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 | |
ea6efd2c |
9 | use IO::Compress::Base::Common 2.018 qw(createSelfTiedObject); |
1a6a8453 |
10 | |
ea6efd2c |
11 | use IO::Uncompress::Adapter::Inflate 2.018 (); |
1a6a8453 |
12 | |
13 | |
ea6efd2c |
14 | use IO::Uncompress::Base 2.018 ; |
15 | use IO::Uncompress::Gunzip 2.018 ; |
16 | use IO::Uncompress::Inflate 2.018 ; |
17 | use IO::Uncompress::RawInflate 2.018 ; |
18 | use IO::Uncompress::Unzip 2.018 ; |
642e522c |
19 | |
20 | require Exporter ; |
21 | |
22 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyInflateError); |
23 | |
ea6efd2c |
24 | $VERSION = '2.018'; |
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 | { |
ea6efd2c |
51 | use IO::Compress::Base::Common 2.018 qw(:Parse); |
6ecef415 |
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 ; |
1a6a8453 |
70 | my $got = shift ; |
71 | |
a02d0f6f |
72 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject(); |
1a6a8453 |
73 | |
74 | return $self->saveErrorString(undef, $errstr, $errno) |
75 | if ! defined $obj; |
76 | |
77 | *$self->{Uncomp} = $obj; |
78 | |
6ecef415 |
79 | my @possible = qw( Inflate Gunzip Unzip ); |
80 | unshift @possible, 'RawInflate' |
81 | if 1 || $got->value('RawInflate'); |
82 | |
83 | my $magic = $self->ckMagic( @possible ); |
1a6a8453 |
84 | |
85 | if ($magic) { |
86 | *$self->{Info} = $self->readHeader($magic) |
87 | or return undef ; |
88 | |
89 | return 1; |
90 | } |
91 | |
92 | return 0 ; |
93 | } |
94 | |
95 | |
96 | |
97 | sub ckMagic |
98 | { |
99 | my $self = shift; |
100 | my @names = @_ ; |
101 | |
102 | my $keep = ref $self ; |
103 | for my $class ( map { "IO::Uncompress::$_" } @names) |
104 | { |
105 | bless $self => $class; |
106 | my $magic = $self->ckMagic(); |
107 | |
108 | if ($magic) |
109 | { |
110 | #bless $self => $class; |
111 | return $magic ; |
112 | } |
113 | |
114 | $self->pushBack(*$self->{HeaderPending}) ; |
115 | *$self->{HeaderPending} = '' ; |
116 | } |
117 | |
118 | bless $self => $keep; |
119 | return undef; |
642e522c |
120 | } |
121 | |
122 | 1 ; |
123 | |
124 | __END__ |
125 | |
126 | |
127 | =head1 NAME |
128 | |
cb7abd7f |
129 | IO::Uncompress::AnyInflate - Uncompress zlib-based (zip, gzip) file/buffer |
642e522c |
130 | |
131 | =head1 SYNOPSIS |
132 | |
133 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
134 | |
135 | my $status = anyinflate $input => $output [,OPTS] |
136 | or die "anyinflate failed: $AnyInflateError\n"; |
137 | |
138 | my $z = new IO::Uncompress::AnyInflate $input [OPTS] |
139 | or die "anyinflate failed: $AnyInflateError\n"; |
140 | |
141 | $status = $z->read($buffer) |
142 | $status = $z->read($buffer, $length) |
143 | $status = $z->read($buffer, $length, $offset) |
144 | $line = $z->getline() |
145 | $char = $z->getc() |
146 | $char = $z->ungetc() |
a02d0f6f |
147 | $char = $z->opened() |
148 | |
642e522c |
149 | $status = $z->inflateSync() |
a02d0f6f |
150 | |
e7d45986 |
151 | $data = $z->trailingData() |
152 | $status = $z->nextStream() |
642e522c |
153 | $data = $z->getHeaderInfo() |
154 | $z->tell() |
155 | $z->seek($position, $whence) |
156 | $z->binmode() |
157 | $z->fileno() |
158 | $z->eof() |
159 | $z->close() |
160 | |
161 | $AnyInflateError ; |
162 | |
163 | # IO::File mode |
164 | |
165 | <$z> |
166 | read($z, $buffer); |
167 | read($z, $buffer, $length); |
168 | read($z, $buffer, $length, $offset); |
169 | tell($z) |
170 | seek($z, $position, $whence) |
171 | binmode($z) |
172 | fileno($z) |
173 | eof($z) |
174 | close($z) |
175 | |
642e522c |
176 | =head1 DESCRIPTION |
177 | |
1a6a8453 |
178 | This module provides a Perl interface that allows the reading of |
cb7abd7f |
179 | files/buffers that have been compressed in a number of formats that use the |
180 | zlib compression library. |
181 | |
182 | The formats supported are |
183 | |
184 | =over 5 |
185 | |
186 | =item RFC 1950 |
187 | |
258133d1 |
188 | =item RFC 1951 (optionally) |
cb7abd7f |
