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 | |
1a6a8453 |
12 | use IO::Uncompress::RawInflate ; |
13 | |
a02d0f6f |
14 | use Compress::Raw::Zlib qw( crc32 ) ; |
15 | use IO::Compress::Base::Common qw(:Status createSelfTiedObject); |
16 | use IO::Compress::Gzip::Constants; |
1a6a8453 |
17 | |
642e522c |
18 | require Exporter ; |
19 | |
20 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $GunzipError); |
21 | |
1a6a8453 |
22 | @ISA = qw( Exporter IO::Uncompress::RawInflate ); |
642e522c |
23 | @EXPORT_OK = qw( $GunzipError gunzip ); |
1a6a8453 |
24 | %EXPORT_TAGS = %IO::Uncompress::RawInflate::DEFLATE_CONSTANTS ; |
642e522c |
25 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; |
26 | Exporter::export_ok_tags('all'); |
27 | |
642e522c |
28 | $GunzipError = ''; |
29 | |
a02d0f6f |
30 | $VERSION = '2.000_08'; |
642e522c |
31 | |
1a6a8453 |
32 | sub new |
642e522c |
33 | { |
1a6a8453 |
34 | my $class = shift ; |
35 | $GunzipError = ''; |
36 | my $obj = createSelfTiedObject($class, \$GunzipError); |
642e522c |
37 | |
1a6a8453 |
38 | $obj->_create(undef, 0, @_); |
642e522c |
39 | } |
40 | |
1a6a8453 |
41 | sub gunzip |
642e522c |
42 | { |
1a6a8453 |
43 | my $obj = createSelfTiedObject(undef, \$GunzipError); |
44 | return $obj->_inf(@_) ; |
642e522c |
45 | } |
46 | |
1a6a8453 |
47 | sub getExtraParams |
642e522c |
48 | { |
a02d0f6f |
49 | use IO::Compress::Base::Common qw(:Parse); |
1a6a8453 |
50 | return ( 'ParseExtra' => [1, 1, Parse_boolean, 0] ) ; |
642e522c |
51 | } |
52 | |
1a6a8453 |
53 | sub ckParams |
642e522c |
54 | { |
1a6a8453 |
55 | my $self = shift ; |
56 | my $got = shift ; |
642e522c |
57 | |
1a6a8453 |
58 | # gunzip always needs crc32 |
59 | $got->value('CRC32' => 1); |
642e522c |
60 | |
1a6a8453 |
61 | return 1; |
642e522c |
62 | } |
63 | |
1a6a8453 |
64 | sub ckMagic |
642e522c |
65 | { |
1a6a8453 |
66 | my $self = shift; |
642e522c |
67 | |
1a6a8453 |
68 | my $magic ; |
69 | $self->smartReadExact(\$magic, GZIP_ID_SIZE); |
642e522c |
70 | |
1a6a8453 |
71 | *$self->{HeaderPending} = $magic ; |
642e522c |
72 | |
1a6a8453 |
73 | return $self->HeaderError("Minimum header size is " . |
74 | GZIP_MIN_HEADER_SIZE . " bytes") |
75 | if length $magic != GZIP_ID_SIZE ; |
642e522c |
76 | |
1a6a8453 |
77 | return $self->HeaderError("Bad Magic") |
78 | if ! isGzipMagic($magic) ; |
642e522c |
79 | |
1a6a8453 |
80 | *$self->{Type} = 'rfc1952'; |
642e522c |
81 | |
1a6a8453 |
82 | return $magic ; |
642e522c |
83 | } |
84 | |
1a6a8453 |
85 | sub readHeader |
642e522c |
86 | { |
1a6a8453 |
87 | my $self = shift; |
88 | my $magic = shift; |
642e522c |
89 | |
1a6a8453 |
90 | return $self->_readGzipHeader($magic); |
642e522c |
91 | } |
92 | |
1a6a8453 |
93 | sub chkTrailer |
642e522c |
94 | { |
1a6a8453 |
95 | my $self = shift; |
96 | my $trailer = shift; |
642e522c |
97 | |
1a6a8453 |
98 | # Check CRC & ISIZE |
99 | my ($CRC32, $ISIZE) = unpack("V V", $trailer) ; |
100 | *$self->{Info}{CRC32} = $CRC32; |
101 | *$self->{Info}{ISIZE} = $ISIZE; |
102 | |
103 | if (*$self->{Strict}) { |
104 | return $self->TrailerError("CRC mismatch") |
105 | if $CRC32 != *$self->{Uncomp}->crc32() ; |
106 | |
107 | my $exp_isize = *$self->{Uncomp}->uncompressedBytes(); |
108 | return $self->TrailerError("ISIZE mismatch. Got $ISIZE" |
109 | . ", expected $exp_isize") |
110 | if $ISIZE != $exp_isize ; |
642e522c |
111 | } |
112 | |
a02d0f6f |
113 | return STATUS_OK; |
1a6a8453 |
114 | } |
642e522c |
115 | |
1a6a8453 |
116 | sub isGzipMagic |
117 | { |
118 | my $buffer = shift ; |
119 | return 0 if length $buffer < GZIP_ID_SIZE ; |
120 | my ($id1, $id2) = unpack("C C", $buffer) ; |
121 | return $id1 == GZIP_ID1 && $id2 == GZIP_ID2 ; |
642e522c |
122 | } |
123 | |
1a6a8453 |
124 | sub _readFullGzipHeader($) |
642e522c |
125 | { |
1a6a8453 |
126 | my ($self) = @_ ; |
127 | my $magic = '' ; |
642e522c |
128 | |
1a6a8453 |
129 | $self->smartReadExact(\$magic, GZIP_ID_SIZE); |
642e522c |
130 | |
1a6a8453 |
131 | *$self->{HeaderPending} = $magic ; |
642e522c |
132 | |
1a6a8453 |
133 | return $self->HeaderError("Minimum header size is " . |
134 | GZIP_MIN_HEADER_SIZE . " bytes") |
135 | if length $magic != GZIP_ID_SIZE ; |
642e522c |
136 | |
642e522c |
137 | |
1a6a8453 |
138 | return $self->HeaderError("Bad Magic") |
139 | if ! isGzipMagic($magic) ; |
642e522c |
140 | |
1a6a8453 |
141 | my $status = $self->_readGzipHeader($magic); |
142 | delete *$self->{Transparent} if ! defined $status ; |
143 | return $status ; |
642e522c |
