Commit | Line | Data |
25f0751f |
1 | package IO::Uncompress::AnyUncompress ; |
2 | |
3 | use strict; |
4 | use warnings; |
5 | use bytes; |
6 | |
10c2b2bb |
7 | use IO::Compress::Base::Common 2.021 qw(createSelfTiedObject); |
25f0751f |
8 | |
10c2b2bb |
9 | use IO::Uncompress::Base 2.021 ; |
25f0751f |
10 | |
25f0751f |
11 | |
12 | require Exporter ; |
13 | |
14 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyUncompressError); |
15 | |
10c2b2bb |
16 | $VERSION = '2.021'; |
25f0751f |
17 | $AnyUncompressError = ''; |
18 | |
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'); |
24 | |
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. |
27 | |
258133d1 |
28 | BEGIN |
29 | { |
10c2b2bb |
30 | eval ' use IO::Uncompress::Adapter::Inflate 2.021 ;'; |
31 | eval ' use IO::Uncompress::Adapter::Bunzip2 2.021 ;'; |
32 | eval ' use IO::Uncompress::Adapter::LZO 2.021 ;'; |
33 | eval ' use IO::Uncompress::Adapter::Lzf 2.021 ;'; |
34 | eval ' use IO::Uncompress::Adapter::UnLzma 2.020 ;'; |
35 | eval ' use IO::Uncompress::Adapter::UnXz 2.020 ;'; |
36 | |
37 | eval ' use IO::Uncompress::Bunzip2 2.021 ;'; |
38 | eval ' use IO::Uncompress::UnLzop 2.021 ;'; |
39 | eval ' use IO::Uncompress::Gunzip 2.021 ;'; |
40 | eval ' use IO::Uncompress::Inflate 2.021 ;'; |
41 | eval ' use IO::Uncompress::RawInflate 2.021 ;'; |
42 | eval ' use IO::Uncompress::Unzip 2.021 ;'; |
43 | eval ' use IO::Uncompress::UnLzf 2.021 ;'; |
44 | eval ' use IO::Uncompress::UnLzma 2.018 ;'; |
45 | eval ' use IO::Uncompress::UnXz 2.018 ;'; |
258133d1 |
46 | } |
47 | |
25f0751f |
48 | sub new |
49 | { |
50 | my $class = shift ; |
51 | my $obj = createSelfTiedObject($class, \$AnyUncompressError); |
52 | $obj->_create(undef, 0, @_); |
53 | } |
54 | |
55 | sub anyuncompress |
56 | { |
57 | my $obj = createSelfTiedObject(undef, \$AnyUncompressError); |
58 | return $obj->_inf(@_) ; |
59 | } |
60 | |
61 | sub getExtraParams |
62 | { |
10c2b2bb |
63 | use IO::Compress::Base::Common 2.021 qw(:Parse); |
6ecef415 |
64 | return ( 'RawInflate' => [1, 1, Parse_boolean, 0] ) ; |
25f0751f |
65 | } |
66 | |
67 | sub ckParams |
68 | { |
69 | my $self = shift ; |
70 | my $got = shift ; |
71 | |
72 | # any always needs both crc32 and adler32 |
73 | $got->value('CRC32' => 1); |
74 | $got->value('ADLER32' => 1); |
75 | |
76 | return 1; |
77 | } |
78 | |
79 | sub mkUncomp |
80 | { |
81 | my $self = shift ; |
25f0751f |
82 | my $got = shift ; |
83 | |
cb7abd7f |
84 | my $magic ; |
85 | |
25f0751f |
86 | # try zlib first |
cb7abd7f |
87 | if (defined $IO::Uncompress::RawInflate::VERSION ) |
88 | { |
89 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject(); |
25f0751f |
90 | |
cb7abd7f |
91 | return $self->saveErrorString(undef, $errstr, $errno) |
92 | if ! defined $obj; |
25f0751f |
93 | |
cb7abd7f |
94 | *$self->{Uncomp} = $obj; |
95 | |
6ecef415 |
96 | my @possible = qw( Inflate Gunzip Unzip ); |
97 | unshift @possible, 'RawInflate' |
98 | if $got->value('RawInflate'); |
25f0751f |
99 | |
6ecef415 |
100 | $magic = $self->ckMagic( @possible ); |
101 | |
102 | if ($magic) { |
cb7abd7f |
103 | *$self->{Info} = $self->readHeader($magic) |
104 | or return undef ; |
25f0751f |
105 | |
cb7abd7f |
106 | return 1; |
6ecef415 |
107 | } |
25f0751f |
108 | } |
109 | |
319fab50 |
110 | # if (defined $IO::Uncompress::UnLzma::VERSION ) |
111 | # { |
112 | # my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::UnLzma::mkUncompObject(); |
113 | # |
114 | # return $self->saveErrorString(undef, $errstr, $errno) |
115 | # if ! defined $obj; |
116 | # |
117 | # *$self->{Uncomp} = $obj; |
118 | # |
119 | # my @possible = qw( UnLzma ); |
120 | # #unshift @possible, 'RawInflate' |
121 | # # if $got->value('RawInflate'); |
122 | # |
123 | # if ( *$self->{Info} = $self->ckMagic( @possible )) |
124 | # { |
125 | # return 1; |
126 | # } |
127 | # } |
128 | |
10c2b2bb |
129 | if (defined $IO::Uncompress::UnXz::VERSION and |
130 | $magic = $self->ckMagic('UnXz')) { |
131 | *$self->{Info} = $self->readHeader($magic) |
