This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
Merge branch 'empty-destroy-optimisation' into blead
[perl5.git] / lib / Archive / Tar.pm
CommitLineData
39713df4 1### the gnu tar specification:
f38c1908 2### http://www.gnu.org/software/tar/manual/tar.html
39713df4
RGS
3###
4### and the pax format spec, which tar derives from:
5### http://www.opengroup.org/onlinepubs/007904975/utilities/pax.html
6
7package Archive::Tar;
8require 5.005_03;
9
642eb381
SH
10use Cwd;
11use IO::Zlib;
12use IO::File;
13use Carp qw(carp croak);
14use File::Spec ();
15use File::Spec::Unix ();
16use File::Path ();
17
18use Archive::Tar::File;
19use Archive::Tar::Constant;
20
21require Exporter;
22
39713df4
RGS
23use strict;
24use vars qw[$DEBUG $error $VERSION $WARN $FOLLOW_SYMLINK $CHOWN $CHMOD
178aef9a 25 $DO_NOT_USE_PREFIX $HAS_PERLIO $HAS_IO_STRING
642eb381 26 $INSECURE_EXTRACT_MODE @ISA @EXPORT
178aef9a
RGS
27 ];
28
642eb381
SH
29@ISA = qw[Exporter];
30@EXPORT = ( COMPRESS_GZIP, COMPRESS_BZIP );
178aef9a
RGS
31$DEBUG = 0;
32$WARN = 1;
33$FOLLOW_SYMLINK = 0;
2610e7a4 34$VERSION = "1.42";
178aef9a
RGS
35$CHOWN = 1;
36$CHMOD = 1;
37$DO_NOT_USE_PREFIX = 0;
38$INSECURE_EXTRACT_MODE = 0;
39713df4
RGS
39
40BEGIN {
41 use Config;
42 $HAS_PERLIO = $Config::Config{useperlio};
43
44 ### try and load IO::String anyway, so you can dynamically
45 ### switch between perlio and IO::String
642eb381 46 $HAS_IO_STRING = eval {
39713df4
RGS
47 require IO::String;
48 import IO::String;
642eb381
SH
49 1;
50 } || 0;
39713df4
RGS
51}
52
39713df4
RGS
53=head1 NAME
54
55Archive::Tar - module for manipulations of tar archives
56
57=head1 SYNOPSIS
58
59 use Archive::Tar;
60 my $tar = Archive::Tar->new;
61
642eb381 62 $tar->read('origin.tgz');
39713df4
RGS
63 $tar->extract();
64
65 $tar->add_files('file/foo.pl', 'docs/README');
66 $tar->add_data('file/baz.txt', 'This is the contents now');
67
68 $tar->rename('oldname', 'new/file/name');
69
642eb381
SH
70 $tar->write('files.tar'); # plain tar
71 $tar->write('files.tgz', COMPRESSED_GZIP); # gzip compressed
72 $tar->write('files.tbz', COMPRESSED_BZIP); # bzip2 compressed
39713df4
RGS
73
74=head1 DESCRIPTION
75
76Archive::Tar provides an object oriented mechanism for handling tar
77files. It provides class methods for quick and easy files handling
78while also allowing for the creation of tar file objects for custom
79manipulation. If you have the IO::Zlib module installed,
80Archive::Tar will also support compressed or gzipped tar files.
81
82An object of class Archive::Tar represents a .tar(.gz) archive full
83of files and things.
84
85=head1 Object Methods
86
87=head2 Archive::Tar->new( [$file, $compressed] )
88
89Returns a new Tar object. If given any arguments, C<new()> calls the
90C<read()> method automatically, passing on the arguments provided to
91the C<read()> method.
92
93If C<new()> is invoked with arguments and the C<read()> method fails
94for any reason, C<new()> returns undef.
95
96=cut
97
98my $tmpl = {
99 _data => [ ],
100 _file => 'Unknown',
101};
102
103### install get/set accessors for this object.
104for my $key ( keys %$tmpl ) {
105 no strict 'refs';
106 *{__PACKAGE__."::$key"} = sub {
107 my $self = shift;
108 $self->{$key} = $_[0] if @_;
109 return $self->{$key};
110 }
111}
112
113sub new {
114 my $class = shift;
115 $class = ref $class if ref $class;
116
117 ### copying $tmpl here since a shallow copy makes it use the
118 ### same aref, causing for files to remain in memory always.
119 my $obj = bless { _data => [ ], _file => 'Unknown' }, $class;
120
121 if (@_) {
81a5970e
RGS
122 unless ( $obj->read( @_ ) ) {
123 $obj->_error(qq[No data could be read from file]);
124 return;
125 }
39713df4
RGS
126 }
127
128 return $obj;
129}
130
642eb381 131=head2 $tar->read ( $filename|$handle, [$compressed, {opt => 'val'}] )
39713df4
RGS
132
133Read the given tar file into memory.
134The first argument can either be the name of a file or a reference to
135an already open filehandle (or an IO::Zlib object if it's compressed)
39713df4
RGS
136
137The C<read> will I<replace> any previous content in C<$tar>!
138
642eb381
SH
139The second argument may be considered optional, but remains for
140backwards compatibility. Archive::Tar now looks at the file
141magic to determine what class should be used to open the file
142and will transparently Do The Right Thing.
143
144Archive::Tar will warn if you try to pass a bzip2 compressed file and the
145IO::Zlib / IO::Uncompress::Bunzip2 modules are not available and simply return.
39713df4 146
b3200c5d 147Note that you can currently B<not> pass a C<gzip> compressed
642eb381
SH
148filehandle, which is not opened with C<IO::Zlib>, a C<bzip2> compressed
149filehandle, which is not opened with C<IO::Uncompress::Bunzip2>, nor a string
b3200c5d
SP
150containing the full archive information (either compressed or
151uncompressed). These are worth while features, but not currently
152implemented. See the C<TODO> section.
153
39713df4
RGS
154The third argument can be a hash reference with options. Note that
155all options are case-sensitive.
156
157=over 4
158
159=item limit
160
161Do not read more than C<limit> files. This is useful if you have
162very big archives, and are only interested in the first few files.
163
642eb381
SH
164=item filter
165
166Can be set to a regular expression. Only files with names that match
167the expression will be read.
168
39713df4
RGS
169=item extract
170
171If set to true, immediately extract entries when reading them. This
172gives you the same memory break as the C<extract_archive> function.
173Note however that entries will not be read into memory, but written
642eb381
SH
174straight to disk. This means no C<Archive::Tar::File> objects are
175created for you to inspect.
39713df4
RGS
176
177=back
178
179All files are stored internally as C<Archive::Tar::File> objects.
180Please consult the L<Archive::Tar::File> documentation for details.
181
182Returns the number of files read in scalar context, and a list of
183C<Archive::Tar::File> objects in list context.
184
185=cut
186
187sub read {
188 my $self = shift;
189 my $file = shift;
190 my $gzip = shift || 0;
191 my $opts = shift || {};
192
193 unless( defined $file ) {
194 $self->_error( qq[No file to read from!] );
195 return;
196 } else {
197 $self->_file( $file );
198 }
199
200 my $handle = $self->_get_handle($file, $gzip, READ_ONLY->( ZLIB ) )
201 or return;
202
203 my $data = $self->_read_tar( $handle, $opts ) or return;
204
205 $self->_data( $data );
206
207 return wantarray ? @$data : scalar @$data;
208}
209
210sub _get_handle {
642eb381
SH
211 my $self = shift;
212 my $file = shift; return unless defined $file;
213 return $file if ref $file;
214 my $compress = shift || 0;
215 my $mode = shift || READ_ONLY->( ZLIB ); # default to read only
216
217
218 ### get a FH opened to the right class, so we can use it transparently
219 ### throughout the program
220 my $fh;
221 { ### reading magic only makes sense if we're opening a file for
222 ### reading. otherwise, just use what the user requested.
223 my $magic = '';
224 if( MODE_READ->($mode) ) {
225 open my $tmp, $file or do {
226 $self->_error( qq[Could not open '$file' for reading: $!] );
227 return;
228 };
229
230 ### read the first 4 bites of the file to figure out which class to
231 ### use to open the file.
232 sysread( $tmp, $magic, 4 );
233 close $tmp;
234 }
39713df4 235
642eb381
SH
236 ### is it bzip?
237 ### if you asked specifically for bzip compression, or if we're in
238 ### read mode and the magic numbers add up, use bzip
239 if( BZIP and (
240 ($compress eq COMPRESS_BZIP) or
241 ( MODE_READ->($mode) and $magic =~ BZIP_MAGIC_NUM )
242 )
243 ) {
244
245 ### different reader/writer modules, different error vars... sigh
246 if( MODE_READ->($mode) ) {
247 $fh = IO::Uncompress::Bunzip2->new( $file ) or do {
248 $self->_error( qq[Could not read '$file': ] .
249 $IO::Uncompress::Bunzip2::Bunzip2Error
250 );
251 return;
252 };
253
254 } else {
255 $fh = IO::Compress::Bzip2->new( $file ) or do {
256 $self->_error( qq[Could not write to '$file': ] .
257 $IO::Compress::Bzip2::Bzip2Error
258 );
259 return;
260 };
261 }
262
263 ### is it gzip?
