Commit | Line | Data |
a02d0f6f |
1 | package IO::Uncompress::Unzip; |
2 | |
3 | require 5.004 ; |
4 | |
5 | # for RFC1952 |
6 | |
7 | use strict ; |
8 | use warnings; |
9 | use bytes; |
10 | |
11 | use IO::Uncompress::RawInflate ; |
12 | use IO::Compress::Base::Common qw(:Status createSelfTiedObject); |
13 | use IO::Uncompress::Adapter::Identity; |
c70c1701 |
14 | use IO::Compress::Zlib::Extra; |
15 | use IO::Compress::Zip::Constants; |
a02d0f6f |
16 | |
2b4e0969 |
17 | use Compress::Raw::Zlib qw(crc32) ; |
c70c1701 |
18 | |
2b4e0969 |
19 | BEGIN |
20 | { |
c70c1701 |
21 | eval { require IO::Uncompress::Adapter::Bunzip2 ; |
22 | import IO::Uncompress::Adapter::Bunzip2 } ; |
2b4e0969 |
23 | } |
24 | |
25 | |
a02d0f6f |
26 | require Exporter ; |
27 | |
e7d45986 |
28 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $UnzipError, %headerLookup); |
a02d0f6f |
29 | |
63ad731d |
30 | $VERSION = '2.001'; |
a02d0f6f |
31 | $UnzipError = ''; |
32 | |
33 | @ISA = qw(Exporter IO::Uncompress::RawInflate); |
34 | @EXPORT_OK = qw( $UnzipError unzip ); |
35 | %EXPORT_TAGS = %IO::Uncompress::RawInflate::EXPORT_TAGS ; |
36 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; |
37 | Exporter::export_ok_tags('all'); |
38 | |
e7d45986 |
39 | %headerLookup = ( |
40 | ZIP_CENTRAL_HDR_SIG, \&skipCentralDirectory, |
41 | ZIP_END_CENTRAL_HDR_SIG, \&skipEndCentralDirectory, |
42 | ZIP64_END_CENTRAL_REC_HDR_SIG, \&skipCentralDirectory64Rec, |
43 | ZIP64_END_CENTRAL_LOC_HDR_SIG, \&skipCentralDirectory64Loc, |
44 | ZIP64_ARCHIVE_EXTRA_SIG, \&skipArchiveExtra, |
45 | ZIP64_DIGITAL_SIGNATURE_SIG, \&skipDigitalSignature, |
46 | ); |
47 | |
a02d0f6f |
48 | sub new |
49 | { |
50 | my $class = shift ; |
51 | my $obj = createSelfTiedObject($class, \$UnzipError); |
52 | $obj->_create(undef, 0, @_); |
53 | } |
54 | |
55 | sub unzip |
56 | { |
57 | my $obj = createSelfTiedObject(undef, \$UnzipError); |
58 | return $obj->_inf(@_) ; |
59 | } |
60 | |
61 | sub getExtraParams |
62 | { |
63 | use IO::Compress::Base::Common qw(:Parse); |
64 | |
65 | |
66 | return ( |
67 | # # Zip header fields |
68 | 'Name' => [1, 1, Parse_any, undef], |
69 | |
70 | # 'Streaming' => [1, 1, Parse_boolean, 1], |
71 | ); |
72 | } |
73 | |
74 | sub ckParams |
75 | { |
76 | my $self = shift ; |
77 | my $got = shift ; |
78 | |
79 | # unzip always needs crc32 |
80 | $got->value('CRC32' => 1); |
81 | |
82 | *$self->{UnzipData}{Name} = $got->value('Name'); |
83 | |
84 | return 1; |
85 | } |
86 | |
87 | |
88 | sub ckMagic |
89 | { |
90 | my $self = shift; |
91 | |
92 | my $magic ; |
93 | $self->smartReadExact(\$magic, 4); |
94 | |
95 | *$self->{HeaderPending} = $magic ; |
96 | |
97 | return $self->HeaderError("Minimum header size is " . |
98 | 4 . " bytes") |
99 | if length $magic != 4 ; |
100 | |
101 | return $self->HeaderError("Bad Magic") |
102 | if ! _isZipMagic($magic) ; |
103 | |
104 | *$self->{Type} = 'zip'; |
105 | |
106 | return $magic ; |
107 | } |
108 | |
109 | |
110 | |
111 | sub readHeader |
112 | { |
113 | my $self = shift; |
114 | my $magic = shift ; |
