1 package IO::Uncompress::Inflate ;
8 use IO::Compress::Base::Common qw(:Status createSelfTiedObject);
9 use IO::Compress::Zlib::Constants;
11 use IO::Uncompress::RawInflate ;
14 our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $InflateError);
16 $VERSION = '2.000_13';
19 @ISA = qw( Exporter IO::Uncompress::RawInflate );
20 @EXPORT_OK = qw( $InflateError inflate ) ;
21 %EXPORT_TAGS = %IO::Uncompress::RawInflate::DEFLATE_CONSTANTS ;
22 push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ;
23 Exporter::export_ok_tags('all');
29 my $obj = createSelfTiedObject($class, \$InflateError);
31 $obj->_create(undef, 0, @_);
36 my $obj = createSelfTiedObject(undef, \$InflateError);
37 return $obj->_inf(@_);
50 # gunzip always needs adler32
51 $got->value('ADLER32' => 1);
61 $self->smartReadExact(\$magic, ZLIB_HEADER_SIZE);
63 *$self->{HeaderPending} = $magic ;
65 return $self->HeaderError("Header size is " .
66 ZLIB_HEADER_SIZE . " bytes")
67 if length $magic != ZLIB_HEADER_SIZE;
69 return $self->HeaderError("CRC mismatch.")
70 if ! isZlibMagic($magic) ;
72 *$self->{Type} = 'rfc1950';
81 return $self->_readDeflateHeader($magic) ;
89 my $ADLER32 = unpack("N", $trailer) ;
90 *$self->{Info}{ADLER32} = $ADLER32;
91 return $self->TrailerError("CRC mismatch")
92 if *$self->{Strict} && $ADLER32 != *$self->{Uncomp}->adler32() ;
102 return 0 if length $buffer < ZLIB_HEADER_SIZE ;
103 my $hdr = unpack("n", $buffer) ;
104 return $hdr % 31 == 0 ;
113 ($data >> $offset ) & $mask & 0xFF ;
117 sub _readDeflateHeader
119 my ($self, $buffer) = @_ ;
122 # $self->smartReadExact(\$buffer, ZLIB_HEADER_SIZE);
124 # *$self->{HeaderPending} = $buffer ;
126 # return $self->HeaderError("Header size is " .
127 # ZLIB_HEADER_SIZE . " bytes")
128 # if length $buffer != ZLIB_HEADER_SIZE;
130 # return $self->HeaderError("CRC mismatch.")
131 # if ! isZlibMagic($buffer) ;
134 my ($CMF, $FLG) = unpack "C C", $buffer;
135 my $FDICT = bits($FLG, ZLIB_FLG_FDICT_OFFSET, ZLIB_FLG_FDICT_BITS ),
137 my $cm = bits($CMF, ZLIB_CMF_CM_OFFSET, ZLIB_CMF_CM_BITS) ;
138 $cm == ZLIB_CMF_CM_DEFLATED
139 or return $self->HeaderError("Not Deflate (CM is $cm)") ;
143 $self->smartReadExact(\$buffer, ZLIB_FDICT_SIZE)
144 or return $self->TruncatedHeader("FDICT");
146 $DICTID = unpack("N", $buffer) ;
149 *$self->{Type} = 'rfc1950';
153 'FingerprintLength' => ZLIB_HEADER_SIZE,
154 'HeaderLength' => ZLIB_HEADER_SIZE,
155 'TrailerLength' => ZLIB_TRAILER_SIZE,
159 CM => bits($CMF, ZLIB_CMF_CM_OFFSET, ZLIB_CMF_CM_BITS ),
160 CINFO => bits($CMF, ZLIB_CMF_CINFO_OFFSET, ZLIB_CMF_CINFO_BITS ),
162 FCHECK => bits($FLG, ZLIB_FLG_FCHECK_OFFSET, ZLIB_FLG_FCHECK_BITS),
163 FDICT => bits($FLG, ZLIB_FLG_FDICT_OFFSET, ZLIB_FLG_FDICT_BITS ),
164 FLEVEL => bits($FLG, ZLIB_FLG_LEVEL_OFFSET, ZLIB_FLG_LEVEL_BITS ),
182 IO::Uncompress::Inflate - Read RFC 1950 files/buffers
188 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
190 my $status = inflate $input => $output [,OPTS]
191 or die "inflate failed: $InflateError\n";
193 my $z = new IO::Uncompress::Inflate $input [OPTS]
194 or die "inflate failed: $InflateError\n";
196 $status = $z->read($buffer)
197 $status = $z->read($buffer, $length)
198 $status = $z->read($buffer, $length, $offset)
199 $line = $z->getline()
204 $status = $z->inflateSync()
206 $data = $z->trailingData()
207 $status = $z->nextStream()
208 $data = $z->getHeaderInfo()
210 $z->seek($position, $whence)
222 read($z, $buffer, $length);
223 read($z, $buffer, $length, $offset);
225 seek($z, $position, $whence)
