Commit | Line | Data |
39713df4 |
1 | ### the gnu tar specification: |
f38c1908 |
2 | ### http://www.gnu.org/software/tar/manual/tar.html |
39713df4 |
3 | ### |
4 | ### and the pax format spec, which tar derives from: |
5 | ### http://www.opengroup.org/onlinepubs/007904975/utilities/pax.html |
6 | |
7 | package Archive::Tar; |
8 | require 5.005_03; |
9 | |
642eb381 |
10 | use Cwd; |
11 | use IO::Zlib; |
12 | use IO::File; |
13 | use Carp qw(carp croak); |
14 | use File::Spec (); |
15 | use File::Spec::Unix (); |
16 | use File::Path (); |
17 | |
18 | use Archive::Tar::File; |
19 | use Archive::Tar::Constant; |
20 | |
21 | require Exporter; |
22 | |
39713df4 |
23 | use strict; |
24 | use 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 |
27 | ]; |
28 | |
642eb381 |
29 | @ISA = qw[Exporter]; |
bef46b70 |
30 | @EXPORT = qw[ COMPRESS_GZIP COMPRESS_BZIP ]; |
178aef9a |
31 | $DEBUG = 0; |
32 | $WARN = 1; |
33 | $FOLLOW_SYMLINK = 0; |
bef46b70 |
34 | $VERSION = "1.46"; |
178aef9a |
35 | $CHOWN = 1; |
36 | $CHMOD = 1; |
37 | $DO_NOT_USE_PREFIX = 0; |
38 | $INSECURE_EXTRACT_MODE = 0; |
39713df4 |
39 | |
40 | BEGIN { |
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 |
47 | require IO::String; |
48 | import IO::String; |
642eb381 |
49 | 1; |
50 | } || 0; |
39713df4 |
51 | } |
52 | |
39713df4 |
53 | =head1 NAME |
54 | |
55 | Archive::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 |
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 |
70 | $tar->write('files.tar'); # plain tar |
bef46b70 |
71 | $tar->write('files.tgz', COMPRESS_GZIP); # gzip compressed |
72 | $tar->write('files.tbz', COMPRESS_BZIP); # bzip2 compressed |
39713df4 |
73 | |
74 | =head1 DESCRIPTION |
75 | |
76 | Archive::Tar provides an object oriented mechanism for handling tar |
77 | files. It provides class methods for quick and easy files handling |
78 | while also allowing for the creation of tar file objects for custom |
79 | manipulation. If you have the IO::Zlib module installed, |
80 | Archive::Tar will also support compressed or gzipped tar files. |
81 | |
82 | An object of class Archive::Tar represents a .tar(.gz) archive full |
83 | of files and things. |
84 | |
85 | =head1 Object Methods |
86 | |
87 | =head2 Archive::Tar->new( [$file, $compressed] ) |
88 | |
89 | Returns a new Tar object. If given any arguments, C<new()> calls the |
90 | C<read()> method automatically, passing on the arguments provided to |
91 | the C<read()> method. |
92 | |
93 | If C<new()> is invoked with arguments and the C<read()> method fails |
94 | for any reason, C<new()> returns undef. |
95 | |
96 | =cut |
97 | |
98 | my $tmpl = { |
99 | _data => [ ], |
100 | _file => 'Unknown', |
101 | }; |
102 | |
103 | ### install get/set accessors for this object. |
104 | for 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 | |
113 | sub 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 |
122 | unless ( $obj->read( @_ ) ) { |
123 | $obj->_error(qq[No data could be read from file]); |
124 | return; |
125 | } |
39713df4 |
126 | } |
127 | |
128 | return $obj; |
129 | } |
130 | |
642eb381 |
131 | =head2 $tar->read ( $filename|$handle, [$compressed, {opt => 'val'}] ) |
39713df4 |
132 | |
133 | Read the given tar file into memory. |
134 | The first argument can either be the name of a file or a reference to |
135 | an already open filehandle (or an IO::Zlib object if it's compressed) |
39713df4 |
136 | |
137 | The C<read> will I<replace> any previous content in C<$tar>! |
138 | |
e0d68803 |
139 | The second argument may be considered optional, but remains for |
642eb381 |
140 | backwards compatibility. Archive::Tar now looks at the file |
141 | magic to determine what class should be used to open the file |
142 | and will transparently Do The Right Thing. |
143 | |
144 | Archive::Tar will warn if you try to pass a bzip2 compressed file and the |
145 | IO::Zlib / IO::Uncompress::Bunzip2 modules are not available and simply return. |
39713df4 |
146 | |
b3200c5d |
147 | Note that you can currently B<not> pass a C<gzip> compressed |
642eb381 |
148 | filehandle, which is not opened with C<IO::Zlib>, a C<bzip2> compressed |
149 | filehandle, which is not opened with C<IO::Uncompress::Bunzip2>, nor a string |
b3200c5d |
150 | containing the full archive information (either compressed or |
151 | uncompressed). These are worth while features, but not currently |
152 | implemented. See the C<TODO> section. |
153 | |
39713df4 |
154 | The third argument can be a hash reference with options. Note that |
155 | all options are case-sensitive. |
156 | |
157 | =over 4 |
158 | |
159 | =item limit |
160 | |
161 | Do not read more than C<limit> files. This is useful if you have |
162 | very big archives, and are only interested in the first few files. |
163 | |
642eb381 |
164 | =item filter |
165 | |
166 | Can be set to a regular expression. Only files with names that match |
167 | the expression will be read. |
168 | |
39713df4 |
169 | =item extract |
170 | |
171 | If set to true, immediately extract entries when reading them. This |
172 | gives you the same memory break as the C<extract_archive> function. |
173 | Note however that entries will not be read into memory, but written |
e0d68803 |
174 | straight to disk. This means no C<Archive::Tar::File> objects are |
642eb381 |
175 | created for you to inspect. |
39713df4 |
176 | |
177 | =back |
178 | |
179 | All files are stored internally as C<Archive::Tar::File> objects. |
180 | Please consult the L<Archive::Tar::File> documentation for details. |
181 | |
182 | Returns the number of files read in scalar context, and a list of |
183 | C<Archive::Tar::File> objects in list context. |
184 | |
185 | =cut |
186 | |
187 | sub 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 | |
210 | sub _get_handle { |
642eb381 |
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 | }; |
e0d68803 |
229 | |
642eb381 |
230 | ### read the first 4 bites of the file to figure out which class to |
231 | ### use to open the file. |
e0d68803 |
232 | sysread( $tmp, $magic, 4 ); |
642eb381 |
233 | close $tmp; |
234 | } |
39713df4 |
235 | |
642eb381 |
236 | ### is it bzip? |
237 | ### if you asked specifically for bzip compression, or if we're in |
238 | ### read mode and the magic numbers add up, use bzip |
239 | if( BZIP and ( |
e0d68803 |
240 | ($compress eq COMPRESS_BZIP) or |
642eb381 |
241 | ( MODE_READ->($mode) and $magic =~ BZIP_MAGIC_NUM ) |
242 | ) |
243 | ) { |
e0d68803 |
244 | |
642eb381 |
245 | ### different reader/writer modules, different error vars... sigh |
246 | if( MODE_READ->($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 | }; |
e0d68803 |
253 | |
642eb381 |
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 | } |
e0d68803 |
262 | |
642eb381 |
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 |
e0d68803 |
268 | ) |
642eb381 |
269 | ) { |
270 | $fh = IO::Zlib->new; |
39713df4 |
271 | |
642eb381 |
272 | unless( $fh->open( $file, $mode ) ) { |
273 | $self->_error(qq[Could not create filehandle for '$file': $!]); |
274 | return; |
275 | } |
e0d68803 |
276 | |
642eb381 |
277 | ### is it plain tar? |
39713df4 |
278 | } else { |
642eb381 |
279 | $fh = IO::File->new; |
39713df4 |
280 | |
642eb381 |
281 | unless( $fh->open( $file, $mode ) ) { |
282 | $self->_error(qq[Could not create filehandle for '$file': $!]); |
283 | return; |
284 | } |
39713df4 |
285 | |
642eb381 |
286 | ### enable bin mode on tar archives |
287 | binmode $fh; |
e0d68803 |
288 | } |
642eb381 |
289 | } |
39713df4 |
290 | |
