Commit | Line | Data |
---|---|---|
25f0751f PM |
1 | package IO::Uncompress::AnyUncompress ; |
2 | ||
3 | use strict; | |
4 | use warnings; | |
5 | use bytes; | |
6 | ||
529174d6 | 7 | use IO::Compress::Base::Common 2.036 qw(createSelfTiedObject); |
25f0751f | 8 | |
529174d6 | 9 | use IO::Uncompress::Base 2.036 ; |
25f0751f | 10 | |
25f0751f PM |
11 | |
12 | require Exporter ; | |
13 | ||
14 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $AnyUncompressError); | |
15 | ||
529174d6 | 16 | $VERSION = '2.036'; |
25f0751f PM |
17 | $AnyUncompressError = ''; |
18 | ||
19 | @ISA = qw( Exporter IO::Uncompress::Base ); | |
20 | @EXPORT_OK = qw( $AnyUncompressError anyuncompress ) ; | |
21 | %EXPORT_TAGS = %IO::Uncompress::Base::DEFLATE_CONSTANTS ; | |
22 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; | |
23 | Exporter::export_ok_tags('all'); | |
24 | ||
25 | # TODO - allow the user to pick a set of the three formats to allow | |
26 | # or just assume want to auto-detect any of the three formats. | |
27 | ||
258133d1 PM |
28 | BEGIN |
29 | { | |
529174d6 CBW |
30 | eval ' use IO::Uncompress::Adapter::Inflate 2.036 ;'; |
31 | eval ' use IO::Uncompress::Adapter::Bunzip2 2.036 ;'; | |
32 | eval ' use IO::Uncompress::Adapter::LZO 2.036 ;'; | |
33 | eval ' use IO::Uncompress::Adapter::Lzf 2.036 ;'; | |
9b5fd1d4 PM |
34 | eval ' use IO::Uncompress::Adapter::UnLzma 2.020 ;'; |
35 | eval ' use IO::Uncompress::Adapter::UnXz 2.020 ;'; | |
36 | ||
529174d6 CBW |
37 | eval ' use IO::Uncompress::Bunzip2 2.036 ;'; |
38 | eval ' use IO::Uncompress::UnLzop 2.036 ;'; | |
39 | eval ' use IO::Uncompress::Gunzip 2.036 ;'; | |
40 | eval ' use IO::Uncompress::Inflate 2.036 ;'; | |
41 | eval ' use IO::Uncompress::RawInflate 2.036 ;'; | |
42 | eval ' use IO::Uncompress::Unzip 2.036 ;'; | |
43 | eval ' use IO::Uncompress::UnLzf 2.036 ;'; | |
44 | eval ' use IO::Uncompress::UnLzma 2.036 ;'; | |
45 | eval ' use IO::Uncompress::UnXz 2.036 ;'; | |
258133d1 PM |
46 | } |
47 | ||
25f0751f PM |
48 | sub new |
49 | { | |
50 | my $class = shift ; | |
51 | my $obj = createSelfTiedObject($class, \$AnyUncompressError); | |
52 | $obj->_create(undef, 0, @_); | |
53 | } | |
54 | ||
55 | sub anyuncompress | |
56 | { | |
57 | my $obj = createSelfTiedObject(undef, \$AnyUncompressError); | |
58 | return $obj->_inf(@_) ; | |
59 | } | |
60 | ||
61 | sub getExtraParams | |
62 | { | |
529174d6 | 63 | use IO::Compress::Base::Common 2.036 qw(:Parse); |
1725f55b PM |
64 | return ( 'RawInflate' => [1, 1, Parse_boolean, 0] , |
65 | 'UnLzma' => [1, 1, Parse_boolean, 0] ) ; | |
25f0751f PM |
66 | } |
67 | ||
68 | sub ckParams | |
69 | { | |
70 | my $self = shift ; | |
71 | my $got = shift ; | |
72 | ||
73 | # any always needs both crc32 and adler32 | |
74 | $got->value('CRC32' => 1); | |
75 | $got->value('ADLER32' => 1); | |
76 | ||
77 | return 1; | |
78 | } | |
79 | ||
80 | sub mkUncomp | |
81 | { | |
82 | my $self = shift ; | |
25f0751f PM |
83 | my $got = shift ; |
84 | ||
cb7abd7f PM |
85 | my $magic ; |
86 | ||
25f0751f | 87 | # try zlib first |
cb7abd7f PM |
88 | if (defined $IO::Uncompress::RawInflate::VERSION ) |
89 | { | |
90 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Inflate::mkUncompObject(); | |
25f0751f | 91 | |
cb7abd7f PM |
92 | return $self->saveErrorString(undef, $errstr, $errno) |
93 | if ! defined $obj; | |
25f0751f | 94 | |
cb7abd7f PM |
95 | *$self->{Uncomp} = $obj; |
96 | ||
6ecef415 PM |
97 | my @possible = qw( Inflate Gunzip Unzip ); |
98 | unshift @possible, 'RawInflate' | |
99 | if $got->value('RawInflate'); | |
25f0751f | 100 | |
6ecef415 PM |
101 | $magic = $self->ckMagic( @possible ); |
102 | ||
103 | if ($magic) { | |
cb7abd7f PM |
104 | *$self->{Info} = $self->readHeader($magic) |
105 | or return undef ; | |
25f0751f | 106 | |
cb7abd7f | 107 | return 1; |
6ecef415 | 108 | } |
25f0751f PM |
109 | } |
110 | ||
9b5fd1d4 PM |
111 | if (defined $IO::Uncompress::UnLzma::VERSION && $got->value('UnLzma')) |
112 | { | |
113 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::UnLzma::mkUncompObject(); | |
114 | ||
115 | return $self->saveErrorString(undef, $errstr, $errno) | |
116 | if ! defined $obj; | |
117 | ||
118 | *$self->{Uncomp} = $obj; | |
119 | ||
120 | my @possible = qw( UnLzma ); | |
121 | #unshift @possible, 'RawInflate' | |
122 | # if $got->value('RawInflate'); | |
123 | ||
124 | if ( *$self->{Info} = $self->ckMagic( @possible )) | |
125 | { | |
126 | return 1; | |
127 | } | |
128 | } | |
129 | ||
130 | if (defined $IO::Uncompress::UnXz::VERSION and | |
131 | $magic = $self->ckMagic('UnXz')) { | |
132 | *$self->{Info} = $self->readHeader($magic) | |
133 | or return undef ; | |
134 | ||
135 | my ($obj, $errstr, $errno) = | |