236 B<WARNING -- This is a Beta release>.
240 =item * DO NOT use in production code.
242 =item * The documentation is incomplete in places.
244 =item * Parts of the interface defined here are tentative.
246 =item * Please report any problems you find.
254 This module provides a Perl interface that allows the reading of
255 files/buffers that conform to RFC 1950.
257 For writing RFC 1950 files/buffers, see the companion module IO::Compress::Deflate.
264 =head1 Functional Interface
266 A top-level function, C<inflate>, 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::Inflate qw(inflate $InflateError) ;
273 inflate $input => $output [,OPTS]
274 or die "inflate failed: $InflateError\n";
278 The functional interface needs Perl5.005 or better.
281 =head2 inflate $input => $output [, OPTS]
284 C<inflate> expects at least two parameters, C<$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<inflate> 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<inflate> 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<$output> parameter is any other type, C<undef> will be returned.
391 When C<$input> maps to multiple compressed files/buffers and C<$output> is
392 a single file/buffer, after uncompression C<$output> will contain a
393 concatenation of all the uncompressed data from each of the input
400 =head2 Optional Parameters
402 Unless specified below, the optional parameters for C<inflate>,
403 C<OPTS>, are the same as those used with the OO interface defined in the
404 L</"Constructor Options"> section below.
408 =item C<< AutoClose => 0|1 >>
410 This option applies to any input or output data streams to
411 C<inflate> that are filehandles.
413 If C<AutoClose> is specified, and the value is true, it will result in all
414 input and/or output filehandles being closed once C<inflate> has
417 This parameter defaults to 0.
420 =item C<< BinModeOut => 0|1 >>
422 When writing to a file or filehandle, set C<binmode> before writing to the
431 =item C<< Append => 0|1 >>
435 =item C<< MultiStream => 0|1 >>
437 If the input file/buffer contains multiple compressed data streams, this
438 option will uncompress the whole lot as a single data stream.
451 To read the contents of the file C<file1.txt.1950> and write the
452 compressed data to the file C<file1.txt>.
456 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
458 my $input = "file1.txt.1950";
459 my $output = "file1.txt";
460 inflate $input => $output
461 or die "inflate failed: $InflateError\n";
464 To read from an existing Perl filehandle, C<$input>, and write the
465 uncompressed data to a buffer, C<$buffer>.
469 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
472 my $input = new IO::File "<file1.txt.1950"
473 or die "Cannot open 'file1.txt.1950': $!\n" ;
475 inflate $input => \$buffer
476 or die "inflate failed: $InflateError\n";
478 To uncompress all files in the directory "/my/home" that match "*.txt.1950" and store the compressed data in the same directory
482 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
484 inflate '</my/home/*.txt.1950>' => '</my/home/#1.txt>'
485 or die "inflate failed: $InflateError\n";
487 and if you want to compress each file one at a time, this will do the trick
491 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
493 for my $input ( glob "/my/home/*.txt.1950" )
496 $output =~ s/.1950// ;
497 inflate $input => $output
498 or die "Error compressing '$input': $InflateError\n";
505 The format of the constructor for IO::Uncompress::Inflate is shown below
508 my $z = new IO::Uncompress::Inflate $input [OPTS]
509 or die "IO::Uncompress::Inflate failed: $InflateError\n";
511 Returns an C<IO::Uncompress::Inflate> object on success and undef on failure.
512 The variable C<$InflateError> will contain an error message on failure.
514 If you are running Perl 5.005 or better the object, C<$z>, returned from
515 IO::Uncompress::Inflate can be used exactly like an L<IO::File|IO::File> filehandle.
516 This means that all normal input file operations can be carried out with
517 C<$z>. For example, to read a line from a compressed file/buffer you can
518 use either of these forms
520 $line = $z->getline();
523 The mandatory parameter C<$input> is used to determine the source of the
524 compressed data. This parameter can take one of three forms.
