1 package IO::Uncompress::RawInflate ;
8 use Compress::Raw::Zlib ;
9 use IO::Compress::Base::Common qw(:Status createSelfTiedObject);
11 use IO::Uncompress::Base ;
12 use IO::Uncompress::Adapter::Inflate ;
18 our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, %DEFLATE_CONSTANTS, $RawInflateError);
20 $VERSION = '2.000_14';
21 $RawInflateError = '';
23 @ISA = qw( Exporter IO::Uncompress::Base );
24 @EXPORT_OK = qw( $RawInflateError rawinflate ) ;
25 %DEFLATE_CONSTANTS = ();
26 %EXPORT_TAGS = %IO::Uncompress::Base::EXPORT_TAGS ;
27 push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ;
28 Exporter::export_ok_tags('all');
35 my $obj = createSelfTiedObject($class, \$RawInflateError);
36 $obj->_create(undef, 0, @_);
41 my $obj = createSelfTiedObject(undef, \$RawInflateError);
42 return $obj->_inf(@_);
64 my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject(
66 $got->value('ADLER32'),
70 return $self->saveErrorString(undef, $errstr, $errno)
73 *$self->{Uncomp} = $obj;
75 my $magic = $self->ckMagic()
78 *$self->{Info} = $self->readHeader($magic)
90 return $self->_isRaw() ;
100 'FingerprintLength' => 0,
102 'TrailerLength' => 0,
116 my $got = $self->_isRawx(@_);
119 *$self->{Pending} = *$self->{HeaderPending} ;
122 $self->pushBack(*$self->{HeaderPending});
123 *$self->{Uncomp}->reset();
125 *$self->{HeaderPending} = '';
135 $magic = '' unless defined $magic ;
139 $self->smartRead(\$buffer, *$self->{BlockSize}) >= 0
140 or return $self->saveErrorString(undef, "No data to read");
142 my $temp_buf = $magic . $buffer ;
143 *$self->{HeaderPending} = $temp_buf ;
145 my $status = *$self->{Uncomp}->uncompr(\$temp_buf, \$buffer, $self->smartEof()) ;
146 return $self->saveErrorString(undef, *$self->{Uncomp}{Error}, STATUS_ERROR)
147 if $status == STATUS_ERROR;
149 #my $buf_len = *$self->{Uncomp}->uncompressedBytes();
150 my $buf_len = length $buffer;
152 if ($status == STATUS_ENDSTREAM) {
153 if (*$self->{MultiStream}
154 && (length $temp_buf || ! $self->smartEof())){
155 *$self->{NewStream} = 1 ;
156 *$self->{EndStream} = 0 ;
157 $self->pushBack($temp_buf);
160 *$self->{EndStream} = 1 ;
161 $self->pushBack($temp_buf);
164 *$self->{HeaderPending} = $buffer ;
165 *$self->{InflatedBytesRead} = $buf_len ;
166 *$self->{TotalInflatedBytesRead} += $buf_len ;
167 *$self->{Type} = 'rfc1951';
169 $self->saveStatus(STATUS_OK);
174 'TrailerLength' => 0,
184 # inflateSync is a no-op in Plain mode
188 return 0 if *$self->{Closed} ;
189 #return G_EOF if !length *$self->{Pending} && *$self->{EndStream} ;
190 return 0 if ! length *$self->{Pending} && *$self->{EndStream} ;
193 *$self->{Strict} = 0 ;
200 if (length *$self->{Pending} )
202 $temp_buf = *$self->{Pending} ;
203 *$self->{Pending} = '';
207 $status = $self->smartRead(\$temp_buf, *$self->{BlockSize}) ;
208 return $self->saveErrorString(0, "Error Reading Data")
212 *$self->{EndStream} = 1 ;
213 return $self->saveErrorString(0, "unexpected end of file", STATUS_ERROR);
217 $status = *$self->{Uncomp}->sync($temp_buf) ;
219 if ($status == STATUS_OK)
221 *$self->{Pending} .= $temp_buf ;
225 last unless $status == STATUS_ERROR ;
236 # my $end_offset = 0;
238 # $status = $self->scan()