136 | IO::Uncompress::Adapter::UnXz::mkUncompObject(); | |
137 | ||
138 | return $self->saveErrorString(undef, $errstr, $errno) | |
139 | if ! defined $obj; | |
140 | ||
141 | *$self->{Uncomp} = $obj; | |
142 | ||
143 | return 1; | |
144 | } | |
10c2b2bb | 145 | |
25f0751f PM |
146 | if (defined $IO::Uncompress::Bunzip2::VERSION and |
147 | $magic = $self->ckMagic('Bunzip2')) { | |
148 | *$self->{Info} = $self->readHeader($magic) | |
149 | or return undef ; | |
150 | ||
151 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Bunzip2::mkUncompObject(); | |
152 | ||
153 | return $self->saveErrorString(undef, $errstr, $errno) | |
154 | if ! defined $obj; | |
155 | ||
156 | *$self->{Uncomp} = $obj; | |
157 | ||
158 | return 1; | |
159 | } | |
6ecef415 PM |
160 | |
161 | if (defined $IO::Uncompress::UnLzop::VERSION and | |
25f0751f PM |
162 | $magic = $self->ckMagic('UnLzop')) { |
163 | ||
164 | *$self->{Info} = $self->readHeader($magic) | |
165 | or return undef ; | |
166 | ||
167 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::LZO::mkUncompObject(); | |
168 | ||
169 | return $self->saveErrorString(undef, $errstr, $errno) | |
170 | if ! defined $obj; | |
171 | ||
172 | *$self->{Uncomp} = $obj; | |
173 | ||
174 | return 1; | |
175 | } | |
176 | ||
258133d1 PM |
177 | if (defined $IO::Uncompress::UnLzf::VERSION and |
178 | $magic = $self->ckMagic('UnLzf')) { | |
179 | ||
180 | *$self->{Info} = $self->readHeader($magic) | |
181 | or return undef ; | |
182 | ||
183 | my ($obj, $errstr, $errno) = IO::Uncompress::Adapter::Lzf::mkUncompObject(); | |
184 | ||
185 | return $self->saveErrorString(undef, $errstr, $errno) | |
186 | if ! defined $obj; | |
187 | ||
188 | *$self->{Uncomp} = $obj; | |
189 | ||
190 | return 1; | |
191 | } | |
192 | ||
25f0751f PM |
193 | return 0 ; |
194 | } | |
195 | ||
196 | ||
197 | ||
198 | sub ckMagic | |
199 | { | |
200 | my $self = shift; | |
201 | my @names = @_ ; | |
202 | ||
203 | my $keep = ref $self ; | |
204 | for my $class ( map { "IO::Uncompress::$_" } @names) | |
205 | { | |
206 | bless $self => $class; | |
207 | my $magic = $self->ckMagic(); | |
208 | ||
209 | if ($magic) | |
210 | { | |
211 | #bless $self => $class; | |
212 | return $magic ; | |
213 | } | |
214 | ||
215 | $self->pushBack(*$self->{HeaderPending}) ; | |
216 | *$self->{HeaderPending} = '' ; | |
217 | } | |
218 | ||
219 | bless $self => $keep; | |
220 | return undef; | |
221 | } | |
222 | ||
223 | 1 ; | |
224 | ||
225 | __END__ | |
226 | ||
227 | ||
228 | =head1 NAME | |
229 | ||
cb7abd7f | 230 | IO::Uncompress::AnyUncompress - Uncompress gzip, zip, bzip2 or lzop file/buffer |
25f0751f | 231 | |
25f0751f PM |
232 | =head1 SYNOPSIS |
233 | ||
234 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
235 | ||
236 | my $status = anyuncompress $input => $output [,OPTS] | |
237 | or die "anyuncompress failed: $AnyUncompressError\n"; | |
238 | ||
239 | my $z = new IO::Uncompress::AnyUncompress $input [OPTS] | |
240 | or die "anyuncompress failed: $AnyUncompressError\n"; | |
241 | ||
242 | $status = $z->read($buffer) | |
243 | $status = $z->read($buffer, $length) | |
244 | $status = $z->read($buffer, $length, $offset) | |
245 | $line = $z->getline() | |
246 | $char = $z->getc() | |
247 | $char = $z->ungetc() | |
248 | $char = $z->opened() | |
249 | ||
e7d45986 PM |
250 | $data = $z->trailingData() |
251 | $status = $z->nextStream() | |
25f0751f PM |
252 | $data = $z->getHeaderInfo() |
253 | $z->tell() | |
254 | $z->seek($position, $whence) | |
255 | $z->binmode() | |
256 | $z->fileno() | |
257 | $z->eof() | |
258 | $z->close() | |
259 | ||
260 | $AnyUncompressError ; | |
261 | ||
262 | # IO::File mode | |
263 | ||
264 | <$z> | |
265 | read($z, $buffer); | |
266 | read($z, $buffer, $length); | |
267 | read($z, $buffer, $length, $offset); | |
268 | tell($z) | |
269 | seek($z, $position, $whence) | |
270 | binmode($z) | |
271 | fileno($z) | |
272 | eof($z) | |
273 | close($z) | |
274 | ||
25f0751f PM |
275 | =head1 DESCRIPTION |
276 | ||
25f0751f | 277 | This module provides a Perl interface that allows the reading of |
cb7abd7f PM |
278 | files/buffers that have been compressed with a variety of compression |
279 | libraries. | |
280 | ||
281 | The formats supported are: | |
282 | ||
283 | =over 5 | |
284 | ||
285 | =item RFC 1950 | |
286 | ||
258133d1 | 287 | =item RFC 1951 (optionally) |
cb7abd7f PM |
288 | |
289 | =item gzip (RFC 1952) | |
290 | ||
291 | =item zip | |
292 | ||
293 | =item bzip2 | |
294 | ||
295 | =item lzop | |
296 | ||
258133d1 PM |
297 | =item lzf |
298 | ||
9b5fd1d4 PM |
299 | =item lzma |
300 | ||
301 | =item xz | |
302 | ||
cb7abd7f PM |
303 | =back |
304 | ||
