Commit | Line | Data |
---|---|---|
642e522c RGS |
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 | |
1a6a8453 PM |
12 | use IO::Uncompress::RawInflate ; |
13 | ||
a02d0f6f RGS |
14 | use Compress::Raw::Zlib qw( crc32 ) ; |
15 | use IO::Compress::Base::Common qw(:Status createSelfTiedObject); | |
16 | use IO::Compress::Gzip::Constants; | |
c70c1701 | 17 | use IO::Compress::Zlib::Extra; |
1a6a8453 | 18 | |
642e522c RGS |
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 RGS |
26 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; |
27 | Exporter::export_ok_tags('all'); | |
28 | ||
642e522c RGS |
29 | $GunzipError = ''; |
30 | ||
e7d45986 | 31 | $VERSION = '2.000_13'; |
642e522c | 32 | |
1a6a8453 | 33 | sub new |
642e522c | 34 | { |
1a6a8453 PM |
35 | my $class = shift ; |
36 | $GunzipError = ''; | |
37 | my $obj = createSelfTiedObject($class, \$GunzipError); | |
642e522c | 38 | |
1a6a8453 | 39 | $obj->_create(undef, 0, @_); |
642e522c RGS |
40 | } |
41 | ||
1a6a8453 | 42 | sub gunzip |
642e522c | 43 | { |
1a6a8453 PM |
44 | my $obj = createSelfTiedObject(undef, \$GunzipError); |
45 | return $obj->_inf(@_) ; | |
642e522c RGS |
46 | } |
47 | ||
1a6a8453 | 48 | sub getExtraParams |
642e522c | 49 | { |
a02d0f6f | 50 | use IO::Compress::Base::Common qw(:Parse); |
1a6a8453 | 51 | return ( 'ParseExtra' => [1, 1, Parse_boolean, 0] ) ; |
642e522c RGS |
52 | } |
53 | ||
1a6a8453 | 54 | sub ckParams |
642e522c | 55 | { |
1a6a8453 PM |
56 | my $self = shift ; |
57 | my $got = shift ; | |
642e522c | 58 | |
1a6a8453 PM |
59 | # gunzip always needs crc32 |
60 | $got->value('CRC32' => 1); | |
642e522c | 61 | |
1a6a8453 | 62 | return 1; |
642e522c RGS |
63 | } |
64 | ||
1a6a8453 | 65 | sub ckMagic |
642e522c | 66 | { |
1a6a8453 | 67 | my $self = shift; |
642e522c | 68 | |
1a6a8453 PM |
69 | my $magic ; |
70 | $self->smartReadExact(\$magic, GZIP_ID_SIZE); | |
642e522c | 71 | |
1a6a8453 | 72 | *$self->{HeaderPending} = $magic ; |
642e522c | 73 | |
1a6a8453 PM |
74 | return $self->HeaderError("Minimum header size is " . |
75 | GZIP_MIN_HEADER_SIZE . " bytes") | |
76 | if length $magic != GZIP_ID_SIZE ; | |
642e522c | 77 | |
1a6a8453 PM |
78 | return $self->HeaderError("Bad Magic") |
79 | if ! isGzipMagic($magic) ; | |
642e522c | 80 | |
1a6a8453 | 81 | *$self->{Type} = 'rfc1952'; |
642e522c | 82 | |
1a6a8453 | 83 | return $magic ; |
642e522c RGS |
84 | } |
85 | ||
1a6a8453 | 86 | sub readHeader |
642e522c | 87 | { |
1a6a8453 PM |
88 | my $self = shift; |
89 | my $magic = shift; | |
642e522c | 90 | |
1a6a8453 | 91 | return $self->_readGzipHeader($magic); |
642e522c RGS |
92 | } |
93 | ||
1a6a8453 | 94 | sub chkTrailer |
642e522c | 95 | { |
1a6a8453 PM |
96 | my $self = shift; |
97 | my $trailer = shift; | |
642e522c | 98 | |
1a6a8453 PM |
99 | # Check CRC & ISIZE |
100 | my ($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 PM |
109 | return $self->TrailerError("ISIZE mismatch. Got $ISIZE" |
110 | . ", expected $exp_isize") | |
111 | if $ISIZE != $exp_isize ; | |
642e522c RGS |
112 | } |
113 | ||
a02d0f6f | 114 | return STATUS_OK; |
1a6a8453 | 115 | } |
642e522c | 116 | |
1a6a8453 PM |
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 && $id2 == GZIP_ID2 ; | |
642e522c RGS |
123 | } |
124 | ||
1a6a8453 | 125 | sub _readFullGzipHeader($) |
642e522c | 126 | { |
1a6a8453 PM |
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 PM |
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 PM |
139 | return $self->HeaderError("Bad Magic") |
140 | if ! isGzipMagic($magic) ; | |
642e522c | 141 | |
1a6a8453 PM |
142 | my $status = $self->_readGzipHeader($magic); |
143 | delete *$self->{Transparent} if ! defined $status ; | |
144 | return $status ; | |
642e522c RGS |
145 | } |
146 | ||
1a6a8453 | 147 | sub _readGzipHeader($) |
642e522c | 148 | { |
1a6a8453 PM |
149 | my ($self, $magic) = @_ ; |
150 | my ($HeaderCRC) ; | |
151 | my ($buffer) = '' ; | |
642e522c | 152 | |
1a6a8453 PM |
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 PM |
157 | my $keep = $magic . $buffer ; |
158 | *$self->{HeaderPending} = $keep ; | |
642e522c | 159 | |
1a6a8453 PM |
160 | # now split out the various parts |
161 | my ($cm, $flag, $mtime, $xfl, $os) = unpack("C C V C C", $buffer) ; | |