264 ### if you asked for compression, if you wanted to read or the gzip
265 ### magic number is present (redundant with read)
266 } elsif( ZLIB and (
267 $compress or MODE_READ->($mode) or $magic =~ GZIP_MAGIC_NUM
268 )
269 ) {
270 $fh = IO::Zlib->new;
39713df4 271
642eb381
SH
272 unless( $fh->open( $file, $mode ) ) {
273 $self->_error(qq[Could not create filehandle for '$file': $!]);
274 return;
275 }
276
277 ### is it plain tar?
39713df4 278 } else {
642eb381 279 $fh = IO::File->new;
39713df4 280
642eb381
SH
281 unless( $fh->open( $file, $mode ) ) {
282 $self->_error(qq[Could not create filehandle for '$file': $!]);
283 return;
284 }
39713df4 285
642eb381
SH
286 ### enable bin mode on tar archives
287 binmode $fh;
288 }
289 }
39713df4
RGS
290
291 return $fh;
292}
293
642eb381 294
39713df4
RGS
295sub _read_tar {
296 my $self = shift;
297 my $handle = shift or return;
298 my $opts = shift || {};
299
300 my $count = $opts->{limit} || 0;
642eb381 301 my $filter = $opts->{filter};
39713df4
RGS
302 my $extract = $opts->{extract} || 0;
303
304 ### set a cap on the amount of files to extract ###
305 my $limit = 0;
306 $limit = 1 if $count > 0;
307
308 my $tarfile = [ ];
309 my $chunk;
310 my $read = 0;
311 my $real_name; # to set the name of a file when
312 # we're encountering @longlink
313 my $data;
314
315 LOOP:
316 while( $handle->read( $chunk, HEAD ) ) {
317 ### IO::Zlib doesn't support this yet
318 my $offset = eval { tell $handle } || 'unknown';
319
320 unless( $read++ ) {
321 my $gzip = GZIP_MAGIC_NUM;
322 if( $chunk =~ /$gzip/ ) {
323 $self->_error( qq[Cannot read compressed format in tar-mode] );
324 return;
325 }
326 }
327
328 ### if we can't read in all bytes... ###
329 last if length $chunk != HEAD;
330
331 ### Apparently this should really be two blocks of 512 zeroes,
332 ### but GNU tar sometimes gets it wrong. See comment in the
333 ### source code (tar.c) to GNU cpio.
334 next if $chunk eq TAR_END;
335
b30bcf62
RGS
336 ### according to the posix spec, the last 12 bytes of the header are
337 ### null bytes, to pad it to a 512 byte block. That means if these
338 ### bytes are NOT null bytes, it's a corrrupt header. See:
339 ### www.koders.com/c/fidCE473AD3D9F835D690259D60AD5654591D91D5BA.aspx
340 ### line 111
341 { my $nulls = join '', "\0" x 12;
342 unless( $nulls eq substr( $chunk, 500, 12 ) ) {
343 $self->_error( qq[Invalid header block at offset $offset] );
344 next LOOP;
345 }
346 }
347
81a5970e
RGS
348 ### pass the realname, so we can set it 'proper' right away
349 ### some of the heuristics are done on the name, so important
350 ### to set it ASAP
39713df4 351 my $entry;
81a5970e
RGS
352 { my %extra_args = ();
353 $extra_args{'name'} = $$real_name if defined $real_name;
354
355 unless( $entry = Archive::Tar::File->new( chunk => $chunk,
356 %extra_args )
357 ) {
358 $self->_error( qq[Couldn't read chunk at offset $offset] );
b30bcf62 359 next LOOP;
81a5970e 360 }
39713df4
RGS
361 }
362
363 ### ignore labels:
364 ### http://www.gnu.org/manual/tar/html_node/tar_139.html
365 next if $entry->is_label;
366
367 if( length $entry->type and ($entry->is_file || $entry->is_longlink) ) {
368
369 if ( $entry->is_file && !$entry->validate ) {
370 ### sometimes the chunk is rather fux0r3d and a whole 512
c3745331 371 ### bytes ends up in the ->name area.
39713df4
RGS
372 ### clean it up, if need be
373 my $name = $entry->name;
374 $name = substr($name, 0, 100) if length $name > 100;
375 $name =~ s/\n/ /g;
376
377 $self->_error( $name . qq[: checksum error] );
378 next LOOP;
379 }
380
381 my $block = BLOCK_SIZE->( $entry->size );
382
383 $data = $entry->get_content_by_ref;
384
385 ### just read everything into memory
386 ### can't do lazy loading since IO::Zlib doesn't support 'seek'
387 ### this is because Compress::Zlib doesn't support it =/
388 ### this reads in the whole data in one read() call.
389 if( $handle->read( $$data, $block ) < $block ) {
390 $self->_error( qq[Read error on tarfile (missing data) '].
391 $entry->full_path ."' at offset $offset" );
b30bcf62 392 next LOOP;
39713df4
RGS
393 }
394
395 ### throw away trailing garbage ###
376cc5ea 396 substr ($$data, $entry->size) = "" if defined $$data;
39713df4
RGS
397
398 ### part II of the @LongLink munging -- need to do /after/
399 ### the checksum check.
400 if( $entry->is_longlink ) {
401 ### weird thing in tarfiles -- if the file is actually a
402 ### @LongLink, the data part seems to have a trailing ^@
403 ### (unprintable) char. to display, pipe output through less.
404 ### but that doesn't *always* happen.. so check if the last
405 ### character is a control character, and if so remove it
406 ### at any rate, we better remove that character here, or tests
407 ### like 'eq' and hashlook ups based on names will SO not work
408 ### remove it by calculating the proper size, and then
409 ### tossing out everything that's longer than that size.
410
411 ### count number of nulls
412 my $nulls = $$data =~ tr/\0/\0/;
413
414 ### cut data + size by that many bytes
415 $entry->size( $entry->size - $nulls );
416 substr ($$data, $entry->size) = "";
417 }
418 }
419
420 ### clean up of the entries.. posix tar /apparently/ has some
421 ### weird 'feature' that allows for filenames > 255 characters
422 ### they'll put a header in with as name '././@LongLink' and the
423 ### contents will be the name of the /next/ file in the archive
424 ### pretty crappy and kludgy if you ask me
425
426 ### set the name for the next entry if this is a @LongLink;
427 ### this is one ugly hack =/ but needed for direct extraction
428 if( $entry->is_longlink ) {
429 $real_name = $data;
b30bcf62 430 next LOOP;
39713df4
RGS
431 } elsif ( defined $real_name ) {
432 $entry->name( $$real_name );
433 $entry->prefix('');
434 undef $real_name;
435 }
436
642eb381
SH
437 ### skip this entry if we're filtering
438 if ($filter && $entry->name !~ $filter) {
439 next LOOP;
440
441 ### skip this entry if it's a pax header. This is a special file added
442 ### by, among others, git-generated tarballs. It holds comments and is
443 ### not meant for extracting. See #38932: pax_global_header extracted
444 } elsif ( $entry->name eq PAX_HEADER ) {
445 next LOOP;
446 }
447
39713df4
RGS
448 $self->_extract_file( $entry ) if $extract
449 && !$entry->is_longlink
450 && !$entry->is_unknown
451 && !$entry->is_label;
452
453 ### Guard against tarfiles with garbage at the end
454 last LOOP if $entry->name eq '';
455
456 ### push only the name on the rv if we're extracting
457 ### -- for extract_archive
458 push @$tarfile, ($extract ? $entry->name : $entry);
459
460 if( $limit ) {
461 $count-- unless $entry->is_longlink || $entry->is_dir;
462 last LOOP unless $count;
463 }
464 } continue {
465 undef $data;
466 }
467
468 return $tarfile;
469}
470
471=head2 $tar->contains_file( $filename )
472
473Check if the archive contains a certain file.
474It will return true if the file is in the archive, false otherwise.
475
476Note however, that this function does an exact match using C<eq>
477on the full path. So it cannot compensate for case-insensitive file-
478systems or compare 2 paths to see if they would point to the same
479underlying file.
480
481=cut
482
483sub contains_file {
484 my $self = shift;
01d11a1c
SP
485 my $full = shift;
486
487 return unless defined $full;
39713df4 488
c3745331
RGS
489 ### don't warn if the entry isn't there.. that's what this function
490 ### is for after all.
491 local $WARN = 0;
39713df4
RGS
492 return 1 if $self->_find_entry($full);
493 return;
494}
495
496=head2 $tar->extract( [@filenames] )
497
498Write files whose names are equivalent to any of the names in
499C<@filenames> to disk, creating subdirectories as necessary. This
500might not work too well under VMS.
501Under MacPerl, the file's modification time will be converted to the
502MacOS zero of time, and appropriate conversions will be done to the
503path. However, the length of each element of the path is not
504inspected to see whether it's longer than MacOS currently allows (32
505characters).
506
507If C<extract> is called without a list of file names, the entire
508contents of the archive are extracted.
509
510Returns a list of filenames extracted.