189 | |
190 | =item gzip (RFC 1952) |
191 | |
192 | =item zip |
642e522c |
193 | |
cb7abd7f |
194 | =back |
195 | |
196 | The module will auto-detect which, if any, of the supported |
1a6a8453 |
197 | compression formats is being used. |
642e522c |
198 | |
642e522c |
199 | =head1 Functional Interface |
200 | |
1a6a8453 |
201 | A top-level function, C<anyinflate>, is provided to carry out |
202 | "one-shot" uncompression between buffers and/or files. For finer |
203 | control over the uncompression process, see the L</"OO Interface"> |
204 | section. |
642e522c |
205 | |
206 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
207 | |
208 | anyinflate $input => $output [,OPTS] |
209 | or die "anyinflate failed: $AnyInflateError\n"; |
210 | |
642e522c |
211 | The functional interface needs Perl5.005 or better. |
212 | |
642e522c |
213 | =head2 anyinflate $input => $output [, OPTS] |
214 | |
1a6a8453 |
215 | C<anyinflate> expects at least two parameters, C<$input> and C<$output>. |
642e522c |
216 | |
217 | =head3 The C<$input> parameter |
218 | |
219 | The parameter, C<$input>, is used to define the source of |
220 | the compressed data. |
221 | |
222 | It can take one of the following forms: |
223 | |
224 | =over 5 |
225 | |
226 | =item A filename |
227 | |
228 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
229 | filename. This file will be opened for reading and the input data |
230 | will be read from it. |
231 | |
232 | =item A filehandle |
233 | |
234 | If the C<$input> parameter is a filehandle, the input data will be |
235 | read from it. |
236 | The string '-' can be used as an alias for standard input. |
237 | |
238 | =item A scalar reference |
239 | |
240 | If C<$input> is a scalar reference, the input data will be read |
241 | from C<$$input>. |
242 | |
243 | =item An array reference |
244 | |
1a6a8453 |
245 | If C<$input> is an array reference, each element in the array must be a |
246 | filename. |
247 | |
248 | The input data will be read from each file in turn. |
249 | |
642e522c |
250 | The complete array will be walked to ensure that it only |
1a6a8453 |
251 | contains valid filenames before any data is uncompressed. |
252 | |
642e522c |
253 | =item An Input FileGlob string |
254 | |
255 | If C<$input> is a string that is delimited by the characters "<" and ">" |
256 | C<anyinflate> will assume that it is an I<input fileglob string>. The |
257 | input is the list of files that match the fileglob. |
258 | |
259 | If the fileglob does not match any files ... |
260 | |
261 | See L<File::GlobMapper|File::GlobMapper> for more details. |
262 | |
642e522c |
263 | =back |
264 | |
265 | If the C<$input> parameter is any other type, C<undef> will be returned. |
266 | |
642e522c |
267 | =head3 The C<$output> parameter |
268 | |
269 | The parameter C<$output> is used to control the destination of the |
270 | uncompressed data. This parameter can take one of these forms. |
271 | |
272 | =over 5 |
273 | |
274 | =item A filename |
275 | |
1a6a8453 |
276 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
277 | filename. This file will be opened for writing and the uncompressed |
278 | data will be written to it. |
642e522c |
279 | |
280 | =item A filehandle |
281 | |
1a6a8453 |
282 | If the C<$output> parameter is a filehandle, the uncompressed data |
283 | will be written to it. |
642e522c |
284 | The string '-' can be used as an alias for standard output. |
285 | |
642e522c |
286 | =item A scalar reference |
287 | |
1a6a8453 |
288 | If C<$output> is a scalar reference, the uncompressed data will be |
289 | stored in C<$$output>. |
642e522c |
290 | |
642e522c |
291 | =item An Array Reference |
292 | |
1a6a8453 |
293 | If C<$output> is an array reference, the uncompressed data will be |
294 | pushed onto the array. |
642e522c |
295 | |
296 | =item An Output FileGlob |
297 | |
298 | If C<$output> is a string that is delimited by the characters "<" and ">" |