115 | |
116 | my $name = *$self->{UnzipData}{Name} ; |
117 | my $hdr = $self->_readZipHeader($magic) ; |
118 | |
119 | while (defined $hdr) |
120 | { |
121 | if (! defined $name || $hdr->{Name} eq $name) |
122 | { |
123 | return $hdr ; |
124 | } |
125 | |
126 | # skip the data |
127 | my $buffer; |
128 | if (*$self->{ZipData}{Streaming}) { |
129 | |
130 | while (1) { |
131 | |
132 | my $b; |
133 | my $status = $self->smartRead(\$b, 1024 * 16); |
134 | return undef |
135 | if $status <= 0 ; |
136 | |
137 | my $temp_buf; |
138 | my $out; |
139 | $status = *$self->{Uncomp}->uncompr(\$b, \$temp_buf, 0, $out); |
140 | |
141 | return $self->saveErrorString(undef, *$self->{Uncomp}{Error}, |
142 | *$self->{Uncomp}{ErrorNo}) |
143 | if $self->saveStatus($status) == STATUS_ERROR; |
144 | |
145 | if ($status == STATUS_ENDSTREAM) { |
146 | *$self->{Uncomp}->reset(); |
147 | $self->pushBack($b) ; |
148 | last; |
149 | } |
150 | } |
151 | |
152 | # skip the trailer |
153 | $self->smartReadExact(\$buffer, $hdr->{TrailerLength}) |
154 | or return $self->saveErrorString(undef, "Truncated file"); |
155 | } |
156 | else { |
e7d45986 |
157 | my $c = $hdr->{CompressedLength}->get32bit(); |
a02d0f6f |
158 | $self->smartReadExact(\$buffer, $c) |
159 | or return $self->saveErrorString(undef, "Truncated file"); |
160 | $buffer = ''; |
161 | } |
162 | |
163 | $self->chkTrailer($buffer) == STATUS_OK |
164 | or return $self->saveErrorString(undef, "Truncated file"); |
165 | |
166 | $hdr = $self->_readFullZipHeader(); |
167 | |
168 | return $self->saveErrorString(undef, "Cannot find '$name'") |
169 | if $self->smartEof(); |
170 | } |
171 | |
172 | return undef; |
173 | } |
174 | |
175 | sub chkTrailer |
176 | { |
177 | my $self = shift; |
178 | my $trailer = shift; |
179 | |
180 | my ($sig, $CRC32, $cSize, $uSize) ; |
e7d45986 |
181 | my ($cSizeHi, $uSizeHi) = (0, 0); |
a02d0f6f |
182 | if (*$self->{ZipData}{Streaming}) { |
e7d45986 |
183 | $sig = unpack ("V", substr($trailer, 0, 4)); |
184 | $CRC32 = unpack ("V", substr($trailer, 4, 4)); |
185 | |
186 | if (*$self->{ZipData}{Zip64} ) { |
187 | $cSize = U64::newUnpack_V64 substr($trailer, 8, 8); |
188 | $uSize = U64::newUnpack_V64 substr($trailer, 16, 8); |
189 | } |
190 | else { |
191 | $cSize = U64::newUnpack_V32 substr($trailer, 8, 4); |
192 | $uSize = U64::newUnpack_V32 substr($trailer, 12, 4); |
193 | } |
194 | |
a02d0f6f |
195 | return $self->TrailerError("Data Descriptor signature, got $sig") |
c70c1701 |
196 | if $sig != ZIP_DATA_HDR_SIG; |
a02d0f6f |
197 | } |
198 | else { |
199 | ($CRC32, $cSize, $uSize) = |
200 | (*$self->{ZipData}{Crc32}, |
201 | *$self->{ZipData}{CompressedLen}, |
202 | *$self->{ZipData}{UnCompressedLen}); |
203 | } |
204 | |
205 | if (*$self->{Strict}) { |
2b4e0969 |
206 | return $self->TrailerError("CRC mismatch") |
207 | if $CRC32 != *$self->{ZipData}{CRC32} ; |
a02d0f6f |
208 | |
e7d45986 |
209 | return $self->TrailerError("CSIZE mismatch.") |
210 | if ! $cSize->equal(*$self->{CompSize}); |
a02d0f6f |
211 | |
e7d45986 |