530 If the C<$input> parameter is a scalar, it is assumed to be a filename. This
531 file will be opened for reading and the compressed data will be read from it.
535 If the C<$input> parameter is a filehandle, the compressed data will be
537 The string '-' can be used as an alias for standard input.
540 =item A scalar reference
542 If C<$input> is a scalar reference, the compressed data will be read from
547 =head2 Constructor Options
550 The option names defined below are case insensitive and can be optionally
551 prefixed by a '-'. So all of the following are valid
558 OPTS is a combination of the following options:
562 =item C<< AutoClose => 0|1 >>
564 This option is only valid when the C<$input> parameter is a filehandle. If
565 specified, and the value is true, it will result in the file being closed once
566 either the C<close> method is called or the IO::Uncompress::Inflate object is
569 This parameter defaults to 0.
571 =item C<< MultiStream => 0|1 >>
575 Allows multiple concatenated compressed streams to be treated as a single
576 compressed stream. Decompression will stop once either the end of the
577 file/buffer is reached, an error is encountered (premature eof, corrupt
578 compressed data) or the end of a stream is not immediately followed by the
579 start of another stream.
581 This parameter defaults to 0.
584 =item C<< Prime => $string >>
586 This option will uncompress the contents of C<$string> before processing the
589 This option can be useful when the compressed data is embedded in another
590 file/data structure and it is not possible to work out where the compressed
591 data begins without having to read the first few bytes. If this is the
592 case, the uncompression can be I<primed> with these bytes using this
595 =item C<< Transparent => 0|1 >>
597 If this option is set and the input file or buffer is not compressed data,
598 the module will allow reading of it anyway.
600 This option defaults to 1.
602 =item C<< BlockSize => $num >>
604 When reading the compressed input data, IO::Uncompress::Inflate will read it in
605 blocks of C<$num> bytes.
607 This option defaults to 4096.
609 =item C<< InputLength => $size >>
611 When present this option will limit the number of compressed bytes read
612 from the input file/buffer to C<$size>. This option can be used in the
613 situation where there is useful data directly after the compressed data
614 stream and you know beforehand the exact length of the compressed data
617 This option is mostly used when reading from a filehandle, in which case
618 the file pointer will be left pointing to the first byte directly after the
619 compressed data stream.
623 This option defaults to off.
625 =item C<< Append => 0|1 >>
627 This option controls what the C<read> method does with uncompressed data.
629 If set to 1, all uncompressed data will be appended to the output parameter
630 of the C<read> method.
632 If set to 0, the contents of the output parameter of the C<read> method
633 will be overwritten by the uncompressed data.
637 =item C<< Strict => 0|1 >>
641 This option controls whether the extra checks defined below are used when
642 carrying out the decompression. When Strict is on, the extra tests are
643 carried out, when Strict is off they are not.
645 The default for this option is off.
655 The ADLER32 checksum field must be present.
659 The value of the ADLER32 field read must match the adler32 value of the
660 uncompressed data actually contained in the file.
686 $status = $z->read($buffer)
688 Reads a block of compressed data (the size the the compressed block is
689 determined by the C<Buffer> option in the constructor), uncompresses it and
690 writes any uncompressed data into C<$buffer>. If the C<Append> parameter is
691 set in the constructor, the uncompressed data will be appended to the
692 C<$buffer> parameter. Otherwise C<$buffer> will be overwritten.
694 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
695 or a negative number on error.
701 $status = $z->read($buffer, $length)
702 $status = $z->read($buffer, $length, $offset)
704 $status = read($z, $buffer, $length)
705 $status = read($z, $buffer, $length, $offset)
707 Attempt to read C<$length> bytes of uncompressed data into C<$buffer>.
709 The main difference between this form of the C<read> method and the
710 previous one, is that this one will attempt to return I<exactly> C<$length>
711 bytes. The only circumstances that this function will not is if end-of-file
712 or an IO error is encountered.
714 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
715 or a negative number on error.
722 $line = $z->getline()
727 This method fully supports the use of of the variable C<$/>
728 (or C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to
729 determine what constitutes an end of line. Both paragraph mode and file
730 slurp mode are supported.