299 | C<anyinflate> will assume that it is an I<output fileglob string>. The |
300 | output is the list of files that match the fileglob. |
301 | |
302 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
303 | string. Anything else is an error. |
304 | |
305 | =back |
306 | |
307 | If the C<$output> parameter is any other type, C<undef> will be returned. |
308 | |
642e522c |
309 | =head2 Notes |
310 | |
c70c1701 |
311 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
312 | a single file/buffer, after uncompression C<$output> will contain a |
313 | concatenation of all the uncompressed data from each of the input |
314 | files/buffers. |
315 | |
642e522c |
316 | =head2 Optional Parameters |
317 | |
318 | Unless specified below, the optional parameters for C<anyinflate>, |
319 | C<OPTS>, are the same as those used with the OO interface defined in the |
320 | L</"Constructor Options"> section below. |
321 | |
322 | =over 5 |
323 | |
e7d45986 |
324 | =item C<< AutoClose => 0|1 >> |
642e522c |
325 | |
1a6a8453 |
326 | This option applies to any input or output data streams to |
327 | C<anyinflate> that are filehandles. |
642e522c |
328 | |
329 | If C<AutoClose> is specified, and the value is true, it will result in all |
330 | input and/or output filehandles being closed once C<anyinflate> has |
331 | completed. |
332 | |
333 | This parameter defaults to 0. |
334 | |
e7d45986 |
335 | =item C<< BinModeOut => 0|1 >> |
1a6a8453 |
336 | |
337 | When writing to a file or filehandle, set C<binmode> before writing to the |
338 | file. |
339 | |
340 | Defaults to 0. |
341 | |
e7d45986 |
342 | =item C<< Append => 0|1 >> |
642e522c |
343 | |
344 | TODO |
345 | |
e7d45986 |
346 | =item C<< MultiStream => 0|1 >> |
1a6a8453 |
347 | |
e7d45986 |
348 | If the input file/buffer contains multiple compressed data streams, this |
349 | option will uncompress the whole lot as a single data stream. |
1a6a8453 |
350 | |
e7d45986 |
351 | Defaults to 0. |
1a6a8453 |
352 | |
258133d1 |
353 | =item C<< TrailingData => $scalar >> |
354 | |
355 | Returns the data, if any, that is present immediately after the compressed |
356 | data stream once uncompression is complete. |
357 | |
358 | This option can be used when there is useful information immediately |
359 | following the compressed data stream, and you don't know the length of the |
360 | compressed data stream. |
361 | |
362 | If the input is a buffer, C<trailingData> will return everything from the |
363 | end of the compressed data stream to the end of the buffer. |
364 | |
365 | If the input is a filehandle, C<trailingData> will return the data that is |
366 | left in the filehandle input buffer once the end of the compressed data |
367 | stream has been reached. You can then use the filehandle to read the rest |
368 | of the input file. |
369 | |
370 | Don't bother using C<trailingData> if the input is a filename. |
371 | |
258133d1 |
372 | If you know the length of the compressed data stream before you start |
373 | uncompressing, you can avoid having to use C<trailingData> by setting the |
374 | C<InputLength> option. |
375 | |
642e522c |
376 | =back |
377 | |
642e522c |
378 | =head2 Examples |
379 | |
380 | To read the contents of the file C<file1.txt.Compressed> and write the |
381 | compressed data to the file C<file1.txt>. |
382 | |
383 | use strict ; |
384 | use warnings ; |
385 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
386 | |
387 | my $input = "file1.txt.Compressed"; |
388 | my $output = "file1.txt"; |
389 | anyinflate $input => $output |
390 | or die "anyinflate failed: $AnyInflateError\n"; |
391 | |
642e522c |
392 | To read from an existing Perl filehandle, C<$input>, and write the |
393 | uncompressed data to a buffer, C<$buffer>. |
394 | |
395 | use strict ; |
396 | use warnings ; |
397 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
398 | use IO::File ; |
399 | |
400 | my $input = new IO::File "<file1.txt.Compressed" |