291 | return $fh; |
292 | } |
293 | |
642eb381 |
294 | |
39713df4 |
295 | sub _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 |
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 |
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 |
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 |
352 | { my %extra_args = (); |
353 | $extra_args{'name'} = $$real_name if defined $real_name; |
e0d68803 |
354 | |
355 | unless( $entry = Archive::Tar::File->new( chunk => $chunk, |
356 | %extra_args ) |
81a5970e |
357 | ) { |
358 | $self->_error( qq[Couldn't read chunk at offset $offset] ); |
b30bcf62 |
359 | next LOOP; |
81a5970e |
360 | } |
39713df4 |
361 | } |
362 | |
363 | ### ignore labels: |
364 | ### http://www.gnu.org/manual/tar/html_node/tar_139.html |
365 | next if $entry->is_label; |
366 | |
367 | if( length $entry->type and ($entry->is_file || $entry->is_longlink) ) { |
368 | |
369 | if ( $entry->is_file && !$entry->validate ) { |
370 | ### sometimes the chunk is rather fux0r3d and a whole 512 |
c3745331 |
371 | ### bytes ends up in the ->name area. |
39713df4 |
372 | ### clean it up, if need be |
373 | my $name = $entry->name; |
374 | $name = substr($name, 0, 100) if length $name > 100; |
375 | $name =~ s/\n/ /g; |
376 | |
377 | $self->_error( $name . qq[: checksum error] ); |
378 | next LOOP; |
379 | } |
380 | |
381 | my $block = BLOCK_SIZE->( $entry->size ); |
382 | |
383 | $data = $entry->get_content_by_ref; |
384 | |
385 | ### just read everything into memory |
386 | ### can't do lazy loading since IO::Zlib doesn't support 'seek' |
387 | ### this is because Compress::Zlib doesn't support it =/ |
388 | ### this reads in the whole data in one read() call. |
389 | if( $handle->read( $$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 |
393 | } |
394 | |
395 | ### throw away trailing garbage ### |
376cc5ea |
396 | substr ($$data, $entry->size) = "" if defined $$data; |
39713df4 |
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 |
431 | } elsif ( defined $real_name ) { |
432 | $entry->name( $$real_name ); |
433 | $entry->prefix(''); |
434 | undef $real_name; |
435 | } |
436 | |
642eb381 |
437 | ### skip this entry if we're filtering |
438 | if ($filter && $entry->name !~ $filter) { |
439 | next LOOP; |
e0d68803 |
440 | |
642eb381 |
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 |
e0d68803 |
443 | ### not meant for extracting. See #38932: pax_global_header extracted |
642eb381 |
444 | } elsif ( $entry->name eq PAX_HEADER ) { |
445 | next LOOP; |
446 | } |
e0d68803 |
447 | |
39713df4 |
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 | |
473 | Check if the archive contains a certain file. |
474 | It will return true if the file is in the archive, false otherwise. |
475 | |
476 | Note however, that this function does an exact match using C<eq> |
477 | on the full path. So it cannot compensate for case-insensitive file- |
478 | systems or compare 2 paths to see if they would point to the same |
479 | underlying file. |
480 | |
481 | =cut |
482 | |
483 | sub contains_file { |
484 | my $self = shift; |
01d11a1c |
485 | my $full = shift; |
e0d68803 |
486 | |
01d11a1c |
487 | return unless defined $full; |
39713df4 |
488 | |
c3745331 |
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 |
492 | return 1 if $self->_find_entry($full); |
493 | return; |
494 | } |
495 | |
496 | =head2 $tar->extract( [@filenames] ) |
497 | |
498 | Write files whose names are equivalent to any of the names in |
499 | C<@filenames> to disk, creating subdirectories as necessary. This |
500 | might not work too well under VMS. |
501 | Under MacPerl, the file's modification time will be converted to the |
502 | MacOS zero of time, and appropriate conversions will be done to the |
503 | path. However, the length of each element of the path is not |
504 | inspected to see whether it's longer than MacOS currently allows (32 |
505 | characters). |
506 | |
507 | If C<extract> is called without a list of file names, the entire |
508 | contents of the archive are extracted. |
509 | |
510 | Returns a list of filenames extracted. |
511 | |
512 | =cut |
513 | |
514 | sub extract { |
515 | my $self = shift; |
b30bcf62 |
516 | my @args = @_; |
39713df4 |
517 | my @files; |
518 | |
f38c1908 |
519 | # use the speed optimization for all extracted files |
520 | local($self->{cwd}) = cwd() unless $self->{cwd}; |
521 | |
39713df4 |
522 | ### you requested the extraction of only certian files |
b30bcf62 |
523 | if( @args ) { |
524 | for my $file ( @args ) { |
e0d68803 |
525 | |
b30bcf62 |
526 | ### it's already an object? |
527 | if( UNIVERSAL::isa( $file, 'Archive::Tar::File' ) ) { |
528 | push @files, $file; |
529 | next; |
39713df4 |
530 | |
b30bcf62 |
531 | ### go find it then |
532 | } else { |
e0d68803 |
533 | |
b30bcf62 |
534 | my $found; |
535 | for my $entry ( @{$self->_data} ) { |
536 | next unless $file eq $entry->full_path; |
e0d68803 |
537 | |
b30bcf62 |
538 | ### we found the file you're looking for |
539 | push @files, $entry; |
540 | $found++; |
541 | } |
e0d68803 |
542 | |
b30bcf62 |
543 | unless( $found ) { |
e0d68803 |
544 | return $self->_error( |
b30bcf62 |
545 | qq[Could not find '$file' in archive] ); |
546 | } |
39713df4 |
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 | |
574 | Write an entry, whose name is equivalent to the file name provided to |
48e76d2d |
575 | disk. Optionally takes a second parameter, which is the full native |
39713df4 |
576 | path (including filename) the entry will be written to. |
577 | |
578 | For example: |
579 | |
580 | $tar->extract_file( 'name/in/archive', 'name/i/want/to/give/it' ); |
581 | |
b30bcf62 |
582 | $tar->extract_file( $at_file_object, 'name/i/want/to/give/it' ); |
583 | |
39713df4 |
584 | Returns true on success, false on failure. |
585 | |
586 | =cut |
587 | |
588 | sub extract_file { |
589 | my $self = shift; |
01d11a1c |
590 | my $file = shift; return unless defined $file; |
39713df4 |
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 | |
599 | sub _extract_file { |
600 | my $self = shift; |
601 | my $entry = shift or return; |
602 | my $alt = shift; |
39713df4 |
603 | |
604 | ### you wanted an alternate extraction location ### |
605 | my $name = defined $alt ? $alt : $entry->full_path; |
606 | |
607 | ### splitpath takes a bool at the end to indicate |
608 | ### that it's splitting a dir |
7f10f74b |
609 | my ($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 |
618 | my $dir; |
619 | ### is $name an absolute path? ### |
642eb381 |
620 | if( $vol || File::Spec->file_name_is_absolute( $dirs ) ) { |
178aef9a |
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 ) { |
e0d68803 |
625 | $self->_error( |
178aef9a |
626 | q[Entry ']. $entry->full_path .q[' is an absolute path. ]. |
627 | q[Not extracting absolute paths under SECURE EXTRACT MODE] |
e0d68803 |
628 | ); |
178aef9a |
629 | return; |
630 | } |
e0d68803 |
631 | |
178aef9a |
632 | ### user asked us to, it's fine. |
642eb381 |
633 | $dir = File::Spec->catpath( $vol, $dirs, "" ); |
39713df4 |
634 | |
635 | ### it's a relative path ### |
636 | } else { |
e0d68803 |
637 | my $cwd = (ref $self and defined $self->{cwd}) |
638 | ? $self->{cwd} |
642eb381 |
639 | : cwd(); |
f5afd28d |
640 | |
f5afd28d |
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 | |
e0d68803 |
646 | if( not defined $alt and |
647 | not $INSECURE_EXTRACT_MODE |
648 | ) { |
642eb381 |
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 ) { |
e0d68803 |
653 | |
642eb381 |
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; |