144 | } |
145 | |
1a6a8453 |
146 | sub _readGzipHeader($) |
642e522c |
147 | { |
1a6a8453 |
148 | my ($self, $magic) = @_ ; |
149 | my ($HeaderCRC) ; |
150 | my ($buffer) = '' ; |
642e522c |
151 | |
1a6a8453 |
152 | $self->smartReadExact(\$buffer, GZIP_MIN_HEADER_SIZE - GZIP_ID_SIZE) |
153 | or return $self->HeaderError("Minimum header size is " . |
154 | GZIP_MIN_HEADER_SIZE . " bytes") ; |
642e522c |
155 | |
1a6a8453 |
156 | my $keep = $magic . $buffer ; |
157 | *$self->{HeaderPending} = $keep ; |
642e522c |
158 | |
1a6a8453 |
159 | # now split out the various parts |
160 | my ($cm, $flag, $mtime, $xfl, $os) = unpack("C C V C C", $buffer) ; |
642e522c |
161 | |
1a6a8453 |
162 | $cm == GZIP_CM_DEFLATED |
163 | or return $self->HeaderError("Not Deflate (CM is $cm)") ; |
642e522c |
164 | |
1a6a8453 |
165 | # check for use of reserved bits |
166 | return $self->HeaderError("Use of Reserved Bits in FLG field.") |
167 | if $flag & GZIP_FLG_RESERVED ; |
642e522c |
168 | |
1a6a8453 |
169 | my $EXTRA ; |
170 | my @EXTRA = () ; |
171 | if ($flag & GZIP_FLG_FEXTRA) { |
172 | $EXTRA = "" ; |
173 | $self->smartReadExact(\$buffer, GZIP_FEXTRA_HEADER_SIZE) |
174 | or return $self->TruncatedHeader("FEXTRA Length") ; |
642e522c |
175 | |
1a6a8453 |
176 | my ($XLEN) = unpack("v", $buffer) ; |
177 | $self->smartReadExact(\$EXTRA, $XLEN) |
178 | or return $self->TruncatedHeader("FEXTRA Body"); |
179 | $keep .= $buffer . $EXTRA ; |
642e522c |
180 | |
1a6a8453 |
181 | if ($XLEN && *$self->{'ParseExtra'}) { |
182 | my $offset = 0 ; |
183 | while ($offset < $XLEN) { |
642e522c |
184 | |
1a6a8453 |
185 | return $self->TruncatedHeader("FEXTRA Body") |
186 | if $offset + GZIP_FEXTRA_SUBFIELD_HEADER_SIZE > $XLEN ; |
642e522c |
187 | |
1a6a8453 |
188 | my $id = substr($EXTRA, $offset, GZIP_FEXTRA_SUBFIELD_ID_SIZE); |
189 | $offset += GZIP_FEXTRA_SUBFIELD_ID_SIZE ; |
642e522c |
190 | |
1a6a8453 |
191 | return $self->HeaderError("SubField ID 2nd byte is 0x00") |
192 | if *$self->{Strict} && substr($id, 1, 1) eq "\x00" ; |
642e522c |
193 | |
1a6a8453 |
194 | my ($subLen) = unpack("v", substr($EXTRA, $offset, |
195 | GZIP_FEXTRA_SUBFIELD_LEN_SIZE)) ; |
196 | $offset += GZIP_FEXTRA_SUBFIELD_LEN_SIZE ; |
642e522c |
197 | |
1a6a8453 |
198 | return $self->TruncatedHeader("FEXTRA Body") |
199 | if $offset + $subLen > $XLEN ; |
642e522c |
200 | |
1a6a8453 |
201 | push @EXTRA, [$id => substr($EXTRA, $offset, $subLen)]; |
202 | $offset += $subLen ; |
203 | } |
204 | } |
205 | } |
642e522c |
206 | |
1a6a8453 |
207 | my $origname ; |
208 | if ($flag & GZIP_FLG_FNAME) { |
209 | $origname = "" ; |
210 | while (1) { |
211 | $self->smartReadExact(\$buffer, 1) |
212 | or return $self->TruncatedHeader("FNAME"); |
213 | last if $buffer eq GZIP_NULL_BYTE ; |
214 | $origname .= $buffer |
215 | } |
216 | $keep .= $origname . GZIP_NULL_BYTE ; |
642e522c |
217 | |
1a6a8453 |
218 | return $self->HeaderError("Non ISO 8859-1 Character found in Name") |
219 | if *$self->{Strict} && $origname =~ /$GZIP_FNAME_INVALID_CHAR_RE/o ; |
220 | } |
642e522c |
221 | |
1a6a8453 |
222 | my $comment ; |
223 | if ($flag & GZIP_FLG_FCOMMENT) { |
224 | $comment = ""; |
225 | while (1) { |
226 | $self->smartReadExact(\$buffer, 1) |
227 | or return $self->TruncatedHeader("FCOMMENT"); |
228 | last if $buffer eq GZIP_NULL_BYTE ; |
229 | $comment .= $buffer |
230 | } |
231 | $keep .= $comment . GZIP_NULL_BYTE ; |
642e522c |
232 | |
1a6a8453 |
233 | return $self->HeaderError("Non ISO 8859-1 Character found in Comment") |
234 | if *$self->{Strict} && $comment =~ /$GZIP_FCOMMENT_INVALID_CHAR_RE/o ; |
235 | } |
642e522c |
236 | |
1a6a8453 |
237 | if ($flag & GZIP_FLG_FHCRC) { |
238 | $self->smartReadExact(\$buffer, GZIP_FHCRC_SIZE) |
239 | or return $self->TruncatedHeader("FHCRC"); |
642e522c |
240 | |
1a6a8453 |
241 | $HeaderCRC = unpack("v", $buffer) ; |
242 | my $crc16 = crc32($keep) & 0xFF ; |
642e522c |
243 | |
1a6a8453 |
244 | return $self->HeaderError("CRC16 mismatch.") |
245 | if *$self->{Strict} && $crc16 != $HeaderCRC; |
642e522c |
246 | |
1a6a8453 |
247 | $keep .= $buffer ; |
248 | } |
642e522c |
249 | |
1a6a8453 |
250 | # Assume compression method is deflated for xfl tests |
251 | #if ($xfl) { |
252 | #} |
642e522c |
253 | |
1a6a8453 |
254 | *$self->{Type} = 'rfc1952'; |
642e522c |
255 | |
1a6a8453 |
256 | return { |
257 | 'Type' => 'rfc1952', |
258 | 'FingerprintLength' => 2, |
259 | 'HeaderLength' => length $keep, |
260 | 'TrailerLength' => GZIP_TRAILER_SIZE, |
261 | 'Header' => $keep, |