401 | or die "Cannot open 'file1.txt.Compressed': $!\n" ; |
402 | my $buffer ; |
403 | anyinflate $input => \$buffer |
404 | or die "anyinflate failed: $AnyInflateError\n"; |
405 | |
406 | To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory |
407 | |
408 | use strict ; |
409 | use warnings ; |
410 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
411 | |
412 | anyinflate '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>' |
413 | or die "anyinflate failed: $AnyInflateError\n"; |
414 | |
415 | and if you want to compress each file one at a time, this will do the trick |
416 | |
417 | use strict ; |
418 | use warnings ; |
419 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
420 | |
421 | for my $input ( glob "/my/home/*.txt.Compressed" ) |
422 | { |
423 | my $output = $input; |
424 | $output =~ s/.Compressed// ; |
425 | anyinflate $input => $output |
426 | or die "Error compressing '$input': $AnyInflateError\n"; |
427 | } |
428 | |
429 | =head1 OO Interface |
430 | |
431 | =head2 Constructor |
432 | |
433 | The format of the constructor for IO::Uncompress::AnyInflate is shown below |
434 | |
642e522c |
435 | my $z = new IO::Uncompress::AnyInflate $input [OPTS] |
436 | or die "IO::Uncompress::AnyInflate failed: $AnyInflateError\n"; |
437 | |
438 | Returns an C<IO::Uncompress::AnyInflate> object on success and undef on failure. |
439 | The variable C<$AnyInflateError> will contain an error message on failure. |
440 | |
1a6a8453 |
441 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
442 | IO::Uncompress::AnyInflate can be used exactly like an L<IO::File|IO::File> filehandle. |
443 | This means that all normal input file operations can be carried out with |
444 | C<$z>. For example, to read a line from a compressed file/buffer you can |
445 | use either of these forms |
642e522c |
446 | |
447 | $line = $z->getline(); |
448 | $line = <$z>; |
449 | |
450 | The mandatory parameter C<$input> is used to determine the source of the |
451 | compressed data. This parameter can take one of three forms. |
452 | |
453 | =over 5 |
454 | |
455 | =item A filename |
456 | |
457 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
458 | file will be opened for reading and the compressed data will be read from it. |
459 | |
460 | =item A filehandle |
461 | |
462 | If the C<$input> parameter is a filehandle, the compressed data will be |
463 | read from it. |
464 | The string '-' can be used as an alias for standard input. |
465 | |
642e522c |
466 | =item A scalar reference |
467 | |
468 | If C<$input> is a scalar reference, the compressed data will be read from |
469 | C<$$output>. |
470 | |
471 | =back |
472 | |
473 | =head2 Constructor Options |
474 | |
642e522c |
475 | The option names defined below are case insensitive and can be optionally |
476 | prefixed by a '-'. So all of the following are valid |
477 | |
478 | -AutoClose |
479 | -autoclose |
480 | AUTOCLOSE |
481 | autoclose |
482 | |
483 | OPTS is a combination of the following options: |
484 | |
485 | =over 5 |
486 | |
e7d45986 |
487 | =item C<< AutoClose => 0|1 >> |
642e522c |
488 | |
489 | This option is only valid when the C<$input> parameter is a filehandle. If |
490 | specified, and the value is true, it will result in the file being closed once |
491 | either the C<close> method is called or the IO::Uncompress::AnyInflate object is |
492 | destroyed. |
493 | |
494 | This parameter defaults to 0. |
495 | |
e7d45986 |
496 | =item C<< MultiStream => 0|1 >> |
642e522c |
497 | |
642e522c |
498 | Allows multiple concatenated compressed streams to be treated as a single |
499 | compressed stream. Decompression will stop once either the end of the |
500 | file/buffer is reached, an error is encountered (premature eof, corrupt |
501 | compressed data) or the end of a stream is not immediately followed by the |
502 | start of another stream. |
503 | |
504 | This parameter defaults to 0. |
505 | |
e7d45986 |
506 | =item C<< Prime => $string >> |
