SF #651082, tarfile module implementation from Lars Gustäbel

This commit is contained in:
Neal Norwitz 2003-01-05 23:19:43 +00:00
parent 6d23b170cf
commit b9ef4aea5e
8 changed files with 2637 additions and 0 deletions

View File

@ -329,6 +329,7 @@ LIBFILES= $(MANSTYLES) $(INDEXSTYLES) $(COMMONTEX) \
lib/libmmap.tex \
lib/tkinter.tex \
lib/libturtle.tex \
lib/libtarfile.tex \
lib/libcfgparser.tex
# LaTeX source files for Macintosh Library Modules.

View File

@ -128,6 +128,7 @@ and how to embed it in other applications.
\input{libcfgparser}
\input{libfileinput}
\input{libxreadlines}
\input{libtarfile}
\input{libcalendar}
\input{libcmd}
\input{libshlex}

450
Doc/lib/libtarfile.tex Normal file
View File

@ -0,0 +1,450 @@
\section{\module{tarfile} --- Read and write tar archive files}
\declaremodule{standard}{tarfile}
\modulesynopsis{Read and write tar-format archive files.}
\versionadded{2.3}
\moduleauthor{Lars Gust\"abel}{lars@gustaebel.de}
\sectionauthor{Lars Gust\"abel}{lars@gustaebel.de}
The \module{tarfile} module makes it possible to read and create tar archives.
Some facts and figures:
\begin{itemize}
\item reads and writes \module{gzip} and \module{bzip2} compressed archives.
\item creates POSIX 1003.1-1990 compliant or GNU tar compatible archives.
\item reads GNU tar extensions \emph{longname}, \emph{longlink} and
\emph{sparse}.
\item stores pathnames of unlimited length using GNU tar extensions.
\item handles directories, regular files, hardlinks, symbolic links, fifos,
character devices and block devices and is able to acquire and
restore file information like timestamp, access permissions and owner.
\item can handle tape devices.
\end{itemize}
\begin{funcdesc}{open}{\optional{name\optional{, mode
\optional{, fileobj\optional{, bufsize}}}}}
Return a \class{TarFile} object for the pathname \var{name}.
For detailed information on \class{TarFile} objects,
see \citetitle{TarFile Objects} (section \ref{tarfile-objects}).
\var{mode} has to be a string of the form \code{'filemode[:compression]'},
it defaults to \code{'r'}. Here is a full list of mode combinations:
\begin{tableii}{c|l}{code}{mode}{action}
\lineii{'r'}{Open for reading with transparent compression (recommended).}
\lineii{'r:'}{Open for reading exclusively without compression.}
\lineii{'r:gz'}{Open for reading with gzip compression.}
\lineii{'r:bz2'}{Open for reading with bzip2 compression.}
\lineii{'a' or 'a:'}{Open for appending with no compression.}
\lineii{'w' or 'w:'}{Open for uncompressed writing.}
\lineii{'w:gz'}{Open for gzip compressed writing.}
\lineii{'w:bz2'}{Open for bzip2 compressed writing.}
\end{tableii}
Note that \code{'a:gz'} or \code{'a:bz2'} is not possible.
If \var{mode} is not suitable to open a certain (compressed) file for
reading, \exception{ReadError} is raised. Use \var{mode} \code{'r'} to
avoid this. If a compression method is not supported,
\exception{CompressionError} is raised.
If \var{fileobj} is specified, it is used as an alternative to
a file object opened for \var{name}.
For special purposes, there is a second format for \var{mode}:
\code{'filemode|[compression]'}. \code{open} will return a \class{TarFile}
object that processes its data as a stream of blocks. No random
seeking will be done on the file. If given, \var{fileobj} may be any
object that has a \code{read()} resp. \code{write()} method.
\var{bufsize} specifies the blocksize and defaults to \code{20 * 512}
bytes. Use this variant in combination with e.g. \code{sys.stdin}, a socket
file object or a tape device.
However, such a \class{TarFile} object is limited in that it does not allow
to be accessed randomly, see \citetitle{Examples} (section
\ref{tar-examples}).
The currently possible modes:
\begin{tableii}{c|l}{code}{mode}{action}
\lineii{'r|'}{Open a \emph{stream} of uncompressed tar blocks for reading.}
\lineii{'r|gz'}{Open a gzip compressed \emph{stream} for reading.}
\lineii{'r|bz2'}{Open a bzip2 compressed \emph{stream} for reading.}
\lineii{'w|'}{Open an uncompressed \emph{stream} for writing.}