262 | 'isMinimalHeader' => $keep eq GZIP_MINIMUM_HEADER ? 1 : 0, |
642e522c |
263 | |
1a6a8453 |
264 | 'MethodID' => $cm, |
265 | 'MethodName' => $cm == GZIP_CM_DEFLATED ? "Deflated" : "Unknown" , |
266 | 'TextFlag' => $flag & GZIP_FLG_FTEXT ? 1 : 0, |
267 | 'HeaderCRCFlag' => $flag & GZIP_FLG_FHCRC ? 1 : 0, |
268 | 'NameFlag' => $flag & GZIP_FLG_FNAME ? 1 : 0, |
269 | 'CommentFlag' => $flag & GZIP_FLG_FCOMMENT ? 1 : 0, |
270 | 'ExtraFlag' => $flag & GZIP_FLG_FEXTRA ? 1 : 0, |
271 | 'Name' => $origname, |
272 | 'Comment' => $comment, |
273 | 'Time' => $mtime, |
274 | 'OsID' => $os, |
275 | 'OsName' => defined $GZIP_OS_Names{$os} |
276 | ? $GZIP_OS_Names{$os} : "Unknown", |
277 | 'HeaderCRC' => $HeaderCRC, |
278 | 'Flags' => $flag, |
279 | 'ExtraFlags' => $xfl, |
280 | 'ExtraFieldRaw' => $EXTRA, |
281 | 'ExtraField' => [ @EXTRA ], |
642e522c |
282 | |
642e522c |
283 | |
1a6a8453 |
284 | #'CompSize'=> $compsize, |
285 | #'CRC32'=> $CRC32, |
286 | #'OrigSize'=> $ISIZE, |
287 | } |
642e522c |
288 | } |
289 | |
290 | |
1a6a8453 |
291 | 1; |
642e522c |
292 | |
642e522c |
293 | __END__ |
294 | |
295 | |
296 | =head1 NAME |
297 | |
a02d0f6f |
298 | |
642e522c |
299 | IO::Uncompress::Gunzip - Perl interface to read RFC 1952 files/buffers |
300 | |
a02d0f6f |
301 | |
642e522c |
302 | =head1 SYNOPSIS |
303 | |
304 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
305 | |
306 | my $status = gunzip $input => $output [,OPTS] |
307 | or die "gunzip failed: $GunzipError\n"; |
308 | |
309 | my $z = new IO::Uncompress::Gunzip $input [OPTS] |
310 | or die "gunzip failed: $GunzipError\n"; |
311 | |
312 | $status = $z->read($buffer) |
313 | $status = $z->read($buffer, $length) |
314 | $status = $z->read($buffer, $length, $offset) |
315 | $line = $z->getline() |
316 | $char = $z->getc() |
317 | $char = $z->ungetc() |
a02d0f6f |
318 | $char = $z->opened() |
319 | |
642e522c |
320 | $status = $z->inflateSync() |
a02d0f6f |
321 | |
642e522c |
322 | $z->trailingData() |
323 | $data = $z->getHeaderInfo() |
324 | $z->tell() |
325 | $z->seek($position, $whence) |
326 | $z->binmode() |
327 | $z->fileno() |
328 | $z->eof() |
329 | $z->close() |
330 | |
331 | $GunzipError ; |
332 | |
333 | # IO::File mode |
334 | |
335 | <$z> |
336 | read($z, $buffer); |
337 | read($z, $buffer, $length); |
338 | read($z, $buffer, $length, $offset); |
339 | tell($z) |
340 | seek($z, $position, $whence) |
341 | binmode($z) |
342 | fileno($z) |
343 | eof($z) |
344 | close($z) |
345 | |
346 | |
347 | =head1 DESCRIPTION |
348 | |
349 | |
350 | |
351 | B<WARNING -- This is a Beta release>. |
352 | |
353 | =over 5 |
354 | |
355 | =item * DO NOT use in production code. |
356 | |
357 | =item * The documentation is incomplete in places. |
358 | |
359 | =item * Parts of the interface defined here are tentative. |
360 | |
361 | =item * Please report any problems you find. |
362 | |
363 | =back |
364 | |
365 | |
366 | |
367 | |
368 | |
1a6a8453 |
369 | This module provides a Perl interface that allows the reading of |
642e522c |
370 | files/buffers that conform to RFC 1952. |
371 | |
1a6a8453 |
372 | For writing RFC 1952 files/buffers, see the companion module IO::Compress::Gzip. |
642e522c |
373 | |
374 | |
375 | |
376 | =head1 Functional Interface |
377 | |
1a6a8453 |
378 | A top-level function, C<gunzip>, is provided to carry out |
379 | "one-shot" uncompression between buffers and/or files. For finer |
380 | control over the uncompression process, see the L</"OO Interface"> |
381 | section. |
642e522c |
382 | |
383 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
384 | |
385 | gunzip $input => $output [,OPTS] |
386 | or die "gunzip failed: $GunzipError\n"; |
387 | |
1a6a8453 |
388 | |
642e522c |
389 | |
390 | The functional interface needs Perl5.005 or better. |
391 | |
392 | |
393 | =head2 gunzip $input => $output [, OPTS] |
394 | |
1a6a8453 |
395 | |
396 | C<gunzip> expects at least two parameters, C<$input> and C<$output>. |
642e522c |
397 | |
398 | =head3 The C<$input> parameter |
399 | |
400 | The parameter, C<$input>, is used to define the source of |
401 | the compressed data. |
402 | |
403 | It can take one of the following forms: |
404 | |
405 | =over 5 |
406 | |
407 | =item A filename |
408 | |
409 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
410 | filename. This file will be opened for reading and the input data |
411 | will be read from it. |
412 | |
413 | =item A filehandle |
414 | |
415 | If the C<$input> parameter is a filehandle, the input data will be |