e0d68803 |
660 | } |
661 | |
642eb381 |
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 ); |
e0d68803 |
670 | |
642eb381 |
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 | } |
e0d68803 |
686 | |
642eb381 |
687 | ### XXX keep a cache if possible, so the stats become cheaper: |
688 | $self->{_link_cache}->{$full_path} = 1 if ref $self; |
689 | } |
690 | } |
691 | |
2610e7a4 |
692 | ### '.' is the directory delimiter on VMS, which has to be escaped |
693 | ### or changed to '_' on vms. vmsify is used, because older versions |
694 | ### of vmspath do not handle this properly. |
695 | ### Must not add a '/' to an empty directory though. |
e0d68803 |
696 | map { length() ? VMS::Filespec::vmsify($_.'/') : $_ } @dirs if ON_VMS; |
f5afd28d |
697 | |
e0d68803 |
698 | my ($cwd_vol,$cwd_dir,$cwd_file) |
48e76d2d |
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 |
703 | ### We need to pass '' as the last elemant to catpath. Craig Berry |
704 | ### explains why (msgid <p0624083dc311ae541393@[172.16.52.1]>): |
e0d68803 |
705 | ### The root problem is that splitpath on UNIX always returns the |
f5afd28d |
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. |
e0d68803 |
714 | $dir = File::Spec->catpath( |
715 | $cwd_vol, File::Spec->catdir( @cwd, @dirs ), '' |
f5afd28d |
716 | ); |
717 | |
e0d68803 |
718 | ### catdir() returns undef if the path is longer than 255 chars on |
2610e7a4 |
719 | ### older VMS systems. |
81a5970e |
720 | unless ( defined $dir ) { |
721 | $^W && $self->_error( qq[Could not compose a path for '$dirs'\n] ); |
722 | return; |
723 | } |
724 | |
39713df4 |
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 |
735 | my $fp = $entry->full_path; |
736 | $self->_error(qq[Could not create directory '$dir' for '$fp': $@]); |
39713df4 |
737 | return; |
738 | } |
e0d68803 |
739 | |
c3745331 |
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 |
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 |
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 |
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 | |
809 | sub _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 |
826 | $err = qq[Making symbolic link '$file' to '] . |
827 | $entry->linkname .q[' failed] if $fail; |
39713df4 |
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 |
865 | sub _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 | |
893 | Returns a list of the names of all the files in the archive. |
894 | |
895 | If C<list_files()> is passed an array reference as its first argument |
896 | it returns a list of hash references containing the requested |
897 | properties of each file. The following list of properties is |
898 | supported: name, size, mtime (last modified date), mode, uid, gid, |
899 | linkname, uname, gname, devmajor, devminor, prefix. |
900 | |
901 | Passing an array reference containing only one element, 'name', is |
902 | special cased to return a list of names rather than a list of hash |
903 | references, making it equivalent to calling C<list_files> without |
904 | arguments. |
905 | |
906 | =cut |
907 | |
908 | sub 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 | |
934 | sub _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 |
943 | ### it's an object already |
944 | return $file if UNIVERSAL::isa( $file, 'Archive::Tar::File' ); |
945 | |
39713df4 |
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 | |
957 | Returns the C<Archive::Tar::File> objects matching the filenames |
958 | provided. If no filename list was passed, all C<Archive::Tar::File> |
959 | objects in the current Tar object are returned. |
960 | |
961 | Please refer to the C<Archive::Tar::File> documentation on how to |
962 | handle these objects. |
963 | |
964 | =cut |
965 | |
966 | sub 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 | |
981 | Return the content of the named file. |
982 | |
983 | =cut |
984 | |
985 | sub 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 | |
994 | Make the string $content be the content for the file named $file. |
995 | |
996 | =cut |
997 | |
998 | sub 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 | |
1007 | Rename the file of the in-memory archive to $new_name. |
1008 | |
1009 | Note that you must specify a Unix path for $new_name, since per tar |
1010 | standard, all files in the archive must be Unix paths. |
1011 | |
1012 | Returns true on success and false on failure. |
1013 | |
1014 | =cut |
1015 | |
1016 | sub 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 | |
1028 | Removes any entries with names matching any of the given filenames |
1029 | from the in-memory archive. Returns a list of C<Archive::Tar::File> |
1030 | objects that remain. |
1031 | |
1032 | =cut |
1033 | |
1034 | sub 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 | |
1048 | C<clear> clears the current in-memory archive. This effectively gives |
1049 | you a 'blank' object, ready to be filled again. Note that C<clear> |
1050 | only has effect on the object, not the underlying tarfile. |
1051 | |
1052 | =cut |
1053 | |
1054 | sub 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 | |
1066 | Write the in-memory archive to disk. The first argument can either |
1067 | be the name of a file or a reference to an already open filehandle (a |
e0d68803 |
1068 | GLOB reference). |
642eb381 |
1069 | |
e0d68803 |
1070 | The second argument is used to indicate compression. You can either |
642eb381 |
1071 | compress using C<gzip> or C<bzip2>. If you pass a digit, it's assumed |
e0d68803 |
1072 | to be the C<gzip> compression level (between 1 and 9), but the use of |
642eb381 |
1073 | constants is prefered: |
1074 | |
1075 | # write a gzip compressed file |
bef46b70 |
1076 | $tar->write( 'out.tgz', COMPRESS_GZIP ); |
642eb381 |
1077 | |
e0d68803 |
1078 | # write a bzip compressed file |
bef46b70 |
1079 | $tar->write( 'out.tbz', COMPRESS_BZIP ); |
39713df4 |
1080 | |
1081 | Note that when you pass in a filehandle, the compression argument |
1082 | is ignored, as all files are printed verbatim to your filehandle. |
1083 | If you wish to enable compression with filehandles, use an |
642eb381 |
1084 | C<IO::Zlib> or C<IO::Compress::Bzip2> filehandle instead. |
39713df4 |
1085 | |
1086 | The third argument is an optional prefix. All files will be tucked |
1087 | away 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 |
1089 | will be written to the archive as 'foo/a' and 'foo/b'. |
1090 | |
1091 | If no arguments are given, C<write> returns the entire formatted |
1092 | archive as a string, which could be useful if you'd like to stuff the |
1093 | archive into a socket or a pipe to gzip or something. |
1094 | |
642eb381 |
1095 | |
39713df4 |
1096 | =cut |
1097 | |
1098 | sub 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 = ''; |
e0d68803 |
1104 | |
39713df4 |
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 } |
e0d68803 |
1110 | : $HAS_IO_STRING ? IO::String->new |
39713df4 |
1111 | : __PACKAGE__->no_string_support(); |
1112 | |
e0d68803 |
1113 | ### Addresses: #41798: Nonempty $\ when writing a TAR file produces a |
1114 | ### corrupt TAR file. Must clear out $\ to make sure no garbage is |
1115 | ### printed to the archive |
1116 | local $\; |
39713df4 |
1117 | |
1118 | for my $entry ( @{$self->_data} ) { |
1119 | ### entries to be written to the tarfile ### |
1120 | my @write_me; |
1121 | |
1122 | ### only now will we change the object to reflect the current state |
1123 | ### of the name and prefix fields -- this needs to be limited to |
