Commit | Line | Data |
25f0751f |
1 | package IO::Uncompress::AnyUncompress ; |
2 | |
3 | use strict; |
4 | use warnings; |
5 | use bytes; |
6 | |
d54256af |
7 | use IO::Compress::Base::Common 2.009 qw(createSelfTiedObject); |
25f0751f |
8 | |
d54256af |
9 | use IO::Uncompress::Base 2.009 ; |
25f0751f |
10 | |
25f0751f |
11 | |
12 | require Exporter ; |
13 | |
14 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyUncompressError); |
15 | |
d54256af |
16 | $VERSION = '2.009'; |
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 | { |
d54256af |
30 | eval ' use IO::Uncompress::Adapter::Inflate 2.009 ;'; |
31 | eval ' use IO::Uncompress::Adapter::Bunzip2 2.009 ;'; |
32 | eval ' use IO::Uncompress::Adapter::LZO 2.009 ;'; |
33 | eval ' use IO::Uncompress::Adapter::Lzf 2.009 ;'; |
34 | |
35 | eval ' use IO::Uncompress::Bunzip2 2.009 ;'; |
36 | eval ' use IO::Uncompress::UnLzop 2.009 ;'; |
37 | eval ' use IO::Uncompress::Gunzip 2.009 ;'; |
38 | eval ' use IO::Uncompress::Inflate 2.009 ;'; |
39 | eval ' use IO::Uncompress::RawInflate 2.009 ;'; |
40 | eval ' use IO::Uncompress::Unzip 2.009 ;'; |
41 | eval ' use IO::Uncompress::UnLzf 2.009 ;'; |
258133d1 |
42 | } |
43 | |
25f0751f |
44 | sub new |
45 | { |
46 | my $class = shift ; |
47 | my $obj = createSelfTiedObject($class, \$AnyUncompressError); |
48 | $obj->_create(undef, 0, @_); |
49 | } |
50 | |
51 | sub anyuncompress |
52 | { |
53 | my $obj = createSelfTiedObject(undef, \$AnyUncompressError); |
54 | return $obj->_inf(@_) ; |
55 | } |
56 | |
57 | sub getExtraParams |
58 | { |
d54256af |
59 | use IO::Compress::Base::Common 2.009 qw(:Parse); |
6ecef415 |
60 | return ( 'RawInflate' => [1, 1, Parse_boolean, 0] ) ; |
25f0751f |
61 | } |
62 | |
63 | sub ckParams |
64 | { |
65 | my $self = shift ; |
66 | my $got = shift ; |
67 | |
68 | # any always needs both crc32 and adler32 |
69 | $got->value('CRC32' => 1); |
70 | $got->value('ADLER32' => 1); |
71 | |
72 | return 1; |
73 | } |
74 | |
75 | sub mkUncomp |
76 | { |
77 | my $self = shift ; |
78 | my $class = shift ; |
79 | my $got = shift ; |
80 | |
cb7abd7f |
81 | my $magic ; |
82 | |
25f0751f |
83 | # try zlib first |
cb7abd7f |
84 | if (defined $IO::Uncompress::RawInflate::VERSION ) |
85 | { |
86 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject(); |
25f0751f |
87 | |
cb7abd7f |
88 | return $self->saveErrorString(undef, $errstr, $errno) |
89 | if ! defined $obj; |
25f0751f |
90 | |
cb7abd7f |
91 | *$self->{Uncomp} = $obj; |
92 | |
6ecef415 |
93 | my @possible = qw( Inflate Gunzip Unzip ); |
94 | unshift @possible, 'RawInflate' |
95 | if $got->value('RawInflate'); |
25f0751f |
96 | |
6ecef415 |
97 | $magic = $self->ckMagic( @possible ); |
98 | |
99 | if ($magic) { |
cb7abd7f |
100 | *$self->{Info} = $self->readHeader($magic) |
101 | or return undef ; |
25f0751f |
102 | |
cb7abd7f |
103 | return 1; |
6ecef415 |
104 | } |
25f0751f |
105 | } |
106 | |
25f0751f |
107 | if (defined $IO::Uncompress::Bunzip2::VERSION and |
108 | $magic = $self->ckMagic('Bunzip2')) { |
109 | *$self->{Info} = $self->readHeader($magic) |
110 | or return undef ; |
111 | |
112 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Bunzip2::mkUncompObject(); |
113 | |
114 | return $self->saveErrorString(undef, $errstr, $errno) |
115 | if ! defined $obj; |
116 | |
117 | *$self->{Uncomp} = $obj; |
118 | |
119 | return 1; |
120 | } |
6ecef415 |
121 | |
122 | if (defined $IO::Uncompress::UnLzop::VERSION and |
25f0751f |
123 | $magic = $self->ckMagic('UnLzop')) { |
124 | |
125 | *$self->{Info} = $self->readHeader($magic) |
126 | or return undef ; |
127 | |
128 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::LZO::mkUncompObject(); |
129 | |
130 | return $self->saveErrorString(undef, $errstr, $errno) |
131 | if ! defined $obj; |
132 | |
133 | *$self->{Uncomp} = $obj; |
134 | |
135 | return 1; |
136 | } |
137 | |
258133d1 |
