cpython/Lib/tarfile.py at 3.3 · python/cpython

executable file

2451 lines (2135 loc) · 86.8 KB

34

#!/usr/bin/env python3

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

# tarfile.py

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

# 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.

"""

version = "0.9.0"

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

__date__ = "$Date: 2011-02-25 17:42:01 +0200 (Fri, 25 Feb 2011) $"

__cvsid__ = "$Id: tarfile.py 88586 2011-02-25 15:42:01Z marc-andre.lemburg $"

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

#---------

# Imports

#---------

import sys

import os

import io

import shutil

import stat

import time

import struct

import copy

import re

try:

import grp, pwd

except ImportError:

grp = pwd = None

# os.symlink on Windows prior to 6.0 raises NotImplementedError

symlink_exception = (AttributeError, NotImplementedError)

try:

# WindowsError (1314) will be raised if the caller does not hold the

# SeCreateSymbolicLinkPrivilege privilege

symlink_exception += (WindowsError,)

except NameError:

pass

# from tarfile import *

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

from builtins import open as _open # Since 'open' is TarFile.open

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

# 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 = GNU_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

}

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

# Bits used in the mode field, values in octal.

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

S_IFLNK = 0o120000 # symbolic link

S_IFREG = 0o100000 # regular file

S_IFBLK = 0o060000 # block device

S_IFDIR = 0o040000 # directory

S_IFCHR = 0o020000 # character device

S_IFIFO = 0o010000 # fifo

TSUID = 0o4000 # set UID on execution

TSGID = 0o2000 # set GID on execution

TSVTX = 0o1000 # reserved

TUREAD = 0o400 # read by owner

TUWRITE = 0o200 # write by owner

TUEXEC = 0o100 # execute/search by owner

TGREAD = 0o040 # read by group

TGWRITE = 0o020 # write by group

TGEXEC = 0o010 # execute/search by group

TOREAD = 0o004 # read by other

TOWRITE = 0o002 # write by other

TOEXEC = 0o001 # execute/search by other

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

# initialization

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

if os.name in ("nt", "ce"):

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.

"""

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:

n = int(nts(s, "ascii", "strict") 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.

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):

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

If length is None, copy the entire content.

"""

if length == 0:

return

if length is None:

shutil.copyfileobj(src, dst)

return

BUFSIZE = 16 * 1024

blocks, remainder = divmod(length, BUFSIZE)

for b in range(blocks):

buf = src.read(BUFSIZE)

if len(buf) < BUFSIZE:

raise IOError("end of file reached")

dst.write(buf)

if remainder != 0:

buf = src.read(remainder)

if len(buf) < remainder:

raise IOError("end of file reached")

dst.write(buf)

return

def filemode(mode):

"""Deprecated in this location; use stat.filemode."""

import warnings

warnings.warn("deprecated in favor of stat.filemode",

DeprecationWarning, 2)

return stat.filemode(mode)

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

< BE9D /div>

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

# 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 and is accessed

blockwise. Use of gzip or bzip2 compression is possible.

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

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

_Stream is intended to be used only internally.

"""

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

"""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 = name or ""

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")

self.zlib = zlib

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

if mode == "r":

self._init_read_gz()

self.exception = zlib.error

else:

self._init_write_gz()

elif comptype == "bz2":

try:

import bz2

except ImportError:

raise CompressionError("bz2 module is not available")

if mode == "r":

self.dbuf = b""

self.cmp = bz2.BZ2Decompressor()

self.exception = IOError

else:

self.cmp = bz2.BZ2Compressor()

elif comptype == "xz":

try:

import lzma

except ImportError:

raise CompressionError("lzma module is not available")

if mode == "r":

self.dbuf = b""

self.cmp = lzma.LZMADecompressor()

self.exception = lzma.LZMAError

else:

self.cmp = lzma.LZMACompressor()

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):

"""Initialize for writing with gzip compression.

"""

self.cmp = self.zlib.compressobj(9, self.zlib.DEFLATED,

-self.zlib.MAX_WBITS,

self.zlib.DEF_MEM_LEVEL,

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

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

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

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

# 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

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":

# The native zlib crc is an unsigned 32-bit integer, but

# the Python wrapper implicitly casts that to a signed C

# long. So, on a 32-bit box self.crc may "look negative",

# while the same crc on a 64-bit box may "look positive".

# To avoid irksome warnings from the `struct` module, force

# it to look positive on all boxes.

self.fileobj.write(struct.pack("<L", self.crc & 0xffffffff))

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

if not self._extfileobj:

self.fileobj.close()

self.closed = True

def _init_read_gz(self):

"""Initialize for reading a gzip compressed fileobj.

