1 package IO::Uncompress::AnyUncompress ;
7 use IO::Compress::Base::Common qw(createSelfTiedObject);
9 use IO::Uncompress::Base ;
14 our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyUncompressError);
16 $VERSION = '2.000_14';
17 $AnyUncompressError = '';
19 @ISA = qw( Exporter IO::Uncompress::Base );
20 @EXPORT_OK = qw( $AnyUncompressError anyuncompress ) ;
21 %EXPORT_TAGS = %IO::Uncompress::Base::DEFLATE_CONSTANTS ;
22 push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ;
23 Exporter::export_ok_tags('all');
25 # TODO - allow the user to pick a set of the three formats to allow
26 # or just assume want to auto-detect any of the three formats.
30 eval ' use IO::Uncompress::Adapter::Inflate ';
31 eval ' use IO::Uncompress::Adapter::Bunzip2 ';
32 eval ' use IO::Uncompress::Adapter::LZO ';
33 eval ' use IO::Uncompress::Adapter::Lzf ';
35 eval ' use IO::Uncompress::Bunzip2 ';
36 eval ' use IO::Uncompress::UnLzop ';
37 eval ' use IO::Uncompress::Gunzip ';
38 eval ' use IO::Uncompress::Inflate ';
39 eval ' use IO::Uncompress::RawInflate ';
40 eval ' use IO::Uncompress::Unzip ';
41 eval ' use IO::Uncompress::UnLzf ';
47 my $obj = createSelfTiedObject($class, \$AnyUncompressError);
48 $obj->_create(undef, 0, @_);
53 my $obj = createSelfTiedObject(undef, \$AnyUncompressError);
54 return $obj->_inf(@_) ;
59 use IO::Compress::Base::Common qw(:Parse);
60 return ( 'RawInflate' => [1, 1, Parse_boolean, 0] ) ;
68 # any always needs both crc32 and adler32
69 $got->value('CRC32' => 1);
70 $got->value('ADLER32' => 1);
84 if (defined $IO::Uncompress::RawInflate::VERSION )
86 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject();
88 return $self->saveErrorString(undef, $errstr, $errno)
91 *$self->{Uncomp} = $obj;
93 my @possible = qw( Inflate Gunzip Unzip );
94 unshift @possible, 'RawInflate'
95 if $got->value('RawInflate');
97 $magic = $self->ckMagic( @possible );
100 *$self->{Info} = $self->readHeader($magic)
107 if (defined $IO::Uncompress::Bunzip2::VERSION and
108 $magic = $self->ckMagic('Bunzip2')) {
109 *$self->{Info} = $self->readHeader($magic)
112 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Bunzip2::mkUncompObject();
114 return $self->saveErrorString(undef, $errstr, $errno)
117 *$self->{Uncomp} = $obj;
122 if (defined $IO::Uncompress::UnLzop::VERSION and
123 $magic = $self->ckMagic('UnLzop')) {
125 *$self->{Info} = $self->readHeader($magic)
128 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::LZO::mkUncompObject();
130 return $self->saveErrorString(undef, $errstr, $errno)
133 *$self->{Uncomp} = $obj;
138 if (defined $IO::Uncompress::UnLzf::VERSION and
139 $magic = $self->ckMagic('UnLzf')) {
141 *$self->{Info} = $self->readHeader($magic)
144 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Lzf::mkUncompObject();
146 return $self->saveErrorString(undef, $errstr, $errno)
149 *$self->{Uncomp} = $obj;
164 my $keep = ref $self ;
165 for my $class ( map { "IO::Uncompress::$_" } @names)
167 bless $self => $class;
168 my $magic = $self->ckMagic();
172 #bless $self => $class;
176 $self->pushBack(*$self->{HeaderPending}) ;
177 *$self->{HeaderPending} = '' ;
180 bless $self => $keep;
192 IO::Uncompress::AnyUncompress - Uncompress gzip, zip, bzip2 or lzop file/buffer
197 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
199 my $status = anyuncompress $input => $output [,OPTS]
200 or die "anyuncompress failed: $AnyUncompressError\n";
202 my $z = new IO::Uncompress::AnyUncompress $input [OPTS]
203 or die "anyuncompress failed: $AnyUncompressError\n";
205 $status = $z->read($buffer)
206 $status = $z->read($buffer, $length)
207 $status = $z->read($buffer, $length, $offset)
208 $line = $z->getline()
213 $data = $z->trailingData()
214 $status = $z->nextStream()
215 $data = $z->getHeaderInfo()
217 $z->seek($position, $whence)
223 $AnyUncompressError ;
229 read($z, $buffer, $length);
230 read($z, $buffer, $length, $offset);
232 seek($z, $position, $whence)