642e522c |
507 | |
508 | This option will uncompress the contents of C<$string> before processing the |
509 | input file/buffer. |
510 | |
511 | This option can be useful when the compressed data is embedded in another |
512 | file/data structure and it is not possible to work out where the compressed |
1a6a8453 |
513 | data begins without having to read the first few bytes. If this is the |
514 | case, the uncompression can be I<primed> with these bytes using this |
515 | option. |
642e522c |
516 | |
e7d45986 |
517 | =item C<< Transparent => 0|1 >> |
642e522c |
518 | |
f6fd7794 |
519 | If this option is set and the input file/buffer is not compressed data, |
642e522c |
520 | the module will allow reading of it anyway. |
521 | |
f6fd7794 |
522 | In addition, if the input file/buffer does contain compressed data and |
523 | there is non-compressed data immediately following it, setting this option |
524 | will make this module treat the whole file/bufffer as a single data stream. |
525 | |
642e522c |
526 | This option defaults to 1. |
527 | |
e7d45986 |
528 | =item C<< BlockSize => $num >> |
642e522c |
529 | |
1a6a8453 |
530 | When reading the compressed input data, IO::Uncompress::AnyInflate will read it in |
531 | blocks of C<$num> bytes. |
642e522c |
532 | |
533 | This option defaults to 4096. |
534 | |
e7d45986 |
535 | =item C<< InputLength => $size >> |
642e522c |
536 | |
1a6a8453 |
537 | When present this option will limit the number of compressed bytes read |
538 | from the input file/buffer to C<$size>. This option can be used in the |
539 | situation where there is useful data directly after the compressed data |
540 | stream and you know beforehand the exact length of the compressed data |
541 | stream. |
642e522c |
542 | |
1a6a8453 |
543 | This option is mostly used when reading from a filehandle, in which case |
544 | the file pointer will be left pointing to the first byte directly after the |
642e522c |
545 | compressed data stream. |
546 | |
642e522c |
547 | This option defaults to off. |
548 | |
e7d45986 |
549 | =item C<< Append => 0|1 >> |
642e522c |
550 | |
551 | This option controls what the C<read> method does with uncompressed data. |
552 | |
1a6a8453 |
553 | If set to 1, all uncompressed data will be appended to the output parameter |
554 | of the C<read> method. |
642e522c |
555 | |
1a6a8453 |
556 | If set to 0, the contents of the output parameter of the C<read> method |
557 | will be overwritten by the uncompressed data. |
642e522c |
558 | |
559 | Defaults to 0. |
560 | |
e7d45986 |
561 | =item C<< Strict => 0|1 >> |
642e522c |
562 | |
642e522c |
563 | This option controls whether the extra checks defined below are used when |
1a6a8453 |
564 | carrying out the decompression. When Strict is on, the extra tests are |
565 | carried out, when Strict is off they are not. |
642e522c |
566 | |
567 | The default for this option is off. |
568 | |
a02d0f6f |
569 | If the input is an RFC 1950 data stream, the following will be checked: |
642e522c |
570 | |
642e522c |
571 | =over 5 |
572 | |
573 | =item 1 |
574 | |
575 | The ADLER32 checksum field must be present. |
576 | |
577 | =item 2 |
578 | |
579 | The value of the ADLER32 field read must match the adler32 value of the |
580 | uncompressed data actually contained in the file. |
581 | |
582 | =back |
583 | |
a02d0f6f |
584 | If the input is a gzip (RFC 1952) data stream, the following will be checked: |
642e522c |
585 | |
642e522c |
586 | =over 5 |
587 | |
588 | =item 1 |
589 | |
590 | If the FHCRC bit is set in the gzip FLG header byte, the CRC16 bytes in the |
591 | header must match the crc16 value of the gzip header actually read. |
592 | |
593 | =item 2 |
594 | |
595 | If the gzip header contains a name field (FNAME) it consists solely of ISO |
596 | 8859-1 characters. |
597 | |
598 | =item 3 |
599 | |
1a6a8453 |
600 | If the gzip header contains a comment field (FCOMMENT) it consists solely |
