Commit | Line | Data |
642e522c |
1 | package IO::Uncompress::AnyInflate ; |
2 | |
3 | # for RFC1950, RFC1951 or RFC1952 |
4 | |
5 | use strict; |
6 | use warnings; |
a02d0f6f |
7 | use bytes; |
1a6a8453 |
8 | |
a02d0f6f |
9 | use IO::Compress::Base::Common qw(createSelfTiedObject); |
1a6a8453 |
10 | |
a02d0f6f |
11 | use IO::Uncompress::Adapter::Inflate (); |
1a6a8453 |
12 | |
13 | |
a02d0f6f |
14 | use IO::Uncompress::Base ; |
642e522c |
15 | use IO::Uncompress::Gunzip ; |
1a6a8453 |
16 | use IO::Uncompress::Inflate ; |
17 | use IO::Uncompress::RawInflate ; |
18 | use IO::Uncompress::Unzip ; |
642e522c |
19 | |
20 | require Exporter ; |
21 | |
22 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyInflateError); |
23 | |
63ad731d |
24 | $VERSION = '2.001'; |
642e522c |
25 | $AnyInflateError = ''; |
26 | |
1a6a8453 |
27 | @ISA = qw( Exporter IO::Uncompress::Base ); |
642e522c |
28 | @EXPORT_OK = qw( $AnyInflateError anyinflate ) ; |
1a6a8453 |
29 | %EXPORT_TAGS = %IO::Uncompress::Base::DEFLATE_CONSTANTS ; |
642e522c |
30 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; |
31 | Exporter::export_ok_tags('all'); |
32 | |
642e522c |
33 | # TODO - allow the user to pick a set of the three formats to allow |
34 | # or just assume want to auto-detect any of the three formats. |
35 | |
36 | sub new |
37 | { |
1a6a8453 |
38 | my $class = shift ; |
39 | my $obj = createSelfTiedObject($class, \$AnyInflateError); |
40 | $obj->_create(undef, 0, @_); |
642e522c |
41 | } |
42 | |
43 | sub anyinflate |
44 | { |
1a6a8453 |
45 | my $obj = createSelfTiedObject(undef, \$AnyInflateError); |
46 | return $obj->_inf(@_) ; |
47 | } |
48 | |
49 | sub getExtraParams |
50 | { |
6ecef415 |
51 | use IO::Compress::Base::Common qw(:Parse); |
52 | return ( 'RawInflate' => [1, 1, Parse_boolean, 0] ) ; |
1a6a8453 |
53 | } |
54 | |
55 | sub ckParams |
56 | { |
57 | my $self = shift ; |
58 | my $got = shift ; |
59 | |
60 | # any always needs both crc32 and adler32 |
61 | $got->value('CRC32' => 1); |
62 | $got->value('ADLER32' => 1); |
63 | |
64 | return 1; |
65 | } |
66 | |
67 | sub mkUncomp |
68 | { |
69 | my $self = shift ; |
70 | my $class = shift ; |
71 | my $got = shift ; |
72 | |
a02d0f6f |
73 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject(); |
1a6a8453 |
74 | |
75 | return $self->saveErrorString(undef, $errstr, $errno) |
76 | if ! defined $obj; |
77 | |
78 | *$self->{Uncomp} = $obj; |
79 | |
6ecef415 |
80 | my @possible = qw( Inflate Gunzip Unzip ); |
81 | unshift @possible, 'RawInflate' |
82 | if 1 || $got->value('RawInflate'); |
83 | |
84 | my $magic = $self->ckMagic( @possible ); |
1a6a8453 |
85 | |
86 | if ($magic) { |
87 | *$self->{Info} = $self->readHeader($magic) |
88 | or return undef ; |
89 | |
90 | return 1; |
91 | } |
92 | |
93 | return 0 ; |
94 | } |
95 | |
96 | |
97 | |
98 | sub ckMagic |
99 | { |
100 | my $self = shift; |
101 | my @names = @_ ; |
102 | |
103 | my $keep = ref $self ; |
104 | for my $class ( map { "IO::Uncompress::$_" } @names) |
105 | { |
106 | bless $self => $class; |
107 | my $magic = $self->ckMagic(); |
108 | |
109 | if ($magic) |
110 | { |
111 | #bless $self => $class; |
112 | return $magic ; |
113 | } |
114 | |
115 | $self->pushBack(*$self->{HeaderPending}) ; |
116 | *$self->{HeaderPending} = '' ; |
117 | } |
118 | |
119 | bless $self => $keep; |
120 | return undef; |
642e522c |
121 | } |
122 | |
123 | 1 ; |
124 | |
125 | __END__ |
126 | |
127 | |
128 | =head1 NAME |
129 | |
a02d0f6f |
130 | |
cb7abd7f |
131 | IO::Uncompress::AnyInflate - Uncompress zlib-based (zip, gzip) file/buffer |
642e522c |
132 | |
a02d0f6f |
133 | |
642e522c |
134 | =head1 SYNOPSIS |
135 | |
136 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
137 | |
138 | my $status = anyinflate $input => $output [,OPTS] |
139 | or die "anyinflate failed: $AnyInflateError\n"; |
140 | |
141 | my $z = new IO::Uncompress::AnyInflate $input [OPTS] |
142 | or die "anyinflate failed: $AnyInflateError\n"; |
143 | |
144 | $status = $z->read($buffer) |
145 | $status = $z->read($buffer, $length) |
146 | $status = $z->read($buffer, $length, $offset) |
147 | $line = $z->getline() |
148 | $char = $z->getc() |