243 B<WARNING -- This is a Beta release>.
247 =item * DO NOT use in production code.
249 =item * The documentation is incomplete in places.
251 =item * Parts of the interface defined here are tentative.
253 =item * Please report any problems you find.
260 This module provides a Perl interface that allows the reading of
261 files/buffers that have been compressed with a variety of compression
264 The formats supported are:
270 =item RFC 1951 (optionally)
272 =item gzip (RFC 1952)
284 The module will auto-detect which, if any, of the supported
285 compression formats is being used.
290 =head1 Functional Interface
292 A top-level function, C<anyuncompress>, is provided to carry out
293 "one-shot" uncompression between buffers and/or files. For finer
294 control over the uncompression process, see the L</"OO Interface">
297 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
299 anyuncompress $input => $output [,OPTS]
300 or die "anyuncompress failed: $AnyUncompressError\n";
304 The functional interface needs Perl5.005 or better.
307 =head2 anyuncompress $input => $output [, OPTS]
310 C<anyuncompress> expects at least two parameters, C<$input> and C<$output>.
312 =head3 The C<$input> parameter
314 The parameter, C<$input>, is used to define the source of
317 It can take one of the following forms:
323 If the C<$input> parameter is a simple scalar, it is assumed to be a
324 filename. This file will be opened for reading and the input data
325 will be read from it.
329 If the C<$input> parameter is a filehandle, the input data will be
331 The string '-' can be used as an alias for standard input.
333 =item A scalar reference
335 If C<$input> is a scalar reference, the input data will be read
338 =item An array reference
340 If C<$input> is an array reference, each element in the array must be a
343 The input data will be read from each file in turn.
345 The complete array will be walked to ensure that it only
346 contains valid filenames before any data is uncompressed.
350 =item An Input FileGlob string
352 If C<$input> is a string that is delimited by the characters "<" and ">"
353 C<anyuncompress> will assume that it is an I<input fileglob string>. The
354 input is the list of files that match the fileglob.
356 If the fileglob does not match any files ...
358 See L<File::GlobMapper|File::GlobMapper> for more details.
363 If the C<$input> parameter is any other type, C<undef> will be returned.
367 =head3 The C<$output> parameter
369 The parameter C<$output> is used to control the destination of the
370 uncompressed data. This parameter can take one of these forms.
376 If the C<$output> parameter is a simple scalar, it is assumed to be a
377 filename. This file will be opened for writing and the uncompressed
378 data will be written to it.
382 If the C<$output> parameter is a filehandle, the uncompressed data
383 will be written to it.
384 The string '-' can be used as an alias for standard output.
387 =item A scalar reference
389 If C<$output> is a scalar reference, the uncompressed data will be
390 stored in C<$$output>.
394 =item An Array Reference
396 If C<$output> is an array reference, the uncompressed data will be
397 pushed onto the array.
399 =item An Output FileGlob
401 If C<$output> is a string that is delimited by the characters "<" and ">"
402 C<anyuncompress> will assume that it is an I<output fileglob string>. The
403 output is the list of files that match the fileglob.
405 When C<$output> is an fileglob string, C<$input> must also be a fileglob
406 string. Anything else is an error.