305 | The module will auto-detect which, if any, of the supported | |
306 | compression formats is being used. | |
307 | ||
25f0751f PM |
308 | =head1 Functional Interface |
309 | ||
310 | A top-level function, C<anyuncompress>, is provided to carry out | |
311 | "one-shot" uncompression between buffers and/or files. For finer | |
312 | control over the uncompression process, see the L</"OO Interface"> | |
313 | section. | |
314 | ||
315 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
316 | ||
317 | anyuncompress $input => $output [,OPTS] | |
318 | or die "anyuncompress failed: $AnyUncompressError\n"; | |
319 | ||
25f0751f PM |
320 | The functional interface needs Perl5.005 or better. |
321 | ||
25f0751f PM |
322 | =head2 anyuncompress $input => $output [, OPTS] |
323 | ||
25f0751f PM |
324 | C<anyuncompress> expects at least two parameters, C<$input> and C<$output>. |
325 | ||
326 | =head3 The C<$input> parameter | |
327 | ||
328 | The parameter, C<$input>, is used to define the source of | |
329 | the compressed data. | |
330 | ||
331 | It can take one of the following forms: | |
332 | ||
333 | =over 5 | |
334 | ||
335 | =item A filename | |
336 | ||
337 | If the C<$input> parameter is a simple scalar, it is assumed to be a | |
338 | filename. This file will be opened for reading and the input data | |
339 | will be read from it. | |
340 | ||
341 | =item A filehandle | |
342 | ||
343 | If the C<$input> parameter is a filehandle, the input data will be | |
344 | read from it. | |
345 | The string '-' can be used as an alias for standard input. | |
346 | ||
347 | =item A scalar reference | |
348 | ||
349 | If C<$input> is a scalar reference, the input data will be read | |
350 | from C<$$input>. | |
351 | ||
352 | =item An array reference | |
353 | ||
354 | If C<$input> is an array reference, each element in the array must be a | |
355 | filename. | |
356 | ||
357 | The input data will be read from each file in turn. | |
358 | ||
359 | The complete array will be walked to ensure that it only | |
360 | contains valid filenames before any data is uncompressed. | |
361 | ||
25f0751f PM |
362 | =item An Input FileGlob string |
363 | ||
364 | If C<$input> is a string that is delimited by the characters "<" and ">" | |
365 | C<anyuncompress> will assume that it is an I<input fileglob string>. The | |
366 | input is the list of files that match the fileglob. | |
367 | ||
25f0751f PM |
368 | See L<File::GlobMapper|File::GlobMapper> for more details. |
369 | ||
25f0751f PM |
370 | =back |
371 | ||
372 | If the C<$input> parameter is any other type, C<undef> will be returned. | |
373 | ||
25f0751f PM |
374 | =head3 The C<$output> parameter |
375 | ||
376 | The parameter C<$output> is used to control the destination of the | |
377 | uncompressed data. This parameter can take one of these forms. | |
378 | ||
379 | =over 5 | |
380 | ||
381 | =item A filename | |
382 | ||
383 | If the C<$output> parameter is a simple scalar, it is assumed to be a | |
384 | filename. This file will be opened for writing and the uncompressed | |
385 | data will be written to it. | |
386 | ||
387 | =item A filehandle | |
388 | ||
389 | If the C<$output> parameter is a filehandle, the uncompressed data | |
390 | will be written to it. | |
391 | The string '-' can be used as an alias for standard output. | |
392 | ||
25f0751f PM |
393 | =item A scalar reference |
394 | ||
395 | If C<$output> is a scalar reference, the uncompressed data will be | |
396 | stored in C<$$output>. | |
397 | ||
25f0751f PM |
398 | =item An Array Reference |
399 | ||
400 | If C<$output> is an array reference, the uncompressed data will be | |
401 | pushed onto the array. | |
402 | ||
403 | =item An Output FileGlob | |
404 | ||
405 | If C<$output> is a string that is delimited by the characters "<" and ">" | |
406 | C<anyuncompress> will assume that it is an I<output fileglob string>. The | |
407 | output is the list of files that match the fileglob. | |
408 | ||
409 | When C<$output> is an fileglob string, C<$input> must also be a fileglob | |
410 | string. Anything else is an error. | |
411 | ||
e8796d61 CBW |
412 | See L<File::GlobMapper|File::GlobMapper> for more details. |
413 | ||
25f0751f PM |
414 | =back |
415 | ||
416 | If the C<$output> parameter is any other type, C<undef> will be returned. | |
417 | ||
25f0751f PM |
418 | =head2 Notes |
419 | ||
c70c1701 PM |
420 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
421 | a single file/buffer, after uncompression C<$output> will contain a | |
422 | concatenation of all the uncompressed data from each of the input | |
423 | files/buffers. | |
424 | ||
25f0751f PM |
425 | =head2 Optional Parameters |
426 | ||