239 # #or return $self->saveErrorString(undef, "Error Scanning: $$error_ref", $self->errorNo) ;
240 # or return $self->saveErrorString(G_ERR, "Error Scanning: $status")
242 # $status = $self->zap($end_offset)
243 # or return $self->saveErrorString(G_ERR, "Error Zapping: $status");
244 # #or return $self->saveErrorString(undef, "Error Zapping: $$error_ref", $self->errorNo) ;
246 # #(*$obj->{Deflate}, $status) = $inf->createDeflate();
248 ## *$obj->{Header} = *$inf->{Info}{Header};
249 ## *$obj->{UnCompSize_32bit} =
250 ## *$obj->{BytesWritten} = *$inf->{UnCompSize_32bit} ;
251 ## *$obj->{CompSize_32bit} = *$inf->{CompSize_32bit} ;
254 ## if ( $outType eq 'buffer')
255 ## { substr( ${ *$self->{Buffer} }, $end_offset) = '' }
256 ## elsif ($outType eq 'handle' || $outType eq 'filename') {
257 ## *$self->{FH} = *$inf->{FH} ;
258 ## delete *$inf->{FH};
259 ## *$obj->{FH}->flush() ;
260 ## *$obj->{Handle} = 1 if $outType eq 'handle';
262 ## #seek(*$obj->{FH}, $end_offset, SEEK_SET)
263 ## *$obj->{FH}->seek($end_offset, SEEK_SET)
264 ## or return $obj->saveErrorString(undef, $!, $!) ;
273 return 1 if *$self->{Closed} ;
274 return 1 if !length *$self->{Pending} && *$self->{EndStream} ;
279 $len = $self->_raw_read(\$buffer, 1)
280 while ! *$self->{EndStream} && $len >= 0 ;
282 #return $len if $len < 0 ? $len : 0 ;
283 return $len < 0 ? 0 : 1 ;
290 my $headerLength = *$self->{Info}{HeaderLength};
291 my $block_offset = $headerLength + *$self->{Uncomp}->getLastBlockOffset();
292 $_[0] = $headerLength + *$self->{Uncomp}->getEndOffset();
293 #printf "# End $_[0], headerlen $headerLength \n";;
294 #printf "# block_offset $block_offset %x\n", $block_offset;
296 ( $self->smartSeek($block_offset) &&
297 $self->smartRead(\$byte, 1) )
298 or return $self->saveErrorString(0, $!, $!);
300 #printf "#byte is %x\n", unpack('C*',$byte);
301 *$self->{Uncomp}->resetLastBlockByte($byte);
302 #printf "#to byte is %x\n", unpack('C*',$byte);
304 ( $self->smartSeek($block_offset) &&
305 $self->smartWrite($byte) )
306 or return $self->saveErrorString(0, $!, $!);
308 #$self->smartSeek($end_offset, 1);
316 my ($def, $status) = *$self->{Uncomp}->createDeflateStream(
318 -WindowBits => - MAX_WBITS,
319 -CRC32 => *$self->{Params}->value('CRC32'),
320 -ADLER32 => *$self->{Params}->value('ADLER32'),
323 return wantarray ? ($status, $def) : $def ;
336 IO::Uncompress::RawInflate - Read RFC 1951 files/buffers
342 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
344 my $status = rawinflate $input => $output [,OPTS]
345 or die "rawinflate failed: $RawInflateError\n";
347 my $z = new IO::Uncompress::RawInflate $input [OPTS]
348 or die "rawinflate failed: $RawInflateError\n";
350 $status = $z->read($buffer)
351 $status = $z->read($buffer, $length)
352 $status = $z->read($buffer, $length, $offset)
353 $line = $z->getline()
358 $status = $z->inflateSync()
360 $data = $z->trailingData()
361 $status = $z->nextStream()
362 $data = $z->getHeaderInfo()
364 $z->seek($position, $whence)
376 read($z, $buffer, $length);
377 read($z, $buffer, $length, $offset);
379 seek($z, $position, $whence)
390 B<WARNING -- This is a Beta release>.
394 =item * DO NOT use in production code.