149 | $char = $z->ungetc() |
a02d0f6f |
150 | $char = $z->opened() |
151 | |
642e522c |
152 | $status = $z->inflateSync() |
a02d0f6f |
153 | |
e7d45986 |
154 | $data = $z->trailingData() |
155 | $status = $z->nextStream() |
642e522c |
156 | $data = $z->getHeaderInfo() |
157 | $z->tell() |
158 | $z->seek($position, $whence) |
159 | $z->binmode() |
160 | $z->fileno() |
161 | $z->eof() |
162 | $z->close() |
163 | |
164 | $AnyInflateError ; |
165 | |
166 | # IO::File mode |
167 | |
168 | <$z> |
169 | read($z, $buffer); |
170 | read($z, $buffer, $length); |
171 | read($z, $buffer, $length, $offset); |
172 | tell($z) |
173 | seek($z, $position, $whence) |
174 | binmode($z) |
175 | fileno($z) |
176 | eof($z) |
177 | close($z) |
178 | |
179 | |
180 | =head1 DESCRIPTION |
181 | |
182 | |
1a6a8453 |
183 | This module provides a Perl interface that allows the reading of |
cb7abd7f |
184 | files/buffers that have been compressed in a number of formats that use the |
185 | zlib compression library. |
186 | |
187 | The formats supported are |
188 | |
189 | =over 5 |
190 | |
191 | =item RFC 1950 |
192 | |
258133d1 |
193 | =item RFC 1951 (optionally) |
cb7abd7f |
194 | |
195 | =item gzip (RFC 1952) |
196 | |
197 | =item zip |
642e522c |
198 | |
cb7abd7f |
199 | =back |
200 | |
201 | The module will auto-detect which, if any, of the supported |
1a6a8453 |
202 | compression formats is being used. |
642e522c |
203 | |
204 | |
205 | |
cb7abd7f |
206 | |
207 | |
642e522c |
208 | =head1 Functional Interface |
209 | |
1a6a8453 |
210 | A top-level function, C<anyinflate>, is provided to carry out |
211 | "one-shot" uncompression between buffers and/or files. For finer |
212 | control over the uncompression process, see the L</"OO Interface"> |
213 | section. |
642e522c |
214 | |
215 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
216 | |
217 | anyinflate $input => $output [,OPTS] |
218 | or die "anyinflate failed: $AnyInflateError\n"; |
219 | |
1a6a8453 |
220 | |
642e522c |
221 | |
222 | The functional interface needs Perl5.005 or better. |
223 | |
224 | |
225 | =head2 anyinflate $input => $output [, OPTS] |
226 | |
1a6a8453 |
227 | |
228 | C<anyinflate> expects at least two parameters, C<$input> and C<$output>. |
642e522c |
229 | |
230 | =head3 The C<$input> parameter |
231 | |
232 | The parameter, C<$input>, is used to define the source of |
233 | the compressed data. |
234 | |
235 | It can take one of the following forms: |
236 | |
237 | =over 5 |
238 | |
239 | =item A filename |
240 | |
241 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
242 | filename. This file will be opened for reading and the input data |
243 | will be read from it. |
244 | |
245 | =item A filehandle |
246 | |
247 | If the C<$input> parameter is a filehandle, the input data will be |
248 | read from it. |
249 | The string '-' can be used as an alias for standard input. |
250 | |
251 | =item A scalar reference |
252 | |
253 | If C<$input> is a scalar reference, the input data will be read |
254 | from C<$$input>. |
255 | |
256 | =item An array reference |
257 | |
1a6a8453 |
258 | If C<$input> is an array reference, each element in the array must be a |
259 | filename. |
260 | |
261 | The input data will be read from each file in turn. |
262 | |
642e522c |
263 | The complete array will be walked to ensure that it only |
1a6a8453 |
264 | contains valid filenames before any data is uncompressed. |
265 | |
266 | |
642e522c |
267 | |
268 | =item An Input FileGlob string |
269 | |
270 | If C<$input> is a string that is delimited by the characters "<" and ">" |
271 | C<anyinflate> will assume that it is an I<input fileglob string>. The |
272 | input is the list of files that match the fileglob. |
273 | |
274 | If the fileglob does not match any files ... |
275 | |
276 | See L<File::GlobMapper|File::GlobMapper> for more details. |
277 | |
278 | |
279 | =back |
280 | |
281 | If the C<$input> parameter is any other type, C<undef> will be returned. |
282 | |
283 | |
284 | |
285 | =head3 The C<$output> parameter |
286 | |
287 | The parameter C<$output> is used to control the destination of the |