410 If the C<$output> parameter is any other type, C<undef> will be returned.
417 When C<$input> maps to multiple compressed files/buffers and C<$output> is
418 a single file/buffer, after uncompression C<$output> will contain a
419 concatenation of all the uncompressed data from each of the input
426 =head2 Optional Parameters
428 Unless specified below, the optional parameters for C<anyuncompress>,
429 C<OPTS>, are the same as those used with the OO interface defined in the
430 L</"Constructor Options"> section below.
434 =item C<< AutoClose => 0|1 >>
436 This option applies to any input or output data streams to
437 C<anyuncompress> that are filehandles.
439 If C<AutoClose> is specified, and the value is true, it will result in all
440 input and/or output filehandles being closed once C<anyuncompress> has
443 This parameter defaults to 0.
446 =item C<< BinModeOut => 0|1 >>
448 When writing to a file or filehandle, set C<binmode> before writing to the
457 =item C<< Append => 0|1 >>
461 =item C<< MultiStream => 0|1 >>
464 If the input file/buffer contains multiple compressed data streams, this
465 option will uncompress the whole lot as a single data stream.
473 =item C<< TrailingData => $scalar >>
475 Returns the data, if any, that is present immediately after the compressed
476 data stream once uncompression is complete.
478 This option can be used when there is useful information immediately
479 following the compressed data stream, and you don't know the length of the
480 compressed data stream.
482 If the input is a buffer, C<trailingData> will return everything from the
483 end of the compressed data stream to the end of the buffer.
485 If the input is a filehandle, C<trailingData> will return the data that is
486 left in the filehandle input buffer once the end of the compressed data
487 stream has been reached. You can then use the filehandle to read the rest
490 Don't bother using C<trailingData> if the input is a filename.
494 If you know the length of the compressed data stream before you start
495 uncompressing, you can avoid having to use C<trailingData> by setting the
496 C<InputLength> option.
507 To read the contents of the file C<file1.txt.Compressed> and write the
508 compressed data to the file C<file1.txt>.
512 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
514 my $input = "file1.txt.Compressed";
515 my $output = "file1.txt";
516 anyuncompress $input => $output
517 or die "anyuncompress failed: $AnyUncompressError\n";
520 To read from an existing Perl filehandle, C<$input>, and write the
521 uncompressed data to a buffer, C<$buffer>.
525 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
528 my $input = new IO::File "<file1.txt.Compressed"
529 or die "Cannot open 'file1.txt.Compressed': $!\n" ;
531 anyuncompress $input => \$buffer
532 or die "anyuncompress failed: $AnyUncompressError\n";
534 To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory
538 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
540 anyuncompress '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>'
541 or die "anyuncompress failed: $AnyUncompressError\n";
543 and if you want to compress each file one at a time, this will do the trick
547 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
549 for my $input ( glob "/my/home/*.txt.Compressed" )
552 $output =~ s/.Compressed// ;
553 anyuncompress $input => $output
554 or die "Error compressing '$input': $AnyUncompressError\n";
561 The format of the constructor for IO::Uncompress::AnyUncompress is shown below
564 my $z = new IO::Uncompress::AnyUncompress $input [OPTS]
565 or die "IO::Uncompress::AnyUncompress failed: $AnyUncompressError\n";
567 Returns an C<IO::Uncompress::AnyUncompress> object on success and undef on failure.
568 The variable C<$AnyUncompressError> will contain an error message on failure.
570 If you are running Perl 5.005 or better the object, C<$z>, returned from
571 IO::Uncompress::AnyUncompress can be used exactly like an L<IO::File|IO::File> filehandle.
572 This means that all normal input file operations can be carried out with
573 C<$z>. For example, to read a line from a compressed file/buffer you can
574 use either of these forms
576 $line = $z->getline();
579 The mandatory parameter C<$input> is used to determine the source of the
580 compressed data. This parameter can take one of three forms.
586 If the C<$input> parameter is a scalar, it is assumed to be a filename. This
587 file will be opened for reading and the compressed data will be read from it.
591 If the C<$input> parameter is a filehandle, the compressed data will be
593 The string '-' can be used as an alias for standard input.
596 =item A scalar reference
598 If C<$input> is a scalar reference, the compressed data will be read from
603 =head2 Constructor Options
606 The option names defined below are case insensitive and can be optionally
607 prefixed by a '-'. So all of the following are valid
614 OPTS is a combination of the following options:
618 =item C<< AutoClose => 0|1 >>
620 This option is only valid when the C<$input> parameter is a filehandle. If
621 specified, and the value is true, it will result in the file being closed once
622 either the C<close> method is called or the IO::Uncompress::AnyUncompress object is
625 This parameter defaults to 0.
627 =item C<< MultiStream => 0|1 >>
631 Allows multiple concatenated compressed streams to be treated as a single
632 compressed stream. Decompression will stop once either the end of the
633 file/buffer is reached, an error is encountered (premature eof, corrupt
634 compressed data) or the end of a stream is not immediately followed by the
635 start of another stream.