396 =item * The documentation is incomplete in places.
398 =item * Parts of the interface defined here are tentative.
400 =item * Please report any problems you find.
408 This module provides a Perl interface that allows the reading of
409 files/buffers that conform to RFC 1951.
411 For writing RFC 1951 files/buffers, see the companion module IO::Compress::RawDeflate.
417 =head1 Functional Interface
419 A top-level function, C<rawinflate>, is provided to carry out
420 "one-shot" uncompression between buffers and/or files. For finer
421 control over the uncompression process, see the L</"OO Interface">
424 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
426 rawinflate $input => $output [,OPTS]
427 or die "rawinflate failed: $RawInflateError\n";
431 The functional interface needs Perl5.005 or better.
434 =head2 rawinflate $input => $output [, OPTS]
437 C<rawinflate> expects at least two parameters, C<$input> and C<$output>.
439 =head3 The C<$input> parameter
441 The parameter, C<$input>, is used to define the source of
444 It can take one of the following forms:
450 If the C<$input> parameter is a simple scalar, it is assumed to be a
451 filename. This file will be opened for reading and the input data
452 will be read from it.
456 If the C<$input> parameter is a filehandle, the input data will be
458 The string '-' can be used as an alias for standard input.
460 =item A scalar reference
462 If C<$input> is a scalar reference, the input data will be read
465 =item An array reference
467 If C<$input> is an array reference, each element in the array must be a
470 The input data will be read from each file in turn.
472 The complete array will be walked to ensure that it only
473 contains valid filenames before any data is uncompressed.
477 =item An Input FileGlob string
479 If C<$input> is a string that is delimited by the characters "<" and ">"
480 C<rawinflate> will assume that it is an I<input fileglob string>. The
481 input is the list of files that match the fileglob.
483 If the fileglob does not match any files ...
485 See L<File::GlobMapper|File::GlobMapper> for more details.
490 If the C<$input> parameter is any other type, C<undef> will be returned.
494 =head3 The C<$output> parameter
496 The parameter C<$output> is used to control the destination of the
497 uncompressed data. This parameter can take one of these forms.
503 If the C<$output> parameter is a simple scalar, it is assumed to be a
504 filename. This file will be opened for writing and the uncompressed
505 data will be written to it.
509 If the C<$output> parameter is a filehandle, the uncompressed data
510 will be written to it.
511 The string '-' can be used as an alias for standard output.
514 =item A scalar reference
516 If C<$output> is a scalar reference, the uncompressed data will be
517 stored in C<$$output>.
521 =item An Array Reference
523 If C<$output> is an array reference, the uncompressed data will be
524 pushed onto the array.
526 =item An Output FileGlob
528 If C<$output> is a string that is delimited by the characters "<" and ">"
529 C<rawinflate> will assume that it is an I<output fileglob string>. The
530 output is the list of files that match the fileglob.
532 When C<$output> is an fileglob string, C<$input> must also be a fileglob
533 string. Anything else is an error.
537 If the C<$output> parameter is any other type, C<undef> will be returned.
544 When C<$input> maps to multiple compressed files/buffers and C<$output> is
545 a single file/buffer, after uncompression C<$output> will contain a
546 concatenation of all the uncompressed data from each of the input
553 =head2 Optional Parameters
555 Unless specified below, the optional parameters for C<rawinflate>,
556 C<OPTS>, are the same as those used with the OO interface defined in the
557 L</"Constructor Options"> section below.
561 =item C<< AutoClose => 0|1 >>
563 This option applies to any input or output data streams to
564 C<rawinflate> that are filehandles.
566 If C<AutoClose> is specified, and the value is true, it will result in all
567 input and/or output filehandles being closed once C<rawinflate> has
570 This parameter defaults to 0.
573 =item C<< BinModeOut => 0|1 >>
575 When writing to a file or filehandle, set C<binmode> before writing to the
584 =item C<< Append => 0|1 >>
588 =item C<< MultiStream => 0|1 >>
592 This option is a no-op.
598 =item C<< TrailingData => $scalar >>
600 Returns the data, if any, that is present immediately after the compressed
601 data stream once uncompression is complete.