288 | uncompressed data. This parameter can take one of these forms. |
289 | |
290 | =over 5 |
291 | |
292 | =item A filename |
293 | |
1a6a8453 |
294 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
295 | filename. This file will be opened for writing and the uncompressed |
296 | data will be written to it. |
642e522c |
297 | |
298 | =item A filehandle |
299 | |
1a6a8453 |
300 | If the C<$output> parameter is a filehandle, the uncompressed data |
301 | will be written to it. |
642e522c |
302 | The string '-' can be used as an alias for standard output. |
303 | |
304 | |
305 | =item A scalar reference |
306 | |
1a6a8453 |
307 | If C<$output> is a scalar reference, the uncompressed data will be |
308 | stored in C<$$output>. |
642e522c |
309 | |
642e522c |
310 | |
311 | |
312 | =item An Array Reference |
313 | |
1a6a8453 |
314 | If C<$output> is an array reference, the uncompressed data will be |
315 | pushed onto the array. |
642e522c |
316 | |
317 | =item An Output FileGlob |
318 | |
319 | If C<$output> is a string that is delimited by the characters "<" and ">" |
320 | C<anyinflate> will assume that it is an I<output fileglob string>. The |
321 | output is the list of files that match the fileglob. |
322 | |
323 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
324 | string. Anything else is an error. |
325 | |
326 | =back |
327 | |
328 | If the C<$output> parameter is any other type, C<undef> will be returned. |
329 | |
642e522c |
330 | |
642e522c |
331 | |
332 | =head2 Notes |
333 | |
c70c1701 |
334 | |
335 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
336 | a single file/buffer, after uncompression C<$output> will contain a |
337 | concatenation of all the uncompressed data from each of the input |
338 | files/buffers. |
339 | |
340 | |
642e522c |
341 | |
342 | |
343 | |
344 | =head2 Optional Parameters |
345 | |
346 | Unless specified below, the optional parameters for C<anyinflate>, |
347 | C<OPTS>, are the same as those used with the OO interface defined in the |
348 | L</"Constructor Options"> section below. |
349 | |
350 | =over 5 |
351 | |
e7d45986 |
352 | =item C<< AutoClose => 0|1 >> |
642e522c |
353 | |
1a6a8453 |
354 | This option applies to any input or output data streams to |
355 | C<anyinflate> that are filehandles. |
642e522c |
356 | |
357 | If C<AutoClose> is specified, and the value is true, it will result in all |
358 | input and/or output filehandles being closed once C<anyinflate> has |
359 | completed. |
360 | |
361 | This parameter defaults to 0. |
362 | |
363 | |
e7d45986 |
364 | =item C<< BinModeOut => 0|1 >> |
1a6a8453 |
365 | |
366 | When writing to a file or filehandle, set C<binmode> before writing to the |
367 | file. |
368 | |
369 | Defaults to 0. |
370 | |
371 | |
372 | |
373 | |
374 | |
e7d45986 |
375 | =item C<< Append => 0|1 >> |
642e522c |
376 | |
377 | TODO |
378 | |
e7d45986 |
379 | =item C<< MultiStream => 0|1 >> |
1a6a8453 |
380 | |
258133d1 |
381 | |
e7d45986 |
382 | If the input file/buffer contains multiple compressed data streams, this |
383 | option will uncompress the whole lot as a single data stream. |
1a6a8453 |
384 | |
e7d45986 |
385 | Defaults to 0. |
1a6a8453 |
386 | |
642e522c |
387 | |
388 | |
258133d1 |
389 | |
390 | |
391 | =item C<< TrailingData => $scalar >> |
392 | |
393 | Returns the data, if any, that is present immediately after the compressed |
394 | data stream once uncompression is complete. |
395 | |
396 | This option can be used when there is useful information immediately |
397 | following the compressed data stream, and you don't know the length of the |
398 | compressed data stream. |
399 | |
400 | If the input is a buffer, C<trailingData> will return everything from the |
401 | end of the compressed data stream to the end of the buffer. |
402 | |
403 | If the input is a filehandle, C<trailingData> will return the data that is |
404 | left in the filehandle input buffer once the end of the compressed data |
405 | stream has been reached. You can then use the filehandle to read the rest |
406 | of the input file. |
407 | |
408 | Don't bother using C<trailingData> if the input is a filename. |
409 | |