132 | or return undef ; |
133 | |
134 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::UnXz::mkUncompObject(); |
135 | |
136 | return $self->saveErrorString(undef, $errstr, $errno) |
137 | if ! defined $obj; |
138 | |
139 | *$self->{Uncomp} = $obj; |
140 | |
141 | return 1; |
142 | } |
143 | |
25f0751f |
144 | if (defined $IO::Uncompress::Bunzip2::VERSION and |
145 | $magic = $self->ckMagic('Bunzip2')) { |
146 | *$self->{Info} = $self->readHeader($magic) |
147 | or return undef ; |
148 | |
149 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Bunzip2::mkUncompObject(); |
150 | |
151 | return $self->saveErrorString(undef, $errstr, $errno) |
152 | if ! defined $obj; |
153 | |
154 | *$self->{Uncomp} = $obj; |
155 | |
156 | return 1; |
157 | } |
6ecef415 |
158 | |
159 | if (defined $IO::Uncompress::UnLzop::VERSION and |
25f0751f |
160 | $magic = $self->ckMagic('UnLzop')) { |
161 | |
162 | *$self->{Info} = $self->readHeader($magic) |
163 | or return undef ; |
164 | |
165 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::LZO::mkUncompObject(); |
166 | |
167 | return $self->saveErrorString(undef, $errstr, $errno) |
168 | if ! defined $obj; |
169 | |
170 | *$self->{Uncomp} = $obj; |
171 | |
172 | return 1; |
173 | } |
174 | |
258133d1 |
175 | if (defined $IO::Uncompress::UnLzf::VERSION and |
176 | $magic = $self->ckMagic('UnLzf')) { |
177 | |
178 | *$self->{Info} = $self->readHeader($magic) |
179 | or return undef ; |
180 | |
181 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Lzf::mkUncompObject(); |
182 | |
183 | return $self->saveErrorString(undef, $errstr, $errno) |
184 | if ! defined $obj; |
185 | |
186 | *$self->{Uncomp} = $obj; |
187 | |
188 | return 1; |
189 | } |
190 | |
25f0751f |
191 | return 0 ; |
192 | } |
193 | |
194 | |
195 | |
196 | sub ckMagic |
197 | { |
198 | my $self = shift; |
199 | my @names = @_ ; |
200 | |
201 | my $keep = ref $self ; |
202 | for my $class ( map { "IO::Uncompress::$_" } @names) |
203 | { |
204 | bless $self => $class; |
205 | my $magic = $self->ckMagic(); |
206 | |
207 | if ($magic) |
208 | { |
209 | #bless $self => $class; |
210 | return $magic ; |
211 | } |
212 | |
213 | $self->pushBack(*$self->{HeaderPending}) ; |
214 | *$self->{HeaderPending} = '' ; |
215 | } |
216 | |
217 | bless $self => $keep; |
218 | return undef; |
219 | } |
220 | |
221 | 1 ; |
222 | |
223 | __END__ |
224 | |
225 | |
226 | =head1 NAME |
227 | |
cb7abd7f |
228 | IO::Uncompress::AnyUncompress - Uncompress gzip, zip, bzip2 or lzop file/buffer |
25f0751f |
229 | |
25f0751f |
230 | =head1 SYNOPSIS |
231 | |
232 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
233 | |
234 | my $status = anyuncompress $input => $output [,OPTS] |
235 | or die "anyuncompress failed: $AnyUncompressError\n"; |
236 | |
237 | my $z = new IO::Uncompress::AnyUncompress $input [OPTS] |
238 | or die "anyuncompress failed: $AnyUncompressError\n"; |
239 | |
240 | $status = $z->read($buffer) |
241 | $status = $z->read($buffer, $length) |
242 | $status = $z->read($buffer, $length, $offset) |
243 | $line = $z->getline() |
244 | $char = $z->getc() |
245 | $char = $z->ungetc() |
246 | $char = $z->opened() |
247 | |
e7d45986 |
248 | $data = $z->trailingData() |
249 | $status = $z->nextStream() |
25f0751f |
250 | $data = $z->getHeaderInfo() |
251 | $z->tell() |
252 | $z->seek($position, $whence) |
253 | $z->binmode() |
254 | $z->fileno() |
255 | $z->eof() |
256 | $z->close() |
257 | |
258 | $AnyUncompressError ; |
259 | |
260 | # IO::File mode |
261 | |
262 | <$z> |
263 | read($z, $buffer); |
264 | read($z, $buffer, $length); |
265 | read($z, $buffer, $length, $offset); |
266 | tell($z) |
267 | seek($z, $position, $whence) |
268 | binmode($z) |
269 | fileno($z) |
270 | eof($z) |
271 | close($z) |
272 | |
25f0751f |
273 | =head1 DESCRIPTION |
274 | |
25f0751f |
275 | This module provides a Perl interface that allows the reading of |
cb7abd7f |
276 | files/buffers that have been compressed with a variety of compression |
277 | libraries. |
278 | |
279 | The formats supported are: |