1124 | ### write() only! |
1125 | my $clone = $entry->clone; |
1126 | |
1127 | |
e0d68803 |
1128 | ### so, if you don't want use to use the prefix, we'll stuff |
39713df4 |
1129 | ### everything in the name field instead |
1130 | if( $DO_NOT_USE_PREFIX ) { |
1131 | |
1132 | ### you might have an extended prefix, if so, set it in the clone |
1133 | ### XXX is ::Unix right? |
1134 | $clone->name( length $ext_prefix |
1135 | ? File::Spec::Unix->catdir( $ext_prefix, |
1136 | $clone->full_path) |
1137 | : $clone->full_path ); |
1138 | $clone->prefix( '' ); |
1139 | |
1140 | ### otherwise, we'll have to set it properly -- prefix part in the |
1141 | ### prefix and name part in the name field. |
1142 | } else { |
1143 | |
1144 | ### split them here, not before! |
1145 | my ($prefix,$name) = $clone->_prefix_and_file( $clone->full_path ); |
1146 | |
1147 | ### you might have an extended prefix, if so, set it in the clone |
1148 | ### XXX is ::Unix right? |
1149 | $prefix = File::Spec::Unix->catdir( $ext_prefix, $prefix ) |
1150 | if length $ext_prefix; |
1151 | |
1152 | $clone->prefix( $prefix ); |
1153 | $clone->name( $name ); |
1154 | } |
1155 | |
1156 | ### names are too long, and will get truncated if we don't add a |
1157 | ### '@LongLink' file... |
1158 | my $make_longlink = ( length($clone->name) > NAME_LENGTH or |
1159 | length($clone->prefix) > PREFIX_LENGTH |
1160 | ) || 0; |
1161 | |
1162 | ### perhaps we need to make a longlink file? |
1163 | if( $make_longlink ) { |
1164 | my $longlink = Archive::Tar::File->new( |
1165 | data => LONGLINK_NAME, |
1166 | $clone->full_path, |
1167 | { type => LONGLINK } |
1168 | ); |
1169 | |
1170 | unless( $longlink ) { |
1171 | $self->_error( qq[Could not create 'LongLink' entry for ] . |
1172 | qq[oversize file '] . $clone->full_path ."'" ); |
1173 | return; |
1174 | }; |
1175 | |
1176 | push @write_me, $longlink; |
1177 | } |
1178 | |
1179 | push @write_me, $clone; |
1180 | |
1181 | ### write the one, optionally 2 a::t::file objects to the handle |
1182 | for my $clone (@write_me) { |
1183 | |
1184 | ### if the file is a symlink, there are 2 options: |
1185 | ### either we leave the symlink intact, but then we don't write any |
1186 | ### data OR we follow the symlink, which means we actually make a |
1187 | ### copy. if we do the latter, we have to change the TYPE of the |
1188 | ### clone to 'FILE' |
1189 | my $link_ok = $clone->is_symlink && $Archive::Tar::FOLLOW_SYMLINK; |
1190 | my $data_ok = !$clone->is_symlink && $clone->has_content; |
1191 | |
1192 | ### downgrade to a 'normal' file if it's a symlink we're going to |
1193 | ### treat as a regular file |
1194 | $clone->_downgrade_to_plainfile if $link_ok; |
1195 | |
1196 | ### get the header for this block |
1197 | my $header = $self->_format_tar_entry( $clone ); |
1198 | unless( $header ) { |
1199 | $self->_error(q[Could not format header for: ] . |
1200 | $clone->full_path ); |
1201 | return; |
1202 | } |
1203 | |
1204 | unless( print $handle $header ) { |
1205 | $self->_error(q[Could not write header for: ] . |
1206 | $clone->full_path); |
1207 | return; |
1208 | } |
1209 | |
1210 | if( $link_ok or $data_ok ) { |
1211 | unless( print $handle $clone->data ) { |
1212 | $self->_error(q[Could not write data for: ] . |
1213 | $clone->full_path); |
1214 | return; |
1215 | } |
1216 | |
1217 | ### pad the end of the clone if required ### |
1218 | print $handle TAR_PAD->( $clone->size ) if $clone->size % BLOCK |
1219 | } |
1220 | |
1221 | } ### done writing these entries |
1222 | } |
1223 | |
1224 | ### write the end markers ### |
1225 | print $handle TAR_END x 2 or |
1226 | return $self->_error( qq[Could not write tar end markers] ); |
b30bcf62 |
1227 | |
39713df4 |
1228 | ### did you want it written to a file, or returned as a string? ### |
b30bcf62 |
1229 | my $rv = length($file) ? 1 |
39713df4 |
1230 | : $HAS_PERLIO ? $dummy |
b30bcf62 |
1231 | : do { seek $handle, 0, 0; local $/; <$handle> }; |
1232 | |
1233 | ### make sure to close the handle; |
1234 | close $handle; |
e0d68803 |
1235 | |
b30bcf62 |
1236 | return $rv; |
39713df4 |
1237 | } |
1238 | |
1239 | sub _format_tar_entry { |
1240 | my $self = shift; |
1241 | my $entry = shift or return; |
1242 | my $ext_prefix = shift; $ext_prefix = '' unless defined $ext_prefix; |
1243 | my $no_prefix = shift || 0; |
1244 | |
1245 | my $file = $entry->name; |
1246 | my $prefix = $entry->prefix; $prefix = '' unless defined $prefix; |
1247 | |
1248 | ### remove the prefix from the file name |
1249 | ### not sure if this is still neeeded --kane |
1250 | ### no it's not -- Archive::Tar::File->_new_from_file will take care of |
1251 | ### this for us. Even worse, this would break if we tried to add a file |
1252 | ### like x/x. |
1253 | #if( length $prefix ) { |
1254 | # $file =~ s/^$match//; |
1255 | #} |
1256 | |
1257 | $prefix = File::Spec::Unix->catdir($ext_prefix, $prefix) |
1258 | if length $ext_prefix; |
1259 | |
1260 | ### not sure why this is... ### |
1261 | my $l = PREFIX_LENGTH; # is ambiguous otherwise... |
1262 | substr ($prefix, 0, -$l) = "" if length $prefix >= PREFIX_LENGTH; |
1263 | |
1264 | my $f1 = "%06o"; my $f2 = "%11o"; |
1265 | |
1266 | ### this might be optimizable with a 'changed' flag in the file objects ### |
1267 | my $tar = pack ( |
1268 | PACK, |
1269 | $file, |
1270 | |
1271 | (map { sprintf( $f1, $entry->$_() ) } qw[mode uid gid]), |
1272 | (map { sprintf( $f2, $entry->$_() ) } qw[size mtime]), |
1273 | |
1274 | "", # checksum field - space padded a bit down |
1275 | |
1276 | (map { $entry->$_() } qw[type linkname magic]), |
1277 | |
1278 | $entry->version || TAR_VERSION, |
1279 | |
1280 | (map { $entry->$_() } qw[uname gname]), |
1281 | (map { sprintf( $f1, $entry->$_() ) } qw[devmajor devminor]), |
1282 | |
1283 | ($no_prefix ? '' : $prefix) |
1284 | ); |
1285 | |
1286 | ### add the checksum ### |
1287 | substr($tar,148,7) = sprintf("%6o\0", unpack("%16C*",$tar)); |
1288 | |
1289 | return $tar; |
1290 | } |
1291 | |
1292 | =head2 $tar->add_files( @filenamelist ) |
1293 | |
1294 | Takes a list of filenames and adds them to the in-memory archive. |
1295 | |
1296 | The path to the file is automatically converted to a Unix like |
1297 | equivalent for use in the archive, and, if on MacOS, the file's |
1298 | modification time is converted from the MacOS epoch to the Unix epoch. |
1299 | So tar archives created on MacOS with B<Archive::Tar> can be read |
1300 | both with I<tar> on Unix and applications like I<suntar> or |
1301 | I<Stuffit Expander> on MacOS. |
1302 | |
1303 | Be aware that the file's type/creator and resource fork will be lost, |
1304 | which is usually what you want in cross-platform archives. |
1305 | |
2610e7a4 |
1306 | Instead of a filename, you can also pass it an existing C<Archive::Tar::File> |
1307 | object from, for example, another archive. The object will be clone, and |
1308 | effectively be a copy of the original, not an alias. |
1309 | |
39713df4 |
1310 | Returns a list of C<Archive::Tar::File> objects that were just added. |
1311 | |
1312 | =cut |
1313 | |
1314 | sub add_files { |
1315 | my $self = shift; |
1316 | my @files = @_ or return; |
1317 | |
1318 | my @rv; |
1319 | for my $file ( @files ) { |
2610e7a4 |
1320 | |
1321 | ### you passed an Archive::Tar::File object |
1322 | ### clone it so we don't accidentally have a reference to |
1323 | ### an object from another archive |
1324 | if( UNIVERSAL::isa( $file,'Archive::Tar::File' ) ) { |
e0d68803 |
1325 | push @rv, $file->clone; |