410 | |
411 | |
412 | If you know the length of the compressed data stream before you start |
413 | uncompressing, you can avoid having to use C<trailingData> by setting the |
414 | C<InputLength> option. |
415 | |
416 | |
417 | |
642e522c |
418 | =back |
419 | |
420 | |
421 | |
422 | |
423 | =head2 Examples |
424 | |
425 | To read the contents of the file C<file1.txt.Compressed> and write the |
426 | compressed data to the file C<file1.txt>. |
427 | |
428 | use strict ; |
429 | use warnings ; |
430 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
431 | |
432 | my $input = "file1.txt.Compressed"; |
433 | my $output = "file1.txt"; |
434 | anyinflate $input => $output |
435 | or die "anyinflate failed: $AnyInflateError\n"; |
436 | |
437 | |
438 | To read from an existing Perl filehandle, C<$input>, and write the |
439 | uncompressed data to a buffer, C<$buffer>. |
440 | |
441 | use strict ; |
442 | use warnings ; |
443 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
444 | use IO::File ; |
445 | |
446 | my $input = new IO::File "<file1.txt.Compressed" |
447 | or die "Cannot open 'file1.txt.Compressed': $!\n" ; |
448 | my $buffer ; |
449 | anyinflate $input => \$buffer |
450 | or die "anyinflate failed: $AnyInflateError\n"; |
451 | |
452 | To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory |
453 | |
454 | use strict ; |
455 | use warnings ; |
456 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
457 | |
458 | anyinflate '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>' |
459 | or die "anyinflate failed: $AnyInflateError\n"; |
460 | |
461 | and if you want to compress each file one at a time, this will do the trick |
462 | |
463 | use strict ; |
464 | use warnings ; |
465 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
466 | |
467 | for my $input ( glob "/my/home/*.txt.Compressed" ) |
468 | { |
469 | my $output = $input; |
470 | $output =~ s/.Compressed// ; |
471 | anyinflate $input => $output |
472 | or die "Error compressing '$input': $AnyInflateError\n"; |
473 | } |
474 | |
475 | =head1 OO Interface |
476 | |
477 | =head2 Constructor |
478 | |
479 | The format of the constructor for IO::Uncompress::AnyInflate is shown below |
480 | |
481 | |
482 | my $z = new IO::Uncompress::AnyInflate $input [OPTS] |
483 | or die "IO::Uncompress::AnyInflate failed: $AnyInflateError\n"; |
484 | |
485 | Returns an C<IO::Uncompress::AnyInflate> object on success and undef on failure. |
486 | The variable C<$AnyInflateError> will contain an error message on failure. |
487 | |
1a6a8453 |
488 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
489 | IO::Uncompress::AnyInflate can be used exactly like an L<IO::File|IO::File> filehandle. |
490 | This means that all normal input file operations can be carried out with |
491 | C<$z>. For example, to read a line from a compressed file/buffer you can |
492 | use either of these forms |
642e522c |
493 | |
494 | $line = $z->getline(); |
495 | $line = <$z>; |
496 | |
497 | The mandatory parameter C<$input> is used to determine the source of the |
498 | compressed data. This parameter can take one of three forms. |
499 | |
500 | =over 5 |
501 | |
502 | =item A filename |
503 | |
504 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
505 | file will be opened for reading and the compressed data will be read from it. |
506 | |
507 | =item A filehandle |
508 | |
509 | If the C<$input> parameter is a filehandle, the compressed data will be |
510 | read from it. |
511 | The string '-' can be used as an alias for standard input. |
512 | |
513 | |
514 | =item A scalar reference |
515 | |
516 | If C<$input> is a scalar reference, the compressed data will be read from |
517 | C<$$output>. |
518 | |
519 | =back |
520 | |
521 | =head2 Constructor Options |
522 | |
523 | |
524 | The option names defined below are case insensitive and can be optionally |
525 | prefixed by a '-'. So all of the following are valid |
526 | |
527 | -AutoClose |
528 | -autoclose |
529 | AUTOCLOSE |
530 | autoclose |
531 | |
532 | OPTS is a combination of the following options: |
533 | |
534 | =over 5 |
535 | |
e7d45986 |
536 | =item C<< AutoClose => 0|1 >> |
