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 | |
be714331 |
9 | use IO::Compress::Base::Common 2.010 qw(createSelfTiedObject); |
1a6a8453 |
10 | |
be714331 |
11 | use IO::Uncompress::Adapter::Inflate 2.010 (); |
1a6a8453 |
12 | |
13 | |
be714331 |
14 | use IO::Uncompress::Base 2.010 ; |
15 | use IO::Uncompress::Gunzip 2.010 ; |
16 | use IO::Uncompress::Inflate 2.010 ; |
17 | use IO::Uncompress::RawInflate 2.010 ; |
18 | use IO::Uncompress::Unzip 2.010 ; |
642e522c |
19 | |
20 | require Exporter ; |
21 | |
22 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyInflateError); |
23 | |
be714331 |
24 | $VERSION = '2.010'; |
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 | { |
be714331 |
51 | use IO::Compress::Base::Common 2.010 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 ; |
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 | |
cb7abd7f |
130 | IO::Uncompress::AnyInflate - Uncompress zlib-based (zip, gzip) file/buffer |
642e522c |
131 | |
132 | =head1 SYNOPSIS |
133 | |
134 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
135 | |
136 | my $status = anyinflate $input => $output [,OPTS] |
137 | or die "anyinflate failed: $AnyInflateError\n"; |
138 | |
139 | my $z = new IO::Uncompress::AnyInflate $input [OPTS] |
140 | or die "anyinflate failed: $AnyInflateError\n"; |
141 | |
142 | $status = $z->read($buffer) |
143 | $status = $z->read($buffer, $length) |
144 | $status = $z->read($buffer, $length, $offset) |
145 | $line = $z->getline() |
146 | $char = $z->getc() |
147 | $char = $z->ungetc() |
a02d0f6f |
148 | $char = $z->opened() |
149 | |
642e522c |
150 | $status = $z->inflateSync() |
a02d0f6f |
151 | |
e7d45986 |
152 | $data = $z->trailingData() |
153 | $status = $z->nextStream() |
642e522c |
154 | $data = $z->getHeaderInfo() |
155 | $z->tell() |
156 | $z->seek($position, $whence) |
157 | $z->binmode() |
158 | $z->fileno() |
159 | $z->eof() |
160 | $z->close() |
161 | |
162 | $AnyInflateError ; |
163 | |
164 | # IO::File mode |
165 | |
166 | <$z> |
167 | read($z, $buffer); |
168 | read($z, $buffer, $length); |
169 | read($z, $buffer, $length, $offset); |
170 | tell($z) |
171 | seek($z, $position, $whence) |
172 | binmode($z) |
173 | fileno($z) |
174 | eof($z) |
175 | close($z) |
176 | |
642e522c |
177 | =head1 DESCRIPTION |
178 | |
1a6a8453 |
179 | This module provides a Perl interface that allows the reading of |
cb7abd7f |
180 | files/buffers that have been compressed in a number of formats that use the |
181 | zlib compression library. |
182 | |
183 | The formats supported are |
184 | |
185 | =over 5 |
186 | |
187 | =item RFC 1950 |
188 | |
258133d1 |
189 | =item RFC 1951 (optionally) |
cb7abd7f |
190 | |
191 | =item gzip (RFC 1952) |
192 | |
193 | =item zip |
642e522c |
194 | |
cb7abd7f |
195 | =back |
196 | |
197 | The module will auto-detect which, if any, of the supported |
1a6a8453 |
198 | compression formats is being used. |
642e522c |
199 | |
642e522c |
200 | =head1 Functional Interface |
201 | |
1a6a8453 |
202 | A top-level function, C<anyinflate>, is provided to carry out |
203 | "one-shot" uncompression between buffers and/or files. For finer |
204 | control over the uncompression process, see the L</"OO Interface"> |
205 | section. |
642e522c |
206 | |
207 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
208 | |
209 | anyinflate $input => $output [,OPTS] |
210 | or die "anyinflate failed: $AnyInflateError\n"; |
211 | |
642e522c |
212 | The functional interface needs Perl5.005 or better. |
213 | |
642e522c |
214 | =head2 anyinflate $input => $output [, OPTS] |
215 | |
1a6a8453 |
216 | C<anyinflate> expects at least two parameters, C<$input> and C<$output>. |
642e522c |
217 | |
218 | =head3 The C<$input> parameter |
219 | |
220 | The parameter, C<$input>, is used to define the source of |