642e522c | 162 | |
1a6a8453 PM |
163 | $cm == GZIP_CM_DEFLATED |
164 | or return $self->HeaderError("Not Deflate (CM is $cm)") ; | |
642e522c | 165 | |
1a6a8453 PM |
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 PM |
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 $self->TruncatedHeader("FEXTRA Length") ; | |
642e522c | 176 | |
1a6a8453 PM |
177 | my ($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 PM |
183 | my $bad = IO::Compress::Zlib::Extra::parseRawExtra($EXTRA, |
184 | \@EXTRA, 1, 1); | |
185 | return $self->HeaderError($bad) | |
186 | if defined $bad; | |
1a6a8453 PM |
187 | } |
188 | } | |
642e522c | 189 | |
1a6a8453 PM |
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 PM |
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 PM |
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 PM |
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 PM |
220 | if ($flag & GZIP_FLG_FHCRC) { |
221 | $self->smartReadExact(\$buffer, GZIP_FHCRC_SIZE) | |
222 | or return $self->TruncatedHeader("FHCRC"); | |
642e522c | 223 | |
1a6a8453 PM |
224 | $HeaderCRC = unpack("v", $buffer) ; |
225 | my $crc16 = crc32($keep) & 0xFF ; | |
642e522c | 226 | |
1a6a8453 PM |
227 | return $self->HeaderError("CRC16 mismatch.") |
228 | if *$self->{Strict} && $crc16 != $HeaderCRC; | |
642e522c | 229 | |
1a6a8453 PM |
230 | $keep .= $buffer ; |
231 | } | |
642e522c | 232 | |
1a6a8453 PM |
233 | # Assume compression method is deflated for xfl tests |
234 | #if ($xfl) { | |
235 | #} | |
642e522c | 236 | |
1a6a8453 | 237 | *$self->{Type} = 'rfc1952'; |
642e522c | 238 | |
1a6a8453 PM |
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 PM |
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 PM |
267 | #'CompSize'=> $compsize, |
268 | #'CRC32'=> $CRC32, | |
269 | #'OrigSize'=> $ISIZE, | |
270 | } | |
642e522c RGS |
271 | } |
272 | ||
273 | ||
1a6a8453 | 274 | 1; |
642e522c | 275 | |
642e522c RGS |
276 | __END__ |
277 | ||
278 | ||
279 | =head1 NAME | |
280 | ||
a02d0f6f | 281 | |
cb7abd7f PM |
282 | |
283 | IO::Uncompress::Gunzip - Read RFC 1952 files/buffers | |
284 | ||
642e522c | 285 | |
a02d0f6f | 286 | |
642e522c RGS |
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 RGS |
303 | $char = $z->opened() |
304 | ||
642e522c | 305 | $status = $z->inflateSync() |
a02d0f6f | 306 | |
e7d45986 PM |
307 | $data = $z->trailingData() |
308 | $status = $z->nextStream() | |
642e522c RGS |
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 | ||
337 | B<WARNING -- This is a Beta release>. | |
338 | ||
339 | =over 5 | |
340 | ||
341 | =item * DO NOT use in production code. | |
342 | ||
343 | =item * The documentation is incomplete in places. | |
344 | ||
345 | =item * Parts of the interface defined here are tentative. | |
346 | ||
347 | =item * Please report any problems you find. | |
348 | ||
349 | =back | |
350 | ||
351 | ||
352 | ||
353 | ||
354 | ||
1a6a8453 | 355 | This module provides a Perl interface that allows the reading of |
642e522c RGS |
356 | files/buffers that conform to RFC 1952. |
357 | ||
1a6a8453 | 358 | For writing RFC 1952 files/buffers, see the companion module IO::Compress::Gzip. |
642e522c RGS |
359 | |
360 | ||
361 | ||
cb7abd7f PM |
362 | |
363 | ||
364 | ||
642e522c RGS |
365 | =head1 Functional Interface |
366 | ||
1a6a8453 PM |
367 | A top-level function, C<gunzip>, is provided to carry out |
368 | "one-shot" uncompression between buffers and/or files. For finer | |
369 | control over the uncompression process, see the L</"OO Interface"> | |
370 | section. | |
642e522c RGS |
371 | |
372 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; | |
373 | ||
374 | gunzip $input => $output [,OPTS] | |
375 | or die "gunzip failed: $GunzipError\n"; | |
376 | ||
1a6a8453 | 377 | |
642e522c RGS |
378 | |
379 | The functional interface needs Perl5.005 or better. | |
380 | ||
381 | ||
382 | =head2 gunzip $input => $output [, OPTS] | |
383 | ||
1a6a8453 PM |
384 | |
385 | C<gunzip> expects at least two parameters, C<$input> and C<$output>. | |
642e522c RGS |
386 | |
387 | =head3 The C<$input> parameter | |
388 | ||
389 | The parameter, C<$input>, is used to define the source of | |
390 | the compressed data. | |