511
512=cut
513
514sub extract {
515 my $self = shift;
b30bcf62 516 my @args = @_;
39713df4
RGS
517 my @files;
518
f38c1908
SP
519 # use the speed optimization for all extracted files
520 local($self->{cwd}) = cwd() unless $self->{cwd};
521
39713df4 522 ### you requested the extraction of only certian files
b30bcf62
RGS
523 if( @args ) {
524 for my $file ( @args ) {
525
526 ### it's already an object?
527 if( UNIVERSAL::isa( $file, 'Archive::Tar::File' ) ) {
528 push @files, $file;
529 next;
39713df4 530
b30bcf62
RGS
531 ### go find it then
532 } else {
533
534 my $found;
535 for my $entry ( @{$self->_data} ) {
536 next unless $file eq $entry->full_path;
537
538 ### we found the file you're looking for
539 push @files, $entry;
540 $found++;
541 }
542
543 unless( $found ) {
544 return $self->_error(
545 qq[Could not find '$file' in archive] );
546 }
39713df4
RGS
547 }
548 }
549
550 ### just grab all the file items
551 } else {
552 @files = $self->get_files;
553 }
554
555 ### nothing found? that's an error
556 unless( scalar @files ) {
557 $self->_error( qq[No files found for ] . $self->_file );
558 return;
559 }
560
561 ### now extract them
562 for my $entry ( @files ) {
563 unless( $self->_extract_file( $entry ) ) {
564 $self->_error(q[Could not extract ']. $entry->full_path .q['] );
565 return;
566 }
567 }
568
569 return @files;
570}
571
572=head2 $tar->extract_file( $file, [$extract_path] )
573
574Write an entry, whose name is equivalent to the file name provided to
48e76d2d 575disk. Optionally takes a second parameter, which is the full native
39713df4
RGS
576path (including filename) the entry will be written to.
577
578For example:
579
580 $tar->extract_file( 'name/in/archive', 'name/i/want/to/give/it' );
581
b30bcf62
RGS
582 $tar->extract_file( $at_file_object, 'name/i/want/to/give/it' );
583
39713df4
RGS
584Returns true on success, false on failure.
585
586=cut
587
588sub extract_file {
589 my $self = shift;
01d11a1c 590 my $file = shift; return unless defined $file;
39713df4
RGS
591 my $alt = shift;
592
593 my $entry = $self->_find_entry( $file )
594 or $self->_error( qq[Could not find an entry for '$file'] ), return;
595
596 return $self->_extract_file( $entry, $alt );
597}
598
599sub _extract_file {
600 my $self = shift;
601 my $entry = shift or return;
602 my $alt = shift;
39713df4
RGS
603
604 ### you wanted an alternate extraction location ###
605 my $name = defined $alt ? $alt : $entry->full_path;
606
607 ### splitpath takes a bool at the end to indicate
608 ### that it's splitting a dir
7f10f74b
SH
609 my ($vol,$dirs,$file);
610 if ( defined $alt ) { # It's a local-OS path
611 ($vol,$dirs,$file) = File::Spec->splitpath( $alt,
612 $entry->is_dir );
613 } else {
614 ($vol,$dirs,$file) = File::Spec::Unix->splitpath( $name,
615 $entry->is_dir );
616 }
617
39713df4
RGS
618 my $dir;
619 ### is $name an absolute path? ###
642eb381 620 if( $vol || File::Spec->file_name_is_absolute( $dirs ) ) {
178aef9a
RGS
621
622 ### absolute names are not allowed to be in tarballs under
623 ### strict mode, so only allow it if a user tells us to do it
624 if( not defined $alt and not $INSECURE_EXTRACT_MODE ) {
625 $self->_error(
626 q[Entry ']. $entry->full_path .q[' is an absolute path. ].
627 q[Not extracting absolute paths under SECURE EXTRACT MODE]
628 );
629 return;
630 }
631
632 ### user asked us to, it's fine.
642eb381 633 $dir = File::Spec->catpath( $vol, $dirs, "" );
39713df4
RGS
634
635 ### it's a relative path ###
636 } else {
642eb381
SH
637 my $cwd = (ref $self and defined $self->{cwd})
638 ? $self->{cwd}
639 : cwd();
f5afd28d 640
f5afd28d
NC
641 my @dirs = defined $alt
642 ? File::Spec->splitdir( $dirs ) # It's a local-OS path
643 : File::Spec::Unix->splitdir( $dirs ); # it's UNIX-style, likely
644 # straight from the tarball
178aef9a 645
178aef9a 646 if( not defined $alt and
642eb381
SH
647 not $INSECURE_EXTRACT_MODE
648 ) {
649
650 ### paths that leave the current directory are not allowed under
651 ### strict mode, so only allow it if a user tells us to do this.
652 if( grep { $_ eq '..' } @dirs ) {
653
654 $self->_error(
655 q[Entry ']. $entry->full_path .q[' is attempting to leave ].
656 q[the current working directory. Not extracting under ].
657 q[SECURE EXTRACT MODE]
658 );
659 return;
660 }
661
662 ### the archive may be asking us to extract into a symlink. This
663 ### is not sane and a possible security issue, as outlined here:
664 ### https://rt.cpan.org/Ticket/Display.html?id=30380
665 ### https://bugzilla.redhat.com/show_bug.cgi?id=295021
666 ### https://issues.rpath.com/browse/RPL-1716
667 my $full_path = $cwd;
668 for my $d ( @dirs ) {
669 $full_path = File::Spec->catdir( $full_path, $d );
670
671 ### we've already checked this one, and it's safe. Move on.
672 next if ref $self and $self->{_link_cache}->{$full_path};
673
674 if( -l $full_path ) {
675 my $to = readlink $full_path;
676 my $diag = "symlinked directory ($full_path => $to)";
677
678 $self->_error(
679 q[Entry ']. $entry->full_path .q[' is attempting to ].
680 qq[extract to a $diag. This is considered a security ].
681 q[vulnerability and not allowed under SECURE EXTRACT ].
682 q[MODE]
683 );
684 return;
685 }
686
687 ### XXX keep a cache if possible, so the stats become cheaper:
688 $self->{_link_cache}->{$full_path} = 1 if ref $self;
689 }
690 }
691
2610e7a4
JB
692 ### '.' is the directory delimiter on VMS, which has to be escaped
693 ### or changed to '_' on vms. vmsify is used, because older versions
694 ### of vmspath do not handle this properly.
695 ### Must not add a '/' to an empty directory though.
696 map { length() ? VMS::Filespec::vmsify($_.'/') : $_ } @dirs if ON_VMS;
f5afd28d 697
48e76d2d
CB
698 my ($cwd_vol,$cwd_dir,$cwd_file)
699 = File::Spec->splitpath( $cwd );
700 my @cwd = File::Spec->splitdir( $cwd_dir );
701 push @cwd, $cwd_file if length $cwd_file;
81a5970e 702
f5afd28d
NC
703 ### We need to pass '' as the last elemant to catpath. Craig Berry
704 ### explains why (msgid <p0624083dc311ae541393@[172.16.52.1]>):
705 ### The root problem is that splitpath on UNIX always returns the
706 ### final path element as a file even if it is a directory, and of
707 ### course there is no way it can know the difference without checking
708 ### against the filesystem, which it is documented as not doing. When
709 ### you turn around and call catpath, on VMS you have to know which bits
710 ### are directory bits and which bits are file bits. In this case we
711 ### know the result should be a directory. I had thought you could omit
712 ### the file argument to catpath in such a case, but apparently on UNIX
713 ### you can't.
714 $dir = File::Spec->catpath(
715 $cwd_vol, File::Spec->catdir( @cwd, @dirs ), ''
716 );
717
2610e7a4
JB
718 ### catdir() returns undef if the path is longer than 255 chars on
719 ### older VMS systems.
81a5970e
RGS
720 unless ( defined $dir ) {
721 $^W && $self->_error( qq[Could not compose a path for '$dirs'\n] );
722 return;
723 }
724
39713df4
RGS
725 }
726
727 if( -e $dir && !-d _ ) {
728 $^W && $self->_error( qq['$dir' exists, but it's not a directory!\n] );
729 return;
730 }
731
732 unless ( -d _ ) {
733 eval { File::Path::mkpath( $dir, 0, 0777 ) };
734 if( $@ ) {
642eb381
SH
735 my $fp = $entry->full_path;
736 $self->_error(qq[Could not create directory '$dir' for '$fp': $@]);
39713df4
RGS
737 return;
738 }
c3745331
RGS
739
740 ### XXX chown here? that might not be the same as in the archive
741 ### as we're only chown'ing to the owner of the file we're extracting
742 ### not to the owner of the directory itself, which may or may not
743 ### be another entry in the archive
744 ### Answer: no, gnu tar doesn't do it either, it'd be the wrong
745 ### way to go.