221 | the compressed data. |
222 | |
223 | It can take one of the following forms: |
224 | |
225 | =over 5 |
226 | |
227 | =item A filename |
228 | |
229 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
230 | filename. This file will be opened for reading and the input data |
231 | will be read from it. |
232 | |
233 | =item A filehandle |
234 | |
235 | If the C<$input> parameter is a filehandle, the input data will be |
236 | read from it. |
237 | The string '-' can be used as an alias for standard input. |
238 | |
239 | =item A scalar reference |
240 | |
241 | If C<$input> is a scalar reference, the input data will be read |
242 | from C<$$input>. |
243 | |
244 | =item An array reference |
245 | |
1a6a8453 |
246 | If C<$input> is an array reference, each element in the array must be a |
247 | filename. |
248 | |
249 | The input data will be read from each file in turn. |
250 | |
642e522c |
251 | The complete array will be walked to ensure that it only |
1a6a8453 |
252 | contains valid filenames before any data is uncompressed. |
253 | |
642e522c |
254 | =item An Input FileGlob string |
255 | |
256 | If C<$input> is a string that is delimited by the characters "<" and ">" |
257 | C<anyinflate> will assume that it is an I<input fileglob string>. The |
258 | input is the list of files that match the fileglob. |
259 | |
260 | If the fileglob does not match any files ... |
261 | |
262 | See L<File::GlobMapper|File::GlobMapper> for more details. |
263 | |
642e522c |
264 | =back |
265 | |
266 | If the C<$input> parameter is any other type, C<undef> will be returned. |
267 | |
642e522c |
268 | =head3 The C<$output> parameter |
269 | |
270 | The parameter C<$output> is used to control the destination of the |
271 | uncompressed data. This parameter can take one of these forms. |
272 | |
273 | =over 5 |
274 | |
275 | =item A filename |
276 | |
1a6a8453 |
277 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
278 | filename. This file will be opened for writing and the uncompressed |
279 | data will be written to it. |
642e522c |
280 | |
281 | =item A filehandle |
282 | |
1a6a8453 |
283 | If the C<$output> parameter is a filehandle, the uncompressed data |
284 | will be written to it. |
642e522c |
285 | The string '-' can be used as an alias for standard output. |
286 | |
642e522c |
287 | =item A scalar reference |
288 | |
1a6a8453 |
289 | If C<$output> is a scalar reference, the uncompressed data will be |
290 | stored in C<$$output>. |
642e522c |
291 | |
642e522c |
292 | =item An Array Reference |
293 | |
1a6a8453 |
294 | If C<$output> is an array reference, the uncompressed data will be |
295 | pushed onto the array. |
642e522c |
296 | |
297 | =item An Output FileGlob |
298 | |
299 | If C<$output> is a string that is delimited by the characters "<" and ">" |
300 | C<anyinflate> will assume that it is an I<output fileglob string>. The |
301 | output is the list of files that match the fileglob. |
302 | |
303 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
304 | string. Anything else is an error. |
305 | |
306 | =back |
307 | |
308 | If the C<$output> parameter is any other type, C<undef> will be returned. |
309 | |
642e522c |
310 | =head2 Notes |
311 | |
c70c1701 |
312 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
313 | a single file/buffer, after uncompression C<$output> will contain a |
314 | concatenation of all the uncompressed data from each of the input |
315 | files/buffers. |
316 | |
642e522c |
317 | =head2 Optional Parameters |
318 | |
319 | Unless specified below, the optional parameters for C<anyinflate>, |
320 | C<OPTS>, are the same as those used with the OO interface defined in the |
321 | L</"Constructor Options"> section below. |
322 | |
323 | =over 5 |
324 | |
e7d45986 |