2610e7a4 |
1326 | next; |
1327 | } |
e0d68803 |
1328 | |
c3745331 |
1329 | unless( -e $file || -l $file ) { |
39713df4 |
1330 | $self->_error( qq[No such file: '$file'] ); |
1331 | next; |
1332 | } |
1333 | |
1334 | my $obj = Archive::Tar::File->new( file => $file ); |
1335 | unless( $obj ) { |
1336 | $self->_error( qq[Unable to add file: '$file'] ); |
1337 | next; |
1338 | } |
1339 | |
1340 | push @rv, $obj; |
1341 | } |
1342 | |
1343 | push @{$self->{_data}}, @rv; |
1344 | |
1345 | return @rv; |
1346 | } |
1347 | |
1348 | =head2 $tar->add_data ( $filename, $data, [$opthashref] ) |
1349 | |
1350 | Takes a filename, a scalar full of data and optionally a reference to |
1351 | a hash with specific options. |
1352 | |
1353 | Will add a file to the in-memory archive, with name C<$filename> and |
1354 | content C<$data>. Specific properties can be set using C<$opthashref>. |
1355 | The following list of properties is supported: name, size, mtime |
1356 | (last modified date), mode, uid, gid, linkname, uname, gname, |
b3200c5d |
1357 | devmajor, devminor, prefix, type. (On MacOS, the file's path and |
39713df4 |
1358 | modification times are converted to Unix equivalents.) |
1359 | |
b3200c5d |
1360 | Valid values for the file type are the following constants defined in |
1361 | Archive::Tar::Constants: |
1362 | |
1363 | =over 4 |
1364 | |
1365 | =item FILE |
1366 | |
1367 | Regular file. |
1368 | |
1369 | =item HARDLINK |
1370 | |
1371 | =item SYMLINK |
1372 | |
1373 | Hard and symbolic ("soft") links; linkname should specify target. |
1374 | |
1375 | =item CHARDEV |
1376 | |
1377 | =item BLOCKDEV |
1378 | |
1379 | Character and block devices. devmajor and devminor should specify the major |
1380 | and minor device numbers. |
1381 | |
1382 | =item DIR |
1383 | |
1384 | Directory. |
1385 | |
1386 | =item FIFO |
1387 | |
1388 | FIFO (named pipe). |
1389 | |
1390 | =item SOCKET |
1391 | |
1392 | Socket. |
1393 | |
1394 | =back |
1395 | |
39713df4 |
1396 | Returns the C<Archive::Tar::File> object that was just added, or |
1397 | C<undef> on failure. |
1398 | |
1399 | =cut |
1400 | |
1401 | sub add_data { |
1402 | my $self = shift; |
1403 | my ($file, $data, $opt) = @_; |
1404 | |
1405 | my $obj = Archive::Tar::File->new( data => $file, $data, $opt ); |
1406 | unless( $obj ) { |
1407 | $self->_error( qq[Unable to add file: '$file'] ); |
1408 | return; |
1409 | } |
1410 | |
1411 | push @{$self->{_data}}, $obj; |
1412 | |
1413 | return $obj; |
1414 | } |
1415 | |
1416 | =head2 $tar->error( [$BOOL] ) |
1417 | |
1418 | Returns the current errorstring (usually, the last error reported). |
1419 | If a true value was specified, it will give the C<Carp::longmess> |
1420 | equivalent of the error, in effect giving you a stacktrace. |
1421 | |
1422 | For backwards compatibility, this error is also available as |
1423 | C<$Archive::Tar::error> although it is much recommended you use the |
1424 | method call instead. |
1425 | |
1426 | =cut |
1427 | |
1428 | { |
1429 | $error = ''; |
1430 | my $longmess; |
1431 | |
1432 | sub _error { |
1433 | my $self = shift; |
1434 | my $msg = $error = shift; |
1435 | $longmess = Carp::longmess($error); |
1436 | |
1437 | ### set Archive::Tar::WARN to 0 to disable printing |
1438 | ### of errors |
1439 | if( $WARN ) { |
1440 | carp $DEBUG ? $longmess : $msg; |
1441 | } |
1442 | |
1443 | return; |
1444 | } |
1445 | |
1446 | sub error { |
1447 | my $self = shift; |
1448 | return shift() ? $longmess : $error; |
1449 | } |
1450 | } |
1451 | |
f38c1908 |
1452 | =head2 $tar->setcwd( $cwd ); |
1453 | |
1454 | C<Archive::Tar> needs to know the current directory, and it will run |
e0d68803 |
1455 | C<Cwd::cwd()> I<every> time it extracts a I<relative> entry from the |
f38c1908 |
1456 | tarfile and saves it in the file system. (As of version 1.30, however, |
e0d68803 |
1457 | C<Archive::Tar> will use the speed optimization described below |
f38c1908 |
1458 | automatically, so it's only relevant if you're using C<extract_file()>). |
1459 | |
1460 | Since C<Archive::Tar> doesn't change the current directory internally |
1461 | while it is extracting the items in a tarball, all calls to C<Cwd::cwd()> |
1462 | can be avoided if we can guarantee that the current directory doesn't |
1463 | get changed externally. |
1464 | |
1465 | To use this performance boost, set the current directory via |
1466 | |
1467 | use Cwd; |
1468 | $tar->setcwd( cwd() ); |
1469 | |
1470 | once before calling a function like C<extract_file> and |
1471 | C<Archive::Tar> will use the current directory setting from then on |
e0d68803 |
1472 | and won't call C<Cwd::cwd()> internally. |
f38c1908 |
1473 | |
1474 | To switch back to the default behaviour, use |
1475 | |
1476 | $tar->setcwd( undef ); |
1477 | |
1478 | and C<Archive::Tar> will call C<Cwd::cwd()> internally again. |
1479 | |
1480 | If you're using C<Archive::Tar>'s C<exract()> method, C<setcwd()> will |
1481 | be called for you. |
1482 | |
e0d68803 |
1483 | =cut |
f38c1908 |
1484 | |
1485 | sub setcwd { |
1486 | my $self = shift; |
1487 | my $cwd = shift; |
1488 | |
1489 | $self->{cwd} = $cwd; |
1490 | } |
39713df4 |
1491 | |
39713df4 |
1492 | =head1 Class Methods |
1493 | |
642eb381 |
1494 | =head2 Archive::Tar->create_archive($file, $compressed, @filelist) |
39713df4 |
1495 | |
1496 | Creates a tar file from the list of files provided. The first |
1497 | argument can either be the name of the tar file to create or a |
1498 | reference to an open file handle (e.g. a GLOB reference). |
1499 | |
e0d68803 |
1500 | The second argument is used to indicate compression. You can either |
642eb381 |
1501 | compress using C<gzip> or C<bzip2>. If you pass a digit, it's assumed |
e0d68803 |
1502 | to be the C<gzip> compression level (between 1 and 9), but the use of |
642eb381 |
1503 | constants is prefered: |
1504 | |
1505 | # write a gzip compressed file |
bef46b70 |
1506 | Archive::Tar->create_archive( 'out.tgz', COMPRESS_GZIP, @filelist ); |
642eb381 |
1507 | |
e0d68803 |
1508 | # write a bzip compressed file |
bef46b70 |
1509 | Archive::Tar->create_archive( 'out.tbz', COMPRESS_BZIP, @filelist ); |
39713df4 |
1510 | |
1511 | Note that when you pass in a filehandle, the compression argument |
1512 | is ignored, as all files are printed verbatim to your filehandle. |
1513 | If you wish to enable compression with filehandles, use an |
642eb381 |
1514 | C<IO::Zlib> or C<IO::Compress::Bzip2> filehandle instead. |
39713df4 |
1515 | |
1516 | The remaining arguments list the files to be included in the tar file. |
1517 | These files must all exist. Any files which don't exist or can't be |
1518 | read are silently ignored. |
1519 | |
1520 | If the archive creation fails for any reason, C<create_archive> will |
1521 | return false. Please use the C<error> method to find the cause of the |
1522 | failure. |
1523 | |
1524 | Note that this method does not write C<on the fly> as it were; it |
1525 | still reads all the files into memory before writing out the archive. |
1526 | Consult the FAQ below if this is a problem. |
1527 | |
1528 | =cut |
1529 | |
1530 | sub create_archive { |
1531 | my $class = shift; |
1532 | |
1533 | my $file = shift; return unless defined $file; |
1534 | my $gzip = shift || 0; |
1535 | my @files = @_; |
1536 | |
1537 | unless( @files ) { |
1538 | return $class->_error( qq[Cowardly refusing to create empty archive!] ); |
1539 | } |
1540 | |
1541 | my $tar = $class->new; |
1542 | $tar->add_files( @files ); |
1543 | return $tar->write( $file, $gzip ); |