\lineii{'w|gz'}{Open an gzip compressed \emph{stream} for writing.}
\lineii{'w|bz2'}{Open an bzip2 compressed \emph{stream} for writing.}
\end{tableii}
\end{funcdesc}
\begin{classdesc*}{TarFile}
Class for reading and writing tar archives. Do not use this
class directly, better use \function{open()} instead.
See \citetitle{TarFile Objects} (section \ref{tarfile-objects}).
\end{classdesc*}
\begin{funcdesc}{is_tarfile}{name}
Return \code{True} if \var{name} is a tar archive file, that the
\module{tarfile} module can read.
\end{funcdesc}
\begin{classdesc}{TarFileCompat}{filename\optional{, mode\optional{,
compression}}}
Class for limited access to tar archives with a \code{zipfile}-like
interface. Please consult the documentation of \code{zipfile} for more
details.
\code{compression} must be one of the following constants:
\begin{datadesc}{TAR_PLAIN}
Constant for an uncompressed tar archive.
\end{datadesc}
\begin{datadesc}{TAR_GZIPPED}
Constant for a \code{gzip} compressed tar archive.
\end{datadesc}
\end{classdesc}
\begin{excdesc}{TarError}
Base class for all \module{tarfile} exceptions.
\end{excdesc}
\begin{excdesc}{ReadError}
Is raised when a tar archive is opened, that either cannot be handled by
the \module{tarfile} module or is somehow invalid.
\end{excdesc}
\begin{excdesc}{CompressionError}
Is raised when a compression method is not supported or when the data
cannot be decoded properly.
\end{excdesc}
\begin{excdesc}{StreamError}
Is raised for the limitations that are typical for stream-like
\class{TarFile} objects.
\end{excdesc}
\begin{excdesc}{ExtractError}
Is raised for \emph{non-fatal} errors when using \method{extract()}, but
only if \member{TarFile.errorlevel}\code{ == 2}.
\end{excdesc}
\begin{seealso}
\seemodule[module-zipfile]{zipfile}{Documentation of the \code{zipfile}
standard module.}
\seetitle[http://www.gnu.org/manual/tar/html_chapter/tar_8.html\#SEC118]
{GNU tar manual, Standard Section}{Documentation for tar archive files,
including GNU tar extensions.}
\end{seealso}
%-----------------
% TarFile Objects
%-----------------
\subsection{TarFile Objects \label{tarfile-objects}}
The \class{TarFile} object provides an interface to a tar archive. A tar
archive is a sequence of blocks. An archive member (a stored file) is made up
of a header block followed by data blocks. It is possible, to store a file in a
tar archive several times. Each archive member is represented by a
\class{TarInfo} object, see \citetitle{TarInfo Objects} (section
\ref{tarinfo-objects}) for details.
\begin{classdesc}{TarFile}{\optional{name
\optional{, mode\optional{, fileobj}}}}
Open an \emph{(uncompressed)} tar archive \var{name}.
\var{mode} is either \code{'r'} to read from an existing archive,
\code{'a'} to append data to an existing file or \code{'w'} to create a new
file overwriting an existing one. \var{mode} defaults to \code{'r'}.
If \var{fileobj} is given, it is used for reading or writing data.
If it can be determined, \var{mode} is overridden by \var{fileobj}'s mode.
\begin{notice}
\var{fileobj} is not closed, when \class{TarFile} is closed.
\end{notice}
\end{classdesc}
\begin{methoddesc}{open}{...}
Alternative constructor. The \function{open()} function on module level is
actually a shortcut to this classmethod. See section \ref{module-tarfile}
for details.
\end{methoddesc}
\begin{methoddesc}{getmember}{name}
Return a \class{TarInfo} object for member \var{name}. If \var{name} can
not be found in the archive, \exception{KeyError} is raised.
\begin{notice}
If a member occurs more than once in the archive, its last
occurence is assumed to be the most up-to-date version.
\end{notice}
\end{methoddesc}
\begin{methoddesc}{getmembers}{}
Return the members of the archive as a list of \class{TarInfo} objects.
The list has the same order as the members in the archive.
\end{methoddesc}
\begin{methoddesc}{getnames}{}
Return the members as a list of their names. It has the same order as
the list returned by \method{getmembers()}.
\end{methoddesc}
\begin{methoddesc}{list}{verbose=True}
Print a table of contents to \code{sys.stdout}. If \var{verbose} is