391 | ||
392 | It can take one of the following forms: | |
393 | ||
394 | =over 5 | |
395 | ||
396 | =item A filename | |
397 | ||
398 | If the C<$input> parameter is a simple scalar, it is assumed to be a | |
399 | filename. This file will be opened for reading and the input data | |
400 | will be read from it. | |
401 | ||
402 | =item A filehandle | |
403 | ||
404 | If the C<$input> parameter is a filehandle, the input data will be | |
405 | read from it. | |
406 | The string '-' can be used as an alias for standard input. | |
407 | ||
408 | =item A scalar reference | |
409 | ||
410 | If C<$input> is a scalar reference, the input data will be read | |
411 | from C<$$input>. | |
412 | ||
413 | =item An array reference | |
414 | ||
1a6a8453 PM |
415 | If C<$input> is an array reference, each element in the array must be a |
416 | filename. | |
417 | ||
418 | The input data will be read from each file in turn. | |
419 | ||
642e522c | 420 | The complete array will be walked to ensure that it only |
1a6a8453 PM |
421 | contains valid filenames before any data is uncompressed. |
422 | ||
423 | ||
642e522c RGS |
424 | |
425 | =item An Input FileGlob string | |
426 | ||
427 | If C<$input> is a string that is delimited by the characters "<" and ">" | |
428 | C<gunzip> will assume that it is an I<input fileglob string>. The | |
429 | input is the list of files that match the fileglob. | |
430 | ||
431 | If the fileglob does not match any files ... | |
432 | ||
433 | See L<File::GlobMapper|File::GlobMapper> for more details. | |
434 | ||
435 | ||
436 | =back | |
437 | ||
438 | If the C<$input> parameter is any other type, C<undef> will be returned. | |
439 | ||
440 | ||
441 | ||
442 | =head3 The C<$output> parameter | |
443 | ||
444 | The parameter C<$output> is used to control the destination of the | |
445 | uncompressed data. This parameter can take one of these forms. | |
446 | ||
447 | =over 5 | |
448 | ||
449 | =item A filename | |
450 | ||
1a6a8453 PM |
451 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
452 | filename. This file will be opened for writing and the uncompressed | |
453 | data will be written to it. | |
642e522c RGS |
454 | |
455 | =item A filehandle | |
456 | ||
1a6a8453 PM |
457 | If the C<$output> parameter is a filehandle, the uncompressed data |
458 | will be written to it. | |
642e522c RGS |
459 | The string '-' can be used as an alias for standard output. |
460 | ||
461 | ||
462 | =item A scalar reference | |
463 | ||
1a6a8453 PM |
464 | If C<$output> is a scalar reference, the uncompressed data will be |
465 | stored in C<$$output>. | |
642e522c RGS |
466 | |
467 | ||
642e522c RGS |
468 | |
469 | =item An Array Reference | |
470 | ||
1a6a8453 PM |
471 | If C<$output> is an array reference, the uncompressed data will be |
472 | pushed onto the array. | |
642e522c RGS |
473 | |
474 | =item An Output FileGlob | |
475 | ||
476 | If C<$output> is a string that is delimited by the characters "<" and ">" | |
477 | C<gunzip> will assume that it is an I<output fileglob string>. The | |
478 | output is the list of files that match the fileglob. | |
479 | ||
480 | When C<$output> is an fileglob string, C<$input> must also be a fileglob | |
481 | string. Anything else is an error. | |
482 | ||
483 | =back | |
484 | ||
485 | If the C<$output> parameter is any other type, C<undef> will be returned. | |
486 | ||
642e522c | 487 | |
642e522c RGS |
488 | |
489 | =head2 Notes | |
490 | ||
c70c1701 PM |
491 | |
492 | When C<$input> maps to multiple compressed files/buffers and C<$output> is | |
493 | a single file/buffer, after uncompression C<$output> will contain a | |
494 | concatenation of all the uncompressed data from each of the input | |
495 | files/buffers. | |
496 | ||
497 | ||
642e522c RGS |
498 | |
499 | ||
500 | ||
501 | =head2 Optional Parameters | |
502 | ||
503 | Unless specified below, the optional parameters for C<gunzip>, | |
504 | C<OPTS>, are the same as those used with the OO interface defined in the | |
505 | L</"Constructor Options"> section below. | |
506 | ||
507 | =over 5 | |
508 | ||
e7d45986 | 509 | =item C<< AutoClose => 0|1 >> |
642e522c | 510 | |
1a6a8453 PM |
511 | This option applies to any input or output data streams to |