739 Read a single character.
745 $char = $z->ungetc($string)
753 $status = $z->inflateSync()
762 $hdr = $z->getHeaderInfo();
763 @hdrs = $z->getHeaderInfo();
765 This method returns either a hash reference (in scalar context) or a list
766 or hash references (in array context) that contains information about each
767 of the header fields in the compressed data stream(s).
779 Returns the uncompressed file offset.
790 Returns true if the end of the compressed input stream has been reached.
796 $z->seek($position, $whence);
797 seek($z, $position, $whence);
802 Provides a sub-set of the C<seek> functionality, with the restriction
803 that it is only legal to seek forward in the input file/buffer.
804 It is a fatal error to attempt to seek backward.
808 The C<$whence> parameter takes one the usual values, namely SEEK_SET,
809 SEEK_CUR or SEEK_END.
811 Returns 1 on success, 0 on failure.
820 This is a noop provided for completeness.
826 Returns true if the object currently refers to a opened file/buffer.
830 my $prev = $z->autoflush()
831 my $prev = $z->autoflush(EXPR)
833 If the C<$z> object is associated with a file or a filehandle, this method
834 returns the current autoflush setting for the underlying filehandle. If
835 C<EXPR> is present, and is non-zero, it will enable flushing after every
836 write/print operation.
838 If C<$z> is associated with a buffer, this method has no effect and always
841 B<Note> that the special variable C<$|> B<cannot> be used to set or
842 retrieve the autoflush setting.
844 =head2 input_line_number
846 $z->input_line_number()
847 $z->input_line_number(EXPR)
851 Returns the current uncompressed line number. If C<EXPR> is present it has
852 the effect of setting the line number. Note that setting the line number
853 does not change the current position within the file/buffer being read.
855 The contents of C<$/> are used to to determine what constitutes a line
865 If the C<$z> object is associated with a file or a filehandle, this method
866 will return the underlying file descriptor.
868 If the C<$z> object is is associated with a buffer, this method will
878 Closes the output file/buffer.
882 For most versions of Perl this method will be automatically invoked if
883 the IO::Uncompress::Inflate object is destroyed (either explicitly or by the
884 variable with the reference to the object going out of scope). The
885 exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In
886 these cases, the C<close> method will be called automatically, but
887 not until global destruction of all live objects when the program is
890 Therefore, if you want your scripts to be able to run on all versions
891 of Perl, you should call C<close> explicitly and not rely on automatic
894 Returns true on success, otherwise 0.
896 If the C<AutoClose> option has been enabled when the IO::Uncompress::Inflate
897 object was created, and the object is associated with a file, the
898 underlying file will also be closed.
907 my $status = $z->nextStream();
909 Skips to the next compressed data stream in the input file/buffer. If a new
910 compressed data stream is found, the eof marker will be cleared, C<$.> will
913 Returns 1 if a new stream was found, 0 if none was found, and -1 if an
914 error was encountered.
920 my $data = $z->trailingData();
922 Returns any data that
926 No symbolic constants are required by this IO::Uncompress::Inflate at present.
932 Imports C<inflate> and C<$InflateError>.
935 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
946 L<Compress::Zlib>, L<IO::Compress::Gzip>, L<IO::Uncompress::Gunzip>, L<IO::Compress::Deflate>, 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>, L<IO::Uncompress::AnyUncompress>
948 L<Compress::Zlib::FAQ|Compress::Zlib::FAQ>
950 L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>,
951 L<Archive::Tar|Archive::Tar>,
955 For RFC 1950, 1951 and 1952 see
956 F<http://www.faqs.org/rfcs/rfc1950.html>,
957 F<http://www.faqs.org/rfcs/rfc1951.html> and
958 F<http://www.faqs.org/rfcs/rfc1952.html>
960 The I<zlib> compression library was written by Jean-loup Gailly
961 F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>.
963 The primary site for the I<zlib> compression library is
964 F<http://www.zlib.org>.
966 The primary site for gzip is F<http://www.gzip.org>.
973 This module was written by Paul Marquess, F<pmqs@cpan.org>.
977 =head1 MODIFICATION HISTORY
979 See the Changes file.
981 =head1 COPYRIGHT AND LICENSE
983 Copyright (c) 2005-2006 Paul Marquess. All rights reserved.
985 This program is free software; you can redistribute it and/or
986 modify it under the same terms as Perl itself.