325 | =item C<< AutoClose => 0|1 >> |
642e522c |
326 | |
1a6a8453 |
327 | This option applies to any input or output data streams to |
328 | C<anyinflate> that are filehandles. |
642e522c |
329 | |
330 | If C<AutoClose> is specified, and the value is true, it will result in all |
331 | input and/or output filehandles being closed once C<anyinflate> has |
332 | completed. |
333 | |
334 | This parameter defaults to 0. |
335 | |
e7d45986 |
336 | =item C<< BinModeOut => 0|1 >> |
1a6a8453 |
337 | |
338 | When writing to a file or filehandle, set C<binmode> before writing to the |
339 | file. |
340 | |
341 | Defaults to 0. |
342 | |
e7d45986 |
343 | =item C<< Append => 0|1 >> |
642e522c |
344 | |
345 | TODO |
346 | |
e7d45986 |
347 | =item C<< MultiStream => 0|1 >> |
1a6a8453 |
348 | |
e7d45986 |
349 | If the input file/buffer contains multiple compressed data streams, this |
350 | option will uncompress the whole lot as a single data stream. |
1a6a8453 |
351 | |
e7d45986 |
352 | Defaults to 0. |
1a6a8453 |
353 | |
258133d1 |
354 | =item C<< TrailingData => $scalar >> |
355 | |
356 | Returns the data, if any, that is present immediately after the compressed |
357 | data stream once uncompression is complete. |
358 | |
359 | This option can be used when there is useful information immediately |
360 | following the compressed data stream, and you don't know the length of the |
361 | compressed data stream. |
362 | |
363 | If the input is a buffer, C<trailingData> will return everything from the |
364 | end of the compressed data stream to the end of the buffer. |
365 | |
366 | If the input is a filehandle, C<trailingData> will return the data that is |
367 | left in the filehandle input buffer once the end of the compressed data |
368 | stream has been reached. You can then use the filehandle to read the rest |
369 | of the input file. |
370 | |
371 | Don't bother using C<trailingData> if the input is a filename. |
372 | |
258133d1 |
373 | If you know the length of the compressed data stream before you start |
374 | uncompressing, you can avoid having to use C<trailingData> by setting the |
375 | C<InputLength> option. |
376 | |
642e522c |
377 | =back |
378 | |
642e522c |
379 | =head2 Examples |
380 | |
381 | To read the contents of the file C<file1.txt.Compressed> and write the |
382 | compressed data to the file C<file1.txt>. |
383 | |
384 | use strict ; |
385 | use warnings ; |
386 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
387 | |
388 | my $input = "file1.txt.Compressed"; |
389 | my $output = "file1.txt"; |
390 | anyinflate $input => $output |
391 | or die "anyinflate failed: $AnyInflateError\n"; |
392 | |
642e522c |
393 | To read from an existing Perl filehandle, C<$input>, and write the |
394 | uncompressed data to a buffer, C<$buffer>. |
395 | |
396 | use strict ; |
397 | use warnings ; |
398 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
399 | use IO::File ; |
400 | |
401 | my $input = new IO::File "<file1.txt.Compressed" |
402 | or die "Cannot open 'file1.txt.Compressed': $!\n" ; |
403 | my $buffer ; |
404 | anyinflate $input => \$buffer |
405 | or die "anyinflate failed: $AnyInflateError\n"; |
406 | |
407 | To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory |
408 | |
409 | use strict ; |
410 | use warnings ; |
411 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
412 | |
413 | anyinflate '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>' |
414 | or die "anyinflate failed: $AnyInflateError\n"; |
415 | |
416 | and if you want to compress each file one at a time, this will do the trick |
417 | |
418 | use strict ; |
419 | use warnings ; |
420 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
421 | |
422 | for my $input ( glob "/my/home/*.txt.Compressed" ) |
423 | { |
424 | my $output = $input; |