512 | C<gunzip> that are filehandles. | |
642e522c RGS |
513 | |
514 | If C<AutoClose> is specified, and the value is true, it will result in all | |
515 | input and/or output filehandles being closed once C<gunzip> has | |
516 | completed. | |
517 | ||
518 | This parameter defaults to 0. | |
519 | ||
520 | ||
e7d45986 | 521 | =item C<< BinModeOut => 0|1 >> |
1a6a8453 PM |
522 | |
523 | When writing to a file or filehandle, set C<binmode> before writing to the | |
524 | file. | |
525 | ||
526 | Defaults to 0. | |
527 | ||
528 | ||
529 | ||
530 | ||
531 | ||
e7d45986 | 532 | =item C<< Append => 0|1 >> |
642e522c RGS |
533 | |
534 | TODO | |
535 | ||
e7d45986 | 536 | =item C<< MultiStream => 0|1 >> |
1a6a8453 | 537 | |
e7d45986 PM |
538 | If the input file/buffer contains multiple compressed data streams, this |
539 | option will uncompress the whole lot as a single data stream. | |
1a6a8453 | 540 | |
e7d45986 | 541 | Defaults to 0. |
1a6a8453 | 542 | |
642e522c RGS |
543 | |
544 | ||
545 | =back | |
546 | ||
547 | ||
548 | ||
549 | ||
550 | =head2 Examples | |
551 | ||
552 | To read the contents of the file C<file1.txt.gz> and write the | |
553 | compressed data to the file C<file1.txt>. | |
554 | ||
555 | use strict ; | |
556 | use warnings ; | |
557 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; | |
558 | ||
559 | my $input = "file1.txt.gz"; | |
560 | my $output = "file1.txt"; | |
561 | gunzip $input => $output | |
562 | or die "gunzip failed: $GunzipError\n"; | |
563 | ||
564 | ||
565 | To read from an existing Perl filehandle, C<$input>, and write the | |
566 | uncompressed data to a buffer, C<$buffer>. | |
567 | ||
568 | use strict ; | |
569 | use warnings ; | |
570 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; | |
571 | use IO::File ; | |
572 | ||
573 | my $input = new IO::File "<file1.txt.gz" | |
574 | or die "Cannot open 'file1.txt.gz': $!\n" ; | |
575 | my $buffer ; | |
576 | gunzip $input => \$buffer | |
577 | or die "gunzip failed: $GunzipError\n"; | |
578 | ||
579 | To uncompress all files in the directory "/my/home" that match "*.txt.gz" and store the compressed data in the same directory | |
580 | ||
581 | use strict ; | |
582 | use warnings ; | |
583 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; | |
584 | ||
585 | gunzip '</my/home/*.txt.gz>' => '</my/home/#1.txt>' | |
586 | or die "gunzip failed: $GunzipError\n"; | |
587 | ||
588 | and if you want to compress each file one at a time, this will do the trick | |
589 | ||
590 | use strict ; | |
591 | use warnings ; | |
592 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; | |
593 | ||
594 | for my $input ( glob "/my/home/*.txt.gz" ) | |
595 | { | |
596 | my $output = $input; | |
597 | $output =~ s/.gz// ; | |
598 | gunzip $input => $output | |
599 | or die "Error compressing '$input': $GunzipError\n"; | |
600 | } | |
601 | ||
602 | =head1 OO Interface | |
603 | ||
604 | =head2 Constructor | |
605 | ||
606 | The format of the constructor for IO::Uncompress::Gunzip is shown below | |
607 | ||
608 | ||
609 | my $z = new IO::Uncompress::Gunzip $input [OPTS] | |
610 | or die "IO::Uncompress::Gunzip failed: $GunzipError\n"; | |
611 | ||
612 | Returns an C<IO::Uncompress::Gunzip> object on success and undef on failure. | |
613 | The variable C<$GunzipError> will contain an error message on failure. | |
614 | ||
1a6a8453 PM |
615 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
616 | IO::Uncompress::Gunzip can be used exactly like an L<IO::File|IO::File> filehandle. | |
617 | This means that all normal input file operations can be carried out with | |
618 | C<$z>. For example, to read a line from a compressed file/buffer you can | |
619 | use either of these forms | |
642e522c RGS |
620 | |
621 | $line = $z->getline(); | |
622 | $line = <$z>; | |
623 | ||
624 | The mandatory parameter C<$input> is used to determine the source of the | |
625 | compressed data. This parameter can take one of three forms. | |
626 | ||
627 | =over 5 | |
628 | ||
629 | =item A filename | |
630 | ||
631 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This | |
632 | file will be opened for reading and the compressed data will be read from it. | |