637 This parameter defaults to 0.
640 =item C<< Prime => $string >>
642 This option will uncompress the contents of C<$string> before processing the
645 This option can be useful when the compressed data is embedded in another
646 file/data structure and it is not possible to work out where the compressed
647 data begins without having to read the first few bytes. If this is the
648 case, the uncompression can be I<primed> with these bytes using this
651 =item C<< Transparent => 0|1 >>
653 If this option is set and the input file or buffer is not compressed data,
654 the module will allow reading of it anyway.
656 This option defaults to 1.
658 =item C<< BlockSize => $num >>
660 When reading the compressed input data, IO::Uncompress::AnyUncompress will read it in
661 blocks of C<$num> bytes.
663 This option defaults to 4096.
665 =item C<< InputLength => $size >>
667 When present this option will limit the number of compressed bytes read
668 from the input file/buffer to C<$size>. This option can be used in the
669 situation where there is useful data directly after the compressed data
670 stream and you know beforehand the exact length of the compressed data
673 This option is mostly used when reading from a filehandle, in which case
674 the file pointer will be left pointing to the first byte directly after the
675 compressed data stream.
679 This option defaults to off.
681 =item C<< Append => 0|1 >>
683 This option controls what the C<read> method does with uncompressed data.
685 If set to 1, all uncompressed data will be appended to the output parameter
686 of the C<read> method.
688 If set to 0, the contents of the output parameter of the C<read> method
689 will be overwritten by the uncompressed data.
693 =item C<< Strict => 0|1 >>
697 This option controls whether the extra checks defined below are used when
698 carrying out the decompression. When Strict is on, the extra tests are
699 carried out, when Strict is off they are not.
701 The default for this option is off.
713 =item C<< RawInflate => 0|1 >>
715 When auto-detecting the compressed format, try to test for raw-deflate (RFC
716 1951) content using the C<IO::Uncompress::RawInflate> module.
718 The reason this is not default behaviour is because RFC 1951 content can
719 only be detected by attempting to uncompress it. This process is error
720 prone and can result is false positives.
741 $status = $z->read($buffer)
743 Reads a block of compressed data (the size the the compressed block is
744 determined by the C<Buffer> option in the constructor), uncompresses it and
745 writes any uncompressed data into C<$buffer>. If the C<Append> parameter is
746 set in the constructor, the uncompressed data will be appended to the
747 C<$buffer> parameter. Otherwise C<$buffer> will be overwritten.
749 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
750 or a negative number on error.
756 $status = $z->read($buffer, $length)
757 $status = $z->read($buffer, $length, $offset)
759 $status = read($z, $buffer, $length)
760 $status = read($z, $buffer, $length, $offset)
762 Attempt to read C<$length> bytes of uncompressed data into C<$buffer>.
764 The main difference between this form of the C<read> method and the
765 previous one, is that this one will attempt to return I<exactly> C<$length>
766 bytes. The only circumstances that this function will not is if end-of-file
767 or an IO error is encountered.
769 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
770 or a negative number on error.
777 $line = $z->getline()
782 This method fully supports the use of of the variable C<$/> (or
783 C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to
784 determine what constitutes an end of line. Paragraph mode, record mode and
785 file slurp mode are all supported.
794 Read a single character.
800 $char = $z->ungetc($string)
809 $hdr = $z->getHeaderInfo();
810 @hdrs = $z->getHeaderInfo();
812 This method returns either a hash reference (in scalar context) or a list
813 or hash references (in array context) that contains information about each
814 of the header fields in the compressed data stream(s).
