Commit | Line | Data |
642e522c |
1 | |
2 | package IO::Uncompress::Gunzip ; |
3 | |
4 | require 5.004 ; |
5 | |
6 | # for RFC1952 |
7 | |
8 | use strict ; |
9 | use warnings; |
a02d0f6f |
10 | use bytes; |
642e522c |
11 | |
d56f7e4c |
12 | use IO::Uncompress::RawInflate 2.006 ; |
1a6a8453 |
13 | |
d56f7e4c |
14 | use Compress::Raw::Zlib 2.006 qw( crc32 ) ; |
15 | use IO::Compress::Base::Common 2.006 qw(:Status createSelfTiedObject); |
16 | use IO::Compress::Gzip::Constants 2.006 ; |
17 | use IO::Compress::Zlib::Extra 2.006 ; |
1a6a8453 |
18 | |
642e522c |
19 | require Exporter ; |
20 | |
21 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $GunzipError); |
22 | |
1a6a8453 |
23 | @ISA = qw( Exporter IO::Uncompress::RawInflate ); |
642e522c |
24 | @EXPORT_OK = qw( $GunzipError gunzip ); |
1a6a8453 |
25 | %EXPORT_TAGS = %IO::Uncompress::RawInflate::DEFLATE_CONSTANTS ; |
642e522c |
26 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; |
27 | Exporter::export_ok_tags('all'); |
28 | |
642e522c |
29 | $GunzipError = ''; |
30 | |
d56f7e4c |
31 | $VERSION = '2.006'; |
642e522c |
32 | |
1a6a8453 |
33 | sub new |
642e522c |
34 | { |
1a6a8453 |
35 | my $class = shift ; |
36 | $GunzipError = ''; |
37 | my $obj = createSelfTiedObject($class, \$GunzipError); |
642e522c |
38 | |
1a6a8453 |
39 | $obj->_create(undef, 0, @_); |
642e522c |
40 | } |
41 | |
1a6a8453 |
42 | sub gunzip |
642e522c |
43 | { |
1a6a8453 |
44 | my $obj = createSelfTiedObject(undef, \$GunzipError); |
45 | return $obj->_inf(@_) ; |
642e522c |
46 | } |
47 | |
1a6a8453 |
48 | sub getExtraParams |
642e522c |
49 | { |
d56f7e4c |
50 | use IO::Compress::Base::Common 2.006 qw(:Parse); |
1a6a8453 |
51 | return ( 'ParseExtra' => [1, 1, Parse_boolean, 0] ) ; |
642e522c |
52 | } |
53 | |
1a6a8453 |
54 | sub ckParams |
642e522c |
55 | { |
1a6a8453 |
56 | my $self = shift ; |
57 | my $got = shift ; |
642e522c |
58 | |
1a6a8453 |
59 | # gunzip always needs crc32 |
60 | $got->value('CRC32' => 1); |
642e522c |
61 | |
1a6a8453 |
62 | return 1; |
642e522c |
63 | } |
64 | |
1a6a8453 |
65 | sub ckMagic |
642e522c |
66 | { |
1a6a8453 |
67 | my $self = shift; |
642e522c |
68 | |
1a6a8453 |
69 | my $magic ; |
70 | $self->smartReadExact(\$magic, GZIP_ID_SIZE); |
642e522c |
71 | |
1a6a8453 |
72 | *$self->{HeaderPending} = $magic ; |
642e522c |
73 | |
1a6a8453 |
74 | return $self->HeaderError("Minimum header size is " . |
75 | GZIP_MIN_HEADER_SIZE . " bytes") |
76 | if length $magic != GZIP_ID_SIZE ; |
642e522c |
77 | |
1a6a8453 |
78 | return $self->HeaderError("Bad Magic") |
79 | if ! isGzipMagic($magic) ; |
642e522c |
80 | |
1a6a8453 |
81 | *$self->{Type} = 'rfc1952'; |
642e522c |
82 | |
1a6a8453 |
83 | return $magic ; |
642e522c |
84 | } |
85 | |
1a6a8453 |
86 | sub readHeader |
642e522c |
87 | { |
1a6a8453 |
88 | my $self = shift; |
89 | my $magic = shift; |
642e522c |
90 | |
1a6a8453 |
91 | return $self->_readGzipHeader($magic); |
642e522c |
92 | } |
93 | |
1a6a8453 |
94 | sub chkTrailer |
642e522c |
95 | { |
1a6a8453 |
96 | my $self = shift; |
97 | my $trailer = shift; |
642e522c |
98 | |
1a6a8453 |
99 | # Check CRC & ISIZE |
100 | my ($CRC32, $ISIZE) = unpack("V V", $trailer) ; |
101 | *$self->{Info}{CRC32} = $CRC32; |
102 | *$self->{Info}{ISIZE} = $ISIZE; |
103 | |
104 | if (*$self->{Strict}) { |
105 | return $self->TrailerError("CRC mismatch") |
106 | if $CRC32 != *$self->{Uncomp}->crc32() ; |
107 | |
e7d45986 |
108 | my $exp_isize = *$self->{UnCompSize}->get32bit(); |
1a6a8453 |
109 | return $self->TrailerError("ISIZE mismatch. Got $ISIZE" |
110 | . ", expected $exp_isize") |
111 | if $ISIZE != $exp_isize ; |
642e522c |
112 | } |
113 | |
a02d0f6f |
114 | return STATUS_OK; |
1a6a8453 |
115 | } |
642e522c |
116 | |
1a6a8453 |
117 | sub isGzipMagic |
118 | { |
119 | my $buffer = shift ; |
120 | return 0 if length $buffer < GZIP_ID_SIZE ; |
121 | my ($id1, $id2) = unpack("C C", $buffer) ; |
122 | return $id1 == GZIP_ID1 && $id2 == GZIP_ID2 ; |
642e522c |
123 | } |
124 | |
1a6a8453 |
125 | sub _readFullGzipHeader($) |
642e522c |
126 | { |
1a6a8453 |
127 | my ($self) = @_ ; |
128 | my $magic = '' ; |
642e522c |
129 | |
1a6a8453 |
130 | $self->smartReadExact(\$magic, GZIP_ID_SIZE); |
642e522c |
131 | |
1a6a8453 |
132 | *$self->{HeaderPending} = $magic ; |
642e522c |
133 | |
1a6a8453 |
134 | return $self->HeaderError("Minimum header size is " . |
135 | GZIP_MIN_HEADER_SIZE . " bytes") |
136 | if length $magic != GZIP_ID_SIZE ; |
642e522c |
137 | |
642e522c |
138 | |
1a6a8453 |
139 | return $self->HeaderError("Bad Magic") |
140 | if ! isGzipMagic($magic) ; |
642e522c |
141 | |
1a6a8453 |
142 | my $status = $self->_readGzipHeader($magic); |
143 | delete *$self->{Transparent} if ! defined $status ; |
144 | return $status ; |
642e522c |
145 | } |
146 | |
1a6a8453 |
147 | sub _readGzipHeader($) |
642e522c |
148 | { |
1a6a8453 |
149 | my ($self, $magic) = @_ ; |
150 | my ($HeaderCRC) ; |