138 | if (defined $IO::Uncompress::UnLzf::VERSION and |
139 | $magic = $self->ckMagic('UnLzf')) { |
140 | |
141 | *$self->{Info} = $self->readHeader($magic) |
142 | or return undef ; |
143 | |
144 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Lzf::mkUncompObject(); |
145 | |
146 | return $self->saveErrorString(undef, $errstr, $errno) |
147 | if ! defined $obj; |
148 | |
149 | *$self->{Uncomp} = $obj; |
150 | |
151 | return 1; |
152 | } |
153 | |
25f0751f |
154 | return 0 ; |
155 | } |
156 | |
157 | |
158 | |
159 | sub ckMagic |
160 | { |
161 | my $self = shift; |
162 | my @names = @_ ; |
163 | |
164 | my $keep = ref $self ; |
165 | for my $class ( map { "IO::Uncompress::$_" } @names) |
166 | { |
167 | bless $self => $class; |
168 | my $magic = $self->ckMagic(); |
169 | |
170 | if ($magic) |
171 | { |
172 | #bless $self => $class; |
173 | return $magic ; |
174 | } |
175 | |
176 | $self->pushBack(*$self->{HeaderPending}) ; |
177 | *$self->{HeaderPending} = '' ; |
178 | } |
179 | |
180 | bless $self => $keep; |
181 | return undef; |
182 | } |
183 | |
184 | 1 ; |
185 | |
186 | __END__ |
187 | |
188 | |
189 | =head1 NAME |
190 | |
cb7abd7f |
191 | IO::Uncompress::AnyUncompress - Uncompress gzip, zip, bzip2 or lzop file/buffer |
25f0751f |
192 | |
25f0751f |
193 | =head1 SYNOPSIS |
194 | |
195 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
196 | |
197 | my $status = anyuncompress $input => $output [,OPTS] |
198 | or die "anyuncompress failed: $AnyUncompressError\n"; |
199 | |
200 | my $z = new IO::Uncompress::AnyUncompress $input [OPTS] |
201 | or die "anyuncompress failed: $AnyUncompressError\n"; |
202 | |
203 | $status = $z->read($buffer) |
204 | $status = $z->read($buffer, $length) |
205 | $status = $z->read($buffer, $length, $offset) |
206 | $line = $z->getline() |
207 | $char = $z->getc() |
208 | $char = $z->ungetc() |
209 | $char = $z->opened() |
210 | |
e7d45986 |
211 | $data = $z->trailingData() |
212 | $status = $z->nextStream() |
25f0751f |
213 | $data = $z->getHeaderInfo() |
214 | $z->tell() |
215 | $z->seek($position, $whence) |
216 | $z->binmode() |
217 | $z->fileno() |
218 | $z->eof() |
219 | $z->close() |
220 | |
221 | $AnyUncompressError ; |
222 | |
223 | # IO::File mode |
224 | |
225 | <$z> |
226 | read($z, $buffer); |
227 | read($z, $buffer, $length); |
228 | read($z, $buffer, $length, $offset); |
229 | tell($z) |
230 | seek($z, $position, $whence) |
231 | binmode($z) |
232 | fileno($z) |
233 | eof($z) |
234 | close($z) |
235 | |
25f0751f |
236 | =head1 DESCRIPTION |
237 | |
25f0751f |
238 | This module provides a Perl interface that allows the reading of |
cb7abd7f |
239 | files/buffers that have been compressed with a variety of compression |
240 | libraries. |
241 | |
242 | The formats supported are: |
243 | |
244 | =over 5 |
245 | |
246 | =item RFC 1950 |
247 | |
258133d1 |
248 | =item RFC 1951 (optionally) |
cb7abd7f |
249 | |
250 | =item gzip (RFC 1952) |
251 | |
252 | =item zip |
253 | |
254 | =item bzip2 |
255 | |
256 | =item lzop |
257 | |
258133d1 |
258 | =item lzf |
259 | |
cb7abd7f |
260 | =back |
261 | |
262 | The module will auto-detect which, if any, of the supported |
263 | compression formats is being used. |
264 | |
25f0751f |
265 | =head1 Functional Interface |
266 | |
267 | A top-level function, C<anyuncompress>, is provided to carry out |
268 | "one-shot" uncompression between buffers and/or files. For finer |
269 | control over the uncompression process, see the L</"OO Interface"> |
270 | section. |
271 | |
272 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
273 | |
274 | anyuncompress $input => $output [,OPTS] |
275 | or die "anyuncompress failed: $AnyUncompressError\n"; |
276 | |
25f0751f |
277 | The functional interface needs Perl5.005 or better. |
278 | |
25f0751f |
279 | =head2 anyuncompress $input => $output [, OPTS] |
280 | |
25f0751f |