212 | return $self->TrailerError("USIZE mismatch.") |
213 | if ! $uSize->equal(*$self->{UnCompSize}); |
a02d0f6f |
214 | } |
215 | |
216 | my $reachedEnd = STATUS_ERROR ; |
217 | # check for central directory or end of central directory |
218 | while (1) |
219 | { |
220 | my $magic ; |
221 | my $got = $self->smartRead(\$magic, 4); |
222 | |
223 | return $self->saveErrorString(STATUS_ERROR, "Truncated file") |
224 | if $got != 4 && *$self->{Strict}; |
225 | |
226 | if ($got == 0) { |
227 | return STATUS_EOF ; |
228 | } |
229 | elsif ($got < 0) { |
230 | return STATUS_ERROR ; |
231 | } |
232 | elsif ($got < 4) { |
233 | $self->pushBack($magic) ; |
234 | return STATUS_OK ; |
235 | } |
236 | |
237 | my $sig = unpack("V", $magic) ; |
238 | |
258133d1 |
239 | my $hdr; |
240 | if ($hdr = $headerLookup{$sig}) |
a02d0f6f |
241 | { |
258133d1 |
242 | if (&$hdr($self, $magic) != STATUS_OK ) { |
a02d0f6f |
243 | if (*$self->{Strict}) { |
244 | return STATUS_ERROR ; |
245 | } |
246 | else { |
247 | $self->clearError(); |
248 | return STATUS_OK ; |
249 | } |
250 | } |
e7d45986 |
251 | |
252 | if ($sig == ZIP_END_CENTRAL_HDR_SIG) |
253 | { |
254 | return STATUS_OK ; |
255 | last; |
a02d0f6f |
256 | } |
a02d0f6f |
257 | } |
c70c1701 |
258 | elsif ($sig == ZIP_LOCAL_HDR_SIG) |
a02d0f6f |
259 | { |
260 | $self->pushBack($magic) ; |
261 | return STATUS_OK ; |
262 | } |
263 | else |
264 | { |
265 | # put the data back |
266 | $self->pushBack($magic) ; |
267 | last; |
268 | } |
269 | } |
270 | |
271 | return $reachedEnd ; |
272 | } |
273 | |
274 | sub skipCentralDirectory |
275 | { |
276 | my $self = shift; |
277 | my $magic = shift ; |
278 | |
279 | my $buffer; |
280 | $self->smartReadExact(\$buffer, 46 - 4) |
281 | or return $self->TrailerError("Minimum header size is " . |
282 | 46 . " bytes") ; |
283 | |
284 | my $keep = $magic . $buffer ; |
285 | *$self->{HeaderPending} = $keep ; |
286 | |
287 | #my $versionMadeBy = unpack ("v", substr($buffer, 4-4, 2)); |
288 | #my $extractVersion = unpack ("v", substr($buffer, 6-4, 2)); |
289 | #my $gpFlag = unpack ("v", substr($buffer, 8-4, 2)); |
290 | #my $compressedMethod = unpack ("v", substr($buffer, 10-4, 2)); |
291 | #my $lastModTime = unpack ("V", substr($buffer, 12-4, 4)); |
292 | #my $crc32 = unpack ("V", substr($buffer, 16-4, 4)); |
e7d45986 |
293 | my $compressedLength = unpack ("V", substr($buffer, 20-4, 4)); |
294 | my $uncompressedLength = unpack ("V", substr($buffer, 24-4, 4)); |
a02d0f6f |
295 | my $filename_length = unpack ("v", substr($buffer, 28-4, 2)); |
296 | my $extra_length = unpack ("v", substr($buffer, 30-4, 2)); |
297 | my $comment_length = unpack ("v", substr($buffer, 32-4, 2)); |
298 | #my $disk_start = unpack ("v", substr($buffer, 34-4, 2)); |
299 | #my $int_file_attrib = unpack ("v", substr($buffer, 36-4, 2)); |
300 | #my $ext_file_attrib = unpack ("V", substr($buffer, 38-4, 2)); |
301 | #my $lcl_hdr_offset = unpack ("V", substr($buffer, 42-4, 2)); |
302 | |
303 | |
304 | my $filename; |
305 | my $extraField; |
306 | my $comment ; |
307 | if ($filename_length) |