151 | my ($buffer) = '' ; |
642e522c |
152 | |
1a6a8453 |
153 | $self->smartReadExact(\$buffer, GZIP_MIN_HEADER_SIZE - GZIP_ID_SIZE) |
154 | or return $self->HeaderError("Minimum header size is " . |
155 | GZIP_MIN_HEADER_SIZE . " bytes") ; |
642e522c |
156 | |
1a6a8453 |
157 | my $keep = $magic . $buffer ; |
158 | *$self->{HeaderPending} = $keep ; |
642e522c |
159 | |
1a6a8453 |
160 | # now split out the various parts |
161 | my ($cm, $flag, $mtime, $xfl, $os) = unpack("C C V C C", $buffer) ; |
642e522c |
162 | |
1a6a8453 |
163 | $cm == GZIP_CM_DEFLATED |
164 | or return $self->HeaderError("Not Deflate (CM is $cm)") ; |
642e522c |
165 | |
1a6a8453 |
166 | # check for use of reserved bits |
167 | return $self->HeaderError("Use of Reserved Bits in FLG field.") |
168 | if $flag & GZIP_FLG_RESERVED ; |
642e522c |
169 | |
1a6a8453 |
170 | my $EXTRA ; |
171 | my @EXTRA = () ; |
172 | if ($flag & GZIP_FLG_FEXTRA) { |
173 | $EXTRA = "" ; |
174 | $self->smartReadExact(\$buffer, GZIP_FEXTRA_HEADER_SIZE) |
175 | or return $self->TruncatedHeader("FEXTRA Length") ; |
642e522c |
176 | |
1a6a8453 |
177 | my ($XLEN) = unpack("v", $buffer) ; |
178 | $self->smartReadExact(\$EXTRA, $XLEN) |
179 | or return $self->TruncatedHeader("FEXTRA Body"); |
180 | $keep .= $buffer . $EXTRA ; |
642e522c |
181 | |
1a6a8453 |
182 | if ($XLEN && *$self->{'ParseExtra'}) { |
c70c1701 |
183 | my $bad = IO::Compress::Zlib::Extra::parseRawExtra($EXTRA, |
184 | \@EXTRA, 1, 1); |
185 | return $self->HeaderError($bad) |
186 | if defined $bad; |
1a6a8453 |
187 | } |
188 | } |
642e522c |
189 | |
1a6a8453 |
190 | my $origname ; |
191 | if ($flag & GZIP_FLG_FNAME) { |
192 | $origname = "" ; |
193 | while (1) { |
194 | $self->smartReadExact(\$buffer, 1) |
195 | or return $self->TruncatedHeader("FNAME"); |
196 | last if $buffer eq GZIP_NULL_BYTE ; |
197 | $origname .= $buffer |
198 | } |
199 | $keep .= $origname . GZIP_NULL_BYTE ; |
642e522c |
200 | |
1a6a8453 |
201 | return $self->HeaderError("Non ISO 8859-1 Character found in Name") |
202 | if *$self->{Strict} && $origname =~ /$GZIP_FNAME_INVALID_CHAR_RE/o ; |
203 | } |
642e522c |
204 | |
1a6a8453 |
205 | my $comment ; |
206 | if ($flag & GZIP_FLG_FCOMMENT) { |
207 | $comment = ""; |
208 | while (1) { |
209 | $self->smartReadExact(\$buffer, 1) |
210 | or return $self->TruncatedHeader("FCOMMENT"); |
211 | last if $buffer eq GZIP_NULL_BYTE ; |
212 | $comment .= $buffer |
213 | } |
214 | $keep .= $comment . GZIP_NULL_BYTE ; |
642e522c |
215 | |
1a6a8453 |
216 | return $self->HeaderError("Non ISO 8859-1 Character found in Comment") |
217 | if *$self->{Strict} && $comment =~ /$GZIP_FCOMMENT_INVALID_CHAR_RE/o ; |
218 | } |
642e522c |
219 | |
1a6a8453 |
220 | if ($flag & GZIP_FLG_FHCRC) { |
221 | $self->smartReadExact(\$buffer, GZIP_FHCRC_SIZE) |
222 | or return $self->TruncatedHeader("FHCRC"); |
642e522c |
223 | |
1a6a8453 |
224 | $HeaderCRC = unpack("v", $buffer) ; |
225 | my $crc16 = crc32($keep) & 0xFF ; |
642e522c |
226 | |
1a6a8453 |
227 | return $self->HeaderError("CRC16 mismatch.") |
228 | if *$self->{Strict} && $crc16 != $HeaderCRC; |
642e522c |
229 | |
1a6a8453 |
230 | $keep .= $buffer ; |
231 | } |
642e522c |
232 | |
1a6a8453 |
233 | # Assume compression method is deflated for xfl tests |
234 | #if ($xfl) { |
235 | #} |
642e522c |
236 | |
1a6a8453 |
237 | *$self->{Type} = 'rfc1952'; |
642e522c |
238 | |
1a6a8453 |
239 | return { |
240 | 'Type' => 'rfc1952', |
241 | 'FingerprintLength' => 2, |
242 | 'HeaderLength' => length $keep, |
243 | 'TrailerLength' => GZIP_TRAILER_SIZE, |
244 | 'Header' => $keep, |
245 | 'isMinimalHeader' => $keep eq GZIP_MINIMUM_HEADER ? 1 : 0, |
642e522c |
246 | |
1a6a8453 |
247 | 'MethodID' => $cm, |
248 | 'MethodName' => $cm == GZIP_CM_DEFLATED ? "Deflated" : "Unknown" , |
249 | 'TextFlag' => $flag & GZIP_FLG_FTEXT ? 1 : 0, |
250 | 'HeaderCRCFlag' => $flag & GZIP_FLG_FHCRC ? 1 : 0, |
251 | 'NameFlag' => $flag & GZIP_FLG_FNAME ? 1 : 0, |
252 | 'CommentFlag' => $flag & GZIP_FLG_FCOMMENT ? 1 : 0, |
253 | 'ExtraFlag' => $flag & GZIP_FLG_FEXTRA ? 1 : 0, |
254 | 'Name' => $origname, |
255 | 'Comment' => $comment, |
256 | 'Time' => $mtime, |
257 | 'OsID' => $os, |
258 | 'OsName' => defined $GZIP_OS_Names{$os} |
259 | ? $GZIP_OS_Names{$os} : "Unknown", |
260 | 'HeaderCRC' => $HeaderCRC, |
261 | 'Flags' => $flag, |
262 | 'ExtraFlags' => $xfl, |
263 | 'ExtraFieldRaw' => $EXTRA, |
264 | 'ExtraField' => [ @EXTRA ], |
642e522c |
265 | |
642e522c |
266 | |
1a6a8453 |
267 | #'CompSize'=> $compsize, |
268 | #'CRC32'=> $CRC32, |
269 | #'OrigSize'=> $ISIZE, |
270 | } |
642e522c |
271 | } |
272 | |
273 | |
1a6a8453 |
274 | 1; |
642e522c |
275 | |
642e522c |
276 | __END__ |
277 | |
278 | |
279 | =head1 NAME |
280 | |
a02d0f6f |
281 | |
cb7abd7f |
282 | |
283 | IO::Uncompress::Gunzip - Read RFC 1952 files/buffers |
284 | |
642e522c |
285 | |
a02d0f6f |
286 | |
642e522c |