425 | $output =~ s/.Compressed// ; |
426 | anyinflate $input => $output |
427 | or die "Error compressing '$input': $AnyInflateError\n"; |
428 | } |
429 | |
430 | =head1 OO Interface |
431 | |
432 | =head2 Constructor |
433 | |
434 | The format of the constructor for IO::Uncompress::AnyInflate is shown below |
435 | |
642e522c |
436 | my $z = new IO::Uncompress::AnyInflate $input [OPTS] |
437 | or die "IO::Uncompress::AnyInflate failed: $AnyInflateError\n"; |
438 | |
439 | Returns an C<IO::Uncompress::AnyInflate> object on success and undef on failure. |
440 | The variable C<$AnyInflateError> will contain an error message on failure. |
441 | |
1a6a8453 |
442 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
443 | IO::Uncompress::AnyInflate can be used exactly like an L<IO::File|IO::File> filehandle. |
444 | This means that all normal input file operations can be carried out with |
445 | C<$z>. For example, to read a line from a compressed file/buffer you can |
446 | use either of these forms |
642e522c |
447 | |
448 | $line = $z->getline(); |
449 | $line = <$z>; |
450 | |
451 | The mandatory parameter C<$input> is used to determine the source of the |
452 | compressed data. This parameter can take one of three forms. |
453 | |
454 | =over 5 |
455 | |
456 | =item A filename |
457 | |
458 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
459 | file will be opened for reading and the compressed data will be read from it. |
460 | |
461 | =item A filehandle |
462 | |
463 | If the C<$input> parameter is a filehandle, the compressed data will be |
464 | read from it. |
465 | The string '-' can be used as an alias for standard input. |
466 | |
642e522c |
467 | =item A scalar reference |
468 | |
469 | If C<$input> is a scalar reference, the compressed data will be read from |
470 | C<$$output>. |
471 | |
472 | =back |
473 | |
474 | =head2 Constructor Options |
475 | |
642e522c |
476 | The option names defined below are case insensitive and can be optionally |
477 | prefixed by a '-'. So all of the following are valid |
478 | |
479 | -AutoClose |
480 | -autoclose |
481 | AUTOCLOSE |
482 | autoclose |
483 | |
484 | OPTS is a combination of the following options: |
485 | |
486 | =over 5 |
487 | |
e7d45986 |
488 | =item C<< AutoClose => 0|1 >> |
642e522c |
489 | |
490 | This option is only valid when the C<$input> parameter is a filehandle. If |
491 | specified, and the value is true, it will result in the file being closed once |
492 | either the C<close> method is called or the IO::Uncompress::AnyInflate object is |
493 | destroyed. |
494 | |
495 | This parameter defaults to 0. |
496 | |
e7d45986 |
497 | =item C<< MultiStream => 0|1 >> |
642e522c |
498 | |
642e522c |
499 | Allows multiple concatenated compressed streams to be treated as a single |
500 | compressed stream. Decompression will stop once either the end of the |
501 | file/buffer is reached, an error is encountered (premature eof, corrupt |
502 | compressed data) or the end of a stream is not immediately followed by the |
503 | start of another stream. |
504 | |
505 | This parameter defaults to 0. |
506 | |
e7d45986 |
507 | =item C<< Prime => $string >> |
642e522c |
508 | |
509 | This option will uncompress the contents of C<$string> before processing the |
510 | input file/buffer. |
511 | |
512 | This option can be useful when the compressed data is embedded in another |
513 | file/data structure and it is not possible to work out where the compressed |
1a6a8453 |
514 | data begins without having to read the first few bytes. If this is the |
515 | case, the uncompression can be I<primed> with these bytes using this |
516 | option. |
642e522c |
517 | |
e7d45986 |
518 | =item C<< Transparent => 0|1 >> |
642e522c |
519 | |
f6fd7794 |
520 | If this option is set and the input file/buffer is not compressed data, |