280 | |
281 | =over 5 |
282 | |
283 | =item RFC 1950 |
284 | |
258133d1 |
285 | =item RFC 1951 (optionally) |
cb7abd7f |
286 | |
287 | =item gzip (RFC 1952) |
288 | |
289 | =item zip |
290 | |
291 | =item bzip2 |
292 | |
293 | =item lzop |
294 | |
258133d1 |
295 | =item lzf |
296 | |
cb7abd7f |
297 | =back |
298 | |
299 | The module will auto-detect which, if any, of the supported |
300 | compression formats is being used. |
301 | |
25f0751f |
302 | =head1 Functional Interface |
303 | |
304 | A top-level function, C<anyuncompress>, is provided to carry out |
305 | "one-shot" uncompression between buffers and/or files. For finer |
306 | control over the uncompression process, see the L</"OO Interface"> |
307 | section. |
308 | |
309 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
310 | |
311 | anyuncompress $input => $output [,OPTS] |
312 | or die "anyuncompress failed: $AnyUncompressError\n"; |
313 | |
25f0751f |
314 | The functional interface needs Perl5.005 or better. |
315 | |
25f0751f |
316 | =head2 anyuncompress $input => $output [, OPTS] |
317 | |
25f0751f |
318 | C<anyuncompress> expects at least two parameters, C<$input> and C<$output>. |
319 | |
320 | =head3 The C<$input> parameter |
321 | |
322 | The parameter, C<$input>, is used to define the source of |
323 | the compressed data. |
324 | |
325 | It can take one of the following forms: |
326 | |
327 | =over 5 |
328 | |
329 | =item A filename |
330 | |
331 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
332 | filename. This file will be opened for reading and the input data |
333 | will be read from it. |
334 | |
335 | =item A filehandle |
336 | |
337 | If the C<$input> parameter is a filehandle, the input data will be |
338 | read from it. |
339 | The string '-' can be used as an alias for standard input. |
340 | |
341 | =item A scalar reference |
342 | |
343 | If C<$input> is a scalar reference, the input data will be read |
344 | from C<$$input>. |
345 | |
346 | =item An array reference |
347 | |
348 | If C<$input> is an array reference, each element in the array must be a |
349 | filename. |
350 | |
351 | The input data will be read from each file in turn. |
352 | |
353 | The complete array will be walked to ensure that it only |
354 | contains valid filenames before any data is uncompressed. |
355 | |
25f0751f |
356 | =item An Input FileGlob string |
357 | |
358 | If C<$input> is a string that is delimited by the characters "<" and ">" |
359 | C<anyuncompress> will assume that it is an I<input fileglob string>. The |
360 | input is the list of files that match the fileglob. |
361 | |
362 | If the fileglob does not match any files ... |
363 | |
364 | See L<File::GlobMapper|File::GlobMapper> for more details. |
365 | |
25f0751f |
366 | =back |
367 | |
368 | If the C<$input> parameter is any other type, C<undef> will be returned. |
369 | |
25f0751f |
370 | =head3 The C<$output> parameter |
371 | |
372 | The parameter C<$output> is used to control the destination of the |
373 | uncompressed data. This parameter can take one of these forms. |
374 | |
375 | =over 5 |
376 | |
377 | =item A filename |
378 | |
379 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
380 | filename. This file will be opened for writing and the uncompressed |
381 | data will be written to it. |
382 | |
383 | =item A filehandle |
384 | |
385 | If the C<$output> parameter is a filehandle, the uncompressed data |
386 | will be written to it. |
387 | The string '-' can be used as an alias for standard output. |
388 | |
25f0751f |
389 | =item A scalar reference |
390 | |
391 | If C<$output> is a scalar reference, the uncompressed data will be |
392 | stored in C<$$output>. |
393 | |
25f0751f |
394 | =item An Array Reference |
395 | |
396 | If C<$output> is an array reference, the uncompressed data will be |
397 | pushed onto the array. |
398 | |
399 | =item An Output FileGlob |
400 | |
401 | If C<$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. |
404 | |
405 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