427 | Unless specified below, the optional parameters for C<anyuncompress>, | |
428 | C<OPTS>, are the same as those used with the OO interface defined in the | |
429 | L</"Constructor Options"> section below. | |
430 | ||
431 | =over 5 | |
432 | ||
e7d45986 | 433 | =item C<< AutoClose => 0|1 >> |
25f0751f PM |
434 | |
435 | This option applies to any input or output data streams to | |
436 | C<anyuncompress> that are filehandles. | |
437 | ||
438 | If C<AutoClose> is specified, and the value is true, it will result in all | |
439 | input and/or output filehandles being closed once C<anyuncompress> has | |
440 | completed. | |
441 | ||
442 | This parameter defaults to 0. | |
443 | ||
e7d45986 | 444 | =item C<< BinModeOut => 0|1 >> |
25f0751f PM |
445 | |
446 | When writing to a file or filehandle, set C<binmode> before writing to the | |
447 | file. | |
448 | ||
449 | Defaults to 0. | |
450 | ||
e7d45986 | 451 | =item C<< Append => 0|1 >> |
25f0751f | 452 | |
9b5fd1d4 PM |
453 | The behaviour of this option is dependent on the type of output data |
454 | stream. | |
455 | ||
456 | =over 5 | |
457 | ||
458 | =item * A Buffer | |
459 | ||
460 | If C<Append> is enabled, all uncompressed data will be append to the end of | |
461 | the output buffer. Otherwise the output buffer will be cleared before any | |
462 | uncompressed data is written to it. | |
463 | ||
464 | =item * A Filename | |
465 | ||
466 | If C<Append> is enabled, the file will be opened in append mode. Otherwise | |
467 | the contents of the file, if any, will be truncated before any uncompressed | |
468 | data is written to it. | |
469 | ||
470 | =item * A Filehandle | |
471 | ||
472 | If C<Append> is enabled, the filehandle will be positioned to the end of | |
473 | the file via a call to C<seek> before any uncompressed data is | |
474 | written to it. Otherwise the file pointer will not be moved. | |
475 | ||
476 | =back | |
477 | ||
478 | When C<Append> is specified, and set to true, it will I<append> all uncompressed | |
479 | data to the output data stream. | |
480 | ||
481 | So when the output is a filehandle it will carry out a seek to the eof | |
482 | before writing any uncompressed data. If the output is a filename, it will be opened for | |
cd0c0e65 CBW |
483 | appending. If the output is a buffer, all uncompressed data will be |
484 | appended to the existing buffer. | |
9b5fd1d4 PM |
485 | |
486 | Conversely when C<Append> is not specified, or it is present and is set to | |
487 | false, it will operate as follows. | |
488 | ||
489 | When the output is a filename, it will truncate the contents of the file | |
490 | before writing any uncompressed data. If the output is a filehandle | |
491 | its position will not be changed. If the output is a buffer, it will be | |
492 | wiped before any uncompressed data is output. | |
493 | ||
494 | Defaults to 0. | |
25f0751f | 495 | |
e7d45986 | 496 | =item C<< MultiStream => 0|1 >> |
25f0751f | 497 | |
e7d45986 PM |
498 | If the input file/buffer contains multiple compressed data streams, this |
499 | option will uncompress the whole lot as a single data stream. | |
25f0751f | 500 | |
e7d45986 | 501 | Defaults to 0. |
25f0751f | 502 | |
258133d1 PM |
503 | =item C<< TrailingData => $scalar >> |
504 | ||
505 | Returns the data, if any, that is present immediately after the compressed | |
506 | data stream once uncompression is complete. | |
507 | ||
508 | This option can be used when there is useful information immediately | |
509 | following the compressed data stream, and you don't know the length of the | |
510 | compressed data stream. | |
511 | ||
512 | If the input is a buffer, C<trailingData> will return everything from the | |
513 | end of the compressed data stream to the end of the buffer. | |
514 | ||
515 | If the input is a filehandle, C<trailingData> will return the data that is | |
516 | left in the filehandle input buffer once the end of the compressed data | |
517 | stream has been reached. You can then use the filehandle to read the rest | |
518 | of the input file. | |
519 | ||
520 | Don't bother using C<trailingData> if the input is a filename. | |
521 | ||
258133d1 PM |
522 | If you know the length of the compressed data stream before you start |
523 | uncompressing, you can avoid having to use C<trailingData> by setting the | |
524 | C<InputLength> option. | |
525 | ||
25f0751f PM |
526 | =back |
527 | ||
25f0751f PM |
528 | =head2 Examples |
529 | ||
530 | To read the contents of the file C<file1.txt.Compressed> and write the | |
10c2b2bb | 531 | uncompressed data to the file C<file1.txt>. |
25f0751f PM |
532 | |
533 | use strict ; | |
534 | use warnings ; | |
535 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