281 | C<anyuncompress> expects at least two parameters, C<$input> and C<$output>. |
282 | |
283 | =head3 The C<$input> parameter |
284 | |
285 | The parameter, C<$input>, is used to define the source of |
286 | the compressed data. |
287 | |
288 | It can take one of the following forms: |
289 | |
290 | =over 5 |
291 | |
292 | =item A filename |
293 | |
294 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
295 | filename. This file will be opened for reading and the input data |
296 | will be read from it. |
297 | |
298 | =item A filehandle |
299 | |
300 | If the C<$input> parameter is a filehandle, the input data will be |
301 | read from it. |
302 | The string '-' can be used as an alias for standard input. |
303 | |
304 | =item A scalar reference |
305 | |
306 | If C<$input> is a scalar reference, the input data will be read |
307 | from C<$$input>. |
308 | |
309 | =item An array reference |
310 | |
311 | If C<$input> is an array reference, each element in the array must be a |
312 | filename. |
313 | |
314 | The input data will be read from each file in turn. |
315 | |
316 | The complete array will be walked to ensure that it only |
317 | contains valid filenames before any data is uncompressed. |
318 | |
25f0751f |
319 | =item An Input FileGlob string |
320 | |
321 | If C<$input> is a string that is delimited by the characters "<" and ">" |
322 | C<anyuncompress> will assume that it is an I<input fileglob string>. The |
323 | input is the list of files that match the fileglob. |
324 | |
325 | If the fileglob does not match any files ... |
326 | |
327 | See L<File::GlobMapper|File::GlobMapper> for more details. |
328 | |
25f0751f |
329 | =back |
330 | |
331 | If the C<$input> parameter is any other type, C<undef> will be returned. |
332 | |
25f0751f |
333 | =head3 The C<$output> parameter |
334 | |
335 | The parameter C<$output> is used to control the destination of the |
336 | uncompressed data. This parameter can take one of these forms. |
337 | |
338 | =over 5 |
339 | |
340 | =item A filename |
341 | |
342 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
343 | filename. This file will be opened for writing and the uncompressed |
344 | data will be written to it. |
345 | |
346 | =item A filehandle |
347 | |
348 | If the C<$output> parameter is a filehandle, the uncompressed data |
349 | will be written to it. |
350 | The string '-' can be used as an alias for standard output. |
351 | |
25f0751f |
352 | =item A scalar reference |
353 | |
354 | If C<$output> is a scalar reference, the uncompressed data will be |
355 | stored in C<$$output>. |
356 | |
25f0751f |
357 | =item An Array Reference |
358 | |
359 | If C<$output> is an array reference, the uncompressed data will be |
360 | pushed onto the array. |
361 | |
362 | =item An Output FileGlob |
363 | |
364 | If C<$output> is a string that is delimited by the characters "<" and ">" |
365 | C<anyuncompress> will assume that it is an I<output fileglob string>. The |
366 | output is the list of files that match the fileglob. |
367 | |
368 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
369 | string. Anything else is an error. |
370 | |
371 | =back |
372 | |
373 | If the C<$output> parameter is any other type, C<undef> will be returned. |
374 | |
25f0751f |
375 | =head2 Notes |
376 | |
c70c1701 |
377 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
378 | a single file/buffer, after uncompression C<$output> will contain a |
379 | concatenation of all the uncompressed data from each of the input |
380 | files/buffers. |
381 | |
25f0751f |
382 | =head2 Optional Parameters |
383 | |
384 | Unless specified below, the optional parameters for C<anyuncompress>, |
385 | C<OPTS>, are the same as those used with the OO interface defined in the |
386 | L</"Constructor Options"> section below. |
387 | |
388 | =over 5 |
389 | |
e7d45986 |
390 | =item C<< AutoClose => 0|1 >> |
25f0751f |
391 | |