308 | { |
309 | $self->smartReadExact(\$filename, $filename_length) |
2b4e0969 |
310 | or return $self->TruncatedTrailer("filename"); |
a02d0f6f |
311 | $keep .= $filename ; |
312 | } |
313 | |
314 | if ($extra_length) |
315 | { |
316 | $self->smartReadExact(\$extraField, $extra_length) |
2b4e0969 |
317 | or return $self->TruncatedTrailer("extra"); |
a02d0f6f |
318 | $keep .= $extraField ; |
319 | } |
320 | |
321 | if ($comment_length) |
322 | { |
323 | $self->smartReadExact(\$comment, $comment_length) |
2b4e0969 |
324 | or return $self->TruncatedTrailer("comment"); |
a02d0f6f |
325 | $keep .= $comment ; |
326 | } |
327 | |
328 | return STATUS_OK ; |
329 | } |
330 | |
e7d45986 |
331 | sub skipArchiveExtra |
332 | { |
333 | my $self = shift; |
334 | my $magic = shift ; |
335 | |
336 | my $buffer; |
337 | $self->smartReadExact(\$buffer, 4) |
338 | or return $self->TrailerError("Minimum header size is " . |
339 | 4 . " bytes") ; |
340 | |
341 | my $keep = $magic . $buffer ; |
342 | |
343 | my $size = unpack ("V", $buffer); |
344 | |
345 | $self->smartReadExact(\$buffer, $size) |
346 | or return $self->TrailerError("Minimum header size is " . |
347 | $size . " bytes") ; |
348 | |
349 | $keep .= $buffer ; |
350 | *$self->{HeaderPending} = $keep ; |
351 | |
352 | return STATUS_OK ; |
353 | } |
354 | |
355 | |
356 | sub skipCentralDirectory64Rec |
357 | { |
358 | my $self = shift; |
359 | my $magic = shift ; |
360 | |
361 | my $buffer; |
362 | $self->smartReadExact(\$buffer, 8) |
363 | or return $self->TrailerError("Minimum header size is " . |
364 | 8 . " bytes") ; |
365 | |
366 | my $keep = $magic . $buffer ; |
367 | |
368 | my ($sizeLo, $sizeHi) = unpack ("V V", $buffer); |
369 | |
370 | # TODO - take SizeHi into account |
371 | $self->smartReadExact(\$buffer, $sizeLo) |
372 | or return $self->TrailerError("Minimum header size is " . |
373 | $sizeLo . " bytes") ; |
374 | |
375 | $keep .= $buffer ; |
376 | *$self->{HeaderPending} = $keep ; |
377 | |
378 | #my $versionMadeBy = unpack ("v", substr($buffer, 0, 2)); |
379 | #my $extractVersion = unpack ("v", substr($buffer, 2, 2)); |
380 | #my $diskNumber = unpack ("V", substr($buffer, 4, 4)); |
381 | #my $cntrlDirDiskNo = unpack ("V", substr($buffer, 8, 4)); |
382 | #my $entriesInThisCD = unpack ("V V", substr($buffer, 12, 8)); |
383 | #my $entriesInCD = unpack ("V V", substr($buffer, 20, 8)); |
384 | #my $sizeOfCD = unpack ("V V", substr($buffer, 28, 8)); |
385 | #my $offsetToCD = unpack ("V V", substr($buffer, 36, 8)); |
386 | |
387 | return STATUS_OK ; |
388 | } |
389 | |
390 | sub skipCentralDirectory64Loc |
391 | { |
392 | my $self = shift; |
393 | my $magic = shift ; |
394 | |
395 | my $buffer; |
396 | $self->smartReadExact(\$buffer, 20 - 4) |
397 | or return $self->TrailerError("Minimum header size is " . |
398 | 20 . " bytes") ; |
399 | |
400 | my $keep = $magic . $buffer ; |
401 | *$self->{HeaderPending} = $keep ; |
402 | |
403 | #my $startCdDisk = unpack ("V", substr($buffer, 4-4, 4)); |
404 | #my $offsetToCD = unpack ("V V", substr($buffer, 8-4, 8)); |
