1 package IO::Uncompress::AnyUncompress ;
7 use IO::Compress::Base::Common qw(createSelfTiedObject);
9 use IO::Uncompress::Base ;
13 eval { require IO::Uncompress::Adapter::Inflate; import IO::Uncompress::Adapter::Inflate };
14 eval { require IO::Uncompress::Adapter::Bunzip2; import IO::Uncompress::Adapter::Bunzip2 };
15 eval { require IO::Uncompress::Adapter::LZO; import IO::Uncompress::Adapter::LZO };
17 eval { require IO::Uncompress::Bunzip2; import IO::Uncompress::Bunzip2 };
18 eval { require IO::Uncompress::UnLzop; import IO::Uncompress::UnLzop };
19 eval { require IO::Uncompress::Gunzip; import IO::Uncompress::Gunzip };
20 eval { require IO::Uncompress::Inflate; import IO::Uncompress::Inflate };
21 eval { require IO::Uncompress::RawInflate; import IO::Uncompress::RawInflate };
22 eval { require IO::Uncompress::Unzip; import IO::Uncompress::Unzip };
27 our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyUncompressError);
29 $VERSION = '2.000_10';
30 $AnyUncompressError = '';
32 @ISA = qw( Exporter IO::Uncompress::Base );
33 @EXPORT_OK = qw( $AnyUncompressError anyuncompress ) ;
34 %EXPORT_TAGS = %IO::Uncompress::Base::DEFLATE_CONSTANTS ;
35 push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ;
36 Exporter::export_ok_tags('all');
38 # TODO - allow the user to pick a set of the three formats to allow
39 # or just assume want to auto-detect any of the three formats.
44 my $obj = createSelfTiedObject($class, \$AnyUncompressError);
45 $obj->_create(undef, 0, @_);
50 my $obj = createSelfTiedObject(undef, \$AnyUncompressError);
51 return $obj->_inf(@_) ;
64 # any always needs both crc32 and adler32
65 $got->value('CRC32' => 1);
66 $got->value('ADLER32' => 1);
80 if (defined $IO::Uncompress::RawInflate::VERSION )
82 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject();
84 return $self->saveErrorString(undef, $errstr, $errno)
87 *$self->{Uncomp} = $obj;
89 $magic = $self->ckMagic( qw( RawInflate Inflate Gunzip Unzip ) );
92 *$self->{Info} = $self->readHeader($magic)
99 #foreach my $type ( qw( Bunzip2 UnLzop ) ) {
100 if (defined $IO::Uncompress::Bunzip2::VERSION and
101 $magic = $self->ckMagic('Bunzip2')) {
102 *$self->{Info} = $self->readHeader($magic)
105 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Bunzip2::mkUncompObject();
107 return $self->saveErrorString(undef, $errstr, $errno)
110 *$self->{Uncomp} = $obj;
114 elsif (defined $IO::Uncompress::UnLzop::VERSION and
115 $magic = $self->ckMagic('UnLzop')) {
117 *$self->{Info} = $self->readHeader($magic)
120 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::LZO::mkUncompObject();
122 return $self->saveErrorString(undef, $errstr, $errno)
125 *$self->{Uncomp} = $obj;
140 my $keep = ref $self ;
141 for my $class ( map { "IO::Uncompress::$_" } @names)
143 bless $self => $class;
144 my $magic = $self->ckMagic();
148 #bless $self => $class;
152 $self->pushBack(*$self->{HeaderPending}) ;
153 *$self->{HeaderPending} = '' ;
156 bless $self => $keep;
168 IO::Uncompress::AnyUncompress - Uncompress gzip, zip, bzip2 or lzop file/buffer
173 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
175 my $status = anyuncompress $input => $output [,OPTS]
176 or die "anyuncompress failed: $AnyUncompressError\n";
178 my $z = new IO::Uncompress::AnyUncompress $input [OPTS]
179 or die "anyuncompress failed: $AnyUncompressError\n";
181 $status = $z->read($buffer)
182 $status = $z->read($buffer, $length)
183 $status = $z->read($buffer, $length, $offset)
184 $line = $z->getline()
190 $data = $z->getHeaderInfo()
192 $z->seek($position, $whence)
198 $AnyUncompressError ;
204 read($z, $buffer, $length);
205 read($z, $buffer, $length, $offset);
207 seek($z, $position, $whence)
218 B<WARNING -- This is a Beta release>.
222 =item * DO NOT use in production code.
224 =item * The documentation is incomplete in places.
226 =item * Parts of the interface defined here are tentative.
228 =item * Please report any problems you find.