\code{False}, only the names of the members are printed. If it is
\code{True}, an \code{"ls -l"}-like output is produced.
\end{methoddesc}
\begin{methoddesc}{next}{}
Return the next member of the archive as a \class{TarInfo} object, when
\class{TarFile} is opened for reading. Return \code{None} if there is no
more available.
\end{methoddesc}
\begin{methoddesc}{extract}{member\optional{, 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.
\var{member} may be a filename or a \class{TarInfo} object.
You can specify a different directory using \var{path}.
\end{methoddesc}
\begin{methoddesc}{extractfile}{member}
Extract a member from the archive as a file object.
\var{member} may be a filename or a \class{TarInfo} object.
If \var{member} is a regular file, a file-like object is returned.
If \var{member} is a link, a file-like object is constructed from the
link's target.
If \var{member} is none of the above, \code{None} is returned.
\begin{notice}
The file-like object is read-only and provides the following methods:
\method{read()}, \method{readline()}, \method{readlines()},
\method{seek()}, \method{tell()}.
\end{notice}
\end{methoddesc}
\begin{methoddesc}{add}{name\optional{, arcname\optional{, recursive=True}}}
Add the file \var{name} to the archive. \var{name} may be any type
of file (directory, fifo, symbolic link, etc.).
If given, \var{arcname} specifies an alternative name for the file in the
archive. Directories are added recursively by default.
This can be avoided by setting \var{recursive} to \code{False}.
\end{methoddesc}
\begin{methoddesc}{addfile}{tarinfo\optional{, fileobj}}
Add the \class{TarInfo} object \var{tarinfo} to the archive.
If \var{fileobj} is given, \code{tarinfo.size} bytes are read
from it and added to the archive. You can create \class{TarInfo} objects
using \method{gettarinfo()}.
\begin{notice}
On Windows platforms, \var{fileobj} should always be opened with mode
\code{'rb'} to avoid irritation about the file size.
\end{notice}
\end{methoddesc}
\begin{methoddesc}{gettarinfo}{\optional{name\optional{, arcname
\optional{, fileobj}}}}
Create a \class{TarInfo} object for either the file \var{name} or the
file object \var{fileobj} (using \code{os.fstat()} on its file descriptor).
You can modify some of the \class{TarInfo}'s attributes before you add it
using \method{addfile()}.
If given, \var{arcname} specifies an alternative name for the file in the
archive.
\end{methoddesc}
\begin{methoddesc}{close}{}
Close the \class{TarFile}. In write-mode, two finishing zero blocks are
appended to the archive.
\end{methoddesc}
\begin{memberdesc}{posix=True}
If \code{True}, create a POSIX 1003.1-1990 compliant archive. GNU
extensions are not used, because they are not part of the POSIX standard.
This limits the length of filenames to at most 256 and linknames to 100
characters. A \exception{ValueError} is raised, if a pathname exceeds this
limit.
If \code{False}, create a GNU tar compatible archive. It will not be POSIX
compliant, but can store pathnames of unlimited length.
\end{memberdesc}
\begin{memberdesc}{dereference=False}
If \code{False}, add symbolic and hard links to archive. If \code{True},
add the content of the target files to the archive. This has no effect on
systems that do not support links.
\end{memberdesc}
\begin{memberdesc}{ignore_zeros=False}
If \code{False}, treat an empty block as the end of the archive. If
\code{True}, skip empty (and invalid) blocks and try to get as many
members as possible. This is only useful for concatenated or damaged
archives.
\end{memberdesc}
\begin{memberdesc}{debug=0}
To be set from \code{0}(no debug messages) up to \code{3}(all debug
messages). The messages are written to \code{sys.stdout}.
\end{memberdesc}
\begin{memberdesc}{errorlevel=0}
If \code{0}, all errors are ignored when using \method{extract()}.
Nevertheless, they appear as error messages in the debug output, when
debugging is enabled.
If \code{1}, all \emph{fatal} errors are raised as \exception{OSError}
or \exception{IOError} exceptions.