416 | read from it. |
417 | The string '-' can be used as an alias for standard input. |
418 | |
419 | =item A scalar reference |
420 | |
421 | If C<$input> is a scalar reference, the input data will be read |
422 | from C<$$input>. |
423 | |
424 | =item An array reference |
425 | |
1a6a8453 |
426 | If C<$input> is an array reference, each element in the array must be a |
427 | filename. |
428 | |
429 | The input data will be read from each file in turn. |
430 | |
642e522c |
431 | The complete array will be walked to ensure that it only |
1a6a8453 |
432 | contains valid filenames before any data is uncompressed. |
433 | |
434 | |
642e522c |
435 | |
436 | =item An Input FileGlob string |
437 | |
438 | If C<$input> is a string that is delimited by the characters "<" and ">" |
439 | C<gunzip> will assume that it is an I<input fileglob string>. The |
440 | input is the list of files that match the fileglob. |
441 | |
442 | If the fileglob does not match any files ... |
443 | |
444 | See L<File::GlobMapper|File::GlobMapper> for more details. |
445 | |
446 | |
447 | =back |
448 | |
449 | If the C<$input> parameter is any other type, C<undef> will be returned. |
450 | |
451 | |
452 | |
453 | =head3 The C<$output> parameter |
454 | |
455 | The parameter C<$output> is used to control the destination of the |
456 | uncompressed data. This parameter can take one of these forms. |
457 | |
458 | =over 5 |
459 | |
460 | =item A filename |
461 | |
1a6a8453 |
462 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
463 | filename. This file will be opened for writing and the uncompressed |
464 | data will be written to it. |
642e522c |
465 | |
466 | =item A filehandle |
467 | |
1a6a8453 |
468 | If the C<$output> parameter is a filehandle, the uncompressed data |
469 | will be written to it. |
642e522c |
470 | The string '-' can be used as an alias for standard output. |
471 | |
472 | |
473 | =item A scalar reference |
474 | |
1a6a8453 |
475 | If C<$output> is a scalar reference, the uncompressed data will be |
476 | stored in C<$$output>. |
642e522c |
477 | |
478 | |
642e522c |
479 | |
480 | =item An Array Reference |
481 | |
1a6a8453 |
482 | If C<$output> is an array reference, the uncompressed data will be |
483 | pushed onto the array. |
642e522c |
484 | |
485 | =item An Output FileGlob |
486 | |
487 | If C<$output> is a string that is delimited by the characters "<" and ">" |
488 | C<gunzip> will assume that it is an I<output fileglob string>. The |
489 | output is the list of files that match the fileglob. |
490 | |
491 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
492 | string. Anything else is an error. |
493 | |
494 | =back |
495 | |
496 | If the C<$output> parameter is any other type, C<undef> will be returned. |
497 | |
642e522c |
498 | |
642e522c |
499 | |
500 | =head2 Notes |
501 | |
502 | When C<$input> maps to multiple files/buffers and C<$output> is a single |
1a6a8453 |
503 | file/buffer the uncompressed input files/buffers will all be stored |
504 | in C<$output> as a single uncompressed stream. |
642e522c |
505 | |
506 | |
507 | |
508 | =head2 Optional Parameters |
509 | |
510 | Unless specified below, the optional parameters for C<gunzip>, |
511 | C<OPTS>, are the same as those used with the OO interface defined in the |
512 | L</"Constructor Options"> section below. |
513 | |
514 | =over 5 |
515 | |
516 | =item AutoClose =E<gt> 0|1 |
517 | |
1a6a8453 |
518 | This option applies to any input or output data streams to |
519 | C<gunzip> that are filehandles. |
642e522c |
520 | |
521 | If C<AutoClose> is specified, and the value is true, it will result in all |
522 | input and/or output filehandles being closed once C<gunzip> has |
523 | completed. |
524 | |
525 | This parameter defaults to 0. |
526 | |
527 | |
528 | |
1a6a8453 |
529 | =item BinModeOut =E<gt> 0|1 |
530 | |
531 | When writing to a file or filehandle, set C<binmode> before writing to the |
532 | file. |
533 | |
534 | Defaults to 0. |
535 | |
536 | |
537 | |
538 | |
539 | |
642e522c |
540 | =item -Append =E<gt> 0|1 |
541 | |
542 | TODO |
543 | |
1a6a8453 |
544 | =item -MultiStream =E<gt> 0|1 |
545 | |
546 | Creates a new stream after each file. |
547 | |
548 | Defaults to 1. |
549 | |
642e522c |
550 | |
551 | |
552 | =back |
553 | |
554 | |
555 | |
556 | |
557 | =head2 Examples |
558 | |
559 | To read the contents of the file C<file1.txt.gz> and write the |
560 | compressed data to the file C<file1.txt>. |