746 #if( $CHOWN && CAN_CHOWN ) {
747 # chown $entry->uid, $entry->gid, $dir or
748 # $self->_error( qq[Could not set uid/gid on '$dir'] );
749 #}
39713df4
RGS
750 }
751
752 ### we're done if we just needed to create a dir ###
753 return 1 if $entry->is_dir;
754
755 my $full = File::Spec->catfile( $dir, $file );
756
757 if( $entry->is_unknown ) {
758 $self->_error( qq[Unknown file type for file '$full'] );
759 return;
760 }
761
762 if( length $entry->type && $entry->is_file ) {
763 my $fh = IO::File->new;
764 $fh->open( '>' . $full ) or (
765 $self->_error( qq[Could not open file '$full': $!] ),
766 return
767 );
768
769 if( $entry->size ) {
770 binmode $fh;
771 syswrite $fh, $entry->data or (
772 $self->_error( qq[Could not write data to '$full'] ),
773 return
774 );
775 }
776
777 close $fh or (
778 $self->_error( qq[Could not close file '$full'] ),
779 return
780 );
781
782 } else {
783 $self->_make_special_file( $entry, $full ) or return;
784 }
785
642eb381
SH
786 ### only update the timestamp if it's not a symlink; that will change the
787 ### timestamp of the original. This addresses bug #33669: Could not update
788 ### timestamp warning on symlinks
789 if( not -l $full ) {
790 utime time, $entry->mtime - TIME_OFFSET, $full or
791 $self->_error( qq[Could not update timestamp] );
792 }
39713df4 793
2610e7a4 794 if( $CHOWN && CAN_CHOWN->() ) {
39713df4
RGS
795 chown $entry->uid, $entry->gid, $full or
796 $self->_error( qq[Could not set uid/gid on '$full'] );
797 }
798
799 ### only chmod if we're allowed to, but never chmod symlinks, since they'll
800 ### change the perms on the file they're linking too...
801 if( $CHMOD and not -l $full ) {
802 chmod $entry->mode, $full or
803 $self->_error( qq[Could not chown '$full' to ] . $entry->mode );
804 }
805
806 return 1;
807}
808
809sub _make_special_file {
810 my $self = shift;
811 my $entry = shift or return;
812 my $file = shift; return unless defined $file;
813
814 my $err;
815
816 if( $entry->is_symlink ) {
817 my $fail;
818 if( ON_UNIX ) {
819 symlink( $entry->linkname, $file ) or $fail++;
820
821 } else {
822 $self->_extract_special_file_as_plain_file( $entry, $file )
823 or $fail++;
824 }
825
642eb381
SH
826 $err = qq[Making symbolic link '$file' to '] .
827 $entry->linkname .q[' failed] if $fail;
39713df4
RGS
828
829 } elsif ( $entry->is_hardlink ) {
830 my $fail;
831 if( ON_UNIX ) {
832 link( $entry->linkname, $file ) or $fail++;
833
834 } else {
835 $self->_extract_special_file_as_plain_file( $entry, $file )
836 or $fail++;
837 }
838
839 $err = qq[Making hard link from '] . $entry->linkname .
840 qq[' to '$file' failed] if $fail;
841
842 } elsif ( $entry->is_fifo ) {
843 ON_UNIX && !system('mknod', $file, 'p') or
844 $err = qq[Making fifo ']. $entry->name .qq[' failed];
845
846 } elsif ( $entry->is_blockdev or $entry->is_chardev ) {
847 my $mode = $entry->is_blockdev ? 'b' : 'c';
848
849 ON_UNIX && !system('mknod', $file, $mode,
850 $entry->devmajor, $entry->devminor) or
851 $err = qq[Making block device ']. $entry->name .qq[' (maj=] .
852 $entry->devmajor . qq[ min=] . $entry->devminor .
853 qq[) failed.];
854
855 } elsif ( $entry->is_socket ) {
856 ### the original doesn't do anything special for sockets.... ###
857 1;
858 }
859
860 return $err ? $self->_error( $err ) : 1;
861}
862
863### don't know how to make symlinks, let's just extract the file as
864### a plain file
865sub _extract_special_file_as_plain_file {
866 my $self = shift;
867 my $entry = shift or return;
868 my $file = shift; return unless defined $file;
869
870 my $err;
871 TRY: {
872 my $orig = $self->_find_entry( $entry->linkname );
873
874 unless( $orig ) {
875 $err = qq[Could not find file '] . $entry->linkname .
876 qq[' in memory.];
877 last TRY;
878 }
879
880 ### clone the entry, make it appear as a normal file ###
881 my $clone = $entry->clone;
882 $clone->_downgrade_to_plainfile;
883 $self->_extract_file( $clone, $file ) or last TRY;
884
885 return 1;
886 }
887
888 return $self->_error($err);
889}
890
891=head2 $tar->list_files( [\@properties] )
892
893Returns a list of the names of all the files in the archive.
894
895If C<list_files()> is passed an array reference as its first argument
896it returns a list of hash references containing the requested
897properties of each file. The following list of properties is
898supported: name, size, mtime (last modified date), mode, uid, gid,
899linkname, uname, gname, devmajor, devminor, prefix.
900
901Passing an array reference containing only one element, 'name', is
902special cased to return a list of names rather than a list of hash
903references, making it equivalent to calling C<list_files> without
904arguments.
905
906=cut
907
908sub list_files {
909 my $self = shift;
910 my $aref = shift || [ ];
911
912 unless( $self->_data ) {
913 $self->read() or return;
914 }
915
916 if( @$aref == 0 or ( @$aref == 1 and $aref->[0] eq 'name' ) ) {
917 return map { $_->full_path } @{$self->_data};
918 } else {
919
920 #my @rv;
921 #for my $obj ( @{$self->_data} ) {
922 # push @rv, { map { $_ => $obj->$_() } @$aref };
923 #}
924 #return @rv;
925
926 ### this does the same as the above.. just needs a +{ }
927 ### to make sure perl doesn't confuse it for a block
928 return map { my $o=$_;
929 +{ map { $_ => $o->$_() } @$aref }
930 } @{$self->_data};
931 }
932}
933
934sub _find_entry {
935 my $self = shift;
936 my $file = shift;
937
938 unless( defined $file ) {
939 $self->_error( qq[No file specified] );
940 return;
941 }
942
b30bcf62
RGS
943 ### it's an object already
944 return $file if UNIVERSAL::isa( $file, 'Archive::Tar::File' );
945
39713df4
RGS
946 for my $entry ( @{$self->_data} ) {
947 my $path = $entry->full_path;
948 return $entry if $path eq $file;
949 }
950
951 $self->_error( qq[No such file in archive: '$file'] );
952 return;
953}
954
955=head2 $tar->get_files( [@filenames] )
956
957Returns the C<Archive::Tar::File> objects matching the filenames
958provided. If no filename list was passed, all C<Archive::Tar::File>
959objects in the current Tar object are returned.
960
961Please refer to the C<Archive::Tar::File> documentation on how to
962handle these objects.
963
964=cut
965
966sub get_files {
967 my $self = shift;
968
969 return @{ $self->_data } unless @_;
970
971 my @list;
972 for my $file ( @_ ) {
973 push @list, grep { defined } $self->_find_entry( $file );
974 }
975
976 return @list;
977}
978
979=head2 $tar->get_content( $file )
980
981Return the content of the named file.
982
983=cut
984
985sub get_content {
986 my $self = shift;
987 my $entry = $self->_find_entry( shift ) or return;
988
989 return $entry->data;
990}
991
992=head2 $tar->replace_content( $file, $content )
993
994Make the string $content be the content for the file named $file.
995
996=cut
997
998sub replace_content {
999 my $self = shift;
1000 my $entry = $self->_find_entry( shift ) or return;
1001
1002 return $entry->replace_content( shift );
1003}
1004
1005=head2 $tar->rename( $file, $new_name )
1006
1007Rename the file of the in-memory archive to $new_name.
1008
1009Note that you must specify a Unix path for $new_name, since per tar
1010standard, all files in the archive must be Unix paths.
1011
1012Returns true on success and false on failure.
1013
1014=cut
1015
1016sub rename {
1017 my $self = shift;
1018 my $file = shift; return unless defined $file;
1019 my $new = shift; return unless defined $new;
1020
1021 my $entry = $self->_find_entry( $file ) or return;
1022
1023 return $entry->rename( $new );
1024}
1025
1026=head2 $tar->remove (@filenamelist)
1027
1028Removes any entries with names matching any of the given filenames
1029from the in-memory archive. Returns a list of C<Archive::Tar::File>
1030objects that remain.
1031
1032=cut
1033
1034sub remove {
1035 my $self = shift;
1036 my @list = @_;
1037
1038 my %seen = map { $_->full_path => $_ } @{$self->_data};
1039 delete $seen{ $_ } for @list;
1040
1041 $self->_data( [values %seen] );
1042
1043 return values %seen;
1044}
1045
1046=head2 $tar->clear
1047
1048C<clear> clears the current in-memory archive. This effectively gives
1049you a 'blank' object, ready to be filled again. Note that C<clear>
1050only has effect on the object, not the underlying tarfile.
1051
1052=cut
1053
1054sub clear {
1055 my $self = shift or return;
1056
1057 $self->_data( [] );
1058 $self->_file( '' );
1059
1060 return 1;
1061}
1062
1063
1064=head2 $tar->write ( [$file, $compressed, $prefix] )
1065
1066Write the in-memory archive to disk. The first argument can either
1067be the name of a file or a reference to an already open filehandle (a
642eb381
SH
1068GLOB reference).