If \code{2}, all \emph{non-fatal} errors are raised as \exception{TarError}
exceptions as well.
\end{memberdesc}
%-----------------
% TarInfo Objects
%-----------------
\subsection{TarInfo Objects \label{tarinfo-objects}}
A \class{TarInfo} object represents one member in a \class{TarFile}. Aside from
storing all required attributes of a file (like file type, size, time,
permissions, owner etc.), it provides some useful methods to determine its
type. It does \emph{not} contain the file's data itself.
\class{TarInfo} objects are returned by \code{TarFile}'s methods
\code{getmember()}, \code{getmembers()} and \code{gettarinfo()}.
\begin{classdesc}{TarInfo}{\optional{name}}
Create a \class{TarInfo} object.
\end{classdesc}
\begin{methoddesc}{frombuf}{}
Create and return a \class{TarInfo} object from a string buffer.
\end{methoddesc}
\begin{methoddesc}{tobuf}{}
Create a string buffer from a \class{TarInfo} object.
\end{methoddesc}
A \code{TarInfo} object has the following public data attributes:
\begin{memberdesc}{name}
Name of the archive member.
\end{memberdesc}
\begin{memberdesc}{size}
Size in bytes.
\end{memberdesc}
\begin{memberdesc}{mtime}
Time of last modification.
\end{memberdesc}
\begin{memberdesc}{mode}
Permission bits.
\end{memberdesc}
\begin{memberdesc}{type}
File type.
\var{type} is usually one of these constants:
\code{REGTYPE, AREGTYPE, LNKTYPE, SYMTYPE, DIRTYPE, FIFOTYPE, CONTTYPE,
CHRTYPE, BLKTYPE, GNUTYPE_SPARSE}.
To determine the type of a \class{TarInfo} object more conveniently, use
the \code{is_*()} methods below.
\end{memberdesc}
\begin{memberdesc}{linkname}
Name of the target file name, which is only present in \class{TarInfo}
objects of type LNKTYPE and SYMTYPE.
\end{memberdesc}
\begin{memberdesc}{uid, gid}
User and group ID of who originally stored this member.
\end{memberdesc}
\begin{memberdesc}{uname, gname}
User and group name.
\end{memberdesc}
A \class{TarInfo} object also provides some convenient query methods:
\begin{methoddesc}{isfile}{}
Return \code{True} if the \class{Tarinfo} object is a regular file.
\end{methoddesc}
\begin{methoddesc}{isreg}{}
Same as \method{isfile()}.
\end{methoddesc}
\begin{methoddesc}{isdir}{}
Return \code{True} if it is a directory.
\end{methoddesc}
\begin{methoddesc}{issym}{}
Return \code{True} if it is a symbolic link.
\end{methoddesc}
\begin{methoddesc}{islnk}{}
Return \code{True} if it is a hard link.
\end{methoddesc}
\begin{methoddesc}{ischr}{}
Return \code{True} if it is a character device.
\end{methoddesc}
\begin{methoddesc}{isblk}{}
Return \code{True} if it is a block device.
\end{methoddesc}
\begin{methoddesc}{isfifo}{}
Return \code{True} if it is a FIFO.
\end{methoddesc}
\begin{methoddesc}{isdev}{}
Return \code{True} if it is one of character device, block device or FIFO.
\end{methoddesc}
%------------------------
% Examples
%------------------------
\subsection{Examples \label{tar-examples}}
How to create an uncompressed tar archive from a list of filenames:
\begin{verbatim}
import tarfile
tar = tarfile.open("sample.tar", "w")
for name in ["foo", "bar", "quux"]:
tar.add(name)
tar.close()
\end{verbatim}
How to read a gzip compressed tar archive and display some member information:
\begin{verbatim}
import tarfile
tar = tarfile.open("sample.tar.gz", "r:gz")
for tarinfo in tar:
print tarinfo.name, "is", tarinfo.size, "bytes in size and is",
if tarinfo.isreg():
print "a regular file."
elif tarinfo.isdir():
print "a directory."
else:
print "something else."
tar.close()
\end{verbatim}
How to create a tar archive with faked information:
\begin{verbatim}
import tarfile
tar = tarfile.open("sample.tar.gz", "w:gz")
for name in namelist:
tarinfo = tar.gettarinfo(name, "fakeproj-1.0/" + name)
tarinfo.uid = 123
tarinfo.gid = 456
tarinfo.uname = "johndoe"
tarinfo.gname = "fake"
tar.addfile(tarinfo, file(name))
tar.close()
\end{verbatim}
The \emph{only} way to extract an uncompressed tar stream from
\code{sys.stdin}:
\begin{verbatim}
import sys
import tarfile
tar = tarfile.open(mode="r|", fileobj=sys.stdin)
for tarinfo in tar:
tar.extract(tarinfo)
tar.close()
\end{verbatim}

