2010-07-31 06:52:47 +04:00
|
|
|
#
|
|
|
|
# The Python Imaging Library.
|
|
|
|
# $Id$
|
|
|
|
#
|
|
|
|
# read files from within a tar file
|
|
|
|
#
|
|
|
|
# History:
|
|
|
|
# 95-06-18 fl Created
|
|
|
|
# 96-05-28 fl Open files in binary mode
|
|
|
|
#
|
|
|
|
# Copyright (c) Secret Labs AB 1997.
|
|
|
|
# Copyright (c) Fredrik Lundh 1995-96.
|
|
|
|
#
|
|
|
|
# See the README file for information on usage and redistribution.
|
|
|
|
#
|
2023-12-21 14:13:31 +03:00
|
|
|
from __future__ import annotations
|
2010-07-31 06:52:47 +04:00
|
|
|
|
2019-01-13 05:05:46 +03:00
|
|
|
import io
|
2023-12-26 04:18:38 +03:00
|
|
|
from types import TracebackType
|
2010-07-31 06:52:47 +04:00
|
|
|
|
2019-07-06 23:40:53 +03:00
|
|
|
from . import ContainerIO
|
2014-08-26 17:47:10 +04:00
|
|
|
|
2010-07-31 06:52:47 +04:00
|
|
|
|
|
|
|
class TarIO(ContainerIO.ContainerIO):
|
2020-06-14 14:47:59 +03:00
|
|
|
"""A file object that provides read access to a given member of a TAR file."""
|
|
|
|
|
2023-12-26 04:18:38 +03:00
|
|
|
def __init__(self, tarfile: str, file: str) -> None:
|
2016-09-24 12:10:46 +03:00
|
|
|
"""
|
|
|
|
Create file object.
|
2010-07-31 06:52:47 +04:00
|
|
|
|
2016-09-24 12:10:46 +03:00
|
|
|
:param tarfile: Name of TAR file.
|
|
|
|
:param file: Name of member file.
|
|
|
|
"""
|
2018-11-11 08:00:17 +03:00
|
|
|
self.fh = open(tarfile, "rb")
|
2010-07-31 06:52:47 +04:00
|
|
|
|
2012-10-17 07:39:56 +04:00
|
|
|
while True:
|
2018-11-11 08:00:17 +03:00
|
|
|
s = self.fh.read(512)
|
2010-07-31 06:52:47 +04:00
|
|
|
if len(s) != 512:
|
2022-12-22 00:51:35 +03:00
|
|
|
msg = "unexpected end of tar file"
|
|
|
|
raise OSError(msg)
|
2010-07-31 06:52:47 +04:00
|
|
|
|
py3k: The big push
There are two main issues fixed with this commit:
* bytes vs. str: All file, image, and palette data are now handled as
bytes. A new _binary module consolidates the hacks needed to do this
across Python versions. tostring/fromstring methods have been renamed to
tobytes/frombytes, but the Python 2.6/2.7 versions alias them to the old
names for compatibility. Users should move to tobytes/frombytes.
One other potentially-breaking change is that text data in image files
(such as tags, comments) are now explicitly handled with a specific
character encoding in mind. This works well with the Unicode str in
Python 3, but may trip up old code expecting a straight byte-for-byte
translation to a Python string. This also required a change to Gohlke's
tags tests (in Tests/test_file_png.py) to expect Unicode strings from
the code.
* True div vs. floor div: Many division operations used the "/" operator
to do floor division, which is now the "//" operator in Python 3. These
were fixed.
As of this commit, on the first pass, I have one failing test (improper
handling of a slice object in a C module, test_imagepath.py) in Python 3,
and three that that I haven't tried running yet (test_imagegl,
test_imagegrab, and test_imageqt). I also haven't tested anything on
Windows. All but the three skipped tests run flawlessly against Pythons
2.6 and 2.7.
2012-10-21 01:01:53 +04:00
|
|
|
name = s[:100].decode("utf-8")
|
2012-10-25 16:57:39 +04:00
|
|
|
i = name.find("\0")
|
2010-07-31 06:52:47 +04:00
|
|
|
if i == 0:
|
2022-12-22 00:51:35 +03:00
|
|
|
msg = "cannot find subfile"
|
|
|
|
raise OSError(msg)
|
2010-07-31 06:52:47 +04:00
|
|
|
if i > 0:
|
|
|
|
name = name[:i]
|
|
|
|
|
2012-10-25 16:57:39 +04:00
|
|
|
size = int(s[124:135], 8)
|
2010-07-31 06:52:47 +04:00
|
|
|
|
|
|
|
if file == name:
|
|
|
|
break
|
|
|
|
|
2019-01-13 05:05:46 +03:00
|
|
|
self.fh.seek((size + 511) & (~511), io.SEEK_CUR)
|
2010-07-31 06:52:47 +04:00
|
|
|
|
|
|
|
# Open region
|
2016-11-05 20:31:11 +03:00
|
|
|
super().__init__(self.fh, self.fh.tell(), size)
|
2018-11-11 08:00:17 +03:00
|
|
|
|
2018-11-11 07:48:32 +03:00
|
|
|
# Context manager support
|
2023-12-26 04:18:38 +03:00
|
|
|
def __enter__(self) -> TarIO:
|
2018-11-11 08:00:17 +03:00
|
|
|
return self
|
|
|
|
|
2023-12-26 04:18:38 +03:00
|
|
|
def __exit__(
|
|
|
|
self,
|
|
|
|
exc_type: type[BaseException] | None,
|
|
|
|
exc_val: BaseException | None,
|
|
|
|
exc_tb: TracebackType | None,
|
|
|
|
) -> None:
|
2018-11-11 08:00:17 +03:00
|
|
|
self.close()
|
|
|
|
|
2023-12-26 04:18:38 +03:00
|
|
|
def close(self) -> None:
|
2018-11-11 08:00:17 +03:00
|
|
|
self.fh.close()
|