601 | of ISO 8859-1 characters plus line-feed. |
642e522c |
602 | |
603 | =item 4 |
604 | |
605 | If the gzip FEXTRA header field is present it must conform to the sub-field |
a02d0f6f |
606 | structure as defined in RFC 1952. |
642e522c |
607 | |
608 | =item 5 |
609 | |
610 | The CRC32 and ISIZE trailer fields must be present. |
611 | |
612 | =item 6 |
613 | |
614 | The value of the CRC32 field read must match the crc32 value of the |
615 | uncompressed data actually contained in the gzip file. |
616 | |
617 | =item 7 |
618 | |
1a6a8453 |
619 | The value of the ISIZE fields read must match the length of the |
620 | uncompressed data actually read from the file. |
642e522c |
621 | |
622 | =back |
623 | |
258133d1 |
624 | =item C<< RawInflate => 0|1 >> |
642e522c |
625 | |
258133d1 |
626 | When auto-detecting the compressed format, try to test for raw-deflate (RFC |
627 | 1951) content using the C<IO::Uncompress::RawInflate> module. |
642e522c |
628 | |
258133d1 |
629 | The reason this is not default behaviour is because RFC 1951 content can |
630 | only be detected by attempting to uncompress it. This process is error |
631 | prone and can result is false positives. |
632 | |
633 | Defaults to 0. |
634 | |
258133d1 |
635 | =item C<< ParseExtra => 0|1 >> |
642e522c |
636 | If the gzip FEXTRA header field is present and this option is set, it will |
637 | force the module to check that it conforms to the sub-field structure as |
a02d0f6f |
638 | defined in RFC 1952. |
642e522c |
639 | |
640 | If the C<Strict> is on it will automatically enable this option. |
641 | |
642 | Defaults to 0. |
643 | |
642e522c |
644 | =back |
645 | |
646 | =head2 Examples |
647 | |
648 | TODO |
649 | |
650 | =head1 Methods |
651 | |
652 | =head2 read |
653 | |
654 | Usage is |
655 | |
656 | $status = $z->read($buffer) |
657 | |
658 | Reads a block of compressed data (the size the the compressed block is |
659 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1a6a8453 |
660 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
661 | set in the constructor, the uncompressed data will be appended to the |
662 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
642e522c |
663 | |
1a6a8453 |
664 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
665 | or a negative number on error. |
642e522c |
666 | |
667 | =head2 read |
668 | |
669 | Usage is |
670 | |
671 | $status = $z->read($buffer, $length) |
672 | $status = $z->read($buffer, $length, $offset) |
673 | |
674 | $status = read($z, $buffer, $length) |
675 | $status = read($z, $buffer, $length, $offset) |
676 | |
677 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
678 | |
1a6a8453 |
679 | The main difference between this form of the C<read> method and the |
680 | previous one, is that this one will attempt to return I<exactly> C<$length> |
681 | bytes. The only circumstances that this function will not is if end-of-file |
682 | or an IO error is encountered. |
642e522c |
683 | |
1a6a8453 |
684 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
685 | or a negative number on error. |
642e522c |
686 | |
642e522c |
687 | =head2 getline |
688 | |
689 | Usage is |
690 | |
691 | $line = $z->getline() |
692 | $line = <$z> |
693 | |
694 | Reads a single line. |
695 | |
258133d1 |
696 | This method fully supports the use of of the variable C<$/> (or |
697 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
698 | determine what constitutes an end of line. Paragraph mode, record mode and |
699 | file slurp mode are all supported. |
642e522c |
700 | |
642e522c |
701 | =head2 getc |
702 | |
703 | Usage is |
704 | |
705 | $char = $z->getc() |
706 | |
707 | Read a single character. |
708 | |
709 | =head2 ungetc |
710 | |
711 | Usage is |
712 | |
713 | $char = $z->ungetc($string) |
714 | |
642e522c |
715 | =head2 inflateSync |
716 | |
717 | Usage is |
718 | |
719 | $status = $z->inflateSync() |
720 | |
721 | TODO |
722 | |
723 | =head2 getHeaderInfo |
724 | |