633 | ||
634 | =item A filehandle | |
635 | ||
636 | If the C<$input> parameter is a filehandle, the compressed data will be | |
637 | read from it. | |
638 | The string '-' can be used as an alias for standard input. | |
639 | ||
640 | ||
641 | =item A scalar reference | |
642 | ||
643 | If C<$input> is a scalar reference, the compressed data will be read from | |
644 | C<$$output>. | |
645 | ||
646 | =back | |
647 | ||
648 | =head2 Constructor Options | |
649 | ||
650 | ||
651 | The option names defined below are case insensitive and can be optionally | |
652 | prefixed by a '-'. So all of the following are valid | |
653 | ||
654 | -AutoClose | |
655 | -autoclose | |
656 | AUTOCLOSE | |
657 | autoclose | |
658 | ||
659 | OPTS is a combination of the following options: | |
660 | ||
661 | =over 5 | |
662 | ||
e7d45986 | 663 | =item C<< AutoClose => 0|1 >> |
642e522c RGS |
664 | |
665 | This option is only valid when the C<$input> parameter is a filehandle. If | |
666 | specified, and the value is true, it will result in the file being closed once | |
667 | either the C<close> method is called or the IO::Uncompress::Gunzip object is | |
668 | destroyed. | |
669 | ||
670 | This parameter defaults to 0. | |
671 | ||
e7d45986 | 672 | =item C<< MultiStream => 0|1 >> |
642e522c RGS |
673 | |
674 | ||
675 | ||
676 | Allows multiple concatenated compressed streams to be treated as a single | |
677 | compressed stream. Decompression will stop once either the end of the | |
678 | file/buffer is reached, an error is encountered (premature eof, corrupt | |
679 | compressed data) or the end of a stream is not immediately followed by the | |
680 | start of another stream. | |
681 | ||
682 | This parameter defaults to 0. | |
683 | ||
684 | ||
e7d45986 | 685 | =item C<< Prime => $string >> |
642e522c RGS |
686 | |
687 | This option will uncompress the contents of C<$string> before processing the | |
688 | input file/buffer. | |
689 | ||
690 | This option can be useful when the compressed data is embedded in another | |
691 | file/data structure and it is not possible to work out where the compressed | |
1a6a8453 PM |
692 | data begins without having to read the first few bytes. If this is the |
693 | case, the uncompression can be I<primed> with these bytes using this | |
694 | option. | |
642e522c | 695 | |
e7d45986 | 696 | =item C<< Transparent => 0|1 >> |
642e522c RGS |
697 | |
698 | If this option is set and the input file or buffer is not compressed data, | |
699 | the module will allow reading of it anyway. | |
700 | ||
701 | This option defaults to 1. | |
702 | ||
e7d45986 | 703 | =item C<< BlockSize => $num >> |
642e522c | 704 | |
1a6a8453 PM |
705 | When reading the compressed input data, IO::Uncompress::Gunzip will read it in |
706 | blocks of C<$num> bytes. | |
642e522c RGS |
707 | |
708 | This option defaults to 4096. | |
709 | ||
e7d45986 | 710 | =item C<< InputLength => $size >> |
642e522c | 711 | |
1a6a8453 PM |
712 | When present this option will limit the number of compressed bytes read |
713 | from the input file/buffer to C<$size>. This option can be used in the | |
714 | situation where there is useful data directly after the compressed data | |
715 | stream and you know beforehand the exact length of the compressed data | |
716 | stream. | |
642e522c | 717 | |
1a6a8453 PM |
718 | This option is mostly used when reading from a filehandle, in which case |
719 | the file pointer will be left pointing to the first byte directly after the | |
642e522c RGS |
720 | compressed data stream. |
721 | ||
722 | ||
723 | ||
724 | This option defaults to off. | |
725 | ||
e7d45986 | 726 | =item C<< Append => 0|1 >> |
642e522c RGS |
727 | |
728 | This option controls what the C<read> method does with uncompressed data. | |
729 | ||
1a6a8453 PM |
730 | If set to 1, all uncompressed data will be appended to the output parameter |
731 | of the C<read> method. | |
642e522c | 732 | |
1a6a8453 PM |
733 | If set to 0, the contents of the output parameter of the C<read> method |
734 | will be overwritten by the uncompressed data. | |
642e522c RGS |
735 | |
736 | Defaults to 0. | |
737 | ||
e7d45986 | 738 | =item C<< Strict => 0|1 >> |
642e522c RGS |