642e522c |
521 | the module will allow reading of it anyway. |
522 | |
f6fd7794 |
523 | In addition, if the input file/buffer does contain compressed data and |
524 | there is non-compressed data immediately following it, setting this option |
525 | will make this module treat the whole file/bufffer as a single data stream. |
526 | |
642e522c |
527 | This option defaults to 1. |
528 | |
e7d45986 |
529 | =item C<< BlockSize => $num >> |
642e522c |
530 | |
1a6a8453 |
531 | When reading the compressed input data, IO::Uncompress::AnyInflate will read it in |
532 | blocks of C<$num> bytes. |
642e522c |
533 | |
534 | This option defaults to 4096. |
535 | |
e7d45986 |
536 | =item C<< InputLength => $size >> |
642e522c |
537 | |
1a6a8453 |
538 | When present this option will limit the number of compressed bytes read |
539 | from the input file/buffer to C<$size>. This option can be used in the |
540 | situation where there is useful data directly after the compressed data |
541 | stream and you know beforehand the exact length of the compressed data |
542 | stream. |
642e522c |
543 | |
1a6a8453 |
544 | This option is mostly used when reading from a filehandle, in which case |
545 | the file pointer will be left pointing to the first byte directly after the |
642e522c |
546 | compressed data stream. |
547 | |
642e522c |
548 | This option defaults to off. |
549 | |
e7d45986 |
550 | =item C<< Append => 0|1 >> |
642e522c |
551 | |
552 | This option controls what the C<read> method does with uncompressed data. |
553 | |
1a6a8453 |
554 | If set to 1, all uncompressed data will be appended to the output parameter |
555 | of the C<read> method. |
642e522c |
556 | |
1a6a8453 |
557 | If set to 0, the contents of the output parameter of the C<read> method |
558 | will be overwritten by the uncompressed data. |
642e522c |
559 | |
560 | Defaults to 0. |
561 | |
e7d45986 |
562 | =item C<< Strict => 0|1 >> |
642e522c |
563 | |
642e522c |
564 | This option controls whether the extra checks defined below are used when |
1a6a8453 |
565 | carrying out the decompression. When Strict is on, the extra tests are |
566 | carried out, when Strict is off they are not. |
642e522c |
567 | |
568 | The default for this option is off. |
569 | |
a02d0f6f |
570 | If the input is an RFC 1950 data stream, the following will be checked: |
642e522c |
571 | |
642e522c |
572 | =over 5 |
573 | |
574 | =item 1 |
575 | |
576 | The ADLER32 checksum field must be present. |
577 | |
578 | =item 2 |
579 | |
580 | The value of the ADLER32 field read must match the adler32 value of the |
581 | uncompressed data actually contained in the file. |
582 | |
583 | =back |
584 | |
a02d0f6f |
585 | If the input is a gzip (RFC 1952) data stream, the following will be checked: |
642e522c |
586 | |
642e522c |
587 | =over 5 |
588 | |
589 | =item 1 |
590 | |
591 | If the FHCRC bit is set in the gzip FLG header byte, the CRC16 bytes in the |
592 | header must match the crc16 value of the gzip header actually read. |
593 | |
594 | =item 2 |
595 | |
596 | If the gzip header contains a name field (FNAME) it consists solely of ISO |
597 | 8859-1 characters. |
598 | |
599 | =item 3 |
600 | |
1a6a8453 |
601 | If the gzip header contains a comment field (FCOMMENT) it consists solely |
602 | of ISO 8859-1 characters plus line-feed. |
642e522c |
603 | |
604 | =item 4 |
605 | |
606 | If the gzip FEXTRA header field is present it must conform to the sub-field |
a02d0f6f |
607 | structure as defined in RFC 1952. |
642e522c |
608 | |
609 | =item 5 |
610 | |
611 | The CRC32 and ISIZE trailer fields must be present. |
612 | |
613 | =item 6 |
614 | |
615 | The value of the CRC32 field read must match the crc32 value of the |
616 | uncompressed data actually contained in the gzip file. |