1069
1070The second argument is used to indicate compression. You can either
1071compress using C<gzip> or C<bzip2>. If you pass a digit, it's assumed
1072to be the C<gzip> compression level (between 1 and 9), but the use of
1073constants is prefered:
1074
1075 # write a gzip compressed file
1076 $tar->write( 'out.tgz', COMPRESSION_GZIP );
1077
1078 # write a bzip compressed file
1079 $tar->write( 'out.tbz', COMPRESSION_BZIP );
39713df4
RGS
1080
1081Note that when you pass in a filehandle, the compression argument
1082is ignored, as all files are printed verbatim to your filehandle.
1083If you wish to enable compression with filehandles, use an
642eb381 1084C<IO::Zlib> or C<IO::Compress::Bzip2> filehandle instead.
39713df4
RGS
1085
1086The third argument is an optional prefix. All files will be tucked
1087away in the directory you specify as prefix. So if you have files
1088'a' and 'b' in your archive, and you specify 'foo' as prefix, they
1089will be written to the archive as 'foo/a' and 'foo/b'.
1090
1091If no arguments are given, C<write> returns the entire formatted
1092archive as a string, which could be useful if you'd like to stuff the
1093archive into a socket or a pipe to gzip or something.
1094
642eb381 1095
39713df4
RGS
1096=cut
1097
1098sub write {
1099 my $self = shift;
1100 my $file = shift; $file = '' unless defined $file;
1101 my $gzip = shift || 0;
1102 my $ext_prefix = shift; $ext_prefix = '' unless defined $ext_prefix;
1103 my $dummy = '';
1104
1105 ### only need a handle if we have a file to print to ###
1106 my $handle = length($file)
1107 ? ( $self->_get_handle($file, $gzip, WRITE_ONLY->($gzip) )
1108 or return )
1109 : $HAS_PERLIO ? do { open my $h, '>', \$dummy; $h }
1110 : $HAS_IO_STRING ? IO::String->new
1111 : __PACKAGE__->no_string_support();
1112
1113
1114
1115 for my $entry ( @{$self->_data} ) {
1116 ### entries to be written to the tarfile ###
1117 my @write_me;
1118
1119 ### only now will we change the object to reflect the current state
1120 ### of the name and prefix fields -- this needs to be limited to
1121 ### write() only!
1122 my $clone = $entry->clone;
1123
1124
1125 ### so, if you don't want use to use the prefix, we'll stuff
1126 ### everything in the name field instead
1127 if( $DO_NOT_USE_PREFIX ) {
1128
1129 ### you might have an extended prefix, if so, set it in the clone
1130 ### XXX is ::Unix right?
1131 $clone->name( length $ext_prefix
1132 ? File::Spec::Unix->catdir( $ext_prefix,
1133 $clone->full_path)
1134 : $clone->full_path );
1135 $clone->prefix( '' );
1136
1137 ### otherwise, we'll have to set it properly -- prefix part in the
1138 ### prefix and name part in the name field.
1139 } else {
1140
1141 ### split them here, not before!
1142 my ($prefix,$name) = $clone->_prefix_and_file( $clone->full_path );
1143
1144 ### you might have an extended prefix, if so, set it in the clone
1145 ### XXX is ::Unix right?
1146 $prefix = File::Spec::Unix->catdir( $ext_prefix, $prefix )
1147 if length $ext_prefix;
1148
1149 $clone->prefix( $prefix );
1150 $clone->name( $name );
1151 }
1152
1153 ### names are too long, and will get truncated if we don't add a
1154 ### '@LongLink' file...
1155 my $make_longlink = ( length($clone->name) > NAME_LENGTH or
1156 length($clone->prefix) > PREFIX_LENGTH
1157 ) || 0;
1158
1159 ### perhaps we need to make a longlink file?
1160 if( $make_longlink ) {
1161 my $longlink = Archive::Tar::File->new(
1162 data => LONGLINK_NAME,
1163 $clone->full_path,
1164 { type => LONGLINK }
1165 );
1166
1167 unless( $longlink ) {
1168 $self->_error( qq[Could not create 'LongLink' entry for ] .
1169 qq[oversize file '] . $clone->full_path ."'" );
1170 return;
1171 };
1172
1173 push @write_me, $longlink;
1174 }
1175
1176 push @write_me, $clone;
1177
1178 ### write the one, optionally 2 a::t::file objects to the handle
1179 for my $clone (@write_me) {
1180
1181 ### if the file is a symlink, there are 2 options:
1182 ### either we leave the symlink intact, but then we don't write any
1183 ### data OR we follow the symlink, which means we actually make a
1184 ### copy. if we do the latter, we have to change the TYPE of the
1185 ### clone to 'FILE'
1186 my $link_ok = $clone->is_symlink && $Archive::Tar::FOLLOW_SYMLINK;
1187 my $data_ok = !$clone->is_symlink && $clone->has_content;
1188
1189 ### downgrade to a 'normal' file if it's a symlink we're going to
1190 ### treat as a regular file
1191 $clone->_downgrade_to_plainfile if $link_ok;
1192
1193 ### get the header for this block
1194 my $header = $self->_format_tar_entry( $clone );
1195 unless( $header ) {
1196 $self->_error(q[Could not format header for: ] .
1197 $clone->full_path );
1198 return;
1199 }
1200
1201 unless( print $handle $header ) {
1202 $self->_error(q[Could not write header for: ] .
1203 $clone->full_path);
1204 return;
1205 }
1206
1207 if( $link_ok or $data_ok ) {
1208 unless( print $handle $clone->data ) {
1209 $self->_error(q[Could not write data for: ] .
1210 $clone->full_path);
1211 return;
1212 }
1213
1214 ### pad the end of the clone if required ###
1215 print $handle TAR_PAD->( $clone->size ) if $clone->size % BLOCK
1216 }
1217
1218 } ### done writing these entries
1219 }
1220
1221 ### write the end markers ###
1222 print $handle TAR_END x 2 or
1223 return $self->_error( qq[Could not write tar end markers] );
b30bcf62 1224
39713df4 1225 ### did you want it written to a file, or returned as a string? ###
b30bcf62 1226 my $rv = length($file) ? 1
39713df4 1227 : $HAS_PERLIO ? $dummy
b30bcf62
RGS
1228 : do { seek $handle, 0, 0; local $/; <$handle> };
1229
1230 ### make sure to close the handle;
1231 close $handle;
1232
1233 return $rv;
39713df4
RGS
1234}
1235
1236sub _format_tar_entry {
1237 my $self = shift;
1238 my $entry = shift or return;
1239 my $ext_prefix = shift; $ext_prefix = '' unless defined $ext_prefix;
1240 my $no_prefix = shift || 0;
1241
1242 my $file = $entry->name;
1243 my $prefix = $entry->prefix; $prefix = '' unless defined $prefix;
1244
1245 ### remove the prefix from the file name
1246 ### not sure if this is still neeeded --kane
1247 ### no it's not -- Archive::Tar::File->_new_from_file will take care of
1248 ### this for us. Even worse, this would break if we tried to add a file
1249 ### like x/x.
1250 #if( length $prefix ) {
1251 # $file =~ s/^$match//;
1252 #}
1253
1254 $prefix = File::Spec::Unix->catdir($ext_prefix, $prefix)
1255 if length $ext_prefix;
1256
1257 ### not sure why this is... ###
1258 my $l = PREFIX_LENGTH; # is ambiguous otherwise...
1259 substr ($prefix, 0, -$l) = "" if length $prefix >= PREFIX_LENGTH;
1260
1261 my $f1 = "%06o"; my $f2 = "%11o";
1262
1263 ### this might be optimizable with a 'changed' flag in the file objects ###
1264 my $tar = pack (
1265 PACK,
1266 $file,
1267
1268 (map { sprintf( $f1, $entry->$_() ) } qw[mode uid gid]),
1269 (map { sprintf( $f2, $entry->$_() ) } qw[size mtime]),
1270
1271 "", # checksum field - space padded a bit down
1272
1273 (map { $entry->$_() } qw[type linkname magic]),
1274
1275 $entry->version || TAR_VERSION,
1276
1277 (map { $entry->$_() } qw[uname gname]),
1278 (map { sprintf( $f1, $entry->$_() ) } qw[devmajor devminor]),
1279
1280 ($no_prefix ? '' : $prefix)
1281 );
1282
1283 ### add the checksum ###
1284 substr($tar,148,7) = sprintf("%6o\0", unpack("%16C*",$tar));
1285
1286 return $tar;
1287}
1288
1289=head2 $tar->add_files( @filenamelist )
1290
1291Takes a list of filenames and adds them to the in-memory archive.
1292
1293The path to the file is automatically converted to a Unix like
1294equivalent for use in the archive, and, if on MacOS, the file's
1295modification time is converted from the MacOS epoch to the Unix epoch.
1296So tar archives created on MacOS with B<Archive::Tar> can be read
1297both with I<tar> on Unix and applications like I<suntar> or
1298I<Stuffit Expander> on MacOS.
1299
1300Be aware that the file's type/creator and resource fork will be lost,
1301which is usually what you want in cross-platform archives.
1302
2610e7a4
JB
1303Instead of a filename, you can also pass it an existing C<Archive::Tar::File>
1304object from, for example, another archive. The object will be clone, and
1305effectively be a copy of the original, not an alias.
1306
39713df4
RGS
1307Returns a list of C<Archive::Tar::File> objects that were just added.