392 | This option applies to any input or output data streams to |
393 | C<anyuncompress> that are filehandles. |
394 | |
395 | If C<AutoClose> is specified, and the value is true, it will result in all |
396 | input and/or output filehandles being closed once C<anyuncompress> has |
397 | completed. |
398 | |
399 | This parameter defaults to 0. |
400 | |
e7d45986 |
401 | =item C<< BinModeOut => 0|1 >> |
25f0751f |
402 | |
403 | When writing to a file or filehandle, set C<binmode> before writing to the |
404 | file. |
405 | |
406 | Defaults to 0. |
407 | |
e7d45986 |
408 | =item C<< Append => 0|1 >> |
25f0751f |
409 | |
410 | TODO |
411 | |
e7d45986 |
412 | =item C<< MultiStream => 0|1 >> |
25f0751f |
413 | |
e7d45986 |
414 | If the input file/buffer contains multiple compressed data streams, this |
415 | option will uncompress the whole lot as a single data stream. |
25f0751f |
416 | |
e7d45986 |
417 | Defaults to 0. |
25f0751f |
418 | |
258133d1 |
419 | =item C<< TrailingData => $scalar >> |
420 | |
421 | Returns the data, if any, that is present immediately after the compressed |
422 | data stream once uncompression is complete. |
423 | |
424 | This option can be used when there is useful information immediately |
425 | following the compressed data stream, and you don't know the length of the |
426 | compressed data stream. |
427 | |
428 | If the input is a buffer, C<trailingData> will return everything from the |
429 | end of the compressed data stream to the end of the buffer. |
430 | |
431 | If the input is a filehandle, C<trailingData> will return the data that is |
432 | left in the filehandle input buffer once the end of the compressed data |
433 | stream has been reached. You can then use the filehandle to read the rest |
434 | of the input file. |
435 | |
436 | Don't bother using C<trailingData> if the input is a filename. |
437 | |
258133d1 |
438 | If you know the length of the compressed data stream before you start |
439 | uncompressing, you can avoid having to use C<trailingData> by setting the |
440 | C<InputLength> option. |
441 | |
25f0751f |
442 | =back |
443 | |
25f0751f |
444 | =head2 Examples |
445 | |
446 | To read the contents of the file C<file1.txt.Compressed> and write the |
447 | compressed data to the file C<file1.txt>. |
448 | |
449 | use strict ; |
450 | use warnings ; |
451 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
452 | |
453 | my $input = "file1.txt.Compressed"; |
454 | my $output = "file1.txt"; |
455 | anyuncompress $input => $output |
456 | or die "anyuncompress failed: $AnyUncompressError\n"; |
457 | |
25f0751f |
458 | To read from an existing Perl filehandle, C<$input>, and write the |
459 | uncompressed data to a buffer, C<$buffer>. |
460 | |
461 | use strict ; |
462 | use warnings ; |
463 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
464 | use IO::File ; |
465 | |
466 | my $input = new IO::File "<file1.txt.Compressed" |
467 | or die "Cannot open 'file1.txt.Compressed': $!\n" ; |
468 | my $buffer ; |
469 | anyuncompress $input => \$buffer |
470 | or die "anyuncompress failed: $AnyUncompressError\n"; |
471 | |
472 | To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory |
473 | |
474 | use strict ; |
475 | use warnings ; |
476 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
477 | |
478 | anyuncompress '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>' |
479 | or die "anyuncompress failed: $AnyUncompressError\n"; |
480 | |
481 | and if you want to compress each file one at a time, this will do the trick |
482 | |
483 | use strict ; |
484 | use warnings ; |
485 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
486 | |
487 | for my $input ( glob "/my/home/*.txt.Compressed" ) |
488 | { |
489 | my $output = $input; |
490 | $output =~ s/.Compressed// ; |
491 | anyuncompress $input => $output |
492 | or die "Error compressing '$input': $AnyUncompressError\n"; |