406 | string. Anything else is an error. |
407 | |
408 | =back |
409 | |
410 | If the C<$output> parameter is any other type, C<undef> will be returned. |
411 | |
25f0751f |
412 | =head2 Notes |
413 | |
c70c1701 |
414 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
415 | a single file/buffer, after uncompression C<$output> will contain a |
416 | concatenation of all the uncompressed data from each of the input |
417 | files/buffers. |
418 | |
25f0751f |
419 | =head2 Optional Parameters |
420 | |
421 | Unless specified below, the optional parameters for C<anyuncompress>, |
422 | C<OPTS>, are the same as those used with the OO interface defined in the |
423 | L</"Constructor Options"> section below. |
424 | |
425 | =over 5 |
426 | |
e7d45986 |
427 | =item C<< AutoClose => 0|1 >> |
25f0751f |
428 | |
429 | This option applies to any input or output data streams to |
430 | C<anyuncompress> that are filehandles. |
431 | |
432 | If C<AutoClose> is specified, and the value is true, it will result in all |
433 | input and/or output filehandles being closed once C<anyuncompress> has |
434 | completed. |
435 | |
436 | This parameter defaults to 0. |
437 | |
e7d45986 |
438 | =item C<< BinModeOut => 0|1 >> |
25f0751f |
439 | |
440 | When writing to a file or filehandle, set C<binmode> before writing to the |
441 | file. |
442 | |
443 | Defaults to 0. |
444 | |
e7d45986 |
445 | =item C<< Append => 0|1 >> |
25f0751f |
446 | |
447 | TODO |
448 | |
e7d45986 |
449 | =item C<< MultiStream => 0|1 >> |
25f0751f |
450 | |
e7d45986 |
451 | If the input file/buffer contains multiple compressed data streams, this |
452 | option will uncompress the whole lot as a single data stream. |
25f0751f |
453 | |
e7d45986 |
454 | Defaults to 0. |
25f0751f |
455 | |
258133d1 |
456 | =item C<< TrailingData => $scalar >> |
457 | |
458 | Returns the data, if any, that is present immediately after the compressed |
459 | data stream once uncompression is complete. |
460 | |
461 | This option can be used when there is useful information immediately |
462 | following the compressed data stream, and you don't know the length of the |
463 | compressed data stream. |
464 | |
465 | If the input is a buffer, C<trailingData> will return everything from the |
466 | end of the compressed data stream to the end of the buffer. |
467 | |
468 | If the input is a filehandle, C<trailingData> will return the data that is |
469 | left in the filehandle input buffer once the end of the compressed data |
470 | stream has been reached. You can then use the filehandle to read the rest |
471 | of the input file. |
472 | |
473 | Don't bother using C<trailingData> if the input is a filename. |
474 | |
258133d1 |
475 | If you know the length of the compressed data stream before you start |
476 | uncompressing, you can avoid having to use C<trailingData> by setting the |
477 | C<InputLength> option. |
478 | |
25f0751f |
479 | =back |
480 | |
25f0751f |
481 | =head2 Examples |
482 | |
483 | To read the contents of the file C<file1.txt.Compressed> and write the |
10c2b2bb |
484 | uncompressed data to the file C<file1.txt>. |
25f0751f |
485 | |
486 | use strict ; |
487 | use warnings ; |
488 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
489 | |
490 | my $input = "file1.txt.Compressed"; |
491 | my $output = "file1.txt"; |
492 | anyuncompress $input => $output |
493 | or die "anyuncompress failed: $AnyUncompressError\n"; |
494 | |
25f0751f |
495 | To read from an existing Perl filehandle, C<$input>, and write the |
496 | uncompressed data to a buffer, C<$buffer>. |
497 | |
498 | use strict ; |
499 | use warnings ; |
500 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
501 | use IO::File ; |
502 | |
503 | my $input = new IO::File "<file1.txt.Compressed" |
504 | or die "Cannot open 'file1.txt.Compressed': $!\n" ; |
505 | my $buffer ; |
506 | anyuncompress $input => \$buffer |
507 | or die "anyuncompress failed: $AnyUncompressError\n"; |
508 | |
509 | To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory |
510 | |
511 | use strict ; |
512 | use warnings ; |
513 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
514 | |
515 | anyuncompress '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>' |
516 | or die "anyuncompress failed: $AnyUncompressError\n"; |
517 | |
518 | and if you want to compress each file one at a time, this will do the trick |
519 | |
520 | use strict ; |
521 | use warnings ; |
522 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
523 | |
524 | for my $input ( glob "/my/home/*.txt.Compressed" ) |
525 | { |
526 | my $output = $input; |
527 | $output =~ s/.Compressed// ; |
528 | anyuncompress $input => $output |
529 | or die "Error compressing '$input': $AnyUncompressError\n"; |
530 | } |
531 | |
532 | =head1 OO Interface |
533 | |
534 | =head2 Constructor |
535 | |
536 | The format of the constructor for IO::Uncompress::AnyUncompress is shown below |
537 | |
25f0751f |
538 | my $z = new IO::Uncompress::AnyUncompress $input [OPTS] |
539 | or die "IO::Uncompress::AnyUncompress failed: $AnyUncompressError\n"; |
540 | |
541 | Returns an C<IO::Uncompress::AnyUncompress> object on success and undef on failure. |
542 | The variable C<$AnyUncompressError> will contain an error message on failure. |
543 | |
544 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
545 | IO::Uncompress::AnyUncompress can be used exactly like an L<IO::File|IO::File> filehandle. |
546 | This means that all normal input file operations can be carried out with |
547 | C<$z>. For example, to read a line from a compressed file/buffer you can |
548 | use either of these forms |
549 | |
550 | $line = $z->getline(); |
551 | $line = <$z>; |
552 | |
553 | The mandatory parameter C<$input> is used to determine the source of the |
554 | compressed data. This parameter can take one of three forms. |
555 | |
556 | =over 5 |
557 | |
558 | =item A filename |
559 | |
560 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
561 | file will be opened for reading and the compressed data will be read from it. |
562 | |
563 | =item A filehandle |
564 | |
565 | If the C<$input> parameter is a filehandle, the compressed data will be |
566 | read from it. |
567 | The string '-' can be used as an alias for standard input. |
568 | |
25f0751f |
569 | =item A scalar reference |
570 | |
571 | If C<$input> is a scalar reference, the compressed data will be read from |
572 | C<$$output>. |
573 | |
574 | =back |
575 | |
576 | =head2 Constructor Options |
577 | |
25f0751f |
578 | The option names defined below are case insensitive and can be optionally |
579 | prefixed by a '-'. So all of the following are valid |
580 | |
581 | -AutoClose |
582 | -autoclose |
583 | AUTOCLOSE |
584 | autoclose |
585 | |
586 | OPTS is a combination of the following options: |
587 | |
588 | =over 5 |
589 | |
e7d45986 |
590 | =item C<< AutoClose => 0|1 >> |
25f0751f |
591 | |
592 | This option is only valid when the C<$input> parameter is a filehandle. If |
593 | specified, and the value is true, it will result in the file being closed once |
594 | either the C<close> method is called or the IO::Uncompress::AnyUncompress object is |
595 | destroyed. |
596 | |
597 | This parameter defaults to 0. |
598 | |
e7d45986 |
599 | =item C<< MultiStream => 0|1 >> |
25f0751f |
600 | |
25f0751f |
601 | Allows multiple concatenated compressed streams to be treated as a single |
602 | compressed stream. Decompression will stop once either the end of the |
603 | file/buffer is reached, an error is encountered (premature eof, corrupt |
604 | compressed data) or the end of a stream is not immediately followed by the |
605 | start of another stream. |
606 | |
607 | This parameter defaults to 0. |
608 | |
e7d45986 |
609 | =item C<< Prime => $string >> |
25f0751f |
610 | |
611 | This option will uncompress the contents of C<$string> before processing the |
612 | input file/buffer. |
613 | |
614 | This option can be useful when the compressed data is embedded in another |