561 | |
562 | use strict ; |
563 | use warnings ; |
564 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
565 | |
566 | my $input = "file1.txt.gz"; |
567 | my $output = "file1.txt"; |
568 | gunzip $input => $output |
569 | or die "gunzip failed: $GunzipError\n"; |
570 | |
571 | |
572 | To read from an existing Perl filehandle, C<$input>, and write the |
573 | uncompressed data to a buffer, C<$buffer>. |
574 | |
575 | use strict ; |
576 | use warnings ; |
577 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
578 | use IO::File ; |
579 | |
580 | my $input = new IO::File "<file1.txt.gz" |
581 | or die "Cannot open 'file1.txt.gz': $!\n" ; |
582 | my $buffer ; |
583 | gunzip $input => \$buffer |
584 | or die "gunzip failed: $GunzipError\n"; |
585 | |
586 | To uncompress all files in the directory "/my/home" that match "*.txt.gz" and store the compressed data in the same directory |
587 | |
588 | use strict ; |
589 | use warnings ; |
590 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
591 | |
592 | gunzip '</my/home/*.txt.gz>' => '</my/home/#1.txt>' |
593 | or die "gunzip failed: $GunzipError\n"; |
594 | |
595 | and if you want to compress each file one at a time, this will do the trick |
596 | |
597 | use strict ; |
598 | use warnings ; |
599 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
600 | |
601 | for my $input ( glob "/my/home/*.txt.gz" ) |
602 | { |
603 | my $output = $input; |
604 | $output =~ s/.gz// ; |
605 | gunzip $input => $output |
606 | or die "Error compressing '$input': $GunzipError\n"; |
607 | } |
608 | |
609 | =head1 OO Interface |
610 | |
611 | =head2 Constructor |
612 | |
613 | The format of the constructor for IO::Uncompress::Gunzip is shown below |
614 | |
615 | |
616 | my $z = new IO::Uncompress::Gunzip $input [OPTS] |
617 | or die "IO::Uncompress::Gunzip failed: $GunzipError\n"; |
618 | |
619 | Returns an C<IO::Uncompress::Gunzip> object on success and undef on failure. |
620 | The variable C<$GunzipError> will contain an error message on failure. |
621 | |
1a6a8453 |
622 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
623 | IO::Uncompress::Gunzip can be used exactly like an L<IO::File|IO::File> filehandle. |
624 | This means that all normal input file operations can be carried out with |
625 | C<$z>. For example, to read a line from a compressed file/buffer you can |
626 | use either of these forms |
642e522c |
627 | |
628 | $line = $z->getline(); |
629 | $line = <$z>; |
630 | |
631 | The mandatory parameter C<$input> is used to determine the source of the |
632 | compressed data. This parameter can take one of three forms. |
633 | |
634 | =over 5 |
635 | |
636 | =item A filename |
637 | |
638 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
639 | file will be opened for reading and the compressed data will be read from it. |
640 | |
641 | =item A filehandle |
642 | |
643 | If the C<$input> parameter is a filehandle, the compressed data will be |
644 | read from it. |
645 | The string '-' can be used as an alias for standard input. |
646 | |
647 | |
648 | =item A scalar reference |
649 | |
650 | If C<$input> is a scalar reference, the compressed data will be read from |
651 | C<$$output>. |
652 | |
653 | =back |
654 | |
655 | =head2 Constructor Options |
656 | |
657 | |
658 | The option names defined below are case insensitive and can be optionally |
659 | prefixed by a '-'. So all of the following are valid |
660 | |
661 | -AutoClose |
662 | -autoclose |
663 | AUTOCLOSE |
664 | autoclose |
665 | |
666 | OPTS is a combination of the following options: |
667 | |
668 | =over 5 |
669 | |
670 | =item -AutoClose =E<gt> 0|1 |
671 | |
672 | This option is only valid when the C<$input> parameter is a filehandle. If |
673 | specified, and the value is true, it will result in the file being closed once |
674 | either the C<close> method is called or the IO::Uncompress::Gunzip object is |
675 | destroyed. |
676 | |
677 | This parameter defaults to 0. |
678 | |
679 | =item -MultiStream =E<gt> 0|1 |
680 | |
681 | |
682 | |
683 | Allows multiple concatenated compressed streams to be treated as a single |
684 | compressed stream. Decompression will stop once either the end of the |
685 | file/buffer is reached, an error is encountered (premature eof, corrupt |
686 | compressed data) or the end of a stream is not immediately followed by the |
687 | start of another stream. |
688 | |
689 | This parameter defaults to 0. |
690 | |
691 | |
692 | |
693 | =item -Prime =E<gt> $string |