1308
1309=cut
1310
1311sub add_files {
1312 my $self = shift;
1313 my @files = @_ or return;
1314
1315 my @rv;
1316 for my $file ( @files ) {
2610e7a4
JB
1317
1318 ### you passed an Archive::Tar::File object
1319 ### clone it so we don't accidentally have a reference to
1320 ### an object from another archive
1321 if( UNIVERSAL::isa( $file,'Archive::Tar::File' ) ) {
1322 push @rv, $file->clone;
1323 next;
1324 }
1325
c3745331 1326 unless( -e $file || -l $file ) {
39713df4
RGS
1327 $self->_error( qq[No such file: '$file'] );
1328 next;
1329 }
1330
1331 my $obj = Archive::Tar::File->new( file => $file );
1332 unless( $obj ) {
1333 $self->_error( qq[Unable to add file: '$file'] );
1334 next;
1335 }
1336
1337 push @rv, $obj;
1338 }
1339
1340 push @{$self->{_data}}, @rv;
1341
1342 return @rv;
1343}
1344
1345=head2 $tar->add_data ( $filename, $data, [$opthashref] )
1346
1347Takes a filename, a scalar full of data and optionally a reference to
1348a hash with specific options.
1349
1350Will add a file to the in-memory archive, with name C<$filename> and
1351content C<$data>. Specific properties can be set using C<$opthashref>.
1352The following list of properties is supported: name, size, mtime
1353(last modified date), mode, uid, gid, linkname, uname, gname,
b3200c5d 1354devmajor, devminor, prefix, type. (On MacOS, the file's path and
39713df4
RGS
1355modification times are converted to Unix equivalents.)
1356
b3200c5d
SP
1357Valid values for the file type are the following constants defined in
1358Archive::Tar::Constants:
1359
1360=over 4
1361
1362=item FILE
1363
1364Regular file.
1365
1366=item HARDLINK
1367
1368=item SYMLINK
1369
1370Hard and symbolic ("soft") links; linkname should specify target.
1371
1372=item CHARDEV
1373
1374=item BLOCKDEV
1375
1376Character and block devices. devmajor and devminor should specify the major
1377and minor device numbers.
1378
1379=item DIR
1380
1381Directory.
1382
1383=item FIFO
1384
1385FIFO (named pipe).
1386
1387=item SOCKET
1388
1389Socket.
1390
1391=back
1392
39713df4
RGS
1393Returns the C<Archive::Tar::File> object that was just added, or
1394C<undef> on failure.
1395
1396=cut
1397
1398sub add_data {
1399 my $self = shift;
1400 my ($file, $data, $opt) = @_;
1401
1402 my $obj = Archive::Tar::File->new( data => $file, $data, $opt );
1403 unless( $obj ) {
1404 $self->_error( qq[Unable to add file: '$file'] );
1405 return;
1406 }
1407
1408 push @{$self->{_data}}, $obj;
1409
1410 return $obj;
1411}
1412
1413=head2 $tar->error( [$BOOL] )
1414
1415Returns the current errorstring (usually, the last error reported).
1416If a true value was specified, it will give the C<Carp::longmess>
1417equivalent of the error, in effect giving you a stacktrace.
1418
1419For backwards compatibility, this error is also available as
1420C<$Archive::Tar::error> although it is much recommended you use the
1421method call instead.
1422
1423=cut
1424
1425{
1426 $error = '';
1427 my $longmess;
1428
1429 sub _error {
1430 my $self = shift;
1431 my $msg = $error = shift;
1432 $longmess = Carp::longmess($error);
1433
1434 ### set Archive::Tar::WARN to 0 to disable printing
1435 ### of errors
1436 if( $WARN ) {
1437 carp $DEBUG ? $longmess : $msg;
1438 }
1439
1440 return;
1441 }
1442
1443 sub error {
1444 my $self = shift;
1445 return shift() ? $longmess : $error;
1446 }
1447}
1448
f38c1908
SP
1449=head2 $tar->setcwd( $cwd );
1450
1451C<Archive::Tar> needs to know the current directory, and it will run
1452C<Cwd::cwd()> I<every> time it extracts a I<relative> entry from the
1453tarfile and saves it in the file system. (As of version 1.30, however,
1454C<Archive::Tar> will use the speed optimization described below
1455automatically, so it's only relevant if you're using C<extract_file()>).
1456
1457Since C<Archive::Tar> doesn't change the current directory internally
1458while it is extracting the items in a tarball, all calls to C<Cwd::cwd()>
1459can be avoided if we can guarantee that the current directory doesn't
1460get changed externally.
1461
1462To use this performance boost, set the current directory via
1463
1464 use Cwd;
1465 $tar->setcwd( cwd() );
1466
1467once before calling a function like C<extract_file> and
1468C<Archive::Tar> will use the current directory setting from then on
1469and won't call C<Cwd::cwd()> internally.
1470
1471To switch back to the default behaviour, use
1472
1473 $tar->setcwd( undef );
1474
1475and C<Archive::Tar> will call C<Cwd::cwd()> internally again.
1476
1477If you're using C<Archive::Tar>'s C<exract()> method, C<setcwd()> will
1478be called for you.
1479
1480=cut
1481
1482sub setcwd {
1483 my $self = shift;
1484 my $cwd = shift;
1485
1486 $self->{cwd} = $cwd;
1487}
39713df4 1488
39713df4
RGS
1489=head1 Class Methods
1490
642eb381 1491=head2 Archive::Tar->create_archive($file, $compressed, @filelist)
39713df4
RGS
1492
1493Creates a tar file from the list of files provided. The first
1494argument can either be the name of the tar file to create or a
1495reference to an open file handle (e.g. a GLOB reference).
1496
642eb381
SH
1497The second argument is used to indicate compression. You can either
1498compress using C<gzip> or C<bzip2>. If you pass a digit, it's assumed
1499to be the C<gzip> compression level (between 1 and 9), but the use of
1500constants is prefered:
1501
1502 # write a gzip compressed file
1503 Archive::Tar->create_archive( 'out.tgz', COMPRESSION_GZIP, @filelist );
1504
1505 # write a bzip compressed file
1506 Archive::Tar->create_archive( 'out.tbz', COMPRESSION_BZIP, @filelist );
39713df4
RGS
1507
1508Note that when you pass in a filehandle, the compression argument
1509is ignored, as all files are printed verbatim to your filehandle.
1510If you wish to enable compression with filehandles, use an
642eb381 1511C<IO::Zlib> or C<IO::Compress::Bzip2> filehandle instead.
39713df4
RGS
1512
1513The remaining arguments list the files to be included in the tar file.
1514These files must all exist. Any files which don't exist or can't be
1515read are silently ignored.
1516
1517If the archive creation fails for any reason, C<create_archive> will
1518return false. Please use the C<error> method to find the cause of the
1519failure.
1520
1521Note that this method does not write C<on the fly> as it were; it
1522still reads all the files into memory before writing out the archive.
1523Consult the FAQ below if this is a problem.
1524
1525=cut
1526
1527sub create_archive {
1528 my $class = shift;
1529
1530 my $file = shift; return unless defined $file;
1531 my $gzip = shift || 0;
1532 my @files = @_;
1533
1534 unless( @files ) {
1535 return $class->_error( qq[Cowardly refusing to create empty archive!] );
1536 }
1537
1538 my $tar = $class->new;
1539 $tar->add_files( @files );
1540 return $tar->write( $file, $gzip );
1541}
1542
642eb381
SH
1543=head2 Archive::Tar->iter( $filename, [ $compressed, {opt => $val} ] )
1544
1545Returns an iterator function that reads the tar file without loading
1546it all in memory. Each time the function is called it will return the
1547next file in the tarball. The files are returned as
1548C<Archive::Tar::File> objects. The iterator function returns the
1549empty list once it has exhausted the the files contained.
1550
1551The second argument can be a hash reference with options, which are
1552identical to the arguments passed to C<read()>.
1553
1554Example usage:
1555
1556 my $next = Archive::Tar->iter( "example.tar.gz", 1, {filter => qr/\.pm$/} );
1557
1558 while( my $f = $next->() ) {
1559 print $f->name, "\n";
1560
1561 $f->extract or warn "Extraction failed";
1562
1563 # ....
1564 }
1565
1566=cut
1567
1568
1569sub iter {
1570 my $class = shift;
1571 my $filename = shift or return;
1572 my $compressed = shift or 0;
1573 my $opts = shift || {};
1574
1575 ### get a handle to read from.
1576 my $handle = $class->_get_handle(
1577 $filename,
1578 $compressed,
1579 READ_ONLY->( ZLIB )
1580 ) or return;
1581
1582 my @data;
1583 return sub {
1584 return shift(@data) if @data; # more than one file returned?
1585 return unless $handle; # handle exhausted?
1586
1587 ### read data, should only return file
1588 @data = @{ $class->_read_tar($handle, { %$opts, limit => 1 }) };
1589
1590 ### return one piece of data
1591 return shift(@data) if @data;
1592
1593 ### data is exhausted, free the filehandle
1594 undef $handle;
1595 return;
1596 };
1597}
1598
1599=head2 Archive::Tar->list_archive($file, $compressed, [\@properties])
39713df4
RGS
1600
1601Returns a list of the names of all the files in the archive. The
1602first argument can either be the name of the tar file to list or a
1603reference to an open file handle (e.g. a GLOB reference).