493 | } |
494 | |
495 | =head1 OO Interface |
496 | |
497 | =head2 Constructor |
498 | |
499 | The format of the constructor for IO::Uncompress::AnyUncompress is shown below |
500 | |
25f0751f |
501 | my $z = new IO::Uncompress::AnyUncompress $input [OPTS] |
502 | or die "IO::Uncompress::AnyUncompress failed: $AnyUncompressError\n"; |
503 | |
504 | Returns an C<IO::Uncompress::AnyUncompress> object on success and undef on failure. |
505 | The variable C<$AnyUncompressError> will contain an error message on failure. |
506 | |
507 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
508 | IO::Uncompress::AnyUncompress can be used exactly like an L<IO::File|IO::File> filehandle. |
509 | This means that all normal input file operations can be carried out with |
510 | C<$z>. For example, to read a line from a compressed file/buffer you can |
511 | use either of these forms |
512 | |
513 | $line = $z->getline(); |
514 | $line = <$z>; |
515 | |
516 | The mandatory parameter C<$input> is used to determine the source of the |
517 | compressed data. This parameter can take one of three forms. |
518 | |
519 | =over 5 |
520 | |
521 | =item A filename |
522 | |
523 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
524 | file will be opened for reading and the compressed data will be read from it. |
525 | |
526 | =item A filehandle |
527 | |
528 | If the C<$input> parameter is a filehandle, the compressed data will be |
529 | read from it. |
530 | The string '-' can be used as an alias for standard input. |
531 | |
25f0751f |
532 | =item A scalar reference |
533 | |
534 | If C<$input> is a scalar reference, the compressed data will be read from |
535 | C<$$output>. |
536 | |
537 | =back |
538 | |
539 | =head2 Constructor Options |
540 | |
25f0751f |
541 | The option names defined below are case insensitive and can be optionally |
542 | prefixed by a '-'. So all of the following are valid |
543 | |
544 | -AutoClose |
545 | -autoclose |
546 | AUTOCLOSE |
547 | autoclose |
548 | |
549 | OPTS is a combination of the following options: |
550 | |
551 | =over 5 |
552 | |
e7d45986 |
553 | =item C<< AutoClose => 0|1 >> |
25f0751f |
554 | |
555 | This option is only valid when the C<$input> parameter is a filehandle. If |
556 | specified, and the value is true, it will result in the file being closed once |
557 | either the C<close> method is called or the IO::Uncompress::AnyUncompress object is |
558 | destroyed. |
559 | |
560 | This parameter defaults to 0. |
561 | |
e7d45986 |
562 | =item C<< MultiStream => 0|1 >> |
25f0751f |
563 | |
25f0751f |
564 | Allows multiple concatenated compressed streams to be treated as a single |
565 | compressed stream. Decompression will stop once either the end of the |
566 | file/buffer is reached, an error is encountered (premature eof, corrupt |
567 | compressed data) or the end of a stream is not immediately followed by the |
568 | start of another stream. |
569 | |
570 | This parameter defaults to 0. |
571 | |
e7d45986 |
572 | =item C<< Prime => $string >> |
25f0751f |
573 | |
574 | This option will uncompress the contents of C<$string> before processing the |
575 | input file/buffer. |
576 | |
577 | This option can be useful when the compressed data is embedded in another |
578 | file/data structure and it is not possible to work out where the compressed |
579 | data begins without having to read the first few bytes. If this is the |
580 | case, the uncompression can be I<primed> with these bytes using this |
581 | option. |
582 | |
e7d45986 |
583 | =item C<< Transparent => 0|1 >> |
25f0751f |
584 | |
f6fd7794 |
585 | If this option is set and the input file/buffer is not compressed data, |
25f0751f |
586 | the module will allow reading of it anyway. |
587 | |
f6fd7794 |
588 | In addition, if the input file/buffer does contain compressed data and |