694 | |
695 | This option will uncompress the contents of C<$string> before processing the |
696 | input file/buffer. |
697 | |
698 | This option can be useful when the compressed data is embedded in another |
699 | file/data structure and it is not possible to work out where the compressed |
1a6a8453 |
700 | data begins without having to read the first few bytes. If this is the |
701 | case, the uncompression can be I<primed> with these bytes using this |
702 | option. |
642e522c |
703 | |
704 | =item -Transparent =E<gt> 0|1 |
705 | |
706 | If this option is set and the input file or buffer is not compressed data, |
707 | the module will allow reading of it anyway. |
708 | |
709 | This option defaults to 1. |
710 | |
711 | =item -BlockSize =E<gt> $num |
712 | |
1a6a8453 |
713 | When reading the compressed input data, IO::Uncompress::Gunzip will read it in |
714 | blocks of C<$num> bytes. |
642e522c |
715 | |
716 | This option defaults to 4096. |
717 | |
718 | =item -InputLength =E<gt> $size |
719 | |
1a6a8453 |
720 | When present this option will limit the number of compressed bytes read |
721 | from the input file/buffer to C<$size>. This option can be used in the |
722 | situation where there is useful data directly after the compressed data |
723 | stream and you know beforehand the exact length of the compressed data |
724 | stream. |
642e522c |
725 | |
1a6a8453 |
726 | This option is mostly used when reading from a filehandle, in which case |
727 | the file pointer will be left pointing to the first byte directly after the |
642e522c |
728 | compressed data stream. |
729 | |
730 | |
731 | |
732 | This option defaults to off. |
733 | |
734 | =item -Append =E<gt> 0|1 |
735 | |
736 | This option controls what the C<read> method does with uncompressed data. |
737 | |
1a6a8453 |
738 | If set to 1, all uncompressed data will be appended to the output parameter |
739 | of the C<read> method. |
642e522c |
740 | |
1a6a8453 |
741 | If set to 0, the contents of the output parameter of the C<read> method |
742 | will be overwritten by the uncompressed data. |
642e522c |
743 | |
744 | Defaults to 0. |
745 | |
746 | =item -Strict =E<gt> 0|1 |
747 | |
748 | |
749 | |
750 | This option controls whether the extra checks defined below are used when |
1a6a8453 |
751 | carrying out the decompression. When Strict is on, the extra tests are |
752 | carried out, when Strict is off they are not. |
642e522c |
753 | |
754 | The default for this option is off. |
755 | |
756 | |
757 | |
758 | |
759 | |
760 | |
761 | |
762 | |
763 | |
764 | =over 5 |
765 | |
766 | =item 1 |
767 | |
768 | If the FHCRC bit is set in the gzip FLG header byte, the CRC16 bytes in the |
769 | header must match the crc16 value of the gzip header actually read. |
770 | |
771 | =item 2 |
772 | |
773 | If the gzip header contains a name field (FNAME) it consists solely of ISO |
774 | 8859-1 characters. |
775 | |
776 | =item 3 |
777 | |
1a6a8453 |
778 | If the gzip header contains a comment field (FCOMMENT) it consists solely |
779 | of ISO 8859-1 characters plus line-feed. |
642e522c |
780 | |
781 | =item 4 |
782 | |
783 | If the gzip FEXTRA header field is present it must conform to the sub-field |
a02d0f6f |
784 | structure as defined in RFC 1952. |
642e522c |
785 | |
786 | =item 5 |
787 | |
788 | The CRC32 and ISIZE trailer fields must be present. |
789 | |
790 | =item 6 |
791 | |
792 | The value of the CRC32 field read must match the crc32 value of the |
793 | uncompressed data actually contained in the gzip file. |
794 | |
795 | =item 7 |
796 | |
1a6a8453 |
797 | The value of the ISIZE fields read must match the length of the |
798 | uncompressed data actually read from the file. |
642e522c |
799 | |
800 | =back |
801 | |
802 | |
803 | |
804 | |
805 | |
806 | |
807 | =item -ParseExtra =E<gt> 0|1 |
808 | |
809 | If the gzip FEXTRA header field is present and this option is set, it will |
810 | force the module to check that it conforms to the sub-field structure as |
a02d0f6f |
811 | defined in RFC 1952. |
642e522c |
812 | |
813 | If the C<Strict> is on it will automatically enable this option. |
814 | |
815 | Defaults to 0. |
816 | |
817 | |
818 | |
a02d0f6f |
819 | |
820 | |
642e522c |
821 | =back |
822 | |
823 | =head2 Examples |
824 | |
825 | TODO |
826 | |
827 | =head1 Methods |
828 | |
829 | =head2 read |
830 | |
831 | Usage is |
832 | |
833 | $status = $z->read($buffer) |
834 | |
835 | Reads a block of compressed data (the size the the compressed block is |