536 | ||
537 | my $input = "file1.txt.Compressed"; | |
538 | my $output = "file1.txt"; | |
539 | anyuncompress $input => $output | |
540 | or die "anyuncompress failed: $AnyUncompressError\n"; | |
541 | ||
25f0751f PM |
542 | To read from an existing Perl filehandle, C<$input>, and write the |
543 | uncompressed data to a buffer, C<$buffer>. | |
544 | ||
545 | use strict ; | |
546 | use warnings ; | |
547 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
548 | use IO::File ; | |
549 | ||
550 | my $input = new IO::File "<file1.txt.Compressed" | |
551 | or die "Cannot open 'file1.txt.Compressed': $!\n" ; | |
552 | my $buffer ; | |
553 | anyuncompress $input => \$buffer | |
554 | or die "anyuncompress failed: $AnyUncompressError\n"; | |
555 | ||
556 | To uncompress all files in the directory "/my/home" that match "*.txt.Compressed" and store the compressed data in the same directory | |
557 | ||
558 | use strict ; | |
559 | use warnings ; | |
560 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
561 | ||
562 | anyuncompress '</my/home/*.txt.Compressed>' => '</my/home/#1.txt>' | |
563 | or die "anyuncompress failed: $AnyUncompressError\n"; | |
564 | ||
565 | and if you want to compress each file one at a time, this will do the trick | |
566 | ||
567 | use strict ; | |
568 | use warnings ; | |
569 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
570 | ||
571 | for my $input ( glob "/my/home/*.txt.Compressed" ) | |
572 | { | |
573 | my $output = $input; | |
574 | $output =~ s/.Compressed// ; | |
575 | anyuncompress $input => $output | |
576 | or die "Error compressing '$input': $AnyUncompressError\n"; | |
577 | } | |
578 | ||
579 | =head1 OO Interface | |
580 | ||
581 | =head2 Constructor | |
582 | ||
583 | The format of the constructor for IO::Uncompress::AnyUncompress is shown below | |
584 | ||
25f0751f PM |
585 | my $z = new IO::Uncompress::AnyUncompress $input [OPTS] |
586 | or die "IO::Uncompress::AnyUncompress failed: $AnyUncompressError\n"; | |
587 | ||
588 | Returns an C<IO::Uncompress::AnyUncompress> object on success and undef on failure. | |
589 | The variable C<$AnyUncompressError> will contain an error message on failure. | |
590 | ||
591 | If you are running Perl 5.005 or better the object, C<$z>, returned from | |
592 | IO::Uncompress::AnyUncompress can be used exactly like an L<IO::File|IO::File> filehandle. | |
593 | This means that all normal input file operations can be carried out with | |
594 | C<$z>. For example, to read a line from a compressed file/buffer you can | |
595 | use either of these forms | |
596 | ||
597 | $line = $z->getline(); | |
598 | $line = <$z>; | |
599 | ||
600 | The mandatory parameter C<$input> is used to determine the source of the | |
601 | compressed data. This parameter can take one of three forms. | |
602 | ||
603 | =over 5 | |
604 | ||
605 | =item A filename | |
606 | ||
607 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This | |
608 | file will be opened for reading and the compressed data will be read from it. | |
609 | ||
610 | =item A filehandle | |
611 | ||
612 | If the C<$input> parameter is a filehandle, the compressed data will be | |
613 | read from it. | |
614 | The string '-' can be used as an alias for standard input. | |
615 | ||
25f0751f PM |
616 | =item A scalar reference |
617 | ||
618 | If C<$input> is a scalar reference, the compressed data will be read from | |
619 | C<$$output>. | |
620 | ||
621 | =back | |
622 | ||
623 | =head2 Constructor Options | |
624 | ||
25f0751f PM |
625 | The option names defined below are case insensitive and can be optionally |
626 | prefixed by a '-'. So all of the following are valid | |
627 | ||
628 | -AutoClose | |
629 | -autoclose | |
630 | AUTOCLOSE | |
631 | autoclose | |
632 | ||
633 | OPTS is a combination of the following options: | |
634 | ||
635 | =over 5 | |
636 | ||
e7d45986 | 637 | =item C<< AutoClose => 0|1 >> |
25f0751f PM |
638 | |
639 | This option is only valid when the C<$input> parameter is a filehandle. If | |
640 | specified, and the value is true, it will result in the file being closed once | |
641 | either the C<close> method is called or the IO::Uncompress::AnyUncompress object is | |
642 | destroyed. | |
643 | ||
644 | This parameter defaults to 0. | |
645 | ||
e7d45986 | 646 | =item C<< MultiStream => 0|1 >> |
25f0751f | 647 | |
25f0751f PM |
648 | Allows multiple concatenated compressed streams to be treated as a single |
649 | compressed stream. Decompression will stop once either the end of the | |
650 | file/buffer is reached, an error is encountered (premature eof, corrupt | |
651 | compressed data) or the end of a stream is not immediately followed by the | |