287 | =head1 SYNOPSIS |
288 | |
289 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
290 | |
291 | my $status = gunzip $input => $output [,OPTS] |
292 | or die "gunzip failed: $GunzipError\n"; |
293 | |
294 | my $z = new IO::Uncompress::Gunzip $input [OPTS] |
295 | or die "gunzip failed: $GunzipError\n"; |
296 | |
297 | $status = $z->read($buffer) |
298 | $status = $z->read($buffer, $length) |
299 | $status = $z->read($buffer, $length, $offset) |
300 | $line = $z->getline() |
301 | $char = $z->getc() |
302 | $char = $z->ungetc() |
a02d0f6f |
303 | $char = $z->opened() |
304 | |
642e522c |
305 | $status = $z->inflateSync() |
a02d0f6f |
306 | |
e7d45986 |
307 | $data = $z->trailingData() |
308 | $status = $z->nextStream() |
642e522c |
309 | $data = $z->getHeaderInfo() |
310 | $z->tell() |
311 | $z->seek($position, $whence) |
312 | $z->binmode() |
313 | $z->fileno() |
314 | $z->eof() |
315 | $z->close() |
316 | |
317 | $GunzipError ; |
318 | |
319 | # IO::File mode |
320 | |
321 | <$z> |
322 | read($z, $buffer); |
323 | read($z, $buffer, $length); |
324 | read($z, $buffer, $length, $offset); |
325 | tell($z) |
326 | seek($z, $position, $whence) |
327 | binmode($z) |
328 | fileno($z) |
329 | eof($z) |
330 | close($z) |
331 | |
332 | |
333 | =head1 DESCRIPTION |
334 | |
335 | |
336 | |
1a6a8453 |
337 | This module provides a Perl interface that allows the reading of |
642e522c |
338 | files/buffers that conform to RFC 1952. |
339 | |
1a6a8453 |
340 | For writing RFC 1952 files/buffers, see the companion module IO::Compress::Gzip. |
642e522c |
341 | |
342 | |
343 | |
cb7abd7f |
344 | |
345 | |
642e522c |
346 | =head1 Functional Interface |
347 | |
1a6a8453 |
348 | A top-level function, C<gunzip>, is provided to carry out |
349 | "one-shot" uncompression between buffers and/or files. For finer |
350 | control over the uncompression process, see the L</"OO Interface"> |
351 | section. |
642e522c |
352 | |
353 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
354 | |
355 | gunzip $input => $output [,OPTS] |
356 | or die "gunzip failed: $GunzipError\n"; |
357 | |
1a6a8453 |
358 | |
642e522c |
359 | |
360 | The functional interface needs Perl5.005 or better. |
361 | |
362 | |
363 | =head2 gunzip $input => $output [, OPTS] |
364 | |
1a6a8453 |
365 | |
366 | C<gunzip> expects at least two parameters, C<$input> and C<$output>. |
642e522c |
367 | |
368 | =head3 The C<$input> parameter |
369 | |
370 | The parameter, C<$input>, is used to define the source of |
371 | the compressed data. |
372 | |
373 | It can take one of the following forms: |
374 | |
375 | =over 5 |
376 | |
377 | =item A filename |
378 | |
379 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
380 | filename. This file will be opened for reading and the input data |
381 | will be read from it. |
382 | |
383 | =item A filehandle |
384 | |
385 | If the C<$input> parameter is a filehandle, the input data will be |
386 | read from it. |
387 | The string '-' can be used as an alias for standard input. |
388 | |
389 | =item A scalar reference |
390 | |
391 | If C<$input> is a scalar reference, the input data will be read |
392 | from C<$$input>. |
393 | |
394 | =item An array reference |
395 | |
1a6a8453 |
396 | If C<$input> is an array reference, each element in the array must be a |
397 | filename. |
398 | |
399 | The input data will be read from each file in turn. |
400 | |
642e522c |
401 | The complete array will be walked to ensure that it only |
1a6a8453 |
402 | contains valid filenames before any data is uncompressed. |
403 | |
404 | |
642e522c |
405 | |
406 | =item An Input FileGlob string |
407 | |
408 | If C<$input> is a string that is delimited by the characters "<" and ">" |
409 | C<gunzip> will assume that it is an I<input fileglob string>. The |
410 | input is the list of files that match the fileglob. |
411 | |
412 | If the fileglob does not match any files ... |
413 | |
414 | See L<File::GlobMapper|File::GlobMapper> for more details. |
415 | |
416 | |
417 | =back |
418 | |
419 | If the C<$input> parameter is any other type, C<undef> will be returned. |
420 | |
421 | |
422 | |
423 | =head3 The C<$output> parameter |
424 | |
425 | The parameter C<$output> is used to control the destination of the |
426 | uncompressed data. This parameter can take one of these forms. |
427 | |
428 | =over 5 |
429 | |
430 | =item A filename |
431 | |
1a6a8453 |
432 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
433 | filename. This file will be opened for writing and the uncompressed |
434 | data will be written to it. |
642e522c |
435 | |
436 | =item A filehandle |
437 | |
1a6a8453 |
438 | If the C<$output> parameter is a filehandle, the uncompressed data |
439 | will be written to it. |
642e522c |
440 | The string '-' can be used as an alias for standard output. |
441 | |
442 | |
443 | =item A scalar reference |
444 | |
1a6a8453 |