836 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1a6a8453 |
837 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
838 | set in the constructor, the uncompressed data will be appended to the |
839 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
642e522c |
840 | |
1a6a8453 |
841 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
842 | or a negative number on error. |
642e522c |
843 | |
844 | =head2 read |
845 | |
846 | Usage is |
847 | |
848 | $status = $z->read($buffer, $length) |
849 | $status = $z->read($buffer, $length, $offset) |
850 | |
851 | $status = read($z, $buffer, $length) |
852 | $status = read($z, $buffer, $length, $offset) |
853 | |
854 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
855 | |
1a6a8453 |
856 | The main difference between this form of the C<read> method and the |
857 | previous one, is that this one will attempt to return I<exactly> C<$length> |
858 | bytes. The only circumstances that this function will not is if end-of-file |
859 | or an IO error is encountered. |
642e522c |
860 | |
1a6a8453 |
861 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
862 | or a negative number on error. |
642e522c |
863 | |
864 | |
865 | =head2 getline |
866 | |
867 | Usage is |
868 | |
869 | $line = $z->getline() |
870 | $line = <$z> |
871 | |
872 | Reads a single line. |
873 | |
874 | This method fully supports the use of of the variable C<$/> |
875 | (or C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
876 | determine what constitutes an end of line. Both paragraph mode and file |
877 | slurp mode are supported. |
878 | |
879 | |
880 | =head2 getc |
881 | |
882 | Usage is |
883 | |
884 | $char = $z->getc() |
885 | |
886 | Read a single character. |
887 | |
888 | =head2 ungetc |
889 | |
890 | Usage is |
891 | |
892 | $char = $z->ungetc($string) |
893 | |
894 | |
a02d0f6f |
895 | |
642e522c |
896 | =head2 inflateSync |
897 | |
898 | Usage is |
899 | |
900 | $status = $z->inflateSync() |
901 | |
902 | TODO |
903 | |
a02d0f6f |
904 | |
642e522c |
905 | =head2 getHeaderInfo |
906 | |
907 | Usage is |
908 | |
1a6a8453 |
909 | $hdr = $z->getHeaderInfo(); |
910 | @hdrs = $z->getHeaderInfo(); |
642e522c |
911 | |
1a6a8453 |
912 | This method returns either a hash reference (in scalar context) or a list |
913 | or hash references (in array context) that contains information about each |
914 | of the header fields in the compressed data stream(s). |
642e522c |
915 | |
916 | |
917 | |
1a6a8453 |
918 | =over 5 |
642e522c |
919 | |
1a6a8453 |
920 | =item Name |
642e522c |
921 | |
1a6a8453 |
922 | The contents of the Name header field, if present. If no name is |
923 | present, the value will be undef. Note this is different from a zero length |
924 | name, which will return an empty string. |
642e522c |
925 | |
926 | =item Comment |
927 | |
1a6a8453 |
928 | The contents of the Comment header field, if present. If no comment is |
929 | present, the value will be undef. Note this is different from a zero length |
930 | comment, which will return an empty string. |
642e522c |
931 | |
932 | =back |
933 | |
934 | |
935 | |
936 | |
937 | =head2 tell |
938 | |
939 | Usage is |
940 | |
941 | $z->tell() |
942 | tell $z |
943 | |
944 | Returns the uncompressed file offset. |
945 | |
946 | =head2 eof |
947 | |
948 | Usage is |
949 | |
950 | $z->eof(); |
951 | eof($z); |
952 | |
953 | |
954 | |
955 | Returns true if the end of the compressed input stream has been reached. |
956 | |
957 | |
958 | |
959 | =head2 seek |
960 | |
961 | $z->seek($position, $whence); |
962 | seek($z, $position, $whence); |
963 | |
964 | |
965 | |
966 | |
967 | Provides a sub-set of the C<seek> functionality, with the restriction |
968 | that it is only legal to seek forward in the input file/buffer. |
969 | It is a fatal error to attempt to seek backward. |
970 | |
971 | |
972 | |
973 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
974 | SEEK_CUR or SEEK_END. |
975 | |
976 | Returns 1 on success, 0 on failure. |
977 | |
978 | =head2 binmode |
979 | |
980 | Usage is |
981 | |
982 | $z->binmode |
983 | binmode $z ; |
984 | |
985 | This is a noop provided for completeness. |
986 | |
a02d0f6f |
987 | =head2 opened |
988 | |
989 | $z->opened() |
990 | |
991 | Returns true if the object currently refers to a opened file/buffer. |
992 | |
993 | =head2 autoflush |
994 | |
995 | my $prev = $z->autoflush() |
996 | my $prev = $z->autoflush(EXPR) |
997 | |