615 | file/data structure and it is not possible to work out where the compressed |
616 | data begins without having to read the first few bytes. If this is the |
617 | case, the uncompression can be I<primed> with these bytes using this |
618 | option. |
619 | |
e7d45986 |
620 | =item C<< Transparent => 0|1 >> |
25f0751f |
621 | |
f6fd7794 |
622 | If this option is set and the input file/buffer is not compressed data, |
25f0751f |
623 | the module will allow reading of it anyway. |
624 | |
f6fd7794 |
625 | In addition, if the input file/buffer does contain compressed data and |
626 | there is non-compressed data immediately following it, setting this option |
627 | will make this module treat the whole file/bufffer as a single data stream. |
628 | |
25f0751f |
629 | This option defaults to 1. |
630 | |
e7d45986 |
631 | =item C<< BlockSize => $num >> |
25f0751f |
632 | |
633 | When reading the compressed input data, IO::Uncompress::AnyUncompress will read it in |
634 | blocks of C<$num> bytes. |
635 | |
636 | This option defaults to 4096. |
637 | |
e7d45986 |
638 | =item C<< InputLength => $size >> |
25f0751f |
639 | |
640 | When present this option will limit the number of compressed bytes read |
641 | from the input file/buffer to C<$size>. This option can be used in the |
642 | situation where there is useful data directly after the compressed data |
643 | stream and you know beforehand the exact length of the compressed data |
644 | stream. |
645 | |
646 | This option is mostly used when reading from a filehandle, in which case |
647 | the file pointer will be left pointing to the first byte directly after the |
648 | compressed data stream. |
649 | |
25f0751f |
650 | This option defaults to off. |
651 | |
e7d45986 |
652 | =item C<< Append => 0|1 >> |
25f0751f |
653 | |
654 | This option controls what the C<read> method does with uncompressed data. |
655 | |
656 | If set to 1, all uncompressed data will be appended to the output parameter |
657 | of the C<read> method. |
658 | |
659 | If set to 0, the contents of the output parameter of the C<read> method |
660 | will be overwritten by the uncompressed data. |
661 | |
662 | Defaults to 0. |
663 | |
e7d45986 |
664 | =item C<< Strict => 0|1 >> |
25f0751f |
665 | |
25f0751f |
666 | This option controls whether the extra checks defined below are used when |
667 | carrying out the decompression. When Strict is on, the extra tests are |
668 | carried out, when Strict is off they are not. |
669 | |
670 | The default for this option is off. |
671 | |
258133d1 |
672 | =item C<< RawInflate => 0|1 >> |
673 | |
674 | When auto-detecting the compressed format, try to test for raw-deflate (RFC |
675 | 1951) content using the C<IO::Uncompress::RawInflate> module. |
676 | |
677 | The reason this is not default behaviour is because RFC 1951 content can |
678 | only be detected by attempting to uncompress it. This process is error |
679 | prone and can result is false positives. |
680 | |
681 | Defaults to 0. |
682 | |
25f0751f |
683 | =back |
684 | |
685 | =head2 Examples |
686 | |
687 | TODO |
688 | |
689 | =head1 Methods |
690 | |
691 | =head2 read |
692 | |
693 | Usage is |
694 | |
695 | $status = $z->read($buffer) |
696 | |
697 | Reads a block of compressed data (the size the the compressed block is |
698 | determined by the C<Buffer> option in the constructor), uncompresses it and |
699 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
700 | set in the constructor, the uncompressed data will be appended to the |
701 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
702 | |
703 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
704 | or a negative number on error. |
705 | |
706 | =head2 read |
707 | |
708 | Usage is |
709 | |
710 | $status = $z->read($buffer, $length) |
711 | $status = $z->read($buffer, $length, $offset) |
712 | |
713 | $status = read($z, $buffer, $length) |
714 | $status = read($z, $buffer, $length, $offset) |
715 | |
716 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
717 | |