617 | |
618 | =item 7 |
619 | |
1a6a8453 |
620 | The value of the ISIZE fields read must match the length of the |
621 | uncompressed data actually read from the file. |
642e522c |
622 | |
623 | =back |
624 | |
258133d1 |
625 | =item C<< RawInflate => 0|1 >> |
642e522c |
626 | |
258133d1 |
627 | When auto-detecting the compressed format, try to test for raw-deflate (RFC |
628 | 1951) content using the C<IO::Uncompress::RawInflate> module. |
642e522c |
629 | |
258133d1 |
630 | The reason this is not default behaviour is because RFC 1951 content can |
631 | only be detected by attempting to uncompress it. This process is error |
632 | prone and can result is false positives. |
633 | |
634 | Defaults to 0. |
635 | |
258133d1 |
636 | =item C<< ParseExtra => 0|1 >> |
642e522c |
637 | If the gzip FEXTRA header field is present and this option is set, it will |
638 | force the module to check that it conforms to the sub-field structure as |
a02d0f6f |
639 | defined in RFC 1952. |
642e522c |
640 | |
641 | If the C<Strict> is on it will automatically enable this option. |
642 | |
643 | Defaults to 0. |
644 | |
642e522c |
645 | =back |
646 | |
647 | =head2 Examples |
648 | |
649 | TODO |
650 | |
651 | =head1 Methods |
652 | |
653 | =head2 read |
654 | |
655 | Usage is |
656 | |
657 | $status = $z->read($buffer) |
658 | |
659 | Reads a block of compressed data (the size the the compressed block is |
660 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1a6a8453 |
661 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
662 | set in the constructor, the uncompressed data will be appended to the |
663 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
642e522c |
664 | |
1a6a8453 |
665 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
666 | or a negative number on error. |
642e522c |
667 | |
668 | =head2 read |
669 | |
670 | Usage is |
671 | |
672 | $status = $z->read($buffer, $length) |
673 | $status = $z->read($buffer, $length, $offset) |
674 | |
675 | $status = read($z, $buffer, $length) |
676 | $status = read($z, $buffer, $length, $offset) |
677 | |
678 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
679 | |
1a6a8453 |
680 | The main difference between this form of the C<read> method and the |
681 | previous one, is that this one will attempt to return I<exactly> C<$length> |
682 | bytes. The only circumstances that this function will not is if end-of-file |
683 | or an IO error is encountered. |
642e522c |
684 | |
1a6a8453 |
685 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
686 | or a negative number on error. |
642e522c |
687 | |
642e522c |
688 | =head2 getline |
689 | |
690 | Usage is |
691 | |
692 | $line = $z->getline() |
693 | $line = <$z> |
694 | |
695 | Reads a single line. |
696 | |
258133d1 |
697 | This method fully supports the use of of the variable C<$/> (or |
698 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
699 | determine what constitutes an end of line. Paragraph mode, record mode and |
700 | file slurp mode are all supported. |
642e522c |
701 | |
642e522c |
702 | =head2 getc |
703 | |
704 | Usage is |
705 | |
706 | $char = $z->getc() |
707 | |
708 | Read a single character. |
709 | |
710 | =head2 ungetc |
711 | |
712 | Usage is |
713 | |
714 | $char = $z->ungetc($string) |
715 | |
642e522c |
716 | =head2 inflateSync |
717 | |
718 | Usage is |
719 | |
720 | $status = $z->inflateSync() |
721 | |
722 | TODO |
723 | |
724 | =head2 getHeaderInfo |
725 | |
726 | Usage is |
727 | |
1a6a8453 |
728 | $hdr = $z->getHeaderInfo(); |
729 | @hdrs = $z->getHeaderInfo(); |
642e522c |
730 | |
1a6a8453 |
731 | This method returns either a hash reference (in scalar context) or a list |
732 | or hash references (in array context) that contains information about each |
733 | of the header fields in the compressed data stream(s). |