1604
1605If C<list_archive()> is passed an array reference as its third
1606argument it returns a list of hash references containing the requested
1607properties of each file. The following list of properties is
b3200c5d
SP
1608supported: full_path, name, size, mtime (last modified date), mode,
1609uid, gid, linkname, uname, gname, devmajor, devminor, prefix.
1610
1611See C<Archive::Tar::File> for details about supported properties.
39713df4
RGS
1612
1613Passing an array reference containing only one element, 'name', is
1614special cased to return a list of names rather than a list of hash
1615references.
1616
1617=cut
1618
1619sub list_archive {
1620 my $class = shift;
1621 my $file = shift; return unless defined $file;
1622 my $gzip = shift || 0;
1623
1624 my $tar = $class->new($file, $gzip);
1625 return unless $tar;
1626
1627 return $tar->list_files( @_ );
1628}
1629
642eb381 1630=head2 Archive::Tar->extract_archive($file, $compressed)
39713df4
RGS
1631
1632Extracts the contents of the tar file. The first argument can either
1633be the name of the tar file to create or a reference to an open file
1634handle (e.g. a GLOB reference). All relative paths in the tar file will
1635be created underneath the current working directory.
1636
1637C<extract_archive> will return a list of files it extracted.
1638If the archive extraction fails for any reason, C<extract_archive>
1639will return false. Please use the C<error> method to find the cause
1640of the failure.
1641
1642=cut
1643
1644sub extract_archive {
1645 my $class = shift;
1646 my $file = shift; return unless defined $file;
1647 my $gzip = shift || 0;
1648
1649 my $tar = $class->new( ) or return;
1650
1651 return $tar->read( $file, $gzip, { extract => 1 } );
1652}
1653
f5695358
JB
1654=head2 $bool = Archive::Tar->has_io_string
1655
1656Returns true if we currently have C<IO::String> support loaded.
1657
1658Either C<IO::String> or C<perlio> support is needed to support writing
1659stringified archives. Currently, C<perlio> is the preferred method, if
1660available.
1661
1662See the C<GLOBAL VARIABLES> section to see how to change this preference.
1663
1664=cut
1665
1666sub has_io_string { return $HAS_IO_STRING; }
1667
1668=head2 $bool = Archive::Tar->has_perlio
1669
1670Returns true if we currently have C<perlio> support loaded.
1671
1672This requires C<perl-5.8> or higher, compiled with C<perlio>
1673
1674Either C<IO::String> or C<perlio> support is needed to support writing
1675stringified archives. Currently, C<perlio> is the preferred method, if
1676available.
1677
1678See the C<GLOBAL VARIABLES> section to see how to change this preference.
1679
1680=cut
1681
1682sub has_perlio { return $HAS_PERLIO; }
1683
1684=head2 $bool = Archive::Tar->has_zlib_support
1685
1686Returns true if C<Archive::Tar> can extract C<zlib> compressed archives
1687
1688=cut
1689
1690sub has_zlib_support { return ZLIB }
1691
1692=head2 $bool = Archive::Tar->has_bzip2_support
1693
1694Returns true if C<Archive::Tar> can extract C<bzip2> compressed archives
1695
1696=cut
1697
1698sub has_bzip2_support { return BZIP }
1699
39713df4
RGS
1700=head2 Archive::Tar->can_handle_compressed_files
1701
1702A simple checking routine, which will return true if C<Archive::Tar>
642eb381
SH
1703is able to uncompress compressed archives on the fly with C<IO::Zlib>
1704and C<IO::Compress::Bzip2> or false if not both are installed.
39713df4
RGS
1705
1706You can use this as a shortcut to determine whether C<Archive::Tar>
1707will do what you think before passing compressed archives to its
1708C<read> method.
1709
1710=cut
1711
642eb381 1712sub can_handle_compressed_files { return ZLIB && BZIP ? 1 : 0 }
39713df4
RGS
1713
1714sub no_string_support {
1715 croak("You have to install IO::String to support writing archives to strings");
1716}
1717
17181;
1719
1720__END__
1721
1722=head1 GLOBAL VARIABLES
1723
1724=head2 $Archive::Tar::FOLLOW_SYMLINK
1725
1726Set this variable to C<1> to make C<Archive::Tar> effectively make a
1727copy of the file when extracting. Default is C<0>, which
1728means the symlink stays intact. Of course, you will have to pack the
1729file linked to as well.
1730
1731This option is checked when you write out the tarfile using C<write>
1732or C<create_archive>.
1733
1734This works just like C</bin/tar>'s C<-h> option.
1735
1736=head2 $Archive::Tar::CHOWN
1737
1738By default, C<Archive::Tar> will try to C<chown> your files if it is
1739able to. In some cases, this may not be desired. In that case, set
1740this variable to C<0> to disable C<chown>-ing, even if it were
1741possible.
1742
1743The default is C<1>.
1744
1745=head2 $Archive::Tar::CHMOD
1746
1747By default, C<Archive::Tar> will try to C<chmod> your files to
1748whatever mode was specified for the particular file in the archive.
1749In some cases, this may not be desired. In that case, set this
1750variable to C<0> to disable C<chmod>-ing.
1751
1752The default is C<1>.
1753
1754=head2 $Archive::Tar::DO_NOT_USE_PREFIX
1755
f38c1908
SP
1756By default, C<Archive::Tar> will try to put paths that are over
1757100 characters in the C<prefix> field of your tar header, as
1758defined per POSIX-standard. However, some (older) tar programs
1759do not implement this spec. To retain compatibility with these older
1760or non-POSIX compliant versions, you can set the C<$DO_NOT_USE_PREFIX>
1761variable to a true value, and C<Archive::Tar> will use an alternate
1762way of dealing with paths over 100 characters by using the
1763C<GNU Extended Header> feature.
1764
1765Note that clients who do not support the C<GNU Extended Header>
1766feature will not be able to read these archives. Such clients include
1767tars on C<Solaris>, C<Irix> and C<AIX>.
39713df4
RGS
1768
1769The default is C<0>.
1770
1771=head2 $Archive::Tar::DEBUG
1772
1773Set this variable to C<1> to always get the C<Carp::longmess> output
1774of the warnings, instead of the regular C<carp>. This is the same
1775message you would get by doing:
1776
1777 $tar->error(1);
1778
1779Defaults to C<0>.
1780
1781=head2 $Archive::Tar::WARN
1782
1783Set this variable to C<0> if you do not want any warnings printed.
1784Personally I recommend against doing this, but people asked for the
1785option. Also, be advised that this is of course not threadsafe.
1786
1787Defaults to C<1>.
1788
1789=head2 $Archive::Tar::error
1790
1791Holds the last reported error. Kept for historical reasons, but its
1792use is very much discouraged. Use the C<error()> method instead:
1793
1794 warn $tar->error unless $tar->extract;
1795
178aef9a
RGS
1796=head2 $Archive::Tar::INSECURE_EXTRACT_MODE
1797
1798This variable indicates whether C<Archive::Tar> should allow
1799files to be extracted outside their current working directory.
1800
1801Allowing this could have security implications, as a malicious
1802tar archive could alter or replace any file the extracting user
1803has permissions to. Therefor, the default is to not allow
1804insecure extractions.
1805
1806If you trust the archive, or have other reasons to allow the
1807archive to write files outside your current working directory,
1808set this variable to C<true>.
1809
1810Note that this is a backwards incompatible change from version
1811C<1.36> and before.
1812
39713df4
RGS
1813=head2 $Archive::Tar::HAS_PERLIO
1814
1815This variable holds a boolean indicating if we currently have
1816C<perlio> support loaded. This will be enabled for any perl
1817greater than C<5.8> compiled with C<perlio>.
1818
1819If you feel strongly about disabling it, set this variable to
1820C<false>. Note that you will then need C<IO::String> installed
1821to support writing stringified archives.
1822
1823Don't change this variable unless you B<really> know what you're
1824doing.
1825
1826=head2 $Archive::Tar::HAS_IO_STRING
1827
1828This variable holds a boolean indicating if we currently have
1829C<IO::String> support loaded. This will be enabled for any perl
1830that has a loadable C<IO::String> module.
1831
1832If you feel strongly about disabling it, set this variable to
1833C<false>. Note that you will then need C<perlio> support from
1834your perl to be able to write stringified archives.
1835
1836Don't change this variable unless you B<really> know what you're
1837doing.
1838
1839=head1 FAQ
1840
1841=over 4
1842
1843=item What's the minimum perl version required to run Archive::Tar?
1844
1845You will need perl version 5.005_03 or newer.
1846
1847=item Isn't Archive::Tar slow?
1848
1849Yes it is. It's pure perl, so it's a lot slower then your C</bin/tar>
1850However, it's very portable. If speed is an issue, consider using
1851C</bin/tar> instead.
1852
1853=item Isn't Archive::Tar heavier on memory than /bin/tar?
1854
1855Yes it is, see previous answer. Since C<Compress::Zlib> and therefore
1856C<IO::Zlib> doesn't support C<seek> on their filehandles, there is little
1857choice but to read the archive into memory.