642e522c |
537 | |
538 | This option is only valid when the C<$input> parameter is a filehandle. If |
539 | specified, and the value is true, it will result in the file being closed once |
540 | either the C<close> method is called or the IO::Uncompress::AnyInflate object is |
541 | destroyed. |
542 | |
543 | This parameter defaults to 0. |
544 | |
e7d45986 |
545 | =item C<< MultiStream => 0|1 >> |
642e522c |
546 | |
547 | |
548 | |
549 | Allows multiple concatenated compressed streams to be treated as a single |
550 | compressed stream. Decompression will stop once either the end of the |
551 | file/buffer is reached, an error is encountered (premature eof, corrupt |
552 | compressed data) or the end of a stream is not immediately followed by the |
553 | start of another stream. |
554 | |
555 | This parameter defaults to 0. |
556 | |
557 | |
e7d45986 |
558 | =item C<< Prime => $string >> |
642e522c |
559 | |
560 | This option will uncompress the contents of C<$string> before processing the |
561 | input file/buffer. |
562 | |
563 | This option can be useful when the compressed data is embedded in another |
564 | file/data structure and it is not possible to work out where the compressed |
1a6a8453 |
565 | data begins without having to read the first few bytes. If this is the |
566 | case, the uncompression can be I<primed> with these bytes using this |
567 | option. |
642e522c |
568 | |
e7d45986 |
569 | =item C<< Transparent => 0|1 >> |
642e522c |
570 | |
571 | If this option is set and the input file or buffer is not compressed data, |
572 | the module will allow reading of it anyway. |
573 | |
574 | This option defaults to 1. |
575 | |
e7d45986 |
576 | =item C<< BlockSize => $num >> |
642e522c |
577 | |
1a6a8453 |
578 | When reading the compressed input data, IO::Uncompress::AnyInflate will read it in |
579 | blocks of C<$num> bytes. |
642e522c |
580 | |
581 | This option defaults to 4096. |
582 | |
e7d45986 |
583 | =item C<< InputLength => $size >> |
642e522c |
584 | |
1a6a8453 |
585 | When present this option will limit the number of compressed bytes read |
586 | from the input file/buffer to C<$size>. This option can be used in the |
587 | situation where there is useful data directly after the compressed data |
588 | stream and you know beforehand the exact length of the compressed data |
589 | stream. |
642e522c |
590 | |
1a6a8453 |
591 | This option is mostly used when reading from a filehandle, in which case |
592 | the file pointer will be left pointing to the first byte directly after the |
642e522c |
593 | compressed data stream. |
594 | |
595 | |
596 | |
597 | This option defaults to off. |
598 | |
e7d45986 |
599 | =item C<< Append => 0|1 >> |
642e522c |
600 | |
601 | This option controls what the C<read> method does with uncompressed data. |
602 | |
1a6a8453 |
603 | If set to 1, all uncompressed data will be appended to the output parameter |
604 | of the C<read> method. |
642e522c |
605 | |
1a6a8453 |
606 | If set to 0, the contents of the output parameter of the C<read> method |
607 | will be overwritten by the uncompressed data. |
642e522c |
608 | |
609 | Defaults to 0. |
610 | |
e7d45986 |
611 | =item C<< Strict => 0|1 >> |
642e522c |
612 | |
613 | |
614 | |
615 | This option controls whether the extra checks defined below are used when |
1a6a8453 |
616 | carrying out the decompression. When Strict is on, the extra tests are |
617 | carried out, when Strict is off they are not. |
642e522c |
618 | |
619 | The default for this option is off. |
620 | |
621 | |
a02d0f6f |
622 | If the input is an RFC 1950 data stream, the following will be checked: |
642e522c |
623 | |
624 | |
625 | |
626 | |
627 | =over 5 |
628 | |
629 | =item 1 |
630 | |
631 | The ADLER32 checksum field must be present. |
632 | |
633 | =item 2 |
634 | |
635 | The value of the ADLER32 field read must match the adler32 value of the |
636 | uncompressed data actually contained in the file. |
637 | |
638 | =back |
639 | |
640 | |
641 | |
a02d0f6f |
642 | If the input is a gzip (RFC 1952) data stream, the following will be checked: |
642e522c |
643 | |
644 | |
645 | |
646 | |
647 | =over 5 |