739 | |
740 | ||
741 | ||
742 | This option controls whether the extra checks defined below are used when | |
1a6a8453 PM |
743 | carrying out the decompression. When Strict is on, the extra tests are |
744 | carried out, when Strict is off they are not. | |
642e522c RGS |
745 | |
746 | The default for this option is off. | |
747 | ||
748 | ||
749 | ||
750 | ||
751 | ||
752 | ||
753 | ||
754 | ||
755 | ||
756 | =over 5 | |
757 | ||
758 | =item 1 | |
759 | ||
760 | If the FHCRC bit is set in the gzip FLG header byte, the CRC16 bytes in the | |
761 | header must match the crc16 value of the gzip header actually read. | |
762 | ||
763 | =item 2 | |
764 | ||
765 | If the gzip header contains a name field (FNAME) it consists solely of ISO | |
766 | 8859-1 characters. | |
767 | ||
768 | =item 3 | |
769 | ||
1a6a8453 PM |
770 | If the gzip header contains a comment field (FCOMMENT) it consists solely |
771 | of ISO 8859-1 characters plus line-feed. | |
642e522c RGS |
772 | |
773 | =item 4 | |
774 | ||
775 | If the gzip FEXTRA header field is present it must conform to the sub-field | |
a02d0f6f | 776 | structure as defined in RFC 1952. |
642e522c RGS |
777 | |
778 | =item 5 | |
779 | ||
780 | The CRC32 and ISIZE trailer fields must be present. | |
781 | ||
782 | =item 6 | |
783 | ||
784 | The value of the CRC32 field read must match the crc32 value of the | |
785 | uncompressed data actually contained in the gzip file. | |
786 | ||
787 | =item 7 | |
788 | ||
1a6a8453 PM |
789 | The value of the ISIZE fields read must match the length of the |
790 | uncompressed data actually read from the file. | |
642e522c RGS |
791 | |
792 | =back | |
793 | ||
794 | ||
795 | ||
796 | ||
797 | ||
798 | ||
e7d45986 | 799 | =item C<< ParseExtra => 0|1 >> |
642e522c RGS |
800 | |
801 | If the gzip FEXTRA header field is present and this option is set, it will | |
802 | force the module to check that it conforms to the sub-field structure as | |
a02d0f6f | 803 | defined in RFC 1952. |
642e522c RGS |
804 | |
805 | If the C<Strict> is on it will automatically enable this option. | |
806 | ||
807 | Defaults to 0. | |
808 | ||
809 | ||
810 | ||
a02d0f6f RGS |
811 | |
812 | ||
642e522c RGS |
813 | =back |
814 | ||
815 | =head2 Examples | |
816 | ||
817 | TODO | |
818 | ||
819 | =head1 Methods | |
820 | ||
821 | =head2 read | |
822 | ||
823 | Usage is | |
824 | ||
825 | $status = $z->read($buffer) | |
826 | ||
827 | Reads a block of compressed data (the size the the compressed block is | |
828 | determined by the C<Buffer> option in the constructor), uncompresses it and | |
1a6a8453 PM |
829 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
830 | set in the constructor, the uncompressed data will be appended to the | |
831 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. | |
642e522c | 832 | |
1a6a8453 PM |
833 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
834 | or a negative number on error. | |
642e522c RGS |
835 | |
836 | =head2 read | |
837 | ||
838 | Usage is | |
839 | ||
840 | $status = $z->read($buffer, $length) | |
841 | $status = $z->read($buffer, $length, $offset) | |
842 | ||
843 | $status = read($z, $buffer, $length) | |
844 | $status = read($z, $buffer, $length, $offset) | |
845 | ||
846 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. | |
847 | ||
1a6a8453 PM |
848 | The main difference between this form of the C<read> method and the |
849 | previous one, is that this one will attempt to return I<exactly> C<$length> | |
850 | bytes. The only circumstances that this function will not is if end-of-file | |
851 | or an IO error is encountered. | |
642e522c | 852 | |
1a6a8453 PM |
853 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
854 | or a negative number on error. | |
642e522c RGS |
855 | |
856 | ||
857 | =head2 getline | |
858 | ||
859 | Usage is | |
860 | ||
861 | $line = $z->getline() | |
862 | $line = <$z> | |
863 | ||
864 | Reads a single line. | |
865 | ||
866 | This method fully supports the use of of the variable C<$/> | |
867 | (or C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to | |
868 | determine what constitutes an end of line. Both paragraph mode and file | |
869 | slurp mode are supported. | |
870 | ||