235 This module provides a Perl interface that allows the reading of
236 files/buffers that have been compressed with a variety of compression
239 The formats supported are:
247 =item gzip (RFC 1952)
257 The module will auto-detect which, if any, of the supported
258 compression formats is being used.
264 =head1 Functional Interface
266 A top-level function, C<anyuncompress>, is provided to carry out
267 "one-shot" uncompression between buffers and/or files. For finer
268 control over the uncompression process, see the L</"OO Interface">
271 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
273 anyuncompress $input => $output [,OPTS]
274 or die "anyuncompress failed: $AnyUncompressError\n";
278 The functional interface needs Perl5.005 or better.
281 =head2 anyuncompress $input => $output [, OPTS]
284 C<anyuncompress> expects at least two parameters, C<$input> and C<$output>.
286 =head3 The C<$input> parameter
288 The parameter, C<$input>, is used to define the source of
291 It can take one of the following forms:
297 If the C<$input> parameter is a simple scalar, it is assumed to be a
298 filename. This file will be opened for reading and the input data
299 will be read from it.
303 If the C<$input> parameter is a filehandle, the input data will be
305 The string '-' can be used as an alias for standard input.
307 =item A scalar reference
309 If C<$input> is a scalar reference, the input data will be read
312 =item An array reference
314 If C<$input> is an array reference, each element in the array must be a
317 The input data will be read from each file in turn.
319 The complete array will be walked to ensure that it only
320 contains valid filenames before any data is uncompressed.
324 =item An Input FileGlob string
326 If C<$input> is a string that is delimited by the characters "<" and ">"
327 C<anyuncompress> will assume that it is an I<input fileglob string>. The
328 input is the list of files that match the fileglob.
330 If the fileglob does not match any files ...
332 See L<File::GlobMapper|File::GlobMapper> for more details.
337 If the C<$input> parameter is any other type, C<undef> will be returned.
341 =head3 The C<$output> parameter
343 The parameter C<$output> is used to control the destination of the
344 uncompressed data. This parameter can take one of these forms.
350 If the C<$output> parameter is a simple scalar, it is assumed to be a
351 filename. This file will be opened for writing and the uncompressed
352 data will be written to it.
356 If the C<$output> parameter is a filehandle, the uncompressed data
357 will be written to it.
358 The string '-' can be used as an alias for standard output.
361 =item A scalar reference
363 If C<$output> is a scalar reference, the uncompressed data will be
364 stored in C<$$output>.
368 =item An Array Reference
370 If C<$output> is an array reference, the uncompressed data will be
371 pushed onto the array.
373 =item An Output FileGlob
375 If C<$output> is a string that is delimited by the characters "<" and ">"
376 C<anyuncompress> will assume that it is an I<output fileglob string>. The
377 output is the list of files that match the fileglob.
379 When C<$output> is an fileglob string, C<$input> must also be a fileglob
380 string. Anything else is an error.
384 If the C<$output> parameter is any other type, C<undef> will be returned.
390 When C<$input> maps to multiple files/buffers and C<$output> is a single
391 file/buffer the uncompressed input files/buffers will all be stored
392 in C<$output> as a single uncompressed stream.
396 =head2 Optional Parameters
398 Unless specified below, the optional parameters for C<anyuncompress>,
399 C<OPTS>, are the same as those used with the OO interface defined in the
400 L</"Constructor Options"> section below.
404 =item AutoClose =E<gt> 0|1
406 This option applies to any input or output data streams to
407 C<anyuncompress> that are filehandles.
409 If C<AutoClose> is specified, and the value is true, it will result in all
410 input and/or output filehandles being closed once C<anyuncompress> has
413 This parameter defaults to 0.
417 =item BinModeOut =E<gt> 0|1
419 When writing to a file or filehandle, set C<binmode> before writing to the
428 =item -Append =E<gt> 0|1
432 =item -MultiStream =E<gt> 0|1
434 Creates a new stream after each file.
447 To read the contents of the file C<file1.txt.Compressed> and write the
448 compressed data to the file C<file1.txt>.
452 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
454 my $input = "file1.txt.Compressed";
455 my $output = "file1.txt";
456 anyuncompress $input => $output
457 or die "anyuncompress failed: $AnyUncompressError\n";
460 To read from an existing Perl filehandle, C<$input>, and write the
461 uncompressed data to a buffer, C<$buffer>.