648 | |
649 | =item 1 |
650 | |
651 | If the FHCRC bit is set in the gzip FLG header byte, the CRC16 bytes in the |
652 | header must match the crc16 value of the gzip header actually read. |
653 | |
654 | =item 2 |
655 | |
656 | If the gzip header contains a name field (FNAME) it consists solely of ISO |
657 | 8859-1 characters. |
658 | |
659 | =item 3 |
660 | |
1a6a8453 |
661 | If the gzip header contains a comment field (FCOMMENT) it consists solely |
662 | of ISO 8859-1 characters plus line-feed. |
642e522c |
663 | |
664 | =item 4 |
665 | |
666 | If the gzip FEXTRA header field is present it must conform to the sub-field |
a02d0f6f |
667 | structure as defined in RFC 1952. |
642e522c |
668 | |
669 | =item 5 |
670 | |
671 | The CRC32 and ISIZE trailer fields must be present. |
672 | |
673 | =item 6 |
674 | |
675 | The value of the CRC32 field read must match the crc32 value of the |
676 | uncompressed data actually contained in the gzip file. |
677 | |
678 | =item 7 |
679 | |
1a6a8453 |
680 | The value of the ISIZE fields read must match the length of the |
681 | uncompressed data actually read from the file. |
642e522c |
682 | |
683 | =back |
684 | |
685 | |
686 | |
687 | |
688 | |
258133d1 |
689 | =item C<< RawInflate => 0|1 >> |
642e522c |
690 | |
258133d1 |
691 | When auto-detecting the compressed format, try to test for raw-deflate (RFC |
692 | 1951) content using the C<IO::Uncompress::RawInflate> module. |
642e522c |
693 | |
258133d1 |
694 | The reason this is not default behaviour is because RFC 1951 content can |
695 | only be detected by attempting to uncompress it. This process is error |
696 | prone and can result is false positives. |
697 | |
698 | Defaults to 0. |
699 | |
700 | |
701 | |
702 | |
703 | =item C<< ParseExtra => 0|1 >> |
642e522c |
704 | If the gzip FEXTRA header field is present and this option is set, it will |
705 | force the module to check that it conforms to the sub-field structure as |
a02d0f6f |
706 | defined in RFC 1952. |
642e522c |
707 | |
708 | If the C<Strict> is on it will automatically enable this option. |
709 | |
710 | Defaults to 0. |
711 | |
712 | |
713 | |
a02d0f6f |
714 | |
642e522c |
715 | =back |
716 | |
717 | =head2 Examples |
718 | |
719 | TODO |
720 | |
721 | =head1 Methods |
722 | |
723 | =head2 read |
724 | |
725 | Usage is |
726 | |
727 | $status = $z->read($buffer) |
728 | |
729 | Reads a block of compressed data (the size the the compressed block is |
730 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1a6a8453 |
731 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
732 | set in the constructor, the uncompressed data will be appended to the |
733 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
642e522c |
734 | |
1a6a8453 |
735 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
736 | or a negative number on error. |
642e522c |
737 | |
738 | =head2 read |
739 | |
740 | Usage is |
741 | |
742 | $status = $z->read($buffer, $length) |
743 | $status = $z->read($buffer, $length, $offset) |
744 | |
745 | $status = read($z, $buffer, $length) |
746 | $status = read($z, $buffer, $length, $offset) |
747 | |
748 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
749 | |
1a6a8453 |
750 | The main difference between this form of the C<read> method and the |
751 | previous one, is that this one will attempt to return I<exactly> C<$length> |
752 | bytes. The only circumstances that this function will not is if end-of-file |
753 | or an IO error is encountered. |
642e522c |
754 | |
1a6a8453 |
755 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
756 | or a negative number on error. |
642e522c |
757 | |
758 | |
759 | =head2 getline |
760 | |
761 | Usage is |
762 | |
763 | $line = $z->getline() |
764 | $line = <$z> |
765 | |
766 | Reads a single line. |
767 | |
258133d1 |
768 | This method fully supports the use of of the variable C<$/> (or |
769 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
770 | determine what constitutes an end of line. Paragraph mode, record mode and |
771 | file slurp mode are all supported. |
642e522c |
772 | |
773 | |
774 | =head2 getc |
775 | |
776 | Usage is |
777 | |