1544 | } |
1545 | |
642eb381 |
1546 | =head2 Archive::Tar->iter( $filename, [ $compressed, {opt => $val} ] ) |
1547 | |
1548 | Returns an iterator function that reads the tar file without loading |
1549 | it all in memory. Each time the function is called it will return the |
1550 | next file in the tarball. The files are returned as |
1551 | C<Archive::Tar::File> objects. The iterator function returns the |
1552 | empty list once it has exhausted the the files contained. |
1553 | |
1554 | The second argument can be a hash reference with options, which are |
1555 | identical to the arguments passed to C<read()>. |
1556 | |
1557 | Example usage: |
1558 | |
1559 | my $next = Archive::Tar->iter( "example.tar.gz", 1, {filter => qr/\.pm$/} ); |
1560 | |
1561 | while( my $f = $next->() ) { |
1562 | print $f->name, "\n"; |
1563 | |
1564 | $f->extract or warn "Extraction failed"; |
e0d68803 |
1565 | |
642eb381 |
1566 | # .... |
1567 | } |
1568 | |
1569 | =cut |
1570 | |
1571 | |
1572 | sub iter { |
1573 | my $class = shift; |
1574 | my $filename = shift or return; |
1575 | my $compressed = shift or 0; |
1576 | my $opts = shift || {}; |
1577 | |
1578 | ### get a handle to read from. |
1579 | my $handle = $class->_get_handle( |
e0d68803 |
1580 | $filename, |
1581 | $compressed, |
642eb381 |
1582 | READ_ONLY->( ZLIB ) |
1583 | ) or return; |
1584 | |
1585 | my @data; |
1586 | return sub { |
1587 | return shift(@data) if @data; # more than one file returned? |
1588 | return unless $handle; # handle exhausted? |
1589 | |
1590 | ### read data, should only return file |
1591 | @data = @{ $class->_read_tar($handle, { %$opts, limit => 1 }) }; |
1592 | |
1593 | ### return one piece of data |
1594 | return shift(@data) if @data; |
e0d68803 |
1595 | |
642eb381 |
1596 | ### data is exhausted, free the filehandle |
1597 | undef $handle; |
1598 | return; |
1599 | }; |
1600 | } |
1601 | |
1602 | =head2 Archive::Tar->list_archive($file, $compressed, [\@properties]) |
39713df4 |
1603 | |
1604 | Returns a list of the names of all the files in the archive. The |
1605 | first argument can either be the name of the tar file to list or a |
1606 | reference to an open file handle (e.g. a GLOB reference). |
1607 | |
1608 | If C<list_archive()> is passed an array reference as its third |
1609 | argument it returns a list of hash references containing the requested |
1610 | properties of each file. The following list of properties is |
e0d68803 |
1611 | supported: full_path, name, size, mtime (last modified date), mode, |
b3200c5d |
1612 | uid, gid, linkname, uname, gname, devmajor, devminor, prefix. |
1613 | |
1614 | See C<Archive::Tar::File> for details about supported properties. |
39713df4 |
1615 | |
1616 | Passing an array reference containing only one element, 'name', is |
1617 | special cased to return a list of names rather than a list of hash |
1618 | references. |
1619 | |
1620 | =cut |
1621 | |
1622 | sub list_archive { |
1623 | my $class = shift; |
1624 | my $file = shift; return unless defined $file; |
1625 | my $gzip = shift || 0; |
1626 | |
1627 | my $tar = $class->new($file, $gzip); |
1628 | return unless $tar; |
1629 | |
1630 | return $tar->list_files( @_ ); |
1631 | } |
1632 | |
642eb381 |
1633 | =head2 Archive::Tar->extract_archive($file, $compressed) |
39713df4 |
1634 | |
1635 | Extracts the contents of the tar file. The first argument can either |
1636 | be the name of the tar file to create or a reference to an open file |
1637 | handle (e.g. a GLOB reference). All relative paths in the tar file will |
1638 | be created underneath the current working directory. |
1639 | |
1640 | C<extract_archive> will return a list of files it extracted. |
1641 | If the archive extraction fails for any reason, C<extract_archive> |
1642 | will return false. Please use the C<error> method to find the cause |
1643 | of the failure. |
1644 | |
1645 | =cut |
1646 | |
1647 | sub extract_archive { |
1648 | my $class = shift; |
1649 | my $file = shift; return unless defined $file; |
1650 | my $gzip = shift || 0; |
1651 | |
1652 | my $tar = $class->new( ) or return; |
1653 | |
1654 | return $tar->read( $file, $gzip, { extract => 1 } ); |
1655 | } |
1656 | |
f5695358 |
1657 | =head2 $bool = Archive::Tar->has_io_string |
1658 | |
1659 | Returns true if we currently have C<IO::String> support loaded. |
1660 | |
e0d68803 |
1661 | Either C<IO::String> or C<perlio> support is needed to support writing |
f5695358 |
1662 | stringified archives. Currently, C<perlio> is the preferred method, if |
1663 | available. |
1664 | |
1665 | See the C<GLOBAL VARIABLES> section to see how to change this preference. |
1666 | |
1667 | =cut |
1668 | |
1669 | sub has_io_string { return $HAS_IO_STRING; } |
1670 | |
1671 | =head2 $bool = Archive::Tar->has_perlio |
1672 | |
1673 | Returns true if we currently have C<perlio> support loaded. |
1674 | |
e0d68803 |
1675 | This requires C<perl-5.8> or higher, compiled with C<perlio> |
f5695358 |
1676 | |
e0d68803 |
1677 | Either C<IO::String> or C<perlio> support is needed to support writing |
f5695358 |
1678 | stringified archives. Currently, C<perlio> is the preferred method, if |
1679 | available. |
1680 | |
1681 | See the C<GLOBAL VARIABLES> section to see how to change this preference. |
1682 | |
1683 | =cut |
1684 | |
1685 | sub has_perlio { return $HAS_PERLIO; } |
1686 | |
1687 | =head2 $bool = Archive::Tar->has_zlib_support |
1688 | |
1689 | Returns true if C<Archive::Tar> can extract C<zlib> compressed archives |
1690 | |
1691 | =cut |
1692 | |
1693 | sub has_zlib_support { return ZLIB } |
1694 | |
1695 | =head2 $bool = Archive::Tar->has_bzip2_support |
1696 | |
1697 | Returns true if C<Archive::Tar> can extract C<bzip2> compressed archives |
1698 | |
1699 | =cut |
1700 | |
1701 | sub has_bzip2_support { return BZIP } |
1702 | |
39713df4 |
1703 | =head2 Archive::Tar->can_handle_compressed_files |
1704 | |
1705 | A simple checking routine, which will return true if C<Archive::Tar> |
642eb381 |
1706 | is able to uncompress compressed archives on the fly with C<IO::Zlib> |
1707 | and C<IO::Compress::Bzip2> or false if not both are installed. |
39713df4 |
1708 | |
1709 | You can use this as a shortcut to determine whether C<Archive::Tar> |
1710 | will do what you think before passing compressed archives to its |
1711 | C<read> method. |
1712 | |
1713 | =cut |
1714 | |
642eb381 |
1715 | sub can_handle_compressed_files { return ZLIB && BZIP ? 1 : 0 } |
39713df4 |
1716 | |
1717 | sub no_string_support { |
1718 | croak("You have to install IO::String to support writing archives to strings"); |
1719 | } |
1720 | |
1721 | 1; |
1722 | |
1723 | __END__ |
1724 | |
1725 | =head1 GLOBAL VARIABLES |
1726 | |
1727 | =head2 $Archive::Tar::FOLLOW_SYMLINK |
1728 | |
1729 | Set this variable to C<1> to make C<Archive::Tar> effectively make a |
1730 | copy of the file when extracting. Default is C<0>, which |
1731 | means the symlink stays intact. Of course, you will have to pack the |
1732 | file linked to as well. |
1733 | |
1734 | This option is checked when you write out the tarfile using C<write> |
1735 | or C<create_archive>. |
1736 | |
1737 | This works just like C</bin/tar>'s C<-h> option. |
1738 | |
1739 | =head2 $Archive::Tar::CHOWN |
1740 | |
1741 | By default, C<Archive::Tar> will try to C<chown> your files if it is |
1742 | able to. In some cases, this may not be desired. In that case, set |
1743 | this variable to C<0> to disable C<chown>-ing, even if it were |
1744 | possible. |