1927
Lib/tarfile.py Normal file

File diff suppressed because it is too large Load Diff

253
Lib/test/test_tarfile.py Normal file
View File

@ -0,0 +1,253 @@
import sys
import os
import shutil
import unittest
import tarfile
from test import test_support
# Check for our compression modules.
try:
import gzip
except ImportError:
gzip = None
try:
import bz2
except ImportError:
bz2 = None
def path(path):
return test_support.findfile(path)
testtar = path("testtar.tar")
tempdir = path("testtar.dir")
tempname = path("testtar.tmp")
membercount = 10
def tarname(comp=""):
if not comp:
return testtar
return "%s.%s" % (testtar, comp)
def dirname():
if not os.path.exists(tempdir):
os.mkdir(tempdir)
return tempdir
def tmpname():
return tempname
class BaseTest(unittest.TestCase):
comp = ''
mode = 'r'
sep = ':'
def setUp(self):
mode = self.mode + self.sep + self.comp
self.tar = tarfile.open(tarname(self.comp), mode)
def tearDown(self):
self.tar.close()
class ReadTest(BaseTest):
def test(self):
"""Test member extraction.
"""
members = 0
for tarinfo in self.tar:
members += 1
if not tarinfo.isreg():
continue
f = self.tar.extractfile(tarinfo)
self.assert_(len(f.read()) == tarinfo.size,
"size read does not match expected size")
f.close()
self.assert_(members == membercount,
"could not find all members")
def test_sparse(self):
"""Test sparse member extraction.
"""
if self.sep != "|":
f1 = self.tar.extractfile("S-SPARSE")
f2 = self.tar.extractfile("S-SPARSE-WITH-NULLS")
self.assert_(f1.read() == f2.read(),
"_FileObject failed on sparse file member")
def test_readlines(self):
"""Test readlines() method of _FileObject.
"""
if self.sep != "|":
filename = "0-REGTYPE-TEXT"
self.tar.extract(filename, dirname())
lines1 = file(os.path.join(dirname(), filename), "r").readlines()
lines2 = self.tar.extractfile(filename).readlines()
self.assert_(lines1 == lines2,
"_FileObject.readline() does not work correctly")
def test_seek(self):
"""Test seek() method of _FileObject, incl. random reading.
"""
if self.sep != "|":
filename = "0-REGTYPE"
self.tar.extract(filename, dirname())
data = file(os.path.join(dirname(), filename), "rb").read()
tarinfo = self.tar.getmember(filename)
fobj = self.tar.extractfile(tarinfo)
text = fobj.read()
fobj.seek(0)
self.assert_(0 == fobj.tell(),
"seek() to file's start failed")
fobj.seek(2048, 0)
self.assert_(2048 == fobj.tell(),
"seek() to absolute position failed")
fobj.seek(-1024, 1)
self.assert_(1024 == fobj.tell(),
"seek() to negative relative position failed")
fobj.seek(1024, 1)
self.assert_(2048 == fobj.tell(),
"seek() to positive relative position failed")
s = fobj.read(10)
self.assert_(s == data[2048:2058],
"read() after seek failed")
fobj.seek(0, 2)
self.assert_(tarinfo.size == fobj.tell(),
"seek() to file's end failed")
self.assert_(fobj.read() == "",
"read() at file's end did not return empty string")
fobj.seek(-tarinfo.size, 2)
self.assert_(0 == fobj.tell(),
"relative seek() to file's start failed")
fobj.seek(512)
s1 = fobj.readlines()
fobj.seek(512)
s2 = fobj.readlines()
self.assert_(s1 == s2,