778 | $char = $z->getc() |
779 | |
780 | Read a single character. |
781 | |
782 | =head2 ungetc |
783 | |
784 | Usage is |
785 | |
786 | $char = $z->ungetc($string) |
787 | |
788 | |
a02d0f6f |
789 | |
642e522c |
790 | =head2 inflateSync |
791 | |
792 | Usage is |
793 | |
794 | $status = $z->inflateSync() |
795 | |
796 | TODO |
797 | |
a02d0f6f |
798 | |
642e522c |
799 | =head2 getHeaderInfo |
800 | |
801 | Usage is |
802 | |
1a6a8453 |
803 | $hdr = $z->getHeaderInfo(); |
804 | @hdrs = $z->getHeaderInfo(); |
642e522c |
805 | |
1a6a8453 |
806 | This method returns either a hash reference (in scalar context) or a list |
807 | or hash references (in array context) that contains information about each |
808 | of the header fields in the compressed data stream(s). |
642e522c |
809 | |
810 | |
811 | |
812 | |
813 | =head2 tell |
814 | |
815 | Usage is |
816 | |
817 | $z->tell() |
818 | tell $z |
819 | |
820 | Returns the uncompressed file offset. |
821 | |
822 | =head2 eof |
823 | |
824 | Usage is |
825 | |
826 | $z->eof(); |
827 | eof($z); |
828 | |
829 | |
830 | |
831 | Returns true if the end of the compressed input stream has been reached. |
832 | |
833 | |
834 | |
835 | =head2 seek |
836 | |
837 | $z->seek($position, $whence); |
838 | seek($z, $position, $whence); |
839 | |
840 | |
841 | |
842 | |
843 | Provides a sub-set of the C<seek> functionality, with the restriction |
844 | that it is only legal to seek forward in the input file/buffer. |
845 | It is a fatal error to attempt to seek backward. |
846 | |
847 | |
848 | |
849 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
850 | SEEK_CUR or SEEK_END. |
851 | |
852 | Returns 1 on success, 0 on failure. |
853 | |
854 | =head2 binmode |
855 | |
856 | Usage is |
857 | |
858 | $z->binmode |
859 | binmode $z ; |
860 | |
861 | This is a noop provided for completeness. |
862 | |
a02d0f6f |
863 | =head2 opened |
864 | |
865 | $z->opened() |
866 | |
867 | Returns true if the object currently refers to a opened file/buffer. |
868 | |
869 | =head2 autoflush |
870 | |
871 | my $prev = $z->autoflush() |
872 | my $prev = $z->autoflush(EXPR) |
873 | |
874 | If the C<$z> object is associated with a file or a filehandle, this method |
875 | returns the current autoflush setting for the underlying filehandle. If |
876 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
877 | write/print operation. |
878 | |
879 | If C<$z> is associated with a buffer, this method has no effect and always |
880 | returns C<undef>. |
881 | |
882 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
883 | retrieve the autoflush setting. |
884 | |
885 | =head2 input_line_number |
886 | |
887 | $z->input_line_number() |
888 | $z->input_line_number(EXPR) |
889 | |
890 | |
891 | |
892 | Returns the current uncompressed line number. If C<EXPR> is present it has |
893 | the effect of setting the line number. Note that setting the line number |
894 | does not change the current position within the file/buffer being read. |
895 | |
896 | The contents of C<$/> are used to to determine what constitutes a line |
897 | terminator. |
898 | |
899 | |
900 | |
642e522c |
901 | =head2 fileno |
902 | |
903 | $z->fileno() |
904 | fileno($z) |
905 | |
a02d0f6f |
906 | If the C<$z> object is associated with a file or a filehandle, this method |
907 | will return the underlying file descriptor. |
642e522c |
908 | |
909 | If the C<$z> object is is associated with a buffer, this method will |
910 | return undef. |
911 | |
912 | =head2 close |
913 | |
914 | $z->close() ; |
915 | close $z ; |
916 | |
917 | |
918 | |
919 | Closes the output file/buffer. |
920 | |
921 | |
922 | |
923 | For most versions of Perl this method will be automatically invoked if |
924 | the IO::Uncompress::AnyInflate object is destroyed (either explicitly or by the |
925 | variable with the reference to the object going out of scope). The |
926 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
927 | these cases, the C<close> method will be called automatically, but |
928 | not until global destruction of all live objects when the program is |
929 | terminating. |
930 | |