871 | ||
872 | =head2 getc | |
873 | ||
874 | Usage is | |
875 | ||
876 | $char = $z->getc() | |
877 | ||
878 | Read a single character. | |
879 | ||
880 | =head2 ungetc | |
881 | ||
882 | Usage is | |
883 | ||
884 | $char = $z->ungetc($string) | |
885 | ||
886 | ||
a02d0f6f | 887 | |
642e522c RGS |
888 | =head2 inflateSync |
889 | ||
890 | Usage is | |
891 | ||
892 | $status = $z->inflateSync() | |
893 | ||
894 | TODO | |
895 | ||
a02d0f6f | 896 | |
642e522c RGS |
897 | =head2 getHeaderInfo |
898 | ||
899 | Usage is | |
900 | ||
1a6a8453 PM |
901 | $hdr = $z->getHeaderInfo(); |
902 | @hdrs = $z->getHeaderInfo(); | |
642e522c | 903 | |
1a6a8453 PM |
904 | This method returns either a hash reference (in scalar context) or a list |
905 | or hash references (in array context) that contains information about each | |
906 | of the header fields in the compressed data stream(s). | |
642e522c RGS |
907 | |
908 | ||
909 | ||
1a6a8453 | 910 | =over 5 |
642e522c | 911 | |
1a6a8453 | 912 | =item Name |
642e522c | 913 | |
1a6a8453 PM |
914 | The contents of the Name header field, if present. If no name is |
915 | present, the value will be undef. Note this is different from a zero length | |
916 | name, which will return an empty string. | |
642e522c RGS |
917 | |
918 | =item Comment | |
919 | ||
1a6a8453 PM |
920 | The contents of the Comment header field, if present. If no comment is |
921 | present, the value will be undef. Note this is different from a zero length | |
922 | comment, which will return an empty string. | |
642e522c RGS |
923 | |
924 | =back | |
925 | ||
926 | ||
927 | ||
928 | ||
929 | =head2 tell | |
930 | ||
931 | Usage is | |
932 | ||
933 | $z->tell() | |
934 | tell $z | |
935 | ||
936 | Returns the uncompressed file offset. | |
937 | ||
938 | =head2 eof | |
939 | ||
940 | Usage is | |
941 | ||
942 | $z->eof(); | |
943 | eof($z); | |
944 | ||
945 | ||
946 | ||
947 | Returns true if the end of the compressed input stream has been reached. | |
948 | ||
949 | ||
950 | ||
951 | =head2 seek | |
952 | ||
953 | $z->seek($position, $whence); | |
954 | seek($z, $position, $whence); | |
955 | ||
956 | ||
957 | ||
958 | ||
959 | Provides a sub-set of the C<seek> functionality, with the restriction | |
960 | that it is only legal to seek forward in the input file/buffer. | |
961 | It is a fatal error to attempt to seek backward. | |
962 | ||
963 | ||
964 | ||
965 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, | |
966 | SEEK_CUR or SEEK_END. | |
967 | ||
968 | Returns 1 on success, 0 on failure. | |
969 | ||
970 | =head2 binmode | |
971 | ||
972 | Usage is | |
973 | ||
974 | $z->binmode | |
975 | binmode $z ; | |
976 | ||
977 | This is a noop provided for completeness. | |
978 | ||
a02d0f6f RGS |
979 | =head2 opened |
980 | ||
981 | $z->opened() | |
982 | ||
983 | Returns true if the object currently refers to a opened file/buffer. | |
984 | ||
985 | =head2 autoflush | |
986 | ||
987 | my $prev = $z->autoflush() | |
988 | my $prev = $z->autoflush(EXPR) | |
989 | ||
990 | If the C<$z> object is associated with a file or a filehandle, this method | |
991 | returns the current autoflush setting for the underlying filehandle. If | |
992 | C<EXPR> is present, and is non-zero, it will enable flushing after every | |
993 | write/print operation. | |
994 | ||
995 | If C<$z> is associated with a buffer, this method has no effect and always | |
996 | returns C<undef>. | |
997 | ||
998 | B<Note> that the special variable C<$|> B<cannot> be used to set or | |
999 | retrieve the autoflush setting. | |
1000 | ||
1001 | =head2 input_line_number | |
1002 | ||
1003 | $z->input_line_number() | |
1004 | $z->input_line_number(EXPR) | |
1005 | ||
1006 | ||
1007 | ||
1008 | Returns the current uncompressed line number. If C<EXPR> is present it has | |
1009 | the effect of setting the line number. Note that setting the line number | |
1010 | does not change the current position within the file/buffer being read. | |
1011 | ||
1012 | The contents of C<$/> are used to to determine what constitutes a line | |
1013 | terminator. | |
1014 | ||
1015 | ||
1016 | ||
642e522c RGS |
1017 | =head2 fileno |
1018 | ||
1019 | $z->fileno() | |
1020 | fileno($z) | |
1021 | ||