445 | If C<$output> is a scalar reference, the uncompressed data will be |
446 | stored in C<$$output>. |
642e522c |
447 | |
448 | |
642e522c |
449 | |
450 | =item An Array Reference |
451 | |
1a6a8453 |
452 | If C<$output> is an array reference, the uncompressed data will be |
453 | pushed onto the array. |
642e522c |
454 | |
455 | =item An Output FileGlob |
456 | |
457 | If C<$output> is a string that is delimited by the characters "<" and ">" |
458 | C<gunzip> will assume that it is an I<output fileglob string>. The |
459 | output is the list of files that match the fileglob. |
460 | |
461 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
462 | string. Anything else is an error. |
463 | |
464 | =back |
465 | |
466 | If the C<$output> parameter is any other type, C<undef> will be returned. |
467 | |
642e522c |
468 | |
642e522c |
469 | |
470 | =head2 Notes |
471 | |
c70c1701 |
472 | |
473 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
474 | a single file/buffer, after uncompression C<$output> will contain a |
475 | concatenation of all the uncompressed data from each of the input |
476 | files/buffers. |
477 | |
478 | |
642e522c |
479 | |
480 | |
481 | |
482 | =head2 Optional Parameters |
483 | |
484 | Unless specified below, the optional parameters for C<gunzip>, |
485 | C<OPTS>, are the same as those used with the OO interface defined in the |
486 | L</"Constructor Options"> section below. |
487 | |
488 | =over 5 |
489 | |
e7d45986 |
490 | =item C<< AutoClose => 0|1 >> |
642e522c |
491 | |
1a6a8453 |
492 | This option applies to any input or output data streams to |
493 | C<gunzip> that are filehandles. |
642e522c |
494 | |
495 | If C<AutoClose> is specified, and the value is true, it will result in all |
496 | input and/or output filehandles being closed once C<gunzip> has |
497 | completed. |
498 | |
499 | This parameter defaults to 0. |
500 | |
501 | |
e7d45986 |
502 | =item C<< BinModeOut => 0|1 >> |
1a6a8453 |
503 | |
504 | When writing to a file or filehandle, set C<binmode> before writing to the |
505 | file. |
506 | |
507 | Defaults to 0. |
508 | |
509 | |
510 | |
511 | |
512 | |
e7d45986 |
513 | =item C<< Append => 0|1 >> |
642e522c |
514 | |
515 | TODO |
516 | |
e7d45986 |
517 | =item C<< MultiStream => 0|1 >> |
1a6a8453 |
518 | |
258133d1 |
519 | |
e7d45986 |
520 | If the input file/buffer contains multiple compressed data streams, this |
521 | option will uncompress the whole lot as a single data stream. |
1a6a8453 |
522 | |
e7d45986 |
523 | Defaults to 0. |
1a6a8453 |
524 | |
642e522c |
525 | |
526 | |
258133d1 |
527 | |
528 | |
529 | =item C<< TrailingData => $scalar >> |
530 | |
531 | Returns the data, if any, that is present immediately after the compressed |
532 | data stream once uncompression is complete. |
533 | |
534 | This option can be used when there is useful information immediately |
535 | following the compressed data stream, and you don't know the length of the |
536 | compressed data stream. |
537 | |
538 | If the input is a buffer, C<trailingData> will return everything from the |
539 | end of the compressed data stream to the end of the buffer. |
540 | |
541 | If the input is a filehandle, C<trailingData> will return the data that is |
542 | left in the filehandle input buffer once the end of the compressed data |
543 | stream has been reached. You can then use the filehandle to read the rest |
544 | of the input file. |
545 | |
546 | Don't bother using C<trailingData> if the input is a filename. |
547 | |
548 | |
549 | |
550 | If you know the length of the compressed data stream before you start |
551 | uncompressing, you can avoid having to use C<trailingData> by setting the |
552 | C<InputLength> option. |
553 | |
554 | |
555 | |
642e522c |
556 | =back |
557 | |
558 | |
559 | |
560 | |
561 | =head2 Examples |
562 | |
563 | To read the contents of the file C<file1.txt.gz> and write the |
564 | compressed data to the file C<file1.txt>. |
565 | |
566 | use strict ; |
567 | use warnings ; |
568 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
569 | |
570 | my $input = "file1.txt.gz"; |
571 | my $output = "file1.txt"; |
572 | gunzip $input => $output |
573 | or die "gunzip failed: $GunzipError\n"; |
574 | |
575 | |
576 | To read from an existing Perl filehandle, C<$input>, and write the |
577 | uncompressed data to a buffer, C<$buffer>. |
578 | |
579 | use strict ; |
580 | use warnings ; |
581 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
582 | use IO::File ; |
583 | |
584 | my $input = new IO::File "<file1.txt.gz" |
585 | or die "Cannot open 'file1.txt.gz': $!\n" ; |
586 | my $buffer ; |
587 | gunzip $input => \$buffer |
588 | or die "gunzip failed: $GunzipError\n"; |
589 | |
590 | To uncompress all files in the directory "/my/home" that match "*.txt.gz" and store the compressed data in the same directory |
591 | |
592 | use strict ; |
593 | use warnings ; |
