = 'Time of last modification.',

chksum = 'Header checksum.',

type = ('File type. type is usually one of these constants: '

'REGTYPE,\n'

'AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, '

'CONTTYPE, CHRTYPE,\n'

'BLKTYPE, GNUTYPE_SPARSE.'),

linkname = ('Name of the target file name, which is only present '

'in TarInfo\n'

'objects of type LNKTYPE and SYMTYPE.'),

uname = 'User name.',

gname = 'Group name.',

devmajor = 'Device major number.',

devminor = 'Device minor number.',

offset = 'The tar header starts here.',

offset_data = "The file's data starts here.",

pax_headers = ('A dictionary containing key-value pairs of an '

'associated pax\n'

'extended header.'),

sparse = 'Sparse member information.',

_tarfile = None,

_sparse_structs = None,

_link_target = None,

)

def __init__(self, name=""):

"""Construct a TarInfo object. name is the optional name

of the member.

"""

self.name = name # member name

self.mode = 0o644 # file permissions

self.uid = 0 # user id

self.gid = 0 # group id

self.size = 0 # file size

self.mtime = 0 # modification time

self.chksum = 0 # header checksum

self.type = REGTYPE # member type

self.linkname = "" # link name

self.uname = "" # user name

self.gname = "" # group name

self.devmajor = 0 # device major number

self.devminor = 0 # device minor number

self.offset = 0 # the tar header starts here

self.offset_data = 0 # the file's data starts here

self.sparse = None # sparse member information