a02d0f6f RGS |
1022 | If the C<$z> object is associated with a file or a filehandle, this method |
1023 | will return the underlying file descriptor. | |
642e522c RGS |
1024 | |
1025 | If the C<$z> object is is associated with a buffer, this method will | |
1026 | return undef. | |
1027 | ||
1028 | =head2 close | |
1029 | ||
1030 | $z->close() ; | |
1031 | close $z ; | |
1032 | ||
1033 | ||
1034 | ||
1035 | Closes the output file/buffer. | |
1036 | ||
1037 | ||
1038 | ||
1039 | For most versions of Perl this method will be automatically invoked if | |
1040 | the IO::Uncompress::Gunzip object is destroyed (either explicitly or by the | |
1041 | variable with the reference to the object going out of scope). The | |
1042 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In | |
1043 | these cases, the C<close> method will be called automatically, but | |
1044 | not until global destruction of all live objects when the program is | |
1045 | terminating. | |
1046 | ||
1047 | Therefore, if you want your scripts to be able to run on all versions | |
1048 | of Perl, you should call C<close> explicitly and not rely on automatic | |
1049 | closing. | |
1050 | ||
1051 | Returns true on success, otherwise 0. | |
1052 | ||
1053 | If the C<AutoClose> option has been enabled when the IO::Uncompress::Gunzip | |
1054 | object was created, and the object is associated with a file, the | |
1055 | underlying file will also be closed. | |
1056 | ||
1057 | ||
1058 | ||
1059 | ||
e7d45986 PM |
1060 | =head2 nextStream |
1061 | ||
1062 | Usage is | |
1063 | ||
1064 | my $status = $z->nextStream(); | |
1065 | ||
1066 | Skips to the next compressed data stream in the input file/buffer. If a new | |
1067 | compressed data stream is found, the eof marker will be cleared, C<$.> will | |
1068 | be reset to 0. | |
1069 | ||
1070 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an | |
1071 | error was encountered. | |
1072 | ||
1073 | =head2 trailingData | |
1074 | ||
1075 | Usage is | |
1076 | ||
1077 | my $data = $z->trailingData(); | |
1078 | ||
1079 | Returns any data that | |
1080 | ||
642e522c RGS |
1081 | =head1 Importing |
1082 | ||
1083 | No symbolic constants are required by this IO::Uncompress::Gunzip at present. | |
1084 | ||
1085 | =over 5 | |
1086 | ||
1087 | =item :all | |
1088 | ||
1089 | Imports C<gunzip> and C<$GunzipError>. | |
1090 | Same as doing this | |
1091 | ||
1092 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; | |
1093 | ||
1094 | =back | |
1095 | ||
1096 | =head1 EXAMPLES | |
1097 | ||
1098 | ||
1099 | ||
1100 | ||
1101 | =head1 SEE ALSO | |
1102 | ||
a02d0f6f | 1103 | 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::Uncompress::AnyInflate>, L<IO::Uncompress::AnyUncompress> |
642e522c RGS |
1104 | |
1105 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> | |
1106 | ||
a02d0f6f RGS |
1107 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1108 | L<Archive::Tar|Archive::Tar>, | |
642e522c RGS |
1109 | L<IO::Zlib|IO::Zlib> |
1110 | ||
a02d0f6f | 1111 | |
642e522c RGS |
1112 | For RFC 1950, 1951 and 1952 see |
1113 | F<http://www.faqs.org/rfcs/rfc1950.html>, | |
1114 | F<http://www.faqs.org/rfcs/rfc1951.html> and | |
1115 | F<http://www.faqs.org/rfcs/rfc1952.html> | |
1116 | ||
a02d0f6f RGS |
1117 | The I<zlib> compression library was written by Jean-loup Gailly |
1118 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. | |
1119 | ||
1120 | The primary site for the I<zlib> compression library is | |
1121 | F<http://www.zlib.org>. | |
1122 | ||
1123 | The primary site for gzip is F<http://www.gzip.org>. | |
1124 | ||
1125 | ||
1126 | ||
1127 | ||
642e522c RGS |
1128 | =head1 AUTHOR |
1129 | ||
cb7abd7f | 1130 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
642e522c | 1131 | |
642e522c | 1132 | |
642e522c RGS |
1133 | |
1134 | =head1 MODIFICATION HISTORY | |
1135 | ||
1136 | See the Changes file. | |
1137 | ||
1138 | =head1 COPYRIGHT AND LICENSE | |
642e522c | 1139 | |
1a6a8453 | 1140 | Copyright (c) 2005-2006 Paul Marquess. All rights reserved. |
a02d0f6f | 1141 | |
642e522c RGS |
1142 | This program is free software; you can redistribute it and/or |
1143 | modify it under the same terms as Perl itself. | |
1144 |