642e522c |
734 | |
642e522c |
735 | =head2 tell |
736 | |
737 | Usage is |
738 | |
739 | $z->tell() |
740 | tell $z |
741 | |
742 | Returns the uncompressed file offset. |
743 | |
744 | =head2 eof |
745 | |
746 | Usage is |
747 | |
748 | $z->eof(); |
749 | eof($z); |
750 | |
642e522c |
751 | Returns true if the end of the compressed input stream has been reached. |
752 | |
642e522c |
753 | =head2 seek |
754 | |
755 | $z->seek($position, $whence); |
756 | seek($z, $position, $whence); |
757 | |
642e522c |
758 | Provides a sub-set of the C<seek> functionality, with the restriction |
759 | that it is only legal to seek forward in the input file/buffer. |
760 | It is a fatal error to attempt to seek backward. |
761 | |
642e522c |
762 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
763 | SEEK_CUR or SEEK_END. |
764 | |
765 | Returns 1 on success, 0 on failure. |
766 | |
767 | =head2 binmode |
768 | |
769 | Usage is |
770 | |
771 | $z->binmode |
772 | binmode $z ; |
773 | |
774 | This is a noop provided for completeness. |
775 | |
a02d0f6f |
776 | =head2 opened |
777 | |
778 | $z->opened() |
779 | |
780 | Returns true if the object currently refers to a opened file/buffer. |
781 | |
782 | =head2 autoflush |
783 | |
784 | my $prev = $z->autoflush() |
785 | my $prev = $z->autoflush(EXPR) |
786 | |
787 | If the C<$z> object is associated with a file or a filehandle, this method |
788 | returns the current autoflush setting for the underlying filehandle. If |
789 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
790 | write/print operation. |
791 | |
792 | If C<$z> is associated with a buffer, this method has no effect and always |
793 | returns C<undef>. |
794 | |
795 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
796 | retrieve the autoflush setting. |
797 | |
798 | =head2 input_line_number |
799 | |
800 | $z->input_line_number() |
801 | $z->input_line_number(EXPR) |
802 | |
a02d0f6f |
803 | Returns the current uncompressed line number. If C<EXPR> is present it has |
804 | the effect of setting the line number. Note that setting the line number |
805 | does not change the current position within the file/buffer being read. |
806 | |
807 | The contents of C<$/> are used to to determine what constitutes a line |
808 | terminator. |
809 | |
642e522c |
810 | =head2 fileno |
811 | |
812 | $z->fileno() |
813 | fileno($z) |
814 | |
d54256af |
815 | If the C<$z> object is associated with a file or a filehandle, C<fileno> |
816 | will return the underlying file descriptor. Once the C<close> method is |
817 | called C<fileno> will return C<undef>. |
642e522c |
818 | |
d54256af |
819 | If the C<$z> object is is associated with a buffer, this method will return |
820 | C<undef>. |
642e522c |
821 | |
822 | =head2 close |
823 | |
824 | $z->close() ; |
825 | close $z ; |
826 | |
642e522c |
827 | Closes the output file/buffer. |
828 | |
642e522c |
829 | For most versions of Perl this method will be automatically invoked if |
830 | the IO::Uncompress::AnyInflate object is destroyed (either explicitly or by the |
831 | variable with the reference to the object going out of scope). The |
832 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
833 | these cases, the C<close> method will be called automatically, but |
834 | not until global destruction of all live objects when the program is |
835 | terminating. |
836 | |
837 | Therefore, if you want your scripts to be able to run on all versions |
838 | of Perl, you should call C<close> explicitly and not rely on automatic |
839 | closing. |
840 | |
841 | Returns true on success, otherwise 0. |
842 | |
843 | If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyInflate |
844 | object was created, and the object is associated with a file, the |