718 | The main difference between this form of the C<read> method and the |
719 | previous one, is that this one will attempt to return I<exactly> C<$length> |
720 | bytes. The only circumstances that this function will not is if end-of-file |
721 | or an IO error is encountered. |
722 | |
723 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
724 | or a negative number on error. |
725 | |
25f0751f |
726 | =head2 getline |
727 | |
728 | Usage is |
729 | |
730 | $line = $z->getline() |
731 | $line = <$z> |
732 | |
733 | Reads a single line. |
734 | |
258133d1 |
735 | This method fully supports the use of of the variable C<$/> (or |
736 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
737 | determine what constitutes an end of line. Paragraph mode, record mode and |
738 | file slurp mode are all supported. |
25f0751f |
739 | |
25f0751f |
740 | =head2 getc |
741 | |
742 | Usage is |
743 | |
744 | $char = $z->getc() |
745 | |
746 | Read a single character. |
747 | |
748 | =head2 ungetc |
749 | |
750 | Usage is |
751 | |
752 | $char = $z->ungetc($string) |
753 | |
25f0751f |
754 | =head2 getHeaderInfo |
755 | |
756 | Usage is |
757 | |
758 | $hdr = $z->getHeaderInfo(); |
759 | @hdrs = $z->getHeaderInfo(); |
760 | |
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). |
764 | |
25f0751f |
765 | =head2 tell |
766 | |
767 | Usage is |
768 | |
769 | $z->tell() |
770 | tell $z |
771 | |
772 | Returns the uncompressed file offset. |
773 | |
774 | =head2 eof |
775 | |
776 | Usage is |
777 | |
778 | $z->eof(); |
779 | eof($z); |
780 | |
25f0751f |
781 | Returns true if the end of the compressed input stream has been reached. |
782 | |
25f0751f |
783 | =head2 seek |
784 | |
785 | $z->seek($position, $whence); |
786 | seek($z, $position, $whence); |
787 | |
25f0751f |
788 | Provides a sub-set of the C<seek> functionality, with the restriction |
789 | that it is only legal to seek forward in the input file/buffer. |
790 | It is a fatal error to attempt to seek backward. |
791 | |
25f0751f |
792 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
793 | SEEK_CUR or SEEK_END. |
794 | |
795 | Returns 1 on success, 0 on failure. |
796 | |
797 | =head2 binmode |
798 | |
799 | Usage is |
800 | |
801 | $z->binmode |
802 | binmode $z ; |
803 | |
804 | This is a noop provided for completeness. |
805 | |
806 | =head2 opened |
807 | |
808 | $z->opened() |
809 | |
810 | Returns true if the object currently refers to a opened file/buffer. |
811 | |
812 | =head2 autoflush |
813 | |
814 | my $prev = $z->autoflush() |
815 | my $prev = $z->autoflush(EXPR) |
816 | |
817 | If the C<$z> object is associated with a file or a filehandle, this method |
818 | returns the current autoflush setting for the underlying filehandle. If |
819 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
820 | write/print operation. |
821 | |
822 | If C<$z> is associated with a buffer, this method has no effect and always |
823 | returns C<undef>. |
824 | |
825 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
826 | retrieve the autoflush setting. |
827 | |
828 | =head2 input_line_number |
829 | |
830 | $z->input_line_number() |
831 | $z->input_line_number(EXPR) |
832 | |
25f0751f |
833 | Returns the current uncompressed line number. If C<EXPR> is present it has |
834 | the effect of setting the line number. Note that setting the line number |
835 | does not change the current position within the file/buffer being read. |
836 | |
837 | The contents of C<$/> are used to to determine what constitutes a line |
838 | terminator. |
839 | |
25f0751f |
840 | =head2 fileno |
841 | |
842 | $z->fileno() |
843 | fileno($z) |
844 | |
d54256af |
845 | If the C<$z> object is associated with a file or a filehandle, C<fileno> |
846 | will return the underlying file descriptor. Once the C<close> method is |
847 | called C<fileno> will return C<undef>. |
25f0751f |
848 | |
d54256af |
849 | If the C<$z> object is is associated with a buffer, this method will return |
850 | C<undef>. |
25f0751f |
851 | |
852 | =head2 close |
853 | |