589 | there is non-compressed data immediately following it, setting this option |
590 | will make this module treat the whole file/bufffer as a single data stream. |
591 | |
25f0751f |
592 | This option defaults to 1. |
593 | |
e7d45986 |
594 | =item C<< BlockSize => $num >> |
25f0751f |
595 | |
596 | When reading the compressed input data, IO::Uncompress::AnyUncompress will read it in |
597 | blocks of C<$num> bytes. |
598 | |
599 | This option defaults to 4096. |
600 | |
e7d45986 |
601 | =item C<< InputLength => $size >> |
25f0751f |
602 | |
603 | When present this option will limit the number of compressed bytes read |
604 | from the input file/buffer to C<$size>. This option can be used in the |
605 | situation where there is useful data directly after the compressed data |
606 | stream and you know beforehand the exact length of the compressed data |
607 | stream. |
608 | |
609 | This option is mostly used when reading from a filehandle, in which case |
610 | the file pointer will be left pointing to the first byte directly after the |
611 | compressed data stream. |
612 | |
25f0751f |
613 | This option defaults to off. |
614 | |
e7d45986 |
615 | =item C<< Append => 0|1 >> |
25f0751f |
616 | |
617 | This option controls what the C<read> method does with uncompressed data. |
618 | |
619 | If set to 1, all uncompressed data will be appended to the output parameter |
620 | of the C<read> method. |
621 | |
622 | If set to 0, the contents of the output parameter of the C<read> method |
623 | will be overwritten by the uncompressed data. |
624 | |
625 | Defaults to 0. |
626 | |
e7d45986 |
627 | =item C<< Strict => 0|1 >> |
25f0751f |
628 | |
25f0751f |
629 | This option controls whether the extra checks defined below are used when |
630 | carrying out the decompression. When Strict is on, the extra tests are |
631 | carried out, when Strict is off they are not. |
632 | |
633 | The default for this option is off. |
634 | |
258133d1 |
635 | =item C<< RawInflate => 0|1 >> |
636 | |
637 | When auto-detecting the compressed format, try to test for raw-deflate (RFC |
638 | 1951) content using the C<IO::Uncompress::RawInflate> module. |
639 | |
640 | The reason this is not default behaviour is because RFC 1951 content can |
641 | only be detected by attempting to uncompress it. This process is error |
642 | prone and can result is false positives. |
643 | |
644 | Defaults to 0. |
645 | |
25f0751f |
646 | =back |
647 | |
648 | =head2 Examples |
649 | |
650 | TODO |
651 | |
652 | =head1 Methods |
653 | |
654 | =head2 read |
655 | |
656 | Usage is |
657 | |
658 | $status = $z->read($buffer) |
659 | |
660 | Reads a block of compressed data (the size the the compressed block is |
661 | determined by the C<Buffer> option in the constructor), uncompresses it and |
662 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
663 | set in the constructor, the uncompressed data will be appended to the |
664 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
665 | |
666 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
667 | or a negative number on error. |
668 | |
669 | =head2 read |
670 | |
671 | Usage is |
672 | |
673 | $status = $z->read($buffer, $length) |
674 | $status = $z->read($buffer, $length, $offset) |
675 | |
676 | $status = read($z, $buffer, $length) |
677 | $status = read($z, $buffer, $length, $offset) |
678 | |
679 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
680 | |
681 | The main difference between this form of the C<read> method and the |
682 | previous one, is that this one will attempt to return I<exactly> C<$length> |
683 | bytes. The only circumstances that this function will not is if end-of-file |
684 | or an IO error is encountered. |
685 | |
686 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
687 | or a negative number on error. |
688 | |
25f0751f |
689 | =head2 getline |
690 | |
691 | Usage is |
692 | |
