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_11';
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()
207 $data = $z->getHeaderInfo()
209 $z->seek($position, $whence)
221 read($z, $buffer, $length);
222 read($z, $buffer, $length, $offset);
224 seek($z, $position, $whence)
235 B<WARNING -- This is a Beta release>.
239 =item * DO NOT use in production code.
241 =item * The documentation is incomplete in places.
243 =item * Parts of the interface defined here are tentative.
245 =item * Please report any problems you find.
253 This module provides a Perl interface that allows the reading of
254 files/buffers that conform to RFC 1950.
256 For writing RFC 1950 files/buffers, see the companion module IO::Compress::Deflate.
263 =head1 Functional Interface
265 A top-level function, C<inflate>, is provided to carry out
266 "one-shot" uncompression between buffers and/or files. For finer
267 control over the uncompression process, see the L</"OO Interface">
270 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
272 inflate $input => $output [,OPTS]
273 or die "inflate failed: $InflateError\n";
277 The functional interface needs Perl5.005 or better.
280 =head2 inflate $input => $output [, OPTS]
283 C<inflate> expects at least two parameters, C<$input> and C<$output>.
285 =head3 The C<$input> parameter
287 The parameter, C<$input>, is used to define the source of
290 It can take one of the following forms:
296 If the C<$input> parameter is a simple scalar, it is assumed to be a
297 filename. This file will be opened for reading and the input data
298 will be read from it.
302 If the C<$input> parameter is a filehandle, the input data will be
304 The string '-' can be used as an alias for standard input.
306 =item A scalar reference
308 If C<$input> is a scalar reference, the input data will be read
311 =item An array reference
313 If C<$input> is an array reference, each element in the array must be a
316 The input data will be read from each file in turn.
318 The complete array will be walked to ensure that it only
319 contains valid filenames before any data is uncompressed.
323 =item An Input FileGlob string
325 If C<$input> is a string that is delimited by the characters "<" and ">"
326 C<inflate> will assume that it is an I<input fileglob string>. The
327 input is the list of files that match the fileglob.
329 If the fileglob does not match any files ...
331 See L<File::GlobMapper|File::GlobMapper> for more details.
336 If the C<$input> parameter is any other type, C<undef> will be returned.
340 =head3 The C<$output> parameter
342 The parameter C<$output> is used to control the destination of the
343 uncompressed data. This parameter can take one of these forms.
349 If the C<$output> parameter is a simple scalar, it is assumed to be a
350 filename. This file will be opened for writing and the uncompressed
351 data will be written to it.
355 If the C<$output> parameter is a filehandle, the uncompressed data
356 will be written to it.
357 The string '-' can be used as an alias for standard output.
360 =item A scalar reference
362 If C<$output> is a scalar reference, the uncompressed data will be
363 stored in C<$$output>.
367 =item An Array Reference
369 If C<$output> is an array reference, the uncompressed data will be
370 pushed onto the array.
372 =item An Output FileGlob
374 If C<$output> is a string that is delimited by the characters "<" and ">"
375 C<inflate> will assume that it is an I<output fileglob string>. The
376 output is the list of files that match the fileglob.
378 When C<$output> is an fileglob string, C<$input> must also be a fileglob
379 string. Anything else is an error.
383 If the C<$output> parameter is any other type, C<undef> will be returned.
389 When C<$input> maps to multiple files/buffers and C<$output> is a single
390 file/buffer the uncompressed input files/buffers will all be stored
391 in C<$output> as a single uncompressed stream.
395 =head2 Optional Parameters
397 Unless specified below, the optional parameters for C<inflate>,
398 C<OPTS>, are the same as those used with the OO interface defined in the
399 L</"Constructor Options"> section below.
403 =item AutoClose =E<gt> 0|1
405 This option applies to any input or output data streams to
406 C<inflate> that are filehandles.
408 If C<AutoClose> is specified, and the value is true, it will result in all
409 input and/or output filehandles being closed once C<inflate> has
412 This parameter defaults to 0.
416 =item BinModeOut =E<gt> 0|1
418 When writing to a file or filehandle, set C<binmode> before writing to the
427 =item -Append =E<gt> 0|1
431 =item -MultiStream =E<gt> 0|1
433 Creates a new stream after each file.
446 To read the contents of the file C<file1.txt.1950> and write the
447 compressed data to the file C<file1.txt>.
451 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
453 my $input = "file1.txt.1950";
454 my $output = "file1.txt";
455 inflate $input => $output
456 or die "inflate failed: $InflateError\n";
459 To read from an existing Perl filehandle, C<$input>, and write the
460 uncompressed data to a buffer, C<$buffer>.