1858This is ok if you want to do in-memory manipulation of the archive.
642eb381 1859
39713df4
RGS
1860If you just want to extract, use the C<extract_archive> class method
1861instead. It will optimize and write to disk immediately.
1862
642eb381
SH
1863Another option is to use the C<iter> class method to iterate over
1864the files in the tarball without reading them all in memory at once.
1865
1866=item Can you lazy-load data instead?
39713df4 1867
642eb381
SH
1868In some cases, yes. You can use the C<iter> class method to iterate
1869over the files in the tarball without reading them all in memory at once.
39713df4
RGS
1870
1871=item How much memory will an X kb tar file need?
1872
1873Probably more than X kb, since it will all be read into memory. If
1874this is a problem, and you don't need to do in memory manipulation
642eb381
SH
1875of the archive, consider using the C<iter> class method, or C</bin/tar>
1876instead.
39713df4
RGS
1877
1878=item What do you do with unsupported filetypes in an archive?
1879
1880C<Unix> has a few filetypes that aren't supported on other platforms,
1881like C<Win32>. If we encounter a C<hardlink> or C<symlink> we'll just
1882try to make a copy of the original file, rather than throwing an error.
1883
1884This does require you to read the entire archive in to memory first,
1885since otherwise we wouldn't know what data to fill the copy with.
642eb381
SH
1886(This means that you cannot use the class methods, including C<iter>
1887on archives that have incompatible filetypes and still expect things
1888to work).
39713df4
RGS
1889
1890For other filetypes, like C<chardevs> and C<blockdevs> we'll warn that
1891the extraction of this particular item didn't work.
1892
f38c1908
SP
1893=item I'm using WinZip, or some other non-POSIX client, and files are not being extracted properly!
1894
1895By default, C<Archive::Tar> is in a completely POSIX-compatible
1896mode, which uses the POSIX-specification of C<tar> to store files.
1897For paths greather than 100 characters, this is done using the
1898C<POSIX header prefix>. Non-POSIX-compatible clients may not support
1899this part of the specification, and may only support the C<GNU Extended
1900Header> functionality. To facilitate those clients, you can set the
1901C<$Archive::Tar::DO_NOT_USE_PREFIX> variable to C<true>. See the
1902C<GLOBAL VARIABLES> section for details on this variable.
1903
c3745331
RGS
1904Note that GNU tar earlier than version 1.14 does not cope well with
1905the C<POSIX header prefix>. If you use such a version, consider setting
1906the C<$Archive::Tar::DO_NOT_USE_PREFIX> variable to C<true>.
1907
b30bcf62
RGS
1908=item How do I extract only files that have property X from an archive?
1909
1910Sometimes, you might not wish to extract a complete archive, just
1911the files that are relevant to you, based on some criteria.
1912
1913You can do this by filtering a list of C<Archive::Tar::File> objects
1914based on your criteria. For example, to extract only files that have
1915the string C<foo> in their title, you would use:
1916
1917 $tar->extract(
1918 grep { $_->full_path =~ /foo/ } $tar->get_files
1919 );
1920
1921This way, you can filter on any attribute of the files in the archive.
1922Consult the C<Archive::Tar::File> documentation on how to use these
1923objects.
1924
81a5970e
RGS
1925=item How do I access .tar.Z files?
1926
1927The C<Archive::Tar> module can optionally use C<Compress::Zlib> (via
1928the C<IO::Zlib> module) to access tar files that have been compressed
1929with C<gzip>. Unfortunately tar files compressed with the Unix C<compress>
1930utility cannot be read by C<Compress::Zlib> and so cannot be directly
1931accesses by C<Archive::Tar>.
1932
1933If the C<uncompress> or C<gunzip> programs are available, you can use
1934one of these workarounds to read C<.tar.Z> files from C<Archive::Tar>
1935
1936Firstly with C<uncompress>
1937
1938 use Archive::Tar;
1939
1940 open F, "uncompress -c $filename |";
1941 my $tar = Archive::Tar->new(*F);
1942 ...
1943
1944and this with C<gunzip>
1945
1946 use Archive::Tar;
1947
1948 open F, "gunzip -c $filename |";
1949 my $tar = Archive::Tar->new(*F);
1950 ...
1951
1952Similarly, if the C<compress> program is available, you can use this to
1953write a C<.tar.Z> file
1954
1955 use Archive::Tar;
1956 use IO::File;
1957
1958 my $fh = new IO::File "| compress -c >$filename";
1959 my $tar = Archive::Tar->new();
1960 ...
1961 $tar->write($fh);
1962 $fh->close ;
1963
01d11a1c
SP
1964=item How do I handle Unicode strings?
1965
1966C<Archive::Tar> uses byte semantics for any files it reads from or writes
1967to disk. This is not a problem if you only deal with files and never
1968look at their content or work solely with byte strings. But if you use
1969Unicode strings with character semantics, some additional steps need
1970to be taken.
1971
1972For example, if you add a Unicode string like
1973
1974 # Problem
1975 $tar->add_data('file.txt', "Euro: \x{20AC}");
1976
1977then there will be a problem later when the tarfile gets written out
1978to disk via C<$tar->write()>:
1979
1980 Wide character in print at .../Archive/Tar.pm line 1014.
1981
1982The data was added as a Unicode string and when writing it out to disk,
1983the C<:utf8> line discipline wasn't set by C<Archive::Tar>, so Perl
1984tried to convert the string to ISO-8859 and failed. The written file
1985now contains garbage.
1986
1987For this reason, Unicode strings need to be converted to UTF-8-encoded
1988bytestrings before they are handed off to C<add_data()>:
1989
1990 use Encode;
1991 my $data = "Accented character: \x{20AC}";
1992 $data = encode('utf8', $data);
1993
1994 $tar->add_data('file.txt', $data);
1995
1996A opposite problem occurs if you extract a UTF8-encoded file from a
1997tarball. Using C<get_content()> on the C<Archive::Tar::File> object
1998will return its content as a bytestring, not as a Unicode string.
1999
2000If you want it to be a Unicode string (because you want character
2001semantics with operations like regular expression matching), you need
2002to decode the UTF8-encoded content and have Perl convert it into
2003a Unicode string:
2004
2005 use Encode;
2006 my $data = $tar->get_content();
2007
2008 # Make it a Unicode string
2009 $data = decode('utf8', $data);
2010
2011There is no easy way to provide this functionality in C<Archive::Tar>,
2012because a tarball can contain many files, and each of which could be
2013encoded in a different way.
81a5970e 2014
39713df4
RGS
2015=back
2016
2017=head1 TODO
2018
2019=over 4
2020
2021=item Check if passed in handles are open for read/write
2022
2023Currently I don't know of any portable pure perl way to do this.
2024Suggestions welcome.
2025
b3200c5d
SP
2026=item Allow archives to be passed in as string
2027
2028Currently, we only allow opened filehandles or filenames, but
2029not strings. The internals would need some reworking to facilitate
2030stringified archives.
2031
2032=item Facilitate processing an opened filehandle of a compressed archive
2033
2034Currently, we only support this if the filehandle is an IO::Zlib object.
2035Environments, like apache, will present you with an opened filehandle
2036to an uploaded file, which might be a compressed archive.
2037
39713df4
RGS
2038=back
2039
f38c1908
SP
2040=head1 SEE ALSO
2041
2042=over 4
2043
2044=item The GNU tar specification
2045
2046C<http://www.gnu.org/software/tar/manual/tar.html>
2047
2048=item The PAX format specication
2049
2050The specifcation which tar derives from; C< http://www.opengroup.org/onlinepubs/007904975/utilities/pax.html>
2051
2052=item A comparison of GNU and POSIX tar standards; C<http://www.delorie.com/gnu/docs/tar/tar_114.html>
2053
2054=item GNU tar intends to switch to POSIX compatibility
2055
2056GNU Tar authors have expressed their intention to become completely
2057POSIX-compatible; C<http://www.gnu.org/software/tar/manual/html_node/Formats.html>
2058
2059=item A Comparison between various tar implementations
2060
2061Lists known issues and incompatibilities; C<http://gd.tuwien.ac.at/utils/archivers/star/README.otherbugs>
2062
2063=back
2064
39713df4
RGS
2065=head1 AUTHOR
2066
c3745331
RGS
2067This module by Jos Boumans E<lt>kane@cpan.orgE<gt>.
2068
2069Please reports bugs to E<lt>bug-archive-tar@rt.cpan.orgE<gt>.
39713df4
RGS
2070
2071=head1 ACKNOWLEDGEMENTS
2072
642eb381
SH
2073Thanks to Sean Burke, Chris Nandor, Chip Salzenberg, Tim Heaney, Gisle Aas
2074and especially Andrew Savige for their help and suggestions.
39713df4
RGS
2075
2076=head1 COPYRIGHT
2077
f5695358 2078This module is copyright (c) 2002 - 2008 Jos Boumans
c3745331 2079E<lt>kane@cpan.orgE<gt>. All rights reserved.
39713df4 2080
c3745331
RGS
2081This library is free software; you may redistribute and/or modify
2082it under the same terms as Perl itself.
39713df4
RGS
2083
2084=cut