594 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
595 | |
596 | gunzip '</my/home/*.txt.gz>' => '</my/home/#1.txt>' |
597 | or die "gunzip failed: $GunzipError\n"; |
598 | |
599 | and if you want to compress each file one at a time, this will do the trick |
600 | |
601 | use strict ; |
602 | use warnings ; |
603 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
604 | |
605 | for my $input ( glob "/my/home/*.txt.gz" ) |
606 | { |
607 | my $output = $input; |
608 | $output =~ s/.gz// ; |
609 | gunzip $input => $output |
610 | or die "Error compressing '$input': $GunzipError\n"; |
611 | } |
612 | |
613 | =head1 OO Interface |
614 | |
615 | =head2 Constructor |
616 | |
617 | The format of the constructor for IO::Uncompress::Gunzip is shown below |
618 | |
619 | |
620 | my $z = new IO::Uncompress::Gunzip $input [OPTS] |
621 | or die "IO::Uncompress::Gunzip failed: $GunzipError\n"; |
622 | |
623 | Returns an C<IO::Uncompress::Gunzip> object on success and undef on failure. |
624 | The variable C<$GunzipError> will contain an error message on failure. |
625 | |
1a6a8453 |
626 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
627 | IO::Uncompress::Gunzip can be used exactly like an L<IO::File|IO::File> filehandle. |
628 | This means that all normal input file operations can be carried out with |
629 | C<$z>. For example, to read a line from a compressed file/buffer you can |
630 | use either of these forms |
642e522c |
631 | |
632 | $line = $z->getline(); |
633 | $line = <$z>; |
634 | |
635 | The mandatory parameter C<$input> is used to determine the source of the |
636 | compressed data. This parameter can take one of three forms. |
637 | |
638 | =over 5 |
639 | |
640 | =item A filename |
641 | |
642 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
643 | file will be opened for reading and the compressed data will be read from it. |
644 | |
645 | =item A filehandle |
646 | |
647 | If the C<$input> parameter is a filehandle, the compressed data will be |
648 | read from it. |
649 | The string '-' can be used as an alias for standard input. |
650 | |
651 | |
652 | =item A scalar reference |
653 | |
654 | If C<$input> is a scalar reference, the compressed data will be read from |
655 | C<$$output>. |
656 | |
657 | =back |
658 | |
659 | =head2 Constructor Options |
660 | |
661 | |
662 | The option names defined below are case insensitive and can be optionally |
663 | prefixed by a '-'. So all of the following are valid |
664 | |
665 | -AutoClose |
666 | -autoclose |
667 | AUTOCLOSE |
668 | autoclose |
669 | |
670 | OPTS is a combination of the following options: |
671 | |
672 | =over 5 |
673 | |
e7d45986 |
674 | =item C<< AutoClose => 0|1 >> |
642e522c |
675 | |
676 | This option is only valid when the C<$input> parameter is a filehandle. If |
677 | specified, and the value is true, it will result in the file being closed once |
678 | either the C<close> method is called or the IO::Uncompress::Gunzip object is |
679 | destroyed. |
680 | |
681 | This parameter defaults to 0. |
682 | |
e7d45986 |
683 | =item C<< MultiStream => 0|1 >> |
642e522c |
684 | |
685 | |
686 | |
687 | Allows multiple concatenated compressed streams to be treated as a single |
688 | compressed stream. Decompression will stop once either the end of the |
689 | file/buffer is reached, an error is encountered (premature eof, corrupt |
690 | compressed data) or the end of a stream is not immediately followed by the |
691 | start of another stream. |
692 | |
693 | This parameter defaults to 0. |
694 | |
695 | |
e7d45986 |
696 | =item C<< Prime => $string >> |
642e522c |
697 | |
698 | This option will uncompress the contents of C<$string> before processing the |
699 | input file/buffer. |
700 | |
701 | This option can be useful when the compressed data is embedded in another |
702 | file/data structure and it is not possible to work out where the compressed |
1a6a8453 |
703 | data begins without having to read the first few bytes. If this is the |
704 | case, the uncompression can be I<primed> with these bytes using this |
705 | option. |
642e522c |
706 | |
e7d45986 |
707 | =item C<< Transparent => 0|1 >> |
642e522c |
708 | |
f6fd7794 |
709 | If this option is set and the input file/buffer is not compressed data, |
642e522c |
710 | the module will allow reading of it anyway. |
711 | |
f6fd7794 |
712 | In addition, if the input file/buffer does contain compressed data and |
713 | there is non-compressed data immediately following it, setting this option |
714 | will make this module treat the whole file/bufffer as a single data stream. |
715 | |
642e522c |
716 | This option defaults to 1. |
717 | |
e7d45986 |
718 | =item C<< BlockSize => $num >> |
642e522c |
719 | |
1a6a8453 |
720 | When reading the compressed input data, IO::Uncompress::Gunzip will read it in |
721 | blocks of C<$num> bytes. |
642e522c |
722 | |
723 | This option defaults to 4096. |