998 | If the C<$z> object is associated with a file or a filehandle, this method |
999 | returns the current autoflush setting for the underlying filehandle. If |
1000 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
1001 | write/print operation. |
1002 | |
1003 | If C<$z> is associated with a buffer, this method has no effect and always |
1004 | returns C<undef>. |
1005 | |
1006 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
1007 | retrieve the autoflush setting. |
1008 | |
1009 | =head2 input_line_number |
1010 | |
1011 | $z->input_line_number() |
1012 | $z->input_line_number(EXPR) |
1013 | |
1014 | |
1015 | |
1016 | Returns the current uncompressed line number. If C<EXPR> is present it has |
1017 | the effect of setting the line number. Note that setting the line number |
1018 | does not change the current position within the file/buffer being read. |
1019 | |
1020 | The contents of C<$/> are used to to determine what constitutes a line |
1021 | terminator. |
1022 | |
1023 | |
1024 | |
642e522c |
1025 | =head2 fileno |
1026 | |
1027 | $z->fileno() |
1028 | fileno($z) |
1029 | |
a02d0f6f |
1030 | If the C<$z> object is associated with a file or a filehandle, this method |
1031 | will return the underlying file descriptor. |
642e522c |
1032 | |
1033 | If the C<$z> object is is associated with a buffer, this method will |
1034 | return undef. |
1035 | |
1036 | =head2 close |
1037 | |
1038 | $z->close() ; |
1039 | close $z ; |
1040 | |
1041 | |
1042 | |
1043 | Closes the output file/buffer. |
1044 | |
1045 | |
1046 | |
1047 | For most versions of Perl this method will be automatically invoked if |
1048 | the IO::Uncompress::Gunzip object is destroyed (either explicitly or by the |
1049 | variable with the reference to the object going out of scope). The |
1050 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
1051 | these cases, the C<close> method will be called automatically, but |
1052 | not until global destruction of all live objects when the program is |
1053 | terminating. |
1054 | |
1055 | Therefore, if you want your scripts to be able to run on all versions |
1056 | of Perl, you should call C<close> explicitly and not rely on automatic |
1057 | closing. |
1058 | |
1059 | Returns true on success, otherwise 0. |
1060 | |
1061 | If the C<AutoClose> option has been enabled when the IO::Uncompress::Gunzip |
1062 | object was created, and the object is associated with a file, the |
1063 | underlying file will also be closed. |
1064 | |
1065 | |
1066 | |
1067 | |
1068 | =head1 Importing |
1069 | |
1070 | No symbolic constants are required by this IO::Uncompress::Gunzip at present. |
1071 | |
1072 | =over 5 |
1073 | |
1074 | =item :all |
1075 | |
1076 | Imports C<gunzip> and C<$GunzipError>. |
1077 | Same as doing this |
1078 | |
1079 | use IO::Uncompress::Gunzip qw(gunzip $GunzipError) ; |
1080 | |
1081 | =back |
1082 | |
1083 | =head1 EXAMPLES |
1084 | |
1085 | |
1086 | |
1087 | |
1088 | =head1 SEE ALSO |
1089 | |
a02d0f6f |
1090 | 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 |
1091 | |
1092 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
1093 | |
a02d0f6f |
1094 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1095 | L<Archive::Tar|Archive::Tar>, |
642e522c |
1096 | L<IO::Zlib|IO::Zlib> |
1097 | |
a02d0f6f |
1098 | |
642e522c |
1099 | For RFC 1950, 1951 and 1952 see |
1100 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
1101 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
1102 | F<http://www.faqs.org/rfcs/rfc1952.html> |
1103 | |
a02d0f6f |
1104 | The I<zlib> compression library was written by Jean-loup Gailly |
1105 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
1106 | |
1107 | The primary site for the I<zlib> compression library is |
1108 | F<http://www.zlib.org>. |
1109 | |
1110 | The primary site for gzip is F<http://www.gzip.org>. |
1111 | |
1112 | |
1113 | |
1114 | |
1115 | |
1116 | |
642e522c |
1117 | |
1118 | =head1 AUTHOR |
1119 | |
1120 | The I<IO::Uncompress::Gunzip> module was written by Paul Marquess, |
a02d0f6f |
1121 | F<pmqs@cpan.org>. |
642e522c |
1122 | |
642e522c |
1123 | |
642e522c |
1124 | |
1125 | =head1 MODIFICATION HISTORY |
1126 | |
1127 | See the Changes file. |
1128 | |
1129 | =head1 COPYRIGHT AND LICENSE |
1130 | |
1131 | |
1a6a8453 |
1132 | Copyright (c) 2005-2006 Paul Marquess. All rights reserved. |
a02d0f6f |
1133 | |
642e522c |
1134 | This program is free software; you can redistribute it and/or |
1135 | modify it under the same terms as Perl itself. |
1136 | |