"""

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

self.dbuf = b""

# 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):

self.read(self.bufsize)

self.read(remainder)

else:

raise StreamError("seeking backwards is not allowed")

return self.pos

def read(self, size=None):

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

If size is not defined, return all bytes of the stream

up to EOF.

"""

if size is None:

t = []

while True:

buf = self._read(self.bufsize)

if not buf:

break

t.append(buf)

buf = "".join(t)

else:

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 = len(self.dbuf)

while c < size:

buf = self.__read(self.bufsize)

if not buf:

break

try:

buf = self.cmp.decompress(buf)

except self.exception:

raise ReadError("invalid compressed data")

self.dbuf += buf

c += len(buf)

buf = self.dbuf[:size]

self.dbuf = self.dbuf[size:]

return buf

def __read(self, size):

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

read another block from the stream.

"""

c = len(self.buf)

while c < size:

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

if not buf:

break

self.buf += buf

c += len(buf)

buf = self.buf[:size]

self.buf = self.buf[size:]

return buf

# 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"

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, blockinfo=None):

self.fileobj = fileobj

self.offset = offset

self.size = size

self.position = 0

self.name = getattr(fileobj, "name", None)

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

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))

buf += self.fileobj.read(length)

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.sparse)

super().__init__(fileobj)

#class ExFileObject

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

# Exported Classes

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

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__ = ("name", "mode", "uid", "gid", "size", "mtime",

"chksum", "type", "linkname", "uname", "gname",

"devmajor", "devminor",

"offset", "offset_data", "pax_headers", "sparse",

"tarfile", "_sparse_structs", "_link_target")

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

self.pax_headers = {} # pax header information

# In pax headers the "name" and "linkname" field are called

# "path" and "linkpath".

def _getpath(self):

return self.name

def _setpath(self, name):

self.name = name

path = property(_getpath, _setpath)

def _getlinkpath(self):

return self.linkname

def _setlinkpath(self, linkname):

self.linkname = linkname

linkpath = property(_getlinkpath, _setlinkpath)

def __repr__(self):

return "<%s %r at %#x>" % (self.__class__.__name__,self.name,id(self))

def get_info(self):

"""Return the TarInfo's attributes as a dictionary.

"""

info = {

"name": self.name,

"mode": self.mode & 0o7777,

"uid": self.uid,

"gid": self.gid,

"size": self.size,

"mtime": self.mtime,

"chksum": self.chksum,

"type": self.type,

"linkname": self.linkname,

"uname": self.uname,

"gname": self.gname,

"devmajor": self.devmajor,

"devminor": self.devminor

}

if info["type"] == DIRTYPE and not info["name"].endswith("/"):

info["name"] += "/"

return info

def tobuf(self, format=DEFAULT_FORMAT, encoding=ENCODING, errors="surrogateescape"):

"""Return a tar header as a string of 512 byte blocks.

"""

info = self.get_info()

if format == USTAR_FORMAT:

return self.create_ustar_header(info, encoding, errors)

elif format == GNU_FORMAT:

return self.create_gnu_header(info, encoding, errors)

elif format == PAX_FORMAT:

return self.create_pax_header(info, encoding)

else:

raise ValueError("invalid format")

def create_ustar_header(self, info, encoding, errors):

"""Return the object as a ustar header block.

"""

info["magic"] = POSIX_MAGIC

if len(info["linkname"]) > LENGTH_LINK:

raise ValueError("linkname is too long")

if len(info["name"]) > LENGTH_NAME:

info["prefix"], info["name"] = self._posix_split_name(info["name"])

return self._create_header(info, USTAR_FORMAT, encoding, errors)

def create_gnu_header(self, info, encoding, errors):

"""Return the object as a GNU header block sequence.

"""

info["magic"] = GNU_MAGIC

buf = b""

if len(info["linkname"]) > LENGTH_LINK:

buf += self._create_gnu_long_header(info["linkname"], GNUTYPE_LONGLINK, encoding, errors)

if len(info["name"]) > LENGTH_NAME:

buf += self._create_gnu_long_header(info["name"], GNUTYPE_LONGNAME, encoding, errors)

return buf + self._create_header(info, GNU_FORMAT, encoding, errors)

def create_pax_header(self, info, encoding):

"""Return the object as a ustar header block. If it cannot be

represented this way, prepend a pax extended header sequence

with supplement information.