652 | start of another stream. | |
653 | ||
654 | This parameter defaults to 0. | |
655 | ||
e7d45986 | 656 | =item C<< Prime => $string >> |
25f0751f PM |
657 | |
658 | This option will uncompress the contents of C<$string> before processing the | |
659 | input file/buffer. | |
660 | ||
661 | This option can be useful when the compressed data is embedded in another | |
662 | file/data structure and it is not possible to work out where the compressed | |
663 | data begins without having to read the first few bytes. If this is the | |
664 | case, the uncompression can be I<primed> with these bytes using this | |
665 | option. | |
666 | ||
e7d45986 | 667 | =item C<< Transparent => 0|1 >> |
25f0751f | 668 | |
f6fd7794 | 669 | If this option is set and the input file/buffer is not compressed data, |
25f0751f PM |
670 | the module will allow reading of it anyway. |
671 | ||
f6fd7794 PM |
672 | In addition, if the input file/buffer does contain compressed data and |
673 | there is non-compressed data immediately following it, setting this option | |
cd0c0e65 | 674 | will make this module treat the whole file/buffer as a single data stream. |
f6fd7794 | 675 | |
25f0751f PM |
676 | This option defaults to 1. |
677 | ||
e7d45986 | 678 | =item C<< BlockSize => $num >> |
25f0751f PM |
679 | |
680 | When reading the compressed input data, IO::Uncompress::AnyUncompress will read it in | |
681 | blocks of C<$num> bytes. | |
682 | ||
683 | This option defaults to 4096. | |
684 | ||
e7d45986 | 685 | =item C<< InputLength => $size >> |
25f0751f PM |
686 | |
687 | When present this option will limit the number of compressed bytes read | |
688 | from the input file/buffer to C<$size>. This option can be used in the | |
689 | situation where there is useful data directly after the compressed data | |
690 | stream and you know beforehand the exact length of the compressed data | |
691 | stream. | |
692 | ||
693 | This option is mostly used when reading from a filehandle, in which case | |
694 | the file pointer will be left pointing to the first byte directly after the | |
695 | compressed data stream. | |
696 | ||
25f0751f PM |
697 | This option defaults to off. |
698 | ||
e7d45986 | 699 | =item C<< Append => 0|1 >> |
25f0751f PM |
700 | |
701 | This option controls what the C<read> method does with uncompressed data. | |
702 | ||
703 | If set to 1, all uncompressed data will be appended to the output parameter | |
704 | of the C<read> method. | |
705 | ||
706 | If set to 0, the contents of the output parameter of the C<read> method | |
707 | will be overwritten by the uncompressed data. | |
708 | ||
709 | Defaults to 0. | |
710 | ||
e7d45986 | 711 | =item C<< Strict => 0|1 >> |
25f0751f | 712 | |
25f0751f PM |
713 | This option controls whether the extra checks defined below are used when |
714 | carrying out the decompression. When Strict is on, the extra tests are | |
715 | carried out, when Strict is off they are not. | |
716 | ||
717 | The default for this option is off. | |
718 | ||
258133d1 PM |
719 | =item C<< RawInflate => 0|1 >> |
720 | ||
721 | When auto-detecting the compressed format, try to test for raw-deflate (RFC | |
722 | 1951) content using the C<IO::Uncompress::RawInflate> module. | |
723 | ||
724 | The reason this is not default behaviour is because RFC 1951 content can | |
725 | only be detected by attempting to uncompress it. This process is error | |
726 | prone and can result is false positives. | |
727 | ||
728 | Defaults to 0. | |
729 | ||
9b5fd1d4 PM |
730 | =item C<< UnLzma => 0|1 >> |
731 | ||
732 | When auto-detecting the compressed format, try to test for lzma_alone | |
733 | content using the C<IO::Uncompress::UnLzma> module. | |
734 | ||
735 | The reason this is not default behaviour is because lzma_alone content can | |
736 | only be detected by attempting to uncompress it. This process is error | |
737 | prone and can result is false positives. | |
738 | ||
739 | Defaults to 0. | |
740 | ||
25f0751f PM |
741 | =back |
742 | ||
743 | =head2 Examples | |
744 | ||
745 | TODO | |
746 | ||
747 | =head1 Methods | |
748 | ||
749 | =head2 read | |
750 | ||
751 | Usage is | |
752 | ||
753 | $status = $z->read($buffer) | |
754 | ||
755 | Reads a block of compressed data (the size the the compressed block is | |
756 | determined by the C<Buffer> option in the constructor), uncompresses it and | |
757 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is | |
758 | set in the constructor, the uncompressed data will be appended to the | |
759 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. | |
760 | ||
761 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof | |
762 | or a negative number on error. | |