464 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
467 my $input = new IO::File "<file1.txt.1950"
468 or die "Cannot open 'file1.txt.1950': $!\n" ;
470 inflate $input => \$buffer
471 or die "inflate failed: $InflateError\n";
473 To uncompress all files in the directory "/my/home" that match "*.txt.1950" and store the compressed data in the same directory
477 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
479 inflate '</my/home/*.txt.1950>' => '</my/home/#1.txt>'
480 or die "inflate failed: $InflateError\n";
482 and if you want to compress each file one at a time, this will do the trick
486 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
488 for my $input ( glob "/my/home/*.txt.1950" )
491 $output =~ s/.1950// ;
492 inflate $input => $output
493 or die "Error compressing '$input': $InflateError\n";
500 The format of the constructor for IO::Uncompress::Inflate is shown below
503 my $z = new IO::Uncompress::Inflate $input [OPTS]
504 or die "IO::Uncompress::Inflate failed: $InflateError\n";
506 Returns an C<IO::Uncompress::Inflate> object on success and undef on failure.
507 The variable C<$InflateError> will contain an error message on failure.
509 If you are running Perl 5.005 or better the object, C<$z>, returned from
510 IO::Uncompress::Inflate can be used exactly like an L<IO::File|IO::File> filehandle.
511 This means that all normal input file operations can be carried out with
512 C<$z>. For example, to read a line from a compressed file/buffer you can
513 use either of these forms
515 $line = $z->getline();
518 The mandatory parameter C<$input> is used to determine the source of the
519 compressed data. This parameter can take one of three forms.
525 If the C<$input> parameter is a scalar, it is assumed to be a filename. This
526 file will be opened for reading and the compressed data will be read from it.
530 If the C<$input> parameter is a filehandle, the compressed data will be
532 The string '-' can be used as an alias for standard input.
535 =item A scalar reference
537 If C<$input> is a scalar reference, the compressed data will be read from
542 =head2 Constructor Options
545 The option names defined below are case insensitive and can be optionally
546 prefixed by a '-'. So all of the following are valid
553 OPTS is a combination of the following options:
557 =item -AutoClose =E<gt> 0|1
559 This option is only valid when the C<$input> parameter is a filehandle. If
560 specified, and the value is true, it will result in the file being closed once
561 either the C<close> method is called or the IO::Uncompress::Inflate object is
564 This parameter defaults to 0.
566 =item -MultiStream =E<gt> 0|1
570 Allows multiple concatenated compressed streams to be treated as a single
571 compressed stream. Decompression will stop once either the end of the
572 file/buffer is reached, an error is encountered (premature eof, corrupt
573 compressed data) or the end of a stream is not immediately followed by the
574 start of another stream.
576 This parameter defaults to 0.
580 =item -Prime =E<gt> $string
582 This option will uncompress the contents of C<$string> before processing the
585 This option can be useful when the compressed data is embedded in another
586 file/data structure and it is not possible to work out where the compressed
587 data begins without having to read the first few bytes. If this is the
588 case, the uncompression can be I<primed> with these bytes using this
591 =item -Transparent =E<gt> 0|1
593 If this option is set and the input file or buffer is not compressed data,
594 the module will allow reading of it anyway.
596 This option defaults to 1.
598 =item -BlockSize =E<gt> $num
600 When reading the compressed input data, IO::Uncompress::Inflate will read it in
601 blocks of C<$num> bytes.
603 This option defaults to 4096.
605 =item -InputLength =E<gt> $size
607 When present this option will limit the number of compressed bytes read
608 from the input file/buffer to C<$size>. This option can be used in the
609 situation where there is useful data directly after the compressed data
610 stream and you know beforehand the exact length of the compressed data
613 This option is mostly used when reading from a filehandle, in which case
614 the file pointer will be left pointing to the first byte directly after the
615 compressed data stream.
619 This option defaults to off.
621 =item -Append =E<gt> 0|1
623 This option controls what the C<read> method does with uncompressed data.
625 If set to 1, all uncompressed data will be appended to the output parameter
626 of the C<read> method.
628 If set to 0, the contents of the output parameter of the C<read> method
629 will be overwritten by the uncompressed data.
633 =item -Strict =E<gt> 0|1
637 This option controls whether the extra checks defined below are used when
638 carrying out the decompression. When Strict is on, the extra tests are
639 carried out, when Strict is off they are not.
641 The default for this option is off.
651 The ADLER32 checksum field must be present.
655 The value of the ADLER32 field read must match the adler32 value of the
656 uncompressed data actually contained in the file.
682 $status = $z->read($buffer)
684 Reads a block of compressed data (the size the the compressed block is
685 determined by the C<Buffer> option in the constructor), uncompresses it and
686 writes any uncompressed data into C<$buffer>. If the C<Append> parameter is
687 set in the constructor, the uncompressed data will be appended to the
688 C<$buffer> parameter. Otherwise C<$buffer> will be overwritten.
690 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
691 or a negative number on error.