465 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
468 my $input = new IO::File "<file1.txt.Compressed"
469 or die "Cannot open 'file1.txt.Compressed': $!\n" ;
471 anyuncompress $input => \$buffer
472 or die "anyuncompress failed: $AnyUncompressError\n";
474 To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory
478 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
480 anyuncompress '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>'
481 or die "anyuncompress failed: $AnyUncompressError\n";
483 and if you want to compress each file one at a time, this will do the trick
487 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
489 for my $input ( glob "/my/home/*.txt.Compressed" )
492 $output =~ s/.Compressed// ;
493 anyuncompress $input => $output
494 or die "Error compressing '$input': $AnyUncompressError\n";
501 The format of the constructor for IO::Uncompress::AnyUncompress is shown below
504 my $z = new IO::Uncompress::AnyUncompress $input [OPTS]
505 or die "IO::Uncompress::AnyUncompress failed: $AnyUncompressError\n";
507 Returns an C<IO::Uncompress::AnyUncompress> object on success and undef on failure.
508 The variable C<$AnyUncompressError> will contain an error message on failure.
510 If you are running Perl 5.005 or better the object, C<$z>, returned from
511 IO::Uncompress::AnyUncompress can be used exactly like an L<IO::File|IO::File> filehandle.
512 This means that all normal input file operations can be carried out with
513 C<$z>. For example, to read a line from a compressed file/buffer you can
514 use either of these forms
516 $line = $z->getline();
519 The mandatory parameter C<$input> is used to determine the source of the
520 compressed data. This parameter can take one of three forms.
526 If the C<$input> parameter is a scalar, it is assumed to be a filename. This
527 file will be opened for reading and the compressed data will be read from it.
531 If the C<$input> parameter is a filehandle, the compressed data will be
533 The string '-' can be used as an alias for standard input.
536 =item A scalar reference
538 If C<$input> is a scalar reference, the compressed data will be read from
543 =head2 Constructor Options
546 The option names defined below are case insensitive and can be optionally
547 prefixed by a '-'. So all of the following are valid
554 OPTS is a combination of the following options:
558 =item -AutoClose =E<gt> 0|1
560 This option is only valid when the C<$input> parameter is a filehandle. If
561 specified, and the value is true, it will result in the file being closed once
562 either the C<close> method is called or the IO::Uncompress::AnyUncompress object is
565 This parameter defaults to 0.
567 =item -MultiStream =E<gt> 0|1
571 Allows multiple concatenated compressed streams to be treated as a single
572 compressed stream. Decompression will stop once either the end of the
573 file/buffer is reached, an error is encountered (premature eof, corrupt
574 compressed data) or the end of a stream is not immediately followed by the
575 start of another stream.
577 This parameter defaults to 0.
581 =item -Prime =E<gt> $string
583 This option will uncompress the contents of C<$string> before processing the
586 This option can be useful when the compressed data is embedded in another
587 file/data structure and it is not possible to work out where the compressed
588 data begins without having to read the first few bytes. If this is the
589 case, the uncompression can be I<primed> with these bytes using this
592 =item -Transparent =E<gt> 0|1
594 If this option is set and the input file or buffer is not compressed data,
595 the module will allow reading of it anyway.
597 This option defaults to 1.
599 =item -BlockSize =E<gt> $num
601 When reading the compressed input data, IO::Uncompress::AnyUncompress will read it in
602 blocks of C<$num> bytes.
604 This option defaults to 4096.
606 =item -InputLength =E<gt> $size
608 When present this option will limit the number of compressed bytes read
609 from the input file/buffer to C<$size>. This option can be used in the
610 situation where there is useful data directly after the compressed data
611 stream and you know beforehand the exact length of the compressed data
614 This option is mostly used when reading from a filehandle, in which case
615 the file pointer will be left pointing to the first byte directly after the
616 compressed data stream.
620 This option defaults to off.
622 =item -Append =E<gt> 0|1
624 This option controls what the C<read> method does with uncompressed data.
626 If set to 1, all uncompressed data will be appended to the output parameter
627 of the C<read> method.
629 If set to 0, the contents of the output parameter of the C<read> method
630 will be overwritten by the uncompressed data.
634 =item -Strict =E<gt> 0|1
638 This option controls whether the extra checks defined below are used when
639 carrying out the decompression. When Strict is on, the extra tests are
640 carried out, when Strict is off they are not.
642 The default for this option is off.
669 $status = $z->read($buffer)
671 Reads a block of compressed data (the size the the compressed block is
672 determined by the C<Buffer> option in the constructor), uncompresses it and
673 writes any uncompressed data into C<$buffer>. If the C<Append> parameter is
674 set in the constructor, the uncompressed data will be appended to the
675 C<$buffer> parameter. Otherwise C<$buffer> will be overwritten.
677 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
678 or a negative number on error.