763 | ||
764 | =head2 read | |
765 | ||
766 | Usage is | |
767 | ||
768 | $status = $z->read($buffer, $length) | |
769 | $status = $z->read($buffer, $length, $offset) | |
770 | ||
771 | $status = read($z, $buffer, $length) | |
772 | $status = read($z, $buffer, $length, $offset) | |
773 | ||
774 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. | |
775 | ||
776 | The main difference between this form of the C<read> method and the | |
777 | previous one, is that this one will attempt to return I<exactly> C<$length> | |
778 | bytes. The only circumstances that this function will not is if end-of-file | |
779 | or an IO error is encountered. | |
780 | ||
781 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof | |
782 | or a negative number on error. | |
783 | ||
25f0751f PM |
784 | =head2 getline |
785 | ||
786 | Usage is | |
787 | ||
788 | $line = $z->getline() | |
789 | $line = <$z> | |
790 | ||
791 | Reads a single line. | |
792 | ||
258133d1 PM |
793 | This method fully supports the use of of the variable C<$/> (or |
794 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to | |
795 | determine what constitutes an end of line. Paragraph mode, record mode and | |
796 | file slurp mode are all supported. | |
25f0751f | 797 | |
25f0751f PM |
798 | =head2 getc |
799 | ||
800 | Usage is | |
801 | ||
802 | $char = $z->getc() | |
803 | ||
804 | Read a single character. | |
805 | ||
806 | =head2 ungetc | |
807 | ||
808 | Usage is | |
809 | ||
810 | $char = $z->ungetc($string) | |
811 | ||
25f0751f PM |
812 | =head2 getHeaderInfo |
813 | ||
814 | Usage is | |
815 | ||
816 | $hdr = $z->getHeaderInfo(); | |
817 | @hdrs = $z->getHeaderInfo(); | |
818 | ||
819 | This method returns either a hash reference (in scalar context) or a list | |
820 | or hash references (in array context) that contains information about each | |
821 | of the header fields in the compressed data stream(s). | |
822 | ||
25f0751f PM |
823 | =head2 tell |
824 | ||
825 | Usage is | |
826 | ||
827 | $z->tell() | |
828 | tell $z | |
829 | ||
830 | Returns the uncompressed file offset. | |
831 | ||
832 | =head2 eof | |
833 | ||
834 | Usage is | |
835 | ||
836 | $z->eof(); | |
837 | eof($z); | |
838 | ||
25f0751f PM |
839 | Returns true if the end of the compressed input stream has been reached. |
840 | ||
25f0751f PM |
841 | =head2 seek |
842 | ||
843 | $z->seek($position, $whence); | |
844 | seek($z, $position, $whence); | |
845 | ||
25f0751f PM |
846 | Provides a sub-set of the C<seek> functionality, with the restriction |
847 | that it is only legal to seek forward in the input file/buffer. | |
848 | It is a fatal error to attempt to seek backward. | |
849 | ||
25f0751f PM |
850 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
851 | SEEK_CUR or SEEK_END. | |
852 | ||
853 | Returns 1 on success, 0 on failure. | |
854 | ||
855 | =head2 binmode | |
856 | ||
857 | Usage is | |
858 | ||
859 | $z->binmode | |
860 | binmode $z ; | |
861 | ||
862 | This is a noop provided for completeness. | |
863 | ||
864 | =head2 opened | |
865 | ||
866 | $z->opened() | |
867 | ||
868 | Returns true if the object currently refers to a opened file/buffer. | |
869 | ||
870 | =head2 autoflush | |
871 | ||
872 | my $prev = $z->autoflush() | |
873 | my $prev = $z->autoflush(EXPR) | |
874 | ||
875 | If the C<$z> object is associated with a file or a filehandle, this method | |
876 | returns the current autoflush setting for the underlying filehandle. If | |
877 | C<EXPR> is present, and is non-zero, it will enable flushing after every | |
878 | write/print operation. | |
879 | ||
880 | If C<$z> is associated with a buffer, this method has no effect and always | |
881 | returns C<undef>. | |
882 | ||
883 | B<Note> that the special variable C<$|> B<cannot> be used to set or | |
884 | retrieve the autoflush setting. | |
885 | ||
886 | =head2 input_line_number | |
887 | ||
888 | $z->input_line_number() | |
889 | $z->input_line_number(EXPR) | |
890 | ||
25f0751f PM |
891 | Returns the current uncompressed line number. If C<EXPR> is present it has |
892 | the effect of setting the line number. Note that setting the line number | |
893 | does not change the current position within the file/buffer being read. | |
894 | ||
895 | The contents of C<$/> are used to to determine what constitutes a line | |
896 | terminator. | |
897 | ||
25f0751f PM |
898 | =head2 fileno |
899 | ||
900 | $z->fileno() | |
901 | fileno($z) | |
902 | ||
d54256af PM |
903 | If the C<$z> object is associated with a file or a filehandle, C<fileno> |
904 | will return the underlying file descriptor. Once the C<close> method is | |
905 | called C<fileno> will return C<undef>. | |
25f0751f | 906 | |
