tarfile.py

    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