603 This option can be used when there is useful information immediately
604 following the compressed data stream, and you don't know the length of the
605 compressed data stream.
607 If the input is a buffer, C<trailingData> will return everything from the
608 end of the compressed data stream to the end of the buffer.
610 If the input is a filehandle, C<trailingData> will return the data that is
611 left in the filehandle input buffer once the end of the compressed data
612 stream has been reached. You can then use the filehandle to read the rest
615 Don't bother using C<trailingData> if the input is a filename.
619 If you know the length of the compressed data stream before you start
620 uncompressing, you can avoid having to use C<trailingData> by setting the
621 C<InputLength> option.
632 To read the contents of the file C<file1.txt.1951> and write the
633 compressed data to the file C<file1.txt>.
637 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
639 my $input = "file1.txt.1951";
640 my $output = "file1.txt";
641 rawinflate $input => $output
642 or die "rawinflate failed: $RawInflateError\n";
645 To read from an existing Perl filehandle, C<$input>, and write the
646 uncompressed data to a buffer, C<$buffer>.
650 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
653 my $input = new IO::File "<file1.txt.1951"
654 or die "Cannot open 'file1.txt.1951': $!\n" ;
656 rawinflate $input => \$buffer
657 or die "rawinflate failed: $RawInflateError\n";
659 To uncompress all files in the directory "/my/home" that match "*.txt.1951" and store the compressed data in the same directory
663 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
665 rawinflate '</my/home/*.txt.1951>' => '</my/home/#1.txt>'
666 or die "rawinflate failed: $RawInflateError\n";
668 and if you want to compress each file one at a time, this will do the trick
672 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
674 for my $input ( glob "/my/home/*.txt.1951" )
677 $output =~ s/.1951// ;
678 rawinflate $input => $output
679 or die "Error compressing '$input': $RawInflateError\n";
686 The format of the constructor for IO::Uncompress::RawInflate is shown below
689 my $z = new IO::Uncompress::RawInflate $input [OPTS]
690 or die "IO::Uncompress::RawInflate failed: $RawInflateError\n";
692 Returns an C<IO::Uncompress::RawInflate> object on success and undef on failure.
693 The variable C<$RawInflateError> will contain an error message on failure.
695 If you are running Perl 5.005 or better the object, C<$z>, returned from
696 IO::Uncompress::RawInflate can be used exactly like an L<IO::File|IO::File> filehandle.
697 This means that all normal input file operations can be carried out with
698 C<$z>. For example, to read a line from a compressed file/buffer you can
699 use either of these forms
701 $line = $z->getline();
704 The mandatory parameter C<$input> is used to determine the source of the
705 compressed data. This parameter can take one of three forms.
711 If the C<$input> parameter is a scalar, it is assumed to be a filename. This
712 file will be opened for reading and the compressed data will be read from it.
716 If the C<$input> parameter is a filehandle, the compressed data will be
718 The string '-' can be used as an alias for standard input.
721 =item A scalar reference
723 If C<$input> is a scalar reference, the compressed data will be read from
728 =head2 Constructor Options
731 The option names defined below are case insensitive and can be optionally
732 prefixed by a '-'. So all of the following are valid
739 OPTS is a combination of the following options:
743 =item C<< AutoClose => 0|1 >>
745 This option is only valid when the C<$input> parameter is a filehandle. If
746 specified, and the value is true, it will result in the file being closed once
747 either the C<close> method is called or the IO::Uncompress::RawInflate object is
750 This parameter defaults to 0.
752 =item C<< MultiStream => 0|1 >>
756 This option is a no-op.
760 =item C<< Prime => $string >>
762 This option will uncompress the contents of C<$string> before processing the
765 This option can be useful when the compressed data is embedded in another
766 file/data structure and it is not possible to work out where the compressed
767 data begins without having to read the first few bytes. If this is the
768 case, the uncompression can be I<primed> with these bytes using this
771 =item C<< Transparent => 0|1 >>
773 If this option is set and the input file or buffer is not compressed data,
774 the module will allow reading of it anyway.