854 | $z->close() ; |
855 | close $z ; |
856 | |
25f0751f |
857 | Closes the output file/buffer. |
858 | |
25f0751f |
859 | For most versions of Perl this method will be automatically invoked if |
860 | the IO::Uncompress::AnyUncompress object is destroyed (either explicitly or by the |
861 | variable with the reference to the object going out of scope). The |
862 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
863 | these cases, the C<close> method will be called automatically, but |
864 | not until global destruction of all live objects when the program is |
865 | terminating. |
866 | |
867 | Therefore, if you want your scripts to be able to run on all versions |
868 | of Perl, you should call C<close> explicitly and not rely on automatic |
869 | closing. |
870 | |
871 | Returns true on success, otherwise 0. |
872 | |
873 | If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyUncompress |
874 | object was created, and the object is associated with a file, the |
875 | underlying file will also be closed. |
876 | |
e7d45986 |
877 | =head2 nextStream |
878 | |
879 | Usage is |
880 | |
881 | my $status = $z->nextStream(); |
882 | |
883 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
884 | compressed data stream is found, the eof marker will be cleared and C<$.> |
885 | will be reset to 0. |
e7d45986 |
886 | |
887 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
888 | error was encountered. |
889 | |
890 | =head2 trailingData |
891 | |
892 | Usage is |
893 | |
894 | my $data = $z->trailingData(); |
895 | |
258133d1 |
896 | Returns the data, if any, that is present immediately after the compressed |
897 | data stream once uncompression is complete. It only makes sense to call |
898 | this method once the end of the compressed data stream has been |
899 | encountered. |
900 | |
901 | This option can be used when there is useful information immediately |
902 | following the compressed data stream, and you don't know the length of the |
903 | compressed data stream. |
904 | |
905 | If the input is a buffer, C<trailingData> will return everything from the |
906 | end of the compressed data stream to the end of the buffer. |
907 | |
908 | If the input is a filehandle, C<trailingData> will return the data that is |
909 | left in the filehandle input buffer once the end of the compressed data |
910 | stream has been reached. You can then use the filehandle to read the rest |
911 | of the input file. |
912 | |
913 | Don't bother using C<trailingData> if the input is a filename. |
914 | |
258133d1 |
915 | If you know the length of the compressed data stream before you start |
916 | uncompressing, you can avoid having to use C<trailingData> by setting the |
917 | C<InputLength> option in the constructor. |
e7d45986 |
918 | |
25f0751f |
919 | =head1 Importing |
920 | |
921 | No symbolic constants are required by this IO::Uncompress::AnyUncompress at present. |
922 | |
923 | =over 5 |
924 | |
925 | =item :all |
926 | |
927 | Imports C<anyuncompress> and C<$AnyUncompressError>. |
928 | Same as doing this |
929 | |
930 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
931 | |
932 | =back |
933 | |
934 | =head1 EXAMPLES |
935 | |
25f0751f |
936 | =head1 SEE ALSO |
937 | |
258133d1 |
938 | 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> |
25f0751f |
939 | |
940 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
941 | |
942 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
943 | L<Archive::Tar|Archive::Tar>, |
944 | L<IO::Zlib|IO::Zlib> |
945 | |
25f0751f |
946 | =head1 AUTHOR |
947 | |
cb7abd7f |
948 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
25f0751f |
949 | |
25f0751f |
950 | =head1 MODIFICATION HISTORY |
951 | |
952 | See the Changes file. |
953 | |
954 | =head1 COPYRIGHT AND LICENSE |
25f0751f |
955 | |
319fab50 |
956 | Copyright (c) 2005-2009 Paul Marquess. All rights reserved. |
25f0751f |
957 | |
958 | This program is free software; you can redistribute it and/or |
959 | modify it under the same terms as Perl itself. |
960 | |