### the gnu tar specification:
-### http://www.gnu.org/software/tar/manual/html_mono/tar.html
+### http://www.gnu.org/software/tar/manual/tar.html
###
### and the pax format spec, which tar derives from:
### http://www.opengroup.org/onlinepubs/007904975/utilities/pax.html
$DEBUG = 0;
$WARN = 1;
$FOLLOW_SYMLINK = 0;
-$VERSION = "1.28";
+$VERSION = "1.30_01";
$CHOWN = 1;
$CHMOD = 1;
$DO_NOT_USE_PREFIX = 0;
### source code (tar.c) to GNU cpio.
next if $chunk eq TAR_END;
+ ### according to the posix spec, the last 12 bytes of the header are
+ ### null bytes, to pad it to a 512 byte block. That means if these
+ ### bytes are NOT null bytes, it's a corrrupt header. See:
+ ### www.koders.com/c/fidCE473AD3D9F835D690259D60AD5654591D91D5BA.aspx
+ ### line 111
+ { my $nulls = join '', "\0" x 12;
+ unless( $nulls eq substr( $chunk, 500, 12 ) ) {
+ $self->_error( qq[Invalid header block at offset $offset] );
+ next LOOP;
+ }
+ }
+
### pass the realname, so we can set it 'proper' right away
### some of the heuristics are done on the name, so important
### to set it ASAP
%extra_args )
) {
$self->_error( qq[Couldn't read chunk at offset $offset] );
- next;
+ next LOOP;
}
}
if( $handle->read( $$data, $block ) < $block ) {
$self->_error( qq[Read error on tarfile (missing data) '].
$entry->full_path ."' at offset $offset" );
- next;
+ next LOOP;
}
### throw away trailing garbage ###
- substr ($$data, $entry->size) = "";
+ substr ($$data, $entry->size) = "" if defined $$data;
### part II of the @LongLink munging -- need to do /after/
### the checksum check.
### this is one ugly hack =/ but needed for direct extraction
if( $entry->is_longlink ) {
$real_name = $data;
- next;
+ next LOOP;
} elsif ( defined $real_name ) {
$entry->name( $$real_name );
$entry->prefix('');
sub extract {
my $self = shift;
+ my @args = @_;
my @files;
+ # use the speed optimization for all extracted files
+ local($self->{cwd}) = cwd() unless $self->{cwd};
+
### you requested the extraction of only certian files
- if( @_ ) {
- for my $file (@_) {
- my $found;
- for my $entry ( @{$self->_data} ) {
- next unless $file eq $entry->full_path;
-
- ### we found the file you're looking for
- push @files, $entry;
- $found++;
- }
+ if( @args ) {
+ for my $file ( @args ) {
+
+ ### it's already an object?
+ if( UNIVERSAL::isa( $file, 'Archive::Tar::File' ) ) {
+ push @files, $file;
+ next;
- unless( $found ) {
- return $self->_error( qq[Could not find '$file' in archive] );
+ ### go find it then
+ } else {
+
+ my $found;
+ for my $entry ( @{$self->_data} ) {
+ next unless $file eq $entry->full_path;
+
+ ### we found the file you're looking for
+ push @files, $entry;
+ $found++;
+ }
+
+ unless( $found ) {
+ return $self->_error(
+ qq[Could not find '$file' in archive] );
+ }
}
}
$tar->extract_file( 'name/in/archive', 'name/i/want/to/give/it' );
+ $tar->extract_file( $at_file_object, 'name/i/want/to/give/it' );
+
Returns true on success, false on failure.
=cut
my $self = shift;
my $entry = shift or return;
my $alt = shift;
- my $cwd = cwd();
### you wanted an alternate extraction location ###
my $name = defined $alt ? $alt : $entry->full_path;
### it's a relative path ###
} else {
+ my $cwd = (defined $self->{cwd} ? $self->{cwd} : cwd());
my @dirs = File::Spec::Unix->splitdir( $dirs );
my @cwd = File::Spec->splitdir( $cwd );
$dir = File::Spec->catdir( @cwd, @dirs );
return;
}
+ ### it's an object already
+ return $file if UNIVERSAL::isa( $file, 'Archive::Tar::File' );
+
for my $entry ( @{$self->_data} ) {
my $path = $entry->full_path;
return $entry if $path eq $file;
### write the end markers ###
print $handle TAR_END x 2 or
return $self->_error( qq[Could not write tar end markers] );
+
### did you want it written to a file, or returned as a string? ###
- return length($file) ? 1
+ my $rv = length($file) ? 1
: $HAS_PERLIO ? $dummy
- : do { seek $handle, 0, 0; local $/; <$handle> }
+ : do { seek $handle, 0, 0; local $/; <$handle> };
+
+ ### make sure to close the handle;
+ close $handle;
+
+ return $rv;
}
sub _format_tar_entry {
}
}
+=head2 $tar->setcwd( $cwd );
+
+C<Archive::Tar> needs to know the current directory, and it will run
+C<Cwd::cwd()> I<every> time it extracts a I<relative> entry from the
+tarfile and saves it in the file system. (As of version 1.30, however,
+C<Archive::Tar> will use the speed optimization described below
+automatically, so it's only relevant if you're using C<extract_file()>).