1745 | |
1746 | The default is C<1>. |
1747 | |
1748 | =head2 $Archive::Tar::CHMOD |
1749 | |
1750 | By default, C<Archive::Tar> will try to C<chmod> your files to |
1751 | whatever mode was specified for the particular file in the archive. |
1752 | In some cases, this may not be desired. In that case, set this |
1753 | variable to C<0> to disable C<chmod>-ing. |
1754 | |
1755 | The default is C<1>. |
1756 | |
1757 | =head2 $Archive::Tar::DO_NOT_USE_PREFIX |
1758 | |
e0d68803 |
1759 | By default, C<Archive::Tar> will try to put paths that are over |
f38c1908 |
1760 | 100 characters in the C<prefix> field of your tar header, as |
e0d68803 |
1761 | defined per POSIX-standard. However, some (older) tar programs |
1762 | do not implement this spec. To retain compatibility with these older |
1763 | or non-POSIX compliant versions, you can set the C<$DO_NOT_USE_PREFIX> |
1764 | variable to a true value, and C<Archive::Tar> will use an alternate |
1765 | way of dealing with paths over 100 characters by using the |
f38c1908 |
1766 | C<GNU Extended Header> feature. |
1767 | |
1768 | Note that clients who do not support the C<GNU Extended Header> |
1769 | feature will not be able to read these archives. Such clients include |
1770 | tars on C<Solaris>, C<Irix> and C<AIX>. |
39713df4 |
1771 | |
1772 | The default is C<0>. |
1773 | |
1774 | =head2 $Archive::Tar::DEBUG |
1775 | |
1776 | Set this variable to C<1> to always get the C<Carp::longmess> output |
1777 | of the warnings, instead of the regular C<carp>. This is the same |
1778 | message you would get by doing: |
1779 | |
1780 | $tar->error(1); |
1781 | |
1782 | Defaults to C<0>. |
1783 | |
1784 | =head2 $Archive::Tar::WARN |
1785 | |
1786 | Set this variable to C<0> if you do not want any warnings printed. |
1787 | Personally I recommend against doing this, but people asked for the |
1788 | option. Also, be advised that this is of course not threadsafe. |
1789 | |
1790 | Defaults to C<1>. |
1791 | |
1792 | =head2 $Archive::Tar::error |
1793 | |
1794 | Holds the last reported error. Kept for historical reasons, but its |
1795 | use is very much discouraged. Use the C<error()> method instead: |
1796 | |
1797 | warn $tar->error unless $tar->extract; |
1798 | |
178aef9a |
1799 | =head2 $Archive::Tar::INSECURE_EXTRACT_MODE |
1800 | |
1801 | This variable indicates whether C<Archive::Tar> should allow |
1802 | files to be extracted outside their current working directory. |
1803 | |
1804 | Allowing this could have security implications, as a malicious |
1805 | tar archive could alter or replace any file the extracting user |
e0d68803 |
1806 | has permissions to. Therefor, the default is to not allow |
1807 | insecure extractions. |
178aef9a |
1808 | |
e0d68803 |
1809 | If you trust the archive, or have other reasons to allow the |
1810 | archive to write files outside your current working directory, |
178aef9a |
1811 | set this variable to C<true>. |
1812 | |
1813 | Note that this is a backwards incompatible change from version |
1814 | C<1.36> and before. |
1815 | |
39713df4 |
1816 | =head2 $Archive::Tar::HAS_PERLIO |
1817 | |
e0d68803 |
1818 | This variable holds a boolean indicating if we currently have |
39713df4 |
1819 | C<perlio> support loaded. This will be enabled for any perl |
e0d68803 |
1820 | greater than C<5.8> compiled with C<perlio>. |
39713df4 |
1821 | |
1822 | If you feel strongly about disabling it, set this variable to |
1823 | C<false>. Note that you will then need C<IO::String> installed |
1824 | to support writing stringified archives. |
1825 | |
1826 | Don't change this variable unless you B<really> know what you're |
1827 | doing. |
1828 | |
1829 | =head2 $Archive::Tar::HAS_IO_STRING |
1830 | |
e0d68803 |
1831 | This variable holds a boolean indicating if we currently have |
39713df4 |
1832 | C<IO::String> support loaded. This will be enabled for any perl |
1833 | that has a loadable C<IO::String> module. |
1834 | |
1835 | If you feel strongly about disabling it, set this variable to |
1836 | C<false>. Note that you will then need C<perlio> support from |
1837 | your perl to be able to write stringified archives. |
1838 | |
1839 | Don't change this variable unless you B<really> know what you're |
1840 | doing. |
1841 | |
1842 | =head1 FAQ |
1843 | |
1844 | =over 4 |
1845 | |
1846 | =item What's the minimum perl version required to run Archive::Tar? |
1847 | |
1848 | You will need perl version 5.005_03 or newer. |
1849 | |
1850 | =item Isn't Archive::Tar slow? |
1851 | |
1852 | Yes it is. It's pure perl, so it's a lot slower then your C</bin/tar> |
1853 | However, it's very portable. If speed is an issue, consider using |
1854 | C</bin/tar> instead. |
1855 | |
1856 | =item Isn't Archive::Tar heavier on memory than /bin/tar? |
1857 | |
1858 | Yes it is, see previous answer. Since C<Compress::Zlib> and therefore |
1859 | C<IO::Zlib> doesn't support C<seek> on their filehandles, there is little |
1860 | choice but to read the archive into memory. |
1861 | This is ok if you want to do in-memory manipulation of the archive. |
642eb381 |
1862 | |
39713df4 |
1863 | If you just want to extract, use the C<extract_archive> class method |
1864 | instead. It will optimize and write to disk immediately. |
1865 | |
642eb381 |
1866 | Another option is to use the C<iter> class method to iterate over |
1867 | the files in the tarball without reading them all in memory at once. |
1868 | |
1869 | =item Can you lazy-load data instead? |
39713df4 |
1870 | |
642eb381 |
1871 | In some cases, yes. You can use the C<iter> class method to iterate |
1872 | over the files in the tarball without reading them all in memory at once. |
39713df4 |
1873 | |
1874 | =item How much memory will an X kb tar file need? |
1875 | |
1876 | Probably more than X kb, since it will all be read into memory. If |
1877 | this is a problem, and you don't need to do in memory manipulation |
e0d68803 |
1878 | of the archive, consider using the C<iter> class method, or C</bin/tar> |
642eb381 |
1879 | instead. |
39713df4 |
1880 | |
1881 | =item What do you do with unsupported filetypes in an archive? |
1882 | |
1883 | C<Unix> has a few filetypes that aren't supported on other platforms, |
1884 | like C<Win32>. If we encounter a C<hardlink> or C<symlink> we'll just |
1885 | try to make a copy of the original file, rather than throwing an error. |
1886 | |
1887 | This does require you to read the entire archive in to memory first, |
1888 | since otherwise we wouldn't know what data to fill the copy with. |
e0d68803 |
1889 | (This means that you cannot use the class methods, including C<iter> |
1890 | on archives that have incompatible filetypes and still expect things |
642eb381 |
1891 | to work). |
39713df4 |
1892 | |
1893 | For other filetypes, like C<chardevs> and C<blockdevs> we'll warn that |
1894 | the extraction of this particular item didn't work. |
1895 | |
f38c1908 |
1896 | =item I'm using WinZip, or some other non-POSIX client, and files are not being extracted properly! |
1897 | |
1898 | By default, C<Archive::Tar> is in a completely POSIX-compatible |
1899 | mode, which uses the POSIX-specification of C<tar> to store files. |
1900 | For paths greather than 100 characters, this is done using the |
1901 | C<POSIX header prefix>. Non-POSIX-compatible clients may not support |
1902 | this part of the specification, and may only support the C<GNU Extended |
1903 | Header> functionality. To facilitate those clients, you can set the |
e0d68803 |