724 | |
e7d45986 |
725 | =item C<< InputLength => $size >> |
642e522c |
726 | |
1a6a8453 |
727 | When present this option will limit the number of compressed bytes read |
728 | from the input file/buffer to C<$size>. This option can be used in the |
729 | situation where there is useful data directly after the compressed data |
730 | stream and you know beforehand the exact length of the compressed data |
731 | stream. |
642e522c |
732 | |
1a6a8453 |
733 | This option is mostly used when reading from a filehandle, in which case |
734 | the file pointer will be left pointing to the first byte directly after the |
642e522c |
735 | compressed data stream. |
736 | |
737 | |
738 | |
739 | This option defaults to off. |
740 | |
e7d45986 |
741 | =item C<< Append => 0|1 >> |
642e522c |
742 | |
743 | This option controls what the C<read> method does with uncompressed data. |
744 | |
1a6a8453 |
745 | If set to 1, all uncompressed data will be appended to the output parameter |
746 | of the C<read> method. |
642e522c |
747 | |
1a6a8453 |
748 | If set to 0, the contents of the output parameter of the C<read> method |
749 | will be overwritten by the uncompressed data. |
642e522c |
750 | |
751 | Defaults to 0. |
752 | |
e7d45986 |
753 | =item C<< Strict => 0|1 >> |
642e522c |
754 | |
755 | |
756 | |
757 | This option controls whether the extra checks defined below are used when |
1a6a8453 |
758 | carrying out the decompression. When Strict is on, the extra tests are |
759 | carried out, when Strict is off they are not. |
642e522c |
760 | |
761 | The default for this option is off. |
762 | |
763 | |
764 | |
765 | |
766 | |
767 | |
768 | |
769 | |
770 | |
771 | =over 5 |
772 | |
773 | =item 1 |
774 | |
775 | If the FHCRC bit is set in the gzip FLG header byte, the CRC16 bytes in the |
776 | header must match the crc16 value of the gzip header actually read. |
777 | |
778 | =item 2 |
779 | |
780 | If the gzip header contains a name field (FNAME) it consists solely of ISO |
781 | 8859-1 characters. |
782 | |
783 | =item 3 |
784 | |
1a6a8453 |
785 | If the gzip header contains a comment field (FCOMMENT) it consists solely |
786 | of ISO 8859-1 characters plus line-feed. |
642e522c |
787 | |
788 | =item 4 |
789 | |
790 | If the gzip FEXTRA header field is present it must conform to the sub-field |
a02d0f6f |
791 | structure as defined in RFC 1952. |
642e522c |
792 | |
793 | =item 5 |
794 | |
795 | The CRC32 and ISIZE trailer fields must be present. |
796 | |
797 | =item 6 |
798 | |
799 | The value of the CRC32 field read must match the crc32 value of the |
800 | uncompressed data actually contained in the gzip file. |
801 | |
802 | =item 7 |
803 | |
1a6a8453 |
804 | The value of the ISIZE fields read must match the length of the |
805 | uncompressed data actually read from the file. |
642e522c |
806 | |
807 | =back |
808 | |
809 | |
810 | |
811 | |
812 | |
813 | |
642e522c |
814 | |
258133d1 |
815 | =item C<< ParseExtra => 0|1 >> |
642e522c |
816 | If the gzip FEXTRA header field is present and this option is set, it will |
817 | force the module to check that it conforms to the sub-field structure as |
a02d0f6f |
818 | defined in RFC 1952. |
642e522c |
819 | |
820 | If the C<Strict> is on it will automatically enable this option. |
821 | |
822 | Defaults to 0. |
823 | |
824 | |
825 | |
a02d0f6f |
826 | |
642e522c |
827 | =back |
828 | |
829 | =head2 Examples |
830 | |
831 | TODO |
832 | |
833 | =head1 Methods |
834 | |
835 | =head2 read |
836 | |
837 | Usage is |
838 | |
839 | $status = $z->read($buffer) |
840 | |
841 | Reads a block of compressed data (the size the the compressed block is |
842 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1a6a8453 |
843 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
844 | set in the constructor, the uncompressed data will be appended to the |
845 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
642e522c |
846 | |
1a6a8453 |
847 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
848 | or a negative number on error. |
642e522c |
849 | |
850 | =head2 read |
851 | |
852 | Usage is |
853 | |
854 | $status = $z->read($buffer, $length) |
855 | $status = $z->read($buffer, $length, $offset) |
856 | |
857 | $status = read($z, $buffer, $length) |
858 | $status = read($z, $buffer, $length, $offset) |
859 | |
860 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
861 | |
1a6a8453 |
862 | The main difference between this form of the C<read> method and the |
863 | previous one, is that this one will attempt to return I<exactly> C<$length> |
864 | bytes. The only circumstances that this function will not is if end-of-file |
865 | or an IO error is encountered. |
642e522c |
866 | |
1a6a8453 |
867 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
868 | or a negative number on error. |
642e522c |
869 | |
870 | |
871 | =head2 getline |
872 | |
873 | Usage is |
874 | |