405 | #my $diskCount = unpack ("V", substr($buffer, 16-4, 4)); |
406 | |
407 | return STATUS_OK ; |
408 | } |
409 | |
a02d0f6f |
410 | sub skipEndCentralDirectory |
411 | { |
412 | my $self = shift; |
413 | my $magic = shift ; |
414 | |
415 | my $buffer; |
416 | $self->smartReadExact(\$buffer, 22 - 4) |
417 | or return $self->TrailerError("Minimum header size is " . |
418 | 22 . " bytes") ; |
419 | |
420 | my $keep = $magic . $buffer ; |
421 | *$self->{HeaderPending} = $keep ; |
422 | |
423 | #my $diskNumber = unpack ("v", substr($buffer, 4-4, 2)); |
424 | #my $cntrlDirDiskNo = unpack ("v", substr($buffer, 6-4, 2)); |
425 | #my $entriesInThisCD = unpack ("v", substr($buffer, 8-4, 2)); |
426 | #my $entriesInCD = unpack ("v", substr($buffer, 10-4, 2)); |
427 | #my $sizeOfCD = unpack ("V", substr($buffer, 12-4, 2)); |
428 | #my $offsetToCD = unpack ("V", substr($buffer, 16-4, 2)); |
429 | my $comment_length = unpack ("v", substr($buffer, 20-4, 2)); |
430 | |
431 | |
432 | my $comment ; |
433 | if ($comment_length) |
434 | { |
435 | $self->smartReadExact(\$comment, $comment_length) |
2b4e0969 |
436 | or return $self->TruncatedTrailer("comment"); |
a02d0f6f |
437 | $keep .= $comment ; |
438 | } |
439 | |
440 | return STATUS_OK ; |
441 | } |
442 | |
443 | |
a02d0f6f |
444 | sub _isZipMagic |
445 | { |
446 | my $buffer = shift ; |
447 | return 0 if length $buffer < 4 ; |
448 | my $sig = unpack("V", $buffer) ; |
c70c1701 |
449 | return $sig == ZIP_LOCAL_HDR_SIG ; |
a02d0f6f |
450 | } |
451 | |
452 | |
453 | sub _readFullZipHeader($) |
454 | { |
455 | my ($self) = @_ ; |
456 | my $magic = '' ; |
457 | |
458 | $self->smartReadExact(\$magic, 4); |
459 | |
460 | *$self->{HeaderPending} = $magic ; |
461 | |
462 | return $self->HeaderError("Minimum header size is " . |
463 | 30 . " bytes") |
464 | if length $magic != 4 ; |
465 | |
466 | |
467 | return $self->HeaderError("Bad Magic") |
468 | if ! _isZipMagic($magic) ; |
469 | |
470 | my $status = $self->_readZipHeader($magic); |
471 | delete *$self->{Transparent} if ! defined $status ; |
472 | return $status ; |
473 | } |
474 | |
475 | sub _readZipHeader($) |
476 | { |
477 | my ($self, $magic) = @_ ; |
478 | my ($HeaderCRC) ; |
479 | my ($buffer) = '' ; |
480 | |
481 | $self->smartReadExact(\$buffer, 30 - 4) |
482 | or return $self->HeaderError("Minimum header size is " . |
483 | 30 . " bytes") ; |
484 | |
485 | my $keep = $magic . $buffer ; |
486 | *$self->{HeaderPending} = $keep ; |
487 | |
488 | my $extractVersion = unpack ("v", substr($buffer, 4-4, 2)); |
489 | my $gpFlag = unpack ("v", substr($buffer, 6-4, 2)); |
490 | my $compressedMethod = unpack ("v", substr($buffer, 8-4, 2)); |
491 | my $lastModTime = unpack ("V", substr($buffer, 10-4, 4)); |
492 | my $crc32 = unpack ("V", substr($buffer, 14-4, 4)); |
e7d45986 |
493 | my $compressedLength = new U64 unpack ("V", substr($buffer, 18-4, 4)); |
494 | my $uncompressedLength = new U64 unpack ("V", substr($buffer, 22-4, 4)); |
a02d0f6f |
495 | my $filename_length = unpack ("v", substr($buffer, 26-4, 2)); |