776 This option defaults to 1.
778 =item C<< BlockSize => $num >>
780 When reading the compressed input data, IO::Uncompress::RawInflate will read it in
781 blocks of C<$num> bytes.
783 This option defaults to 4096.
785 =item C<< InputLength => $size >>
787 When present this option will limit the number of compressed bytes read
788 from the input file/buffer to C<$size>. This option can be used in the
789 situation where there is useful data directly after the compressed data
790 stream and you know beforehand the exact length of the compressed data
793 This option is mostly used when reading from a filehandle, in which case
794 the file pointer will be left pointing to the first byte directly after the
795 compressed data stream.
799 This option defaults to off.
801 =item C<< Append => 0|1 >>
803 This option controls what the C<read> method does with uncompressed data.
805 If set to 1, all uncompressed data will be appended to the output parameter
806 of the C<read> method.
808 If set to 0, the contents of the output parameter of the C<read> method
809 will be overwritten by the uncompressed data.
813 =item C<< Strict => 0|1 >>
817 This option is a no-op.
837 $status = $z->read($buffer)
839 Reads a block of compressed data (the size the the compressed block is
840 determined by the C<Buffer> option in the constructor), uncompresses it and
841 writes any uncompressed data into C<$buffer>. If the C<Append> parameter is
842 set in the constructor, the uncompressed data will be appended to the
843 C<$buffer> parameter. Otherwise C<$buffer> will be overwritten.
845 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
846 or a negative number on error.
852 $status = $z->read($buffer, $length)
853 $status = $z->read($buffer, $length, $offset)
855 $status = read($z, $buffer, $length)
856 $status = read($z, $buffer, $length, $offset)
858 Attempt to read C<$length> bytes of uncompressed data into C<$buffer>.
860 The main difference between this form of the C<read> method and the
861 previous one, is that this one will attempt to return I<exactly> C<$length>
862 bytes. The only circumstances that this function will not is if end-of-file
863 or an IO error is encountered.
865 Returns the number of uncompressed bytes written to C<$buffer>, zero if eof
866 or a negative number on error.
873 $line = $z->getline()
878 This method fully supports the use of of the variable C<$/> (or
879 C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to
880 determine what constitutes an end of line. Paragraph mode, record mode and
881 file slurp mode are all supported.
890 Read a single character.
896 $char = $z->ungetc($string)
904 $status = $z->inflateSync()
913 $hdr = $z->getHeaderInfo();
914 @hdrs = $z->getHeaderInfo();
916 This method returns either a hash reference (in scalar context) or a list
917 or hash references (in array context) that contains information about each
918 of the header fields in the compressed data stream(s).
930 Returns the uncompressed file offset.
941 Returns true if the end of the compressed input stream has been reached.
947 $z->seek($position, $whence);
948 seek($z, $position, $whence);
953 Provides a sub-set of the C<seek> functionality, with the restriction
954 that it is only legal to seek forward in the input file/buffer.
955 It is a fatal error to attempt to seek backward.
959 The C<$whence> parameter takes one the usual values, namely SEEK_SET,
960 SEEK_CUR or SEEK_END.
962 Returns 1 on success, 0 on failure.
971 This is a noop provided for completeness.
977 Returns true if the object currently refers to a opened file/buffer.
981 my $prev = $z->autoflush()
982 my $prev = $z->autoflush(EXPR)
984 If the C<$z> object is associated with a file or a filehandle, this method
985 returns the current autoflush setting for the underlying filehandle. If
986 C<EXPR> is present, and is non-zero, it will enable flushing after every
987 write/print operation.