875 | $line = $z->getline() |
876 | $line = <$z> |
877 | |
878 | Reads a single line. |
879 | |
258133d1 |
880 | This method fully supports the use of of the variable C<$/> (or |
881 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
882 | determine what constitutes an end of line. Paragraph mode, record mode and |
883 | file slurp mode are all supported. |
642e522c |
884 | |
885 | |
886 | =head2 getc |
887 | |
888 | Usage is |
889 | |
890 | $char = $z->getc() |
891 | |
892 | Read a single character. |
893 | |
894 | =head2 ungetc |
895 | |
896 | Usage is |
897 | |
898 | $char = $z->ungetc($string) |
899 | |
900 | |
a02d0f6f |
901 | |
642e522c |
902 | =head2 inflateSync |
903 | |
904 | Usage is |
905 | |
906 | $status = $z->inflateSync() |
907 | |
908 | TODO |
909 | |
a02d0f6f |
910 | |
642e522c |
911 | =head2 getHeaderInfo |
912 | |
913 | Usage is |
914 | |
1a6a8453 |
915 | $hdr = $z->getHeaderInfo(); |
916 | @hdrs = $z->getHeaderInfo(); |
642e522c |
917 | |
1a6a8453 |
918 | This method returns either a hash reference (in scalar context) or a list |
919 | or hash references (in array context) that contains information about each |
920 | of the header fields in the compressed data stream(s). |
642e522c |
921 | |
922 | |
923 | |
1a6a8453 |
924 | =over 5 |
642e522c |
925 | |
1a6a8453 |
926 | =item Name |
642e522c |
927 | |
1a6a8453 |
928 | The contents of the Name header field, if present. If no name is |
929 | present, the value will be undef. Note this is different from a zero length |
930 | name, which will return an empty string. |
642e522c |
931 | |
932 | =item Comment |
933 | |
1a6a8453 |
934 | The contents of the Comment header field, if present. If no comment is |
935 | present, the value will be undef. Note this is different from a zero length |
936 | comment, which will return an empty string. |
642e522c |
937 | |
938 | =back |
939 | |
940 | |
941 | |
942 | |
943 | =head2 tell |
944 | |
945 | Usage is |
946 | |
947 | $z->tell() |
948 | tell $z |
949 | |
950 | Returns the uncompressed file offset. |
951 | |
952 | =head2 eof |
953 | |
954 | Usage is |
955 | |
956 | $z->eof(); |
957 | eof($z); |
958 | |
959 | |
960 | |
961 | Returns true if the end of the compressed input stream has been reached. |
962 | |
963 | |
964 | |
965 | =head2 seek |
966 | |
967 | $z->seek($position, $whence); |
968 | seek($z, $position, $whence); |
969 | |
970 | |
971 | |
972 | |
973 | Provides a sub-set of the C<seek> functionality, with the restriction |
974 | that it is only legal to seek forward in the input file/buffer. |
975 | It is a fatal error to attempt to seek backward. |
976 | |
977 | |
978 | |
979 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
980 | SEEK_CUR or SEEK_END. |
981 | |
982 | Returns 1 on success, 0 on failure. |
983 | |
984 | =head2 binmode |
985 | |
986 | Usage is |
987 | |
988 | $z->binmode |
989 | binmode $z ; |
990 | |
991 | This is a noop provided for completeness. |
992 | |
a02d0f6f |
993 | =head2 opened |
994 | |
995 | $z->opened() |
996 | |
997 | Returns true if the object currently refers to a opened file/buffer. |
998 | |
999 | =head2 autoflush |
1000 | |
1001 | my $prev = $z->autoflush() |
1002 | my $prev = $z->autoflush(EXPR) |
1003 | |
1004 | If the C<$z> object is associated with a file or a filehandle, this method |
1005 | returns the current autoflush setting for the underlying filehandle. If |
1006 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
1007 | write/print operation. |
1008 | |
1009 | If C<$z> is associated with a buffer, this method has no effect and always |
1010 | returns C<undef>. |
1011 | |
1012 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
1013 | retrieve the autoflush setting. |
1014 | |
1015 | =head2 input_line_number |
1016 | |
1017 | $z->input_line_number() |
1018 | $z->input_line_number(EXPR) |
1019 | |
1020 | |
1021 | |
1022 | Returns the current uncompressed line number. If C<EXPR> is present it has |
1023 | the effect of setting the line number. Note that setting the line number |
1024 | does not change the current position within the file/buffer being read. |
1025 | |
1026 | The contents of C<$/> are used to to determine what constitutes a line |
1027 | terminator. |
1028 | |
1029 | |
1030 | |
642e522c |
1031 | =head2 fileno |
1032 | |
1033 | $z->fileno() |
1034 | fileno($z) |
1035 | |
a02d0f6f |
1036 | If the C<$z> object is associated with a file or a filehandle, this method |
1037 | will return the underlying file descriptor. |
642e522c |
1038 | |
1039 | If the C<$z> object is is associated with a buffer, this method will |
1040 | return undef. |
1041 | |
1042 | =head2 close |
1043 | |
1044 | $z->close() ; |
1045 | close $z ; |
1046 | |
1047 | |
1048 | |
1049 | Closes the output file/buffer. |
1050 | |
1051 | |
1052 | |
1053 | For most versions of Perl this method will be automatically invoked if |
1054 | the IO::Uncompress::Gunzip object is destroyed (either explicitly or by the |