496 | my $extra_length = unpack ("v", substr($buffer, 28-4, 2)); |
497 | |
498 | my $filename; |
499 | my $extraField; |
c70c1701 |
500 | my @EXTRA = (); |
501 | my $streamingMode = ($gpFlag & ZIP_GP_FLAG_STREAMING_MASK) ? 1 : 0 ; |
a02d0f6f |
502 | |
503 | return $self->HeaderError("Streamed Stored content not supported") |
504 | if $streamingMode && $compressedMethod == 0 ; |
505 | |
258133d1 |
506 | return $self->HeaderError("Encrypted content not supported") |
507 | if $gpFlag & (ZIP_GP_FLAG_ENCRYPTED_MASK|ZIP_GP_FLAG_STRONG_ENCRYPTED_MASK); |
508 | |
509 | return $self->HeaderError("Patch content not supported") |
510 | if $gpFlag & ZIP_GP_FLAG_PATCHED_MASK; |
511 | |
a02d0f6f |
512 | *$self->{ZipData}{Streaming} = $streamingMode; |
513 | |
a02d0f6f |
514 | |
515 | if ($filename_length) |
516 | { |
517 | $self->smartReadExact(\$filename, $filename_length) |
c70c1701 |
518 | or return $self->TruncatedHeader("Filename"); |
a02d0f6f |
519 | $keep .= $filename ; |
520 | } |
521 | |
e7d45986 |
522 | my $zip64 = 0 ; |
523 | |
a02d0f6f |
524 | if ($extra_length) |
525 | { |
526 | $self->smartReadExact(\$extraField, $extra_length) |
c70c1701 |
527 | or return $self->TruncatedHeader("Extra Field"); |
528 | |
529 | my $bad = IO::Compress::Zlib::Extra::parseRawExtra($extraField, |
530 | \@EXTRA, 1, 0); |
531 | return $self->HeaderError($bad) |
532 | if defined $bad; |
533 | |
a02d0f6f |
534 | $keep .= $extraField ; |
e7d45986 |
535 | |
536 | my %Extra ; |
537 | for (@EXTRA) |
538 | { |
539 | $Extra{$_->[0]} = \$_->[1]; |
540 | } |
541 | |
542 | if (defined $Extra{ZIP_EXTRA_ID_ZIP64()}) |
543 | { |
544 | $zip64 = 1 ; |
545 | |
546 | my $buff = ${ $Extra{ZIP_EXTRA_ID_ZIP64()} }; |
547 | |
258133d1 |
548 | # TODO - This code assumes that all the fields in the Zip64 |
549 | # extra field aren't necessarily present. The spec says that |
550 | # they only exist if the equivalent local headers are -1. |
551 | # Need to check that info-zip fills out -1 in the local header |
552 | # correctly. |
553 | |
554 | if (! $streamingMode) { |
555 | my $offset = 0 ; |
556 | |
557 | $uncompressedLength = U64::newUnpack_V64 substr($buff, 0, 8) |
558 | if $uncompressedLength == 0xFFFF ; |
559 | |
560 | $offset += 8 ; |
561 | |
562 | $compressedLength = U64::newUnpack_V64 substr($buff, $offset, 8) |
563 | if $compressedLength == 0xFFFF ; |
564 | |
565 | $offset += 8 ; |
566 | |
567 | #my $cheaderOffset = U64::newUnpack_V64 substr($buff, 16, 8); |
568 | #my $diskNumber = unpack ("V", substr($buff, 24, 4)); |
569 | } |
e7d45986 |
570 | } |
571 | } |
572 | |
573 | *$self->{ZipData}{Zip64} = $zip64; |
574 | |
575 | if (! $streamingMode) { |
576 | *$self->{ZipData}{Streaming} = 0; |
577 | *$self->{ZipData}{Crc32} = $crc32; |
578 | *$self->{ZipData}{CompressedLen} = $compressedLength; |
579 | *$self->{ZipData}{UnCompressedLen} = $uncompressedLength; |
580 | *$self->{CompressedInputLengthRemaining} = |
581 | *$self->{CompressedInputLength} = $compressedLength->get32bit(); |
a02d0f6f |
582 | } |
583 | |
2b4e0969 |