"readlines() after seek failed")
fobj.close()
class ReadStreamTest(ReadTest):
sep = "|"
def test(self):
"""Test member extraction, and for StreamError when
seeking backwards.
"""
ReadTest.test(self)
tarinfo = self.tar.getmembers()[0]
f = self.tar.extractfile(tarinfo)
self.assertRaises(tarfile.StreamError, f.read)
def test_stream(self):
"""Compare the normal tar and the stream tar.
"""
stream = self.tar
tar = tarfile.open(tarname(), 'r')
while 1:
t1 = tar.next()
t2 = stream.next()
if t1 is None:
break
self.assert_(t2 is not None, "stream.next() failed.")
if t2.islnk() or t2.issym():
self.assertRaises(tarfile.StreamError, stream.extractfile, t2)
continue
v1 = tar.extractfile(t1)
v2 = stream.extractfile(t2)
if v1 is None:
continue
self.assert_(v2 is not None, "stream.extractfile() failed")
self.assert_(v1.read() == v2.read(), "stream extraction failed")
stream.close()
class WriteTest(BaseTest):
mode = 'w'
def setUp(self):
mode = self.mode + self.sep + self.comp
self.src = tarfile.open(tarname(self.comp), 'r')
self.dst = tarfile.open(tmpname(), mode)
def tearDown(self):
self.src.close()
self.dst.close()
def test_posix(self):
self.dst.posix = 1
self._test()
def test_nonposix(self):
self.dst.posix = 0
self._test()
def _test(self):
for tarinfo in self.src:
if not tarinfo.isreg():
continue
f = self.src.extractfile(tarinfo)
if self.dst.posix and len(tarinfo.name) > tarfile.LENGTH_NAME:
self.assertRaises(ValueError, self.dst.addfile,
tarinfo, f)
else:
self.dst.addfile(tarinfo, f)
class WriteStreamTest(WriteTest):
sep = '|'
# Gzip TestCases
class ReadTestGzip(ReadTest):
comp = "gz"
class ReadStreamTestGzip(ReadStreamTest):
comp = "gz"
class WriteTestGzip(WriteTest):
comp = "gz"
class WriteStreamTestGzip(WriteStreamTest):
comp = "gz"
if bz2:
# Bzip2 TestCases
class ReadTestBzip2(ReadTestGzip):
comp = "bz2"
class ReadStreamTestBzip2(ReadStreamTestGzip):
comp = "bz2"
class WriteTestBzip2(WriteTest):
comp = "bz2"
class WriteStreamTestBzip2(WriteStreamTestGzip):
comp = "bz2"
# If importing gzip failed, discard the Gzip TestCases.
if not gzip:
del ReadTestGzip
del ReadStreamTestGzip
del WriteTestGzip
del WriteStreamTestGzip
if __name__ == "__main__":
if gzip:
# create testtar.tar.gz
gzip.open(tarname("gz"), "wb").write(file(tarname(), "rb").read())
if bz2:
# create testtar.tar.bz2
bz2.BZ2File(tarname("bz2"), "wb").write(file(tarname(), "rb").read())
try:
unittest.main()
finally:
if gzip:
os.remove(tarname("gz"))
if bz2:
os.remove(tarname("bz2"))
if os.path.exists(tempdir):
shutil.rmtree(tempdir)
if os.path.exists(tempname):
os.remove(tempname)

BIN
Lib/test/testtar.tar Normal file

Binary file not shown.

View File

@ -196,6 +196,7 @@ Eddy De Greef
Duncan Grisby
Dag Gruneau
Michael Guravage
Lars Gustäbel
Barry Haddow
Paul ten Hagen
Rasmus Hahn

View File

@ -63,6 +63,10 @@ Library
It is also exported for ntpath, macpath, and os2emxpath.
See SF bug #659228.
- New module tarfile from Lars Gustäbel provides a comprehensive interface
to tar archive files with transparent gzip and bzip2 compression.
See SF patch #651082.
Tools/Demos
-----------