826 Returns the uncompressed file offset.
837 Returns true if the end of the compressed input stream has been reached.
843 $z->seek($position, $whence);
844 seek($z, $position, $whence);
849 Provides a sub-set of the C<seek> functionality, with the restriction
850 that it is only legal to seek forward in the input file/buffer.
851 It is a fatal error to attempt to seek backward.
855 The C<$whence> parameter takes one the usual values, namely SEEK_SET,
856 SEEK_CUR or SEEK_END.
858 Returns 1 on success, 0 on failure.
867 This is a noop provided for completeness.
873 Returns true if the object currently refers to a opened file/buffer.
877 my $prev = $z->autoflush()
878 my $prev = $z->autoflush(EXPR)
880 If the C<$z> object is associated with a file or a filehandle, this method
881 returns the current autoflush setting for the underlying filehandle. If
882 C<EXPR> is present, and is non-zero, it will enable flushing after every
883 write/print operation.
885 If C<$z> is associated with a buffer, this method has no effect and always
888 B<Note> that the special variable C<$|> B<cannot> be used to set or
889 retrieve the autoflush setting.
891 =head2 input_line_number
893 $z->input_line_number()
894 $z->input_line_number(EXPR)
898 Returns the current uncompressed line number. If C<EXPR> is present it has
899 the effect of setting the line number. Note that setting the line number
900 does not change the current position within the file/buffer being read.
902 The contents of C<$/> are used to to determine what constitutes a line
912 If the C<$z> object is associated with a file or a filehandle, this method
913 will return the underlying file descriptor.
915 If the C<$z> object is is associated with a buffer, this method will
925 Closes the output file/buffer.
929 For most versions of Perl this method will be automatically invoked if
930 the IO::Uncompress::AnyUncompress object is destroyed (either explicitly or by the
931 variable with the reference to the object going out of scope). The
932 exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In
933 these cases, the C<close> method will be called automatically, but
934 not until global destruction of all live objects when the program is
937 Therefore, if you want your scripts to be able to run on all versions
938 of Perl, you should call C<close> explicitly and not rely on automatic
941 Returns true on success, otherwise 0.
943 If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyUncompress
944 object was created, and the object is associated with a file, the
945 underlying file will also be closed.
954 my $status = $z->nextStream();
956 Skips to the next compressed data stream in the input file/buffer. If a new
957 compressed data stream is found, the eof marker will be cleared and C<$.>
960 Returns 1 if a new stream was found, 0 if none was found, and -1 if an
961 error was encountered.
967 my $data = $z->trailingData();
969 Returns the data, if any, that is present immediately after the compressed
970 data stream once uncompression is complete. It only makes sense to call
971 this method once the end of the compressed data stream has been
974 This option can be used when there is useful information immediately
975 following the compressed data stream, and you don't know the length of the
976 compressed data stream.
978 If the input is a buffer, C<trailingData> will return everything from the
979 end of the compressed data stream to the end of the buffer.
981 If the input is a filehandle, C<trailingData> will return the data that is
982 left in the filehandle input buffer once the end of the compressed data
983 stream has been reached. You can then use the filehandle to read the rest
986 Don't bother using C<trailingData> if the input is a filename.
990 If you know the length of the compressed data stream before you start
991 uncompressing, you can avoid having to use C<trailingData> by setting the
992 C<InputLength> option in the constructor.
996 No symbolic constants are required by this IO::Uncompress::AnyUncompress at present.
1002 Imports C<anyuncompress> and C<$AnyUncompressError>.
1005 use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ;
1016 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::Compress::Lzf>, L<IO::Uncompress::UnLzf>, L<IO::Uncompress::AnyInflate>
1018 L<Compress::Zlib::FAQ|Compress::Zlib::FAQ>
1020 L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>,
1021 L<Archive::Tar|Archive::Tar>,
1022 L<IO::Zlib|IO::Zlib>
1030 This module was written by Paul Marquess, F<pmqs@cpan.org>.
1034 =head1 MODIFICATION HISTORY
1036 See the Changes file.
1038 =head1 COPYRIGHT AND LICENSE
1040 Copyright (c) 2005-2006 Paul Marquess. All rights reserved.
1042 This program is free software; you can redistribute it and/or
1043 modify it under the same terms as Perl itself.