"""

info["magic"] = POSIX_MAGIC

pax_headers = self.pax_headers.copy()

# Test string fields for values that exceed the field length or cannot

# be represented in ASCII encoding.

for name, hname, length in (

("name", "path", LENGTH_NAME), ("linkname", "linkpath", LENGTH_LINK),

("uname", "uname", 32), ("gname", "gname", 32)):

if hname in pax_headers:

# The pax header has priority.

continue

# Try to encode the string as ASCII.

try:

info[name].encode("ascii", "strict")

except UnicodeEncodeError:

pax_headers[hname] = info[name]

continue

if len(info[name]) > length:

pax_headers[hname] = info[name]

# Test number fields for values that exceed the field limit or values

# that like to be stored as float.

for name, digits in (("uid", 8), ("gid", 8), ("size", 12), ("mtime", 12)):

if name in pax_headers:

# The pax header has priority. Avoid overflow.

info[name] = 0

continue

val = info[name]

if not 0 <= val < 8 ** (digits - 1) or isinstance(val, float):

pax_headers[name] = str(val)

info[name] = 0

# Create a pax extended header if necessary.

if pax_headers:

buf = self._create_pax_generic_header(pax_headers, XHDTYPE, encoding)

else:

buf = b""

return buf + self._create_header(info, USTAR_FORMAT, "ascii", "replace")

@classmethod

def create_pax_global_header(cls, pax_headers):

"""Return the object as a pax global header block sequence.

"""

return cls._create_pax_generic_header(pax_headers, XGLTYPE, "utf-8")

def _posix_split_name(self, name):

"""Split a name longer than 100 chars into a prefix

and a name part.

"""

prefix = name[:LENGTH_PREFIX + 1]

while prefix and prefix[-1] != "/":

prefix = prefix[:-1]

name = name[len(prefix):]

prefix = prefix[:-1]

if not prefix or len(name) > LENGTH_NAME:

raise ValueError("name is too long")

return prefix, name

@staticmethod

def _create_header(info, format, encoding, errors):

"""Return a header block. info is a dictionary with file

information, format must be one of the *_FORMAT constants.

"""

parts = [

stn(info.get("name", ""), 100, encoding, errors),

itn(info.get("mode", 0) & 0o7777, 8, format),

itn(info.get("uid", 0), 8, format),

itn(info.get("gid", 0), 8, format),

itn(info.get("size", 0), 12, format),

itn(info.get("mtime", 0), 12, format),

b" ", # checksum field

info.get("type", REGTYPE),

stn(info.get("linkname", ""), 100, encoding, errors),

info.get("magic", POSIX_MAGIC),

stn(info.get("uname", ""), 32, encoding, errors),

stn(info.get("gname", ""), 32, encoding, errors),

itn(info.get("devmajor", 0), 8, format),

itn(info.get("devminor", 0), 8, format),

stn(info.get("prefix", ""), 155, encoding, errors)

]

buf = struct.pack("%ds" % BLOCKSIZE, b"".join(parts))

chksum = calc_chksums(buf[-BLOCKSIZE:])[0]

buf = buf[:-364] + bytes("%06o\0" % chksum, "ascii") + buf[-357:]

return buf

@staticmethod

def _create_payload(payload):

"""Return the string payload filled with zero bytes

up to the next 512 byte border.

"""

blocks, remainder = divmod(len(payload), BLOCKSIZE)

if remainder > 0:

payload += (BLOCKSIZE - remainder) * NUL

return payload

@classmethod

def _create_gnu_long_header(cls, name, type, encoding, errors):

"""Return a GNUTYPE_LONGNAME or GNUTYPE_LONGLINK sequence

for name.

"""

name = name.encode(encoding, errors) + NUL

info = {}

info["name"] = "././@LongLink"

info["type"] = type

info["size"] = len(name)

info["magic"] = GNU_MAGIC

# create extended header + name blocks.

return cls._create_header(info, USTAR_FORMAT, encoding, errors) + \

cls._create_payload(name)

@classmethod

def _create_pax_generic_header(cls, pax_headers, type, encoding):

"""Return a POSIX.1-2008 extended or global header sequence

that contains a list of keyword, value pairs. The values

must be strings.

"""

# Check if one of the fields contains surrogate characters and thereby

# forces hdrcharset=BINARY, see _proc_pax() for more information.

binary = False

for keyword, value in pax_headers.items():

try:

value.encode("utf-8", "strict")

View remainder of file in raw view

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

FilesExpand file tree

tarfile.py

Latest commit

History

tarfile.py

File metadata and controls