725 | Usage is |
726 | |
1a6a8453 |
727 | $hdr = $z->getHeaderInfo(); |
728 | @hdrs = $z->getHeaderInfo(); |
642e522c |
729 | |
1a6a8453 |
730 | This method returns either a hash reference (in scalar context) or a list |
731 | or hash references (in array context) that contains information about each |
732 | of the header fields in the compressed data stream(s). |
642e522c |
733 | |
642e522c |
734 | =head2 tell |
735 | |
736 | Usage is |
737 | |
738 | $z->tell() |
739 | tell $z |
740 | |
741 | Returns the uncompressed file offset. |
742 | |
743 | =head2 eof |
744 | |
745 | Usage is |
746 | |
747 | $z->eof(); |
748 | eof($z); |
749 | |
642e522c |
750 | Returns true if the end of the compressed input stream has been reached. |
751 | |
642e522c |
752 | =head2 seek |
753 | |
754 | $z->seek($position, $whence); |
755 | seek($z, $position, $whence); |
756 | |
642e522c |
757 | Provides a sub-set of the C<seek> functionality, with the restriction |
758 | that it is only legal to seek forward in the input file/buffer. |
759 | It is a fatal error to attempt to seek backward. |
760 | |
642e522c |
761 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
762 | SEEK_CUR or SEEK_END. |
763 | |
764 | Returns 1 on success, 0 on failure. |
765 | |
766 | =head2 binmode |
767 | |
768 | Usage is |
769 | |
770 | $z->binmode |
771 | binmode $z ; |
772 | |
773 | This is a noop provided for completeness. |
774 | |
a02d0f6f |
775 | =head2 opened |
776 | |
777 | $z->opened() |
778 | |
779 | Returns true if the object currently refers to a opened file/buffer. |
780 | |
781 | =head2 autoflush |
782 | |
783 | my $prev = $z->autoflush() |
784 | my $prev = $z->autoflush(EXPR) |
785 | |
786 | If the C<$z> object is associated with a file or a filehandle, this method |
787 | returns the current autoflush setting for the underlying filehandle. If |
788 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
789 | write/print operation. |
790 | |
791 | If C<$z> is associated with a buffer, this method has no effect and always |
792 | returns C<undef>. |
793 | |
794 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
795 | retrieve the autoflush setting. |
796 | |
797 | =head2 input_line_number |
798 | |
799 | $z->input_line_number() |
800 | $z->input_line_number(EXPR) |
801 | |
a02d0f6f |
802 | Returns the current uncompressed line number. If C<EXPR> is present it has |
803 | the effect of setting the line number. Note that setting the line number |
804 | does not change the current position within the file/buffer being read. |
805 | |
806 | The contents of C<$/> are used to to determine what constitutes a line |
807 | terminator. |
808 | |
642e522c |
809 | =head2 fileno |
810 | |
811 | $z->fileno() |
812 | fileno($z) |
813 | |
d54256af |
814 | If the C<$z> object is associated with a file or a filehandle, C<fileno> |
815 | will return the underlying file descriptor. Once the C<close> method is |
816 | called C<fileno> will return C<undef>. |
642e522c |
817 | |
d54256af |
818 | If the C<$z> object is is associated with a buffer, this method will return |
819 | C<undef>. |
642e522c |
820 | |
821 | =head2 close |
822 | |
823 | $z->close() ; |
824 | close $z ; |
825 | |
642e522c |
826 | Closes the output file/buffer. |
827 | |
642e522c |
828 | For most versions of Perl this method will be automatically invoked if |
829 | the IO::Uncompress::AnyInflate object is destroyed (either explicitly or by the |
830 | variable with the reference to the object going out of scope). The |
831 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
832 | these cases, the C<close> method will be called automatically, but |
833 | not until global destruction of all live objects when the program is |
834 | terminating. |
835 | |
836 | Therefore, if you want your scripts to be able to run on all versions |
837 | of Perl, you should call C<close> explicitly and not rely on automatic |
838 | closing. |
839 | |
840 | Returns true on success, otherwise 0. |