693 | $line = $z->getline() |
694 | $line = <$z> |
695 | |
696 | Reads a single line. |
697 | |
258133d1 |
698 | This method fully supports the use of of the variable C<$/> (or |
699 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
700 | determine what constitutes an end of line. Paragraph mode, record mode and |
701 | file slurp mode are all supported. |
25f0751f |
702 | |
25f0751f |
703 | =head2 getc |
704 | |
705 | Usage is |
706 | |
707 | $char = $z->getc() |
708 | |
709 | Read a single character. |
710 | |
711 | =head2 ungetc |
712 | |
713 | Usage is |
714 | |
715 | $char = $z->ungetc($string) |
716 | |
25f0751f |
717 | =head2 getHeaderInfo |
718 | |
719 | Usage is |
720 | |
721 | $hdr = $z->getHeaderInfo(); |
722 | @hdrs = $z->getHeaderInfo(); |
723 | |
724 | This method returns either a hash reference (in scalar context) or a list |
725 | or hash references (in array context) that contains information about each |
726 | of the header fields in the compressed data stream(s). |
727 | |
25f0751f |
728 | =head2 tell |
729 | |
730 | Usage is |
731 | |
732 | $z->tell() |
733 | tell $z |
734 | |
735 | Returns the uncompressed file offset. |
736 | |
737 | =head2 eof |
738 | |
739 | Usage is |
740 | |
741 | $z->eof(); |
742 | eof($z); |
743 | |
25f0751f |
744 | Returns true if the end of the compressed input stream has been reached. |
745 | |
25f0751f |
746 | =head2 seek |
747 | |
748 | $z->seek($position, $whence); |
749 | seek($z, $position, $whence); |
750 | |
25f0751f |
751 | Provides a sub-set of the C<seek> functionality, with the restriction |
752 | that it is only legal to seek forward in the input file/buffer. |
753 | It is a fatal error to attempt to seek backward. |
754 | |
25f0751f |
755 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
756 | SEEK_CUR or SEEK_END. |
757 | |
758 | Returns 1 on success, 0 on failure. |
759 | |
760 | =head2 binmode |
761 | |
762 | Usage is |
763 | |
764 | $z->binmode |
765 | binmode $z ; |
766 | |
767 | This is a noop provided for completeness. |
768 | |
769 | =head2 opened |
770 | |
771 | $z->opened() |
772 | |
773 | Returns true if the object currently refers to a opened file/buffer. |
774 | |
775 | =head2 autoflush |
776 | |
777 | my $prev = $z->autoflush() |
778 | my $prev = $z->autoflush(EXPR) |
779 | |
780 | If the C<$z> object is associated with a file or a filehandle, this method |
781 | returns the current autoflush setting for the underlying filehandle. If |
782 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
783 | write/print operation. |
784 | |
785 | If C<$z> is associated with a buffer, this method has no effect and always |
786 | returns C<undef>. |
787 | |
788 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
789 | retrieve the autoflush setting. |
790 | |
791 | =head2 input_line_number |
792 | |
793 | $z->input_line_number() |
794 | $z->input_line_number(EXPR) |
795 | |
25f0751f |
796 | Returns the current uncompressed line number. If C<EXPR> is present it has |
797 | the effect of setting the line number. Note that setting the line number |
798 | does not change the current position within the file/buffer being read. |
799 | |
800 | The contents of C<$/> are used to to determine what constitutes a line |
801 | terminator. |
802 | |
25f0751f |
803 | =head2 fileno |
804 | |
805 | $z->fileno() |
806 | fileno($z) |
807 | |
d54256af |
808 | If the C<$z> object is associated with a file or a filehandle, C<fileno> |
809 | will return the underlying file descriptor. Once the C<close> method is |
810 | called C<fileno> will return C<undef>. |
25f0751f |
811 | |
d54256af |
812 | If the C<$z> object is is associated with a buffer, this method will return |
813 | C<undef>. |
25f0751f |
814 | |
815 | =head2 close |
816 | |
817 | $z->close() ; |
818 | close $z ; |
819 | |
25f0751f |
820 | Closes the output file/buffer. |
821 | |
25f0751f |