1904 | C<$Archive::Tar::DO_NOT_USE_PREFIX> variable to C<true>. See the |
f38c1908 |
1905 | C<GLOBAL VARIABLES> section for details on this variable. |
1906 | |
c3745331 |
1907 | Note that GNU tar earlier than version 1.14 does not cope well with |
1908 | the C<POSIX header prefix>. If you use such a version, consider setting |
1909 | the C<$Archive::Tar::DO_NOT_USE_PREFIX> variable to C<true>. |
1910 | |
b30bcf62 |
1911 | =item How do I extract only files that have property X from an archive? |
1912 | |
1913 | Sometimes, you might not wish to extract a complete archive, just |
1914 | the files that are relevant to you, based on some criteria. |
1915 | |
1916 | You can do this by filtering a list of C<Archive::Tar::File> objects |
1917 | based on your criteria. For example, to extract only files that have |
1918 | the string C<foo> in their title, you would use: |
1919 | |
e0d68803 |
1920 | $tar->extract( |
b30bcf62 |
1921 | grep { $_->full_path =~ /foo/ } $tar->get_files |
e0d68803 |
1922 | ); |
b30bcf62 |
1923 | |
1924 | This way, you can filter on any attribute of the files in the archive. |
1925 | Consult the C<Archive::Tar::File> documentation on how to use these |
1926 | objects. |
1927 | |
81a5970e |
1928 | =item How do I access .tar.Z files? |
1929 | |
1930 | The C<Archive::Tar> module can optionally use C<Compress::Zlib> (via |
1931 | the C<IO::Zlib> module) to access tar files that have been compressed |
1932 | with C<gzip>. Unfortunately tar files compressed with the Unix C<compress> |
1933 | utility cannot be read by C<Compress::Zlib> and so cannot be directly |
1934 | accesses by C<Archive::Tar>. |
1935 | |
1936 | If the C<uncompress> or C<gunzip> programs are available, you can use |
1937 | one of these workarounds to read C<.tar.Z> files from C<Archive::Tar> |
1938 | |
1939 | Firstly with C<uncompress> |
1940 | |
1941 | use Archive::Tar; |
1942 | |
1943 | open F, "uncompress -c $filename |"; |
1944 | my $tar = Archive::Tar->new(*F); |
1945 | ... |
1946 | |
1947 | and this with C<gunzip> |
1948 | |
1949 | use Archive::Tar; |
1950 | |
1951 | open F, "gunzip -c $filename |"; |
1952 | my $tar = Archive::Tar->new(*F); |
1953 | ... |
1954 | |
1955 | Similarly, if the C<compress> program is available, you can use this to |
1956 | write a C<.tar.Z> file |
1957 | |
1958 | use Archive::Tar; |
1959 | use IO::File; |
1960 | |
1961 | my $fh = new IO::File "| compress -c >$filename"; |
1962 | my $tar = Archive::Tar->new(); |
1963 | ... |
1964 | $tar->write($fh); |
1965 | $fh->close ; |
1966 | |
01d11a1c |
1967 | =item How do I handle Unicode strings? |
1968 | |
1969 | C<Archive::Tar> uses byte semantics for any files it reads from or writes |
1970 | to disk. This is not a problem if you only deal with files and never |
1971 | look at their content or work solely with byte strings. But if you use |
1972 | Unicode strings with character semantics, some additional steps need |
1973 | to be taken. |
1974 | |
1975 | For example, if you add a Unicode string like |
1976 | |
1977 | # Problem |
1978 | $tar->add_data('file.txt', "Euro: \x{20AC}"); |
1979 | |
1980 | then there will be a problem later when the tarfile gets written out |
1981 | to disk via C<$tar->write()>: |
1982 | |
1983 | Wide character in print at .../Archive/Tar.pm line 1014. |
1984 | |
1985 | The data was added as a Unicode string and when writing it out to disk, |
1986 | the C<:utf8> line discipline wasn't set by C<Archive::Tar>, so Perl |
1987 | tried to convert the string to ISO-8859 and failed. The written file |
1988 | now contains garbage. |
1989 | |
1990 | For this reason, Unicode strings need to be converted to UTF-8-encoded |
1991 | bytestrings before they are handed off to C<add_data()>: |
1992 | |
1993 | use Encode; |
1994 | my $data = "Accented character: \x{20AC}"; |
1995 | $data = encode('utf8', $data); |
1996 | |
1997 | $tar->add_data('file.txt', $data); |
1998 | |
e0d68803 |
1999 | A opposite problem occurs if you extract a UTF8-encoded file from a |
01d11a1c |
2000 | tarball. Using C<get_content()> on the C<Archive::Tar::File> object |
2001 | will return its content as a bytestring, not as a Unicode string. |
2002 | |
2003 | If you want it to be a Unicode string (because you want character |
2004 | semantics with operations like regular expression matching), you need |
e0d68803 |
2005 | to decode the UTF8-encoded content and have Perl convert it into |
01d11a1c |
2006 | a Unicode string: |
2007 | |
2008 | use Encode; |
2009 | my $data = $tar->get_content(); |
e0d68803 |
2010 | |
01d11a1c |
2011 | # Make it a Unicode string |
2012 | $data = decode('utf8', $data); |
2013 | |
e0d68803 |
2014 | There is no easy way to provide this functionality in C<Archive::Tar>, |
01d11a1c |
2015 | because a tarball can contain many files, and each of which could be |
2016 | encoded in a different way. |
81a5970e |
2017 | |
39713df4 |
2018 | =back |
2019 | |
2020 | =head1 TODO |
2021 | |
2022 | =over 4 |
2023 | |
2024 | =item Check if passed in handles are open for read/write |
2025 | |
2026 | Currently I don't know of any portable pure perl way to do this. |
2027 | Suggestions welcome. |
2028 | |
b3200c5d |
2029 | =item Allow archives to be passed in as string |
2030 | |
2031 | Currently, we only allow opened filehandles or filenames, but |
2032 | not strings. The internals would need some reworking to facilitate |
2033 | stringified archives. |
2034 | |
2035 | =item Facilitate processing an opened filehandle of a compressed archive |
2036 | |
2037 | Currently, we only support this if the filehandle is an IO::Zlib object. |
2038 | Environments, like apache, will present you with an opened filehandle |
2039 | to an uploaded file, which might be a compressed archive. |
2040 | |
39713df4 |
2041 | =back |
2042 | |
f38c1908 |
2043 | =head1 SEE ALSO |
2044 | |
2045 | =over 4 |
2046 | |
2047 | =item The GNU tar specification |
2048 | |
2049 | C<http://www.gnu.org/software/tar/manual/tar.html> |
2050 | |
2051 | =item The PAX format specication |
2052 | |
2053 | The specifcation which tar derives from; C< http://www.opengroup.org/onlinepubs/007904975/utilities/pax.html> |
2054 | |
2055 | =item A comparison of GNU and POSIX tar standards; C<http://www.delorie.com/gnu/docs/tar/tar_114.html> |
2056 | |
2057 | =item GNU tar intends to switch to POSIX compatibility |
2058 | |
2059 | GNU Tar authors have expressed their intention to become completely |
2060 | POSIX-compatible; C<http://www.gnu.org/software/tar/manual/html_node/Formats.html> |
2061 | |
2062 | =item A Comparison between various tar implementations |
2063 | |
2064 | Lists known issues and incompatibilities; C<http://gd.tuwien.ac.at/utils/archivers/star/README.otherbugs> |
2065 | |
2066 | =back |
2067 | |
39713df4 |
2068 | =head1 AUTHOR |
2069 | |
c3745331 |
2070 | This module by Jos Boumans E<lt>kane@cpan.orgE<gt>. |
2071 | |
2072 | Please reports bugs to E<lt>bug-archive-tar@rt.cpan.orgE<gt>. |
39713df4 |
2073 | |
2074 | =head1 ACKNOWLEDGEMENTS |
2075 | |
642eb381 |
2076 | Thanks to Sean Burke, Chris Nandor, Chip Salzenberg, Tim Heaney, Gisle Aas |
2077 | and especially Andrew Savige for their help and suggestions. |
39713df4 |
2078 | |
2079 | =head1 COPYRIGHT |
2080 | |
e0d68803 |
2081 | This module is copyright (c) 2002 - 2008 Jos Boumans |
c3745331 |
2082 | E<lt>kane@cpan.orgE<gt>. All rights reserved. |
39713df4 |
2083 | |
e0d68803 |
2084 | This library is free software; you may redistribute and/or modify |
c3745331 |
2085 | it under the same terms as Perl itself. |
39713df4 |
2086 | |
2087 | =cut |