841 | |
842 | If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyInflate |
843 | object was created, and the object is associated with a file, the |
844 | underlying file will also be closed. |
845 | |
e7d45986 |
846 | =head2 nextStream |
847 | |
848 | Usage is |
849 | |
850 | my $status = $z->nextStream(); |
851 | |
852 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
853 | compressed data stream is found, the eof marker will be cleared and C<$.> |
854 | will be reset to 0. |
e7d45986 |
855 | |
856 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
857 | error was encountered. |
858 | |
859 | =head2 trailingData |
860 | |
861 | Usage is |
862 | |
863 | my $data = $z->trailingData(); |
864 | |
258133d1 |
865 | Returns the data, if any, that is present immediately after the compressed |
866 | data stream once uncompression is complete. It only makes sense to call |
867 | this method once the end of the compressed data stream has been |
868 | encountered. |
869 | |
870 | This option can be used when there is useful information immediately |
871 | following the compressed data stream, and you don't know the length of the |
872 | compressed data stream. |
873 | |
874 | If the input is a buffer, C<trailingData> will return everything from the |
875 | end of the compressed data stream to the end of the buffer. |
876 | |
877 | If the input is a filehandle, C<trailingData> will return the data that is |
878 | left in the filehandle input buffer once the end of the compressed data |
879 | stream has been reached. You can then use the filehandle to read the rest |
880 | of the input file. |
881 | |
882 | Don't bother using C<trailingData> if the input is a filename. |
883 | |
258133d1 |
884 | If you know the length of the compressed data stream before you start |
885 | uncompressing, you can avoid having to use C<trailingData> by setting the |
886 | C<InputLength> option in the constructor. |
e7d45986 |
887 | |
642e522c |
888 | =head1 Importing |
889 | |
890 | No symbolic constants are required by this IO::Uncompress::AnyInflate at present. |
891 | |
892 | =over 5 |
893 | |
894 | =item :all |
895 | |
896 | Imports C<anyinflate> and C<$AnyInflateError>. |
897 | Same as doing this |
898 | |
899 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
900 | |
901 | =back |
902 | |
903 | =head1 EXAMPLES |
904 | |
d54256af |
905 | =head2 Working with Net::FTP |
642e522c |
906 | |
d54256af |
907 | See L<IO::Uncompress::AnyInflate::FAQ|IO::Uncompress::AnyInflate::FAQ/"Compressed files and Net::FTP"> |
642e522c |
908 | |
909 | =head1 SEE ALSO |
910 | |
258133d1 |
911 | 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 |
912 | |
913 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
914 | |
a02d0f6f |
915 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
916 | L<Archive::Tar|Archive::Tar>, |
642e522c |
917 | L<IO::Zlib|IO::Zlib> |
918 | |
919 | For RFC 1950, 1951 and 1952 see |
920 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
921 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
922 | F<http://www.faqs.org/rfcs/rfc1952.html> |
923 | |
a02d0f6f |
924 | The I<zlib> compression library was written by Jean-loup Gailly |
925 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
926 | |
927 | The primary site for the I<zlib> compression library is |
928 | F<http://www.zlib.org>. |
929 | |
930 | The primary site for gzip is F<http://www.gzip.org>. |
931 | |
642e522c |
932 | =head1 AUTHOR |
933 | |
cb7abd7f |
934 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
642e522c |
935 | |
642e522c |
936 | =head1 MODIFICATION HISTORY |
937 | |
938 | See the Changes file. |
939 | |
940 | =head1 COPYRIGHT AND LICENSE |
642e522c |
941 | |
319fab50 |
942 | Copyright (c) 2005-2009 Paul Marquess. All rights reserved. |
a02d0f6f |
943 | |
642e522c |
944 | This program is free software; you can redistribute it and/or |
945 | modify it under the same terms as Perl itself. |
946 | |