c23ee15d | 907 | If the C<$z> object is associated with a buffer, this method will return |
d54256af | 908 | C<undef>. |
25f0751f PM |
909 | |
910 | =head2 close | |
911 | ||
912 | $z->close() ; | |
913 | close $z ; | |
914 | ||
25f0751f PM |
915 | Closes the output file/buffer. |
916 | ||
25f0751f PM |
917 | For most versions of Perl this method will be automatically invoked if |
918 | the IO::Uncompress::AnyUncompress object is destroyed (either explicitly or by the | |
919 | variable with the reference to the object going out of scope). The | |
920 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In | |
921 | these cases, the C<close> method will be called automatically, but | |
922 | not until global destruction of all live objects when the program is | |
923 | terminating. | |
924 | ||
925 | Therefore, if you want your scripts to be able to run on all versions | |
926 | of Perl, you should call C<close> explicitly and not rely on automatic | |
927 | closing. | |
928 | ||
929 | Returns true on success, otherwise 0. | |
930 | ||
931 | If the C<AutoClose> option has been enabled when the IO::Uncompress::AnyUncompress | |
932 | object was created, and the object is associated with a file, the | |
933 | underlying file will also be closed. | |
934 | ||
e7d45986 PM |
935 | =head2 nextStream |
936 | ||
937 | Usage is | |
938 | ||
939 | my $status = $z->nextStream(); | |
940 | ||
941 | Skips to the next compressed data stream in the input file/buffer. If a new | |
258133d1 PM |
942 | compressed data stream is found, the eof marker will be cleared and C<$.> |
943 | will be reset to 0. | |
e7d45986 PM |
944 | |
945 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an | |
946 | error was encountered. | |
947 | ||
948 | =head2 trailingData | |
949 | ||
950 | Usage is | |
951 | ||
952 | my $data = $z->trailingData(); | |
953 | ||
258133d1 PM |
954 | Returns the data, if any, that is present immediately after the compressed |
955 | data stream once uncompression is complete. It only makes sense to call | |
956 | this method once the end of the compressed data stream has been | |
957 | encountered. | |
958 | ||
959 | This option can be used when there is useful information immediately | |
960 | following the compressed data stream, and you don't know the length of the | |
961 | compressed data stream. | |
962 | ||
963 | If the input is a buffer, C<trailingData> will return everything from the | |
964 | end of the compressed data stream to the end of the buffer. | |
965 | ||
966 | If the input is a filehandle, C<trailingData> will return the data that is | |
967 | left in the filehandle input buffer once the end of the compressed data | |
968 | stream has been reached. You can then use the filehandle to read the rest | |
969 | of the input file. | |
970 | ||
971 | Don't bother using C<trailingData> if the input is a filename. | |
972 | ||
258133d1 PM |
973 | If you know the length of the compressed data stream before you start |
974 | uncompressing, you can avoid having to use C<trailingData> by setting the | |
975 | C<InputLength> option in the constructor. | |
e7d45986 | 976 | |
25f0751f PM |
977 | =head1 Importing |
978 | ||
979 | No symbolic constants are required by this IO::Uncompress::AnyUncompress at present. | |
980 | ||
981 | =over 5 | |
982 | ||
983 | =item :all | |
984 | ||
985 | Imports C<anyuncompress> and C<$AnyUncompressError>. | |
986 | Same as doing this | |
987 | ||
988 | use IO::Uncompress::AnyUncompress qw(anyuncompress $AnyUncompressError) ; | |
989 | ||
990 | =back | |
991 | ||
992 | =head1 EXAMPLES | |
993 | ||
25f0751f PM |
994 | =head1 SEE ALSO |
995 | ||
9b5fd1d4 | 996 | 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::Lzma>, L<IO::Uncompress::UnLzma>, L<IO::Compress::Xz>, L<IO::Uncompress::UnXz>, L<IO::Compress::Lzop>, L<IO::Uncompress::UnLzop>, L<IO::Compress::Lzf>, L<IO::Uncompress::UnLzf>, L<IO::Uncompress::AnyInflate> |
25f0751f PM |
997 | |
998 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> | |
999 | ||
1000 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, | |
1001 | L<Archive::Tar|Archive::Tar>, | |
1002 | L<IO::Zlib|IO::Zlib> | |
1003 | ||
25f0751f PM |
1004 | =head1 AUTHOR |
1005 | ||
cb7abd7f | 1006 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
25f0751f | 1007 | |
25f0751f PM |
1008 | =head1 MODIFICATION HISTORY |
1009 | ||
1010 | See the Changes file. | |
1011 | ||
1012 | =head1 COPYRIGHT AND LICENSE | |
25f0751f | 1013 | |
cd0c0e65 | 1014 | Copyright (c) 2005-2011 Paul Marquess. All rights reserved. |
25f0751f PM |
1015 | |
1016 | This program is free software; you can redistribute it and/or | |
1017 | modify it under the same terms as Perl itself. | |
1018 |