1055 | variable with the reference to the object going out of scope). The |
1056 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
1057 | these cases, the C<close> method will be called automatically, but |
1058 | not until global destruction of all live objects when the program is |
1059 | terminating. |
1060 | |
1061 | Therefore, if you want your scripts to be able to run on all versions |
1062 | of Perl, you should call C<close> explicitly and not rely on automatic |
1063 | closing. |
1064 | |
1065 | Returns true on success, otherwise 0. |
1066 | |
1067 | If the C<AutoClose> option has been enabled when the IO::Uncompress::Gunzip |
1068 | object was created, and the object is associated with a file, the |
1069 | underlying file will also be closed. |
1070 | |
1071 | |
1072 | |
1073 | |
e7d45986 |
1074 | =head2 nextStream |
1075 | |
1076 | Usage is |
1077 | |
1078 | my $status = $z->nextStream(); |
1079 | |
1080 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
1081 | compressed data stream is found, the eof marker will be cleared and C<$.> |
1082 | will be reset to 0. |
e7d45986 |
1083 | |
1084 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
1085 | error was encountered. |
1086 | |
1087 | =head2 trailingData |
1088 | |
1089 | Usage is |
1090 | |
1091 | my $data = $z->trailingData(); |
1092 | |
258133d1 |
1093 | Returns the data, if any, that is present immediately after the compressed |
1094 | data stream once uncompression is complete. It only makes sense to call |
1095 | this method once the end of the compressed data stream has been |
1096 | encountered. |
1097 | |
1098 | This option can be used when there is useful information immediately |
1099 | following the compressed data stream, and you don't know the length of the |
1100 | compressed data stream. |
1101 | |
1102 | If the input is a buffer, C<trailingData> will return everything from the |
1103 | end of the compressed data stream to the end of the buffer. |
1104 | |
1105 | If the input is a filehandle, C<trailingData> will return the data that is |
1106 | left in the filehandle input buffer once the end of the compressed data |
1107 | stream has been reached. You can then use the filehandle to read the rest |
1108 | of the input file. |
1109 | |
1110 | Don't bother using C<trailingData> if the input is a filename. |
1111 | |
1112 | |
1113 | |
1114 | If you know the length of the compressed data stream before you start |
1115 | uncompressing, you can avoid having to use C<trailingData> by setting the |
1116 | C<InputLength> option in the constructor. |
e7d45986 |
1117 | |
642e522c |
1118 | =head1 Importing |
1119 | |
1120 | No symbolic constants are required by this IO::Uncompress::Gunzip at present. |
1121 | |
1122 | =over 5 |
1123 | |
1124 | =item :all |
1125 | |
1126 | Imports C<gunzip> and C<$GunzipError>. |
1127 | Same as doing this |
1128 | |
1129 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
1130 | |
1131 | =back |
1132 | |
1133 | =head1 EXAMPLES |
1134 | |
1135 | |
1136 | |
1137 | |
1138 | =head1 SEE ALSO |
1139 | |
258133d1 |
1140 | L<Compress::Zlib>, L<IO::Compress::Gzip>, L<IO::Compress::Deflate>, L<IO::Uncompress::Inflate>, L<IO::Compress::RawDeflate>, L<IO::Uncompress::RawInflate>, L<IO::Compress::Bzip2>, L<IO::Uncompress::Bunzip2>, L<IO::Compress::Lzop>, L<IO::Uncompress::UnLzop>, L<IO::Compress::Lzf>, L<IO::Uncompress::UnLzf>, L<IO::Uncompress::AnyInflate>, L<IO::Uncompress::AnyUncompress> |
642e522c |
1141 | |
1142 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
1143 | |
a02d0f6f |
1144 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1145 | L<Archive::Tar|Archive::Tar>, |
642e522c |
1146 | L<IO::Zlib|IO::Zlib> |
1147 | |
a02d0f6f |
1148 | |
642e522c |
1149 | For RFC 1950, 1951 and 1952 see |
1150 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
1151 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
1152 | F<http://www.faqs.org/rfcs/rfc1952.html> |
1153 | |
a02d0f6f |
1154 | The I<zlib> compression library was written by Jean-loup Gailly |
1155 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
1156 | |
1157 | The primary site for the I<zlib> compression library is |
1158 | F<http://www.zlib.org>. |
1159 | |
1160 | The primary site for gzip is F<http://www.gzip.org>. |
1161 | |
1162 | |
1163 | |
1164 | |
642e522c |
1165 | =head1 AUTHOR |
1166 | |
cb7abd7f |
1167 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
642e522c |
1168 | |
642e522c |
1169 | |
642e522c |
1170 | |
1171 | =head1 MODIFICATION HISTORY |
1172 | |
1173 | See the Changes file. |
1174 | |
1175 | =head1 COPYRIGHT AND LICENSE |
642e522c |
1176 | |
b0cda13f |
1177 | Copyright (c) 2005-2007 Paul Marquess. All rights reserved. |
a02d0f6f |
1178 | |
642e522c |
1179 | This program is free software; you can redistribute it and/or |
1180 | modify it under the same terms as Perl itself. |
1181 | |