931 | Therefore, if you want your scripts to be able to run on all versions |
932 | of Perl, you should call C<close> explicitly and not rely on automatic |
933 | closing. |
934 | |
935 | Returns true on success, otherwise 0. |
936 | |
937 | If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyInflate |
938 | object was created, and the object is associated with a file, the |
939 | underlying file will also be closed. |
940 | |
941 | |
942 | |
943 | |
e7d45986 |
944 | =head2 nextStream |
945 | |
946 | Usage is |
947 | |
948 | my $status = $z->nextStream(); |
949 | |
950 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
951 | compressed data stream is found, the eof marker will be cleared and C<$.> |
952 | will be reset to 0. |
e7d45986 |
953 | |
954 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
955 | error was encountered. |
956 | |
957 | =head2 trailingData |
958 | |
959 | Usage is |
960 | |
961 | my $data = $z->trailingData(); |
962 | |
258133d1 |
963 | Returns the data, if any, that is present immediately after the compressed |
964 | data stream once uncompression is complete. It only makes sense to call |
965 | this method once the end of the compressed data stream has been |
966 | encountered. |
967 | |
968 | This option can be used when there is useful information immediately |
969 | following the compressed data stream, and you don't know the length of the |
970 | compressed data stream. |
971 | |
972 | If the input is a buffer, C<trailingData> will return everything from the |
973 | end of the compressed data stream to the end of the buffer. |
974 | |
975 | If the input is a filehandle, C<trailingData> will return the data that is |
976 | left in the filehandle input buffer once the end of the compressed data |
977 | stream has been reached. You can then use the filehandle to read the rest |
978 | of the input file. |
979 | |
980 | Don't bother using C<trailingData> if the input is a filename. |
981 | |
982 | |
983 | |
984 | If you know the length of the compressed data stream before you start |
985 | uncompressing, you can avoid having to use C<trailingData> by setting the |
986 | C<InputLength> option in the constructor. |
e7d45986 |
987 | |
642e522c |
988 | =head1 Importing |
989 | |
990 | No symbolic constants are required by this IO::Uncompress::AnyInflate at present. |
991 | |
992 | =over 5 |
993 | |
994 | =item :all |
995 | |
996 | Imports C<anyinflate> and C<$AnyInflateError>. |
997 | Same as doing this |
998 | |
999 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
1000 | |
1001 | =back |
1002 | |
1003 | =head1 EXAMPLES |
1004 | |
1005 | |
1006 | |
1007 | |
1008 | =head1 SEE ALSO |
1009 | |
258133d1 |
1010 | 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::AnyUncompress> |
642e522c |
1011 | |
1012 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
1013 | |
a02d0f6f |
1014 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1015 | L<Archive::Tar|Archive::Tar>, |
642e522c |
1016 | L<IO::Zlib|IO::Zlib> |
1017 | |
a02d0f6f |
1018 | |
642e522c |
1019 | For RFC 1950, 1951 and 1952 see |
1020 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
1021 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
1022 | F<http://www.faqs.org/rfcs/rfc1952.html> |
1023 | |
a02d0f6f |
1024 | The I<zlib> compression library was written by Jean-loup Gailly |
1025 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
1026 | |
1027 | The primary site for the I<zlib> compression library is |
1028 | F<http://www.zlib.org>. |
1029 | |
1030 | The primary site for gzip is F<http://www.gzip.org>. |
1031 | |
1032 | |
1033 | |
1034 | |
642e522c |
1035 | =head1 AUTHOR |
1036 | |
cb7abd7f |
1037 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
642e522c |
1038 | |
642e522c |
1039 | |
642e522c |
1040 | |
1041 | =head1 MODIFICATION HISTORY |
1042 | |
1043 | See the Changes file. |
1044 | |
1045 | =head1 COPYRIGHT AND LICENSE |
642e522c |
1046 | |
1a6a8453 |
1047 | Copyright (c) 2005-2006 Paul Marquess. All rights reserved. |
a02d0f6f |
1048 | |
642e522c |
1049 | This program is free software; you can redistribute it and/or |
1050 | modify it under the same terms as Perl itself. |
1051 | |