845 | underlying file will also be closed. |
846 | |
e7d45986 |
847 | =head2 nextStream |
848 | |
849 | Usage is |
850 | |
851 | my $status = $z->nextStream(); |
852 | |
853 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
854 | compressed data stream is found, the eof marker will be cleared and C<$.> |
855 | will be reset to 0. |
e7d45986 |
856 | |
857 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
858 | error was encountered. |
859 | |
860 | =head2 trailingData |
861 | |
862 | Usage is |
863 | |
864 | my $data = $z->trailingData(); |
865 | |
258133d1 |
866 | Returns the data, if any, that is present immediately after the compressed |
867 | data stream once uncompression is complete. It only makes sense to call |
868 | this method once the end of the compressed data stream has been |
869 | encountered. |
870 | |
871 | This option can be used when there is useful information immediately |
872 | following the compressed data stream, and you don't know the length of the |
873 | compressed data stream. |
874 | |
875 | If the input is a buffer, C<trailingData> will return everything from the |
876 | end of the compressed data stream to the end of the buffer. |
877 | |
878 | If the input is a filehandle, C<trailingData> will return the data that is |
879 | left in the filehandle input buffer once the end of the compressed data |
880 | stream has been reached. You can then use the filehandle to read the rest |
881 | of the input file. |
882 | |
883 | Don't bother using C<trailingData> if the input is a filename. |
884 | |
258133d1 |
885 | If you know the length of the compressed data stream before you start |
886 | uncompressing, you can avoid having to use C<trailingData> by setting the |
887 | C<InputLength> option in the constructor. |
e7d45986 |
888 | |
642e522c |
889 | =head1 Importing |
890 | |
891 | No symbolic constants are required by this IO::Uncompress::AnyInflate at present. |
892 | |
893 | =over 5 |
894 | |
895 | =item :all |
896 | |
897 | Imports C<anyinflate> and C<$AnyInflateError>. |
898 | Same as doing this |
899 | |
900 | use IO::Uncompress::AnyInflate qw(anyinflate $AnyInflateError) ; |
901 | |
902 | =back |
903 | |
904 | =head1 EXAMPLES |
905 | |
d54256af |
906 | =head2 Working with Net::FTP |
642e522c |
907 | |
d54256af |
908 | See L<IO::Uncompress::AnyInflate::FAQ|IO::Uncompress::AnyInflate::FAQ/"Compressed files and Net::FTP"> |
642e522c |
909 | |
910 | =head1 SEE ALSO |
911 | |
258133d1 |
912 | 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 |
913 | |
914 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
915 | |
a02d0f6f |
916 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
917 | L<Archive::Tar|Archive::Tar>, |
642e522c |
918 | L<IO::Zlib|IO::Zlib> |
919 | |
920 | For RFC 1950, 1951 and 1952 see |
921 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
922 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
923 | F<http://www.faqs.org/rfcs/rfc1952.html> |
924 | |
a02d0f6f |
925 | The I<zlib> compression library was written by Jean-loup Gailly |
926 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
927 | |
928 | The primary site for the I<zlib> compression library is |
929 | F<http://www.zlib.org>. |
930 | |
931 | The primary site for gzip is F<http://www.gzip.org>. |
932 | |
642e522c |
933 | =head1 AUTHOR |
934 | |
cb7abd7f |
935 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
642e522c |
936 | |
642e522c |
937 | =head1 MODIFICATION HISTORY |
938 | |
939 | See the Changes file. |
940 | |
941 | =head1 COPYRIGHT AND LICENSE |
642e522c |
942 | |
d54256af |
943 | Copyright (c) 2005-2008 Paul Marquess. All rights reserved. |
a02d0f6f |
944 | |
642e522c |
945 | This program is free software; you can redistribute it and/or |
946 | modify it under the same terms as Perl itself. |
947 | |