684 $status = $z->read($buffer, $length)
685 $status = $z->read($buffer, $length, $offset)
687 $status = read($z, $buffer, $length)
688 $status = read($z, $buffer, $length, $offset)
690 Attempt to read C<$length> bytes of uncompressed data into C<$buffer>.
692 The main difference between this form of the C<read> method and the
693 previous one, is that this one will attempt to return I<exactly> C<$length>
694 bytes. The only circumstances that this function will not is if end-of-file
695 or an IO error is encountered.
697 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
698 or a negative number on error.
705 $line = $z->getline()
710 This method fully supports the use of of the variable C<$/>
711 (or C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to
712 determine what constitutes an end of line. Both paragraph mode and file
713 slurp mode are supported.
722 Read a single character.
728 $char = $z->ungetc($string)
737 $hdr = $z->getHeaderInfo();
738 @hdrs = $z->getHeaderInfo();
740 This method returns either a hash reference (in scalar context) or a list
741 or hash references (in array context) that contains information about each
742 of the header fields in the compressed data stream(s).
754 Returns the uncompressed file offset.
765 Returns true if the end of the compressed input stream has been reached.
771 $z->seek($position, $whence);
772 seek($z, $position, $whence);
777 Provides a sub-set of the C<seek> functionality, with the restriction
778 that it is only legal to seek forward in the input file/buffer.
779 It is a fatal error to attempt to seek backward.
783 The C<$whence> parameter takes one the usual values, namely SEEK_SET,
784 SEEK_CUR or SEEK_END.
786 Returns 1 on success, 0 on failure.
795 This is a noop provided for completeness.
801 Returns true if the object currently refers to a opened file/buffer.
805 my $prev = $z->autoflush()
806 my $prev = $z->autoflush(EXPR)
808 If the C<$z> object is associated with a file or a filehandle, this method
809 returns the current autoflush setting for the underlying filehandle. If
810 C<EXPR> is present, and is non-zero, it will enable flushing after every
811 write/print operation.
813 If C<$z> is associated with a buffer, this method has no effect and always
816 B<Note> that the special variable C<$|> B<cannot> be used to set or
817 retrieve the autoflush setting.
819 =head2 input_line_number
821 $z->input_line_number()
822 $z->input_line_number(EXPR)
826 Returns the current uncompressed line number. If C<EXPR> is present it has
827 the effect of setting the line number. Note that setting the line number
828 does not change the current position within the file/buffer being read.
830 The contents of C<$/> are used to to determine what constitutes a line
840 If the C<$z> object is associated with a file or a filehandle, this method
841 will return the underlying file descriptor.
843 If the C<$z> object is is associated with a buffer, this method will
853 Closes the output file/buffer.
857 For most versions of Perl this method will be automatically invoked if
858 the IO::Uncompress::AnyUncompress object is destroyed (either explicitly or by the
859 variable with the reference to the object going out of scope). The
860 exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In
861 these cases, the C<close> method will be called automatically, but
862 not until global destruction of all live objects when the program is
865 Therefore, if you want your scripts to be able to run on all versions
866 of Perl, you should call C<close> explicitly and not rely on automatic
869 Returns true on success, otherwise 0.
871 If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyUncompress
872 object was created, and the object is associated with a file, the
873 underlying file will also be closed.
880 No symbolic constants are required by this IO::Uncompress::AnyUncompress at present.
886 Imports C<anyuncompress> and C<$AnyUncompressError>.
889 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
900 L<Compress::Zlib>, L<IO::Compress::Gzip>, L<IO::Uncompress::Gunzip>, L<IO::Compress::Deflate>, L<IO::Uncompress::Inflate>, L<IO::Compress::RawDeflate>, L<IO::Uncompress::RawInflate>, L<IO::Compress::Bzip2>, L<IO::Uncompress::Bunzip2>, L<IO::Compress::Lzop>, L<IO::Uncompress::UnLzop>, L<IO::Uncompress::AnyInflate>
902 L<Compress::Zlib::FAQ|Compress::Zlib::FAQ>
904 L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>,
905 L<Archive::Tar|Archive::Tar>,
914 This module was written by Paul Marquess, F<pmqs@cpan.org>.
918 =head1 MODIFICATION HISTORY
920 See the Changes file.
922 =head1 COPYRIGHT AND LICENSE
924 Copyright (c) 2005-2006 Paul Marquess. All rights reserved.
926 This program is free software; you can redistribute it and/or
927 modify it under the same terms as Perl itself.