+
+Since C<Archive::Tar> doesn't change the current directory internally
+while it is extracting the items in a tarball, all calls to C<Cwd::cwd()>
+can be avoided if we can guarantee that the current directory doesn't
+get changed externally.
+
+To use this performance boost, set the current directory via
+
+ use Cwd;
+ $tar->setcwd( cwd() );
+
+once before calling a function like C<extract_file> and
+C<Archive::Tar> will use the current directory setting from then on
+and won't call C<Cwd::cwd()> internally.
+
+To switch back to the default behaviour, use
+
+ $tar->setcwd( undef );
+
+and C<Archive::Tar> will call C<Cwd::cwd()> internally again.
+
+If you're using C<Archive::Tar>'s C<exract()> method, C<setcwd()> will
+be called for you.
+
+=cut
+
+sub setcwd {
+ my $self = shift;
+ my $cwd = shift;
+
+ $self->{cwd} = $cwd;
+}
=head2 $bool = $tar->has_io_string
=head2 $Archive::Tar::DO_NOT_USE_PREFIX
-By default, C<Archive::Tar> will try to put paths that are over
-100 characters in the C<prefix> field of your tar header. However,
-some older tar programs do not implement this spec. To retain
-compatibility with these older versions, you can set the
-C<$DO_NOT_USE_PREFIX> variable to a true value, and C<Archive::Tar>
-will use an alternate way of dealing with paths over 100 characters
-by using the C<GNU Extended Header> feature.
+By default, C<Archive::Tar> will try to put paths that are over
+100 characters in the C<prefix> field of your tar header, as
+defined per POSIX-standard. However, some (older) tar programs
+do not implement this spec. To retain compatibility with these older
+or non-POSIX compliant versions, you can set the C<$DO_NOT_USE_PREFIX>
+variable to a true value, and C<Archive::Tar> will use an alternate
+way of dealing with paths over 100 characters by using the
+C<GNU Extended Header> feature.
+
+Note that clients who do not support the C<GNU Extended Header>
+feature will not be able to read these archives. Such clients include
+tars on C<Solaris>, C<Irix> and C<AIX>.
The default is C<0>.
For other filetypes, like C<chardevs> and C<blockdevs> we'll warn that
the extraction of this particular item didn't work.
+=item I'm using WinZip, or some other non-POSIX client, and files are not being extracted properly!
+
+By default, C<Archive::Tar> is in a completely POSIX-compatible
+mode, which uses the POSIX-specification of C<tar> to store files.
+For paths greather than 100 characters, this is done using the
+C<POSIX header prefix>. Non-POSIX-compatible clients may not support
+this part of the specification, and may only support the C<GNU Extended
+Header> functionality. To facilitate those clients, you can set the
+C<$Archive::Tar::DO_NOT_USE_PREFIX> variable to C<true>. See the
+C<GLOBAL VARIABLES> section for details on this variable.
+
+=item How do I extract only files that have property X from an archive?
+
+Sometimes, you might not wish to extract a complete archive, just
+the files that are relevant to you, based on some criteria.
+
+You can do this by filtering a list of C<Archive::Tar::File> objects
+based on your criteria. For example, to extract only files that have
+the string C<foo> in their title, you would use:
+
+ $tar->extract(
+ grep { $_->full_path =~ /foo/ } $tar->get_files
+ );
+
+This way, you can filter on any attribute of the files in the archive.
+Consult the C<Archive::Tar::File> documentation on how to use these
+objects.
+
=item How do I access .tar.Z files?
The C<Archive::Tar> module can optionally use C<Compress::Zlib> (via
=back
+=head1 SEE ALSO
+
+=over 4
+
+=item The GNU tar specification
+
+C<http://www.gnu.org/software/tar/manual/tar.html>
+
+=item The PAX format specication
+
+The specifcation which tar derives from; C< http://www.opengroup.org/onlinepubs/007904975/utilities/pax.html>
+
+=item A comparison of GNU and POSIX tar standards; C<http://www.delorie.com/gnu/docs/tar/tar_114.html>
+
+=item GNU tar intends to switch to POSIX compatibility
+
+GNU Tar authors have expressed their intention to become completely
+POSIX-compatible; C<http://www.gnu.org/software/tar/manual/html_node/Formats.html>
+
+=item A Comparison between various tar implementations
+
+Lists known issues and incompatibilities; C<http://gd.tuwien.ac.at/utils/archivers/star/README.otherbugs>
+
+=back
+
=head1 AUTHOR
This module by