822 | For most versions of Perl this method will be automatically invoked if |
823 | the IO::Uncompress::AnyUncompress object is destroyed (either explicitly or by the |
824 | variable with the reference to the object going out of scope). The |
825 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
826 | these cases, the C<close> method will be called automatically, but |
827 | not until global destruction of all live objects when the program is |
828 | terminating. |
829 | |
830 | Therefore, if you want your scripts to be able to run on all versions |
831 | of Perl, you should call C<close> explicitly and not rely on automatic |
832 | closing. |
833 | |
834 | Returns true on success, otherwise 0. |
835 | |
836 | If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyUncompress |
837 | object was created, and the object is associated with a file, the |
838 | underlying file will also be closed. |
839 | |
e7d45986 |
840 | =head2 nextStream |
841 | |
842 | Usage is |
843 | |
844 | my $status = $z->nextStream(); |
845 | |
846 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
847 | compressed data stream is found, the eof marker will be cleared and C<$.> |
848 | will be reset to 0. |
e7d45986 |
849 | |
850 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
851 | error was encountered. |
852 | |
853 | =head2 trailingData |
854 | |
855 | Usage is |
856 | |
857 | my $data = $z->trailingData(); |
858 | |
258133d1 |
859 | Returns the data, if any, that is present immediately after the compressed |
860 | data stream once uncompression is complete. It only makes sense to call |
861 | this method once the end of the compressed data stream has been |
862 | encountered. |
863 | |
864 | This option can be used when there is useful information immediately |
865 | following the compressed data stream, and you don't know the length of the |
866 | compressed data stream. |
867 | |
868 | If the input is a buffer, C<trailingData> will return everything from the |
869 | end of the compressed data stream to the end of the buffer. |
870 | |
871 | If the input is a filehandle, C<trailingData> will return the data that is |
872 | left in the filehandle input buffer once the end of the compressed data |
873 | stream has been reached. You can then use the filehandle to read the rest |
874 | of the input file. |
875 | |
876 | Don't bother using C<trailingData> if the input is a filename. |
877 | |
258133d1 |
878 | If you know the length of the compressed data stream before you start |
879 | uncompressing, you can avoid having to use C<trailingData> by setting the |
880 | C<InputLength> option in the constructor. |
e7d45986 |
881 | |
25f0751f |
882 | =head1 Importing |
883 | |
884 | No symbolic constants are required by this IO::Uncompress::AnyUncompress at present. |
885 | |
886 | =over 5 |
887 | |
888 | =item :all |
889 | |
890 | Imports C<anyuncompress> and C<$AnyUncompressError>. |
891 | Same as doing this |
892 | |
893 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; |
894 | |
895 | =back |
896 | |
897 | =head1 EXAMPLES |
898 | |
25f0751f |
899 | =head1 SEE ALSO |
900 | |
258133d1 |
901 | 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 |
902 | |
903 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
904 | |
905 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
906 | L<Archive::Tar|Archive::Tar>, |
907 | L<IO::Zlib|IO::Zlib> |
908 | |
25f0751f |
909 | =head1 AUTHOR |
910 | |
cb7abd7f |
911 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
25f0751f |
912 | |
25f0751f |
913 | =head1 MODIFICATION HISTORY |
914 | |
915 | See the Changes file. |
916 | |
917 | =head1 COPYRIGHT AND LICENSE |
25f0751f |
918 | |
d54256af |
919 | Copyright (c) 2005-2008 Paul Marquess. All rights reserved. |
25f0751f |
920 | |
921 | This program is free software; you can redistribute it and/or |
922 | modify it under the same terms as Perl itself. |
923 | |