989 If C<$z> is associated with a buffer, this method has no effect and always
992 B<Note> that the special variable C<$|> B<cannot> be used to set or
993 retrieve the autoflush setting.
995 =head2 input_line_number
997 $z->input_line_number()
998 $z->input_line_number(EXPR)
1002 Returns the current uncompressed line number. If C<EXPR> is present it has
1003 the effect of setting the line number. Note that setting the line number
1004 does not change the current position within the file/buffer being read.
1006 The contents of C<$/> are used to to determine what constitutes a line
1016 If the C<$z> object is associated with a file or a filehandle, this method
1017 will return the underlying file descriptor.
1019 If the C<$z> object is is associated with a buffer, this method will
1029 Closes the output file/buffer.
1033 For most versions of Perl this method will be automatically invoked if
1034 the IO::Uncompress::RawInflate object is destroyed (either explicitly or by the
1035 variable with the reference to the object going out of scope). The
1036 exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In
1037 these cases, the C<close> method will be called automatically, but
1038 not until global destruction of all live objects when the program is
1041 Therefore, if you want your scripts to be able to run on all versions
1042 of Perl, you should call C<close> explicitly and not rely on automatic
1045 Returns true on success, otherwise 0.
1047 If the C<AutoClose> option has been enabled when the IO::Uncompress::RawInflate
1048 object was created, and the object is associated with a file, the
1049 underlying file will also be closed.
1058 my $status = $z->nextStream();
1060 Skips to the next compressed data stream in the input file/buffer. If a new
1061 compressed data stream is found, the eof marker will be cleared and C<$.>
1064 Returns 1 if a new stream was found, 0 if none was found, and -1 if an
1065 error was encountered.
1071 my $data = $z->trailingData();
1073 Returns the data, if any, that is present immediately after the compressed
1074 data stream once uncompression is complete. It only makes sense to call
1075 this method once the end of the compressed data stream has been
1078 This option can be used when there is useful information immediately
1079 following the compressed data stream, and you don't know the length of the
1080 compressed data stream.
1082 If the input is a buffer, C<trailingData> will return everything from the
1083 end of the compressed data stream to the end of the buffer.
1085 If the input is a filehandle, C<trailingData> will return the data that is
1086 left in the filehandle input buffer once the end of the compressed data
1087 stream has been reached. You can then use the filehandle to read the rest
1090 Don't bother using C<trailingData> if the input is a filename.
1094 If you know the length of the compressed data stream before you start
1095 uncompressing, you can avoid having to use C<trailingData> by setting the
1096 C<InputLength> option in the constructor.
1100 No symbolic constants are required by this IO::Uncompress::RawInflate at present.
1106 Imports C<rawinflate> and C<$RawInflateError>.
1109 use IO::Uncompress::RawInflate qw(rawinflate $RawInflateError) ;
1120 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::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>, L<IO::Uncompress::AnyUncompress>
1122 L<Compress::Zlib::FAQ|Compress::Zlib::FAQ>
1124 L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>,
1125 L<Archive::Tar|Archive::Tar>,
1126 L<IO::Zlib|IO::Zlib>
1129 For RFC 1950, 1951 and 1952 see
1130 F<http://www.faqs.org/rfcs/rfc1950.html>,
1131 F<http://www.faqs.org/rfcs/rfc1951.html> and
1132 F<http://www.faqs.org/rfcs/rfc1952.html>
1134 The I<zlib> compression library was written by Jean-loup Gailly
1135 F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>.
1137 The primary site for the I<zlib> compression library is
1138 F<http://www.zlib.org>.
1140 The primary site for gzip is F<http://www.gzip.org>.
1147 This module was written by Paul Marquess, F<pmqs@cpan.org>.
1151 =head1 MODIFICATION HISTORY
1153 See the Changes file.
1155 =head1 COPYRIGHT AND LICENSE
1157 Copyright (c) 2005-2006 Paul Marquess. All rights reserved.
1159 This program is free software; you can redistribute it and/or
1160 modify it under the same terms as Perl itself.