697 $status = $z->read($buffer, $length)
698 $status = $z->read($buffer, $length, $offset)
700 $status = read($z, $buffer, $length)
701 $status = read($z, $buffer, $length, $offset)
703 Attempt to read C<$length> bytes of uncompressed data into C<$buffer>.
705 The main difference between this form of the C<read> method and the
706 previous one, is that this one will attempt to return I<exactly> C<$length>
707 bytes. The only circumstances that this function will not is if end-of-file
708 or an IO error is encountered.
710 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
711 or a negative number on error.
718 $line = $z->getline()
723 This method fully supports the use of of the variable C<$/>
724 (or C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to
725 determine what constitutes an end of line. Both paragraph mode and file
726 slurp mode are supported.
735 Read a single character.
741 $char = $z->ungetc($string)
749 $status = $z->inflateSync()
758 $hdr = $z->getHeaderInfo();
759 @hdrs = $z->getHeaderInfo();
761 This method returns either a hash reference (in scalar context) or a list
762 or hash references (in array context) that contains information about each
763 of the header fields in the compressed data stream(s).
775 Returns the uncompressed file offset.
786 Returns true if the end of the compressed input stream has been reached.
792 $z->seek($position, $whence);
793 seek($z, $position, $whence);
798 Provides a sub-set of the C<seek> functionality, with the restriction
799 that it is only legal to seek forward in the input file/buffer.
800 It is a fatal error to attempt to seek backward.
804 The C<$whence> parameter takes one the usual values, namely SEEK_SET,
805 SEEK_CUR or SEEK_END.
807 Returns 1 on success, 0 on failure.
816 This is a noop provided for completeness.
822 Returns true if the object currently refers to a opened file/buffer.
826 my $prev = $z->autoflush()
827 my $prev = $z->autoflush(EXPR)
829 If the C<$z> object is associated with a file or a filehandle, this method
830 returns the current autoflush setting for the underlying filehandle. If
831 C<EXPR> is present, and is non-zero, it will enable flushing after every
832 write/print operation.
834 If C<$z> is associated with a buffer, this method has no effect and always
837 B<Note> that the special variable C<$|> B<cannot> be used to set or
838 retrieve the autoflush setting.
840 =head2 input_line_number
842 $z->input_line_number()
843 $z->input_line_number(EXPR)
847 Returns the current uncompressed line number. If C<EXPR> is present it has
848 the effect of setting the line number. Note that setting the line number
849 does not change the current position within the file/buffer being read.
851 The contents of C<$/> are used to to determine what constitutes a line
861 If the C<$z> object is associated with a file or a filehandle, this method
862 will return the underlying file descriptor.
864 If the C<$z> object is is associated with a buffer, this method will
874 Closes the output file/buffer.
878 For most versions of Perl this method will be automatically invoked if
879 the IO::Uncompress::Inflate object is destroyed (either explicitly or by the
880 variable with the reference to the object going out of scope). The
881 exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In
882 these cases, the C<close> method will be called automatically, but
883 not until global destruction of all live objects when the program is
886 Therefore, if you want your scripts to be able to run on all versions
887 of Perl, you should call C<close> explicitly and not rely on automatic
890 Returns true on success, otherwise 0.
892 If the C<AutoClose> option has been enabled when the IO::Uncompress::Inflate
893 object was created, and the object is associated with a file, the
894 underlying file will also be closed.
901 No symbolic constants are required by this IO::Uncompress::Inflate at present.
907 Imports C<inflate> and C<$InflateError>.
910 use IO::Uncompress::Inflate qw(inflate $InflateError) ;
921 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>
923 L<Compress::Zlib::FAQ|Compress::Zlib::FAQ>
925 L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>,
926 L<Archive::Tar|Archive::Tar>,
930 For RFC 1950, 1951 and 1952 see
931 F<http://www.faqs.org/rfcs/rfc1950.html>,
932 F<http://www.faqs.org/rfcs/rfc1951.html> and
933 F<http://www.faqs.org/rfcs/rfc1952.html>
935 The I<zlib> compression library was written by Jean-loup Gailly
936 F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>.
938 The primary site for the I<zlib> compression library is
939 F<http://www.zlib.org>.
941 The primary site for gzip is F<http://www.gzip.org>.
948 This module was written by Paul Marquess, F<pmqs@cpan.org>.
952 =head1 MODIFICATION HISTORY
954 See the Changes file.
956 =head1 COPYRIGHT AND LICENSE
958 Copyright (c) 2005-2006 Paul Marquess. All rights reserved.
960 This program is free software; you can redistribute it and/or
961 modify it under the same terms as Perl itself.