584 | *$self->{ZipData}{Method} = $compressedMethod; |
c70c1701 |
585 | if ($compressedMethod == ZIP_CM_DEFLATE) |
a02d0f6f |
586 | { |
2b4e0969 |
587 | *$self->{Type} = 'zip-deflate'; |
588 | } |
c70c1701 |
589 | elsif ($compressedMethod == ZIP_CM_BZIP2) |
2b4e0969 |
590 | { |
591 | #if (! defined $IO::Uncompress::Adapter::Bunzip2::VERSION) |
592 | |
593 | *$self->{Type} = 'zip-bzip2'; |
594 | |
595 | my $obj = IO::Uncompress::Adapter::Bunzip2::mkUncompObject( |
596 | ); |
597 | |
598 | *$self->{Uncomp} = $obj; |
599 | *$self->{ZipData}{CRC32} = crc32(undef); |
600 | |
a02d0f6f |
601 | } |
c70c1701 |
602 | elsif ($compressedMethod == ZIP_CM_STORE) |
a02d0f6f |
603 | { |
604 | # TODO -- add support for reading uncompressed |
605 | |
2b4e0969 |
606 | *$self->{Type} = 'zip-stored'; |
a02d0f6f |
607 | |
608 | my $obj = IO::Uncompress::Adapter::Identity::mkUncompObject(# $got->value('CRC32'), |
609 | # $got->value('ADLER32'), |
610 | ); |
611 | |
612 | *$self->{Uncomp} = $obj; |
613 | |
614 | } |
615 | else |
616 | { |
617 | return $self->HeaderError("Unsupported Compression format $compressedMethod"); |
618 | } |
619 | |
620 | return { |
621 | 'Type' => 'zip', |
622 | 'FingerprintLength' => 4, |
623 | #'HeaderLength' => $compressedMethod == 8 ? length $keep : 0, |
624 | 'HeaderLength' => length $keep, |
e7d45986 |
625 | 'Zip64' => $zip64, |
626 | 'TrailerLength' => ! $streamingMode ? 0 : $zip64 ? 24 : 16, |
a02d0f6f |
627 | 'Header' => $keep, |
628 | 'CompressedLength' => $compressedLength , |
629 | 'UncompressedLength' => $uncompressedLength , |
630 | 'CRC32' => $crc32 , |
631 | 'Name' => $filename, |
632 | 'Time' => _dosToUnixTime($lastModTime), |
633 | 'Stream' => $streamingMode, |
634 | |
635 | 'MethodID' => $compressedMethod, |
c70c1701 |
636 | 'MethodName' => $compressedMethod == ZIP_CM_DEFLATE |
a02d0f6f |
637 | ? "Deflated" |
c70c1701 |
638 | : $compressedMethod == ZIP_CM_BZIP2 |
639 | ? "Bzip2" |
640 | : $compressedMethod == ZIP_CM_STORE |
641 | ? "Stored" |
642 | : "Unknown" , |
a02d0f6f |
643 | |
644 | # 'TextFlag' => $flag & GZIP_FLG_FTEXT ? 1 : 0, |
645 | # 'HeaderCRCFlag' => $flag & GZIP_FLG_FHCRC ? 1 : 0, |
646 | # 'NameFlag' => $flag & GZIP_FLG_FNAME ? 1 : 0, |
647 | # 'CommentFlag' => $flag & GZIP_FLG_FCOMMENT ? 1 : 0, |
648 | # 'ExtraFlag' => $flag & GZIP_FLG_FEXTRA ? 1 : 0, |
649 | # 'Comment' => $comment, |
650 | # 'OsID' => $os, |
651 | # 'OsName' => defined $GZIP_OS_Names{$os} |
652 | # ? $GZIP_OS_Names{$os} : "Unknown", |
653 | # 'HeaderCRC' => $HeaderCRC, |
654 | # 'Flags' => $flag, |
655 | # 'ExtraFlags' => $xfl, |
c70c1701 |
656 | 'ExtraFieldRaw' => $extraField, |
657 | 'ExtraField' => [ @EXTRA ], |
a02d0f6f |
658 | |
659 | |
660 | } |
661 | } |
662 | |
2b4e0969 |
663 | sub filterUncompressed |
664 | { |
665 | my $self = shift ; |
666 | |
667 | if (*$self->{ZipData}{Method} == 12) { |
668 | *$self->{ZipData}{CRC32} = crc32(${$_[0]}, *$self->{ZipData}{CRC32}); |
669 | } |
670 | else { |
671 | *$self->{ZipData}{CRC32} = *$self->{Uncomp}->crc32() ; |
672 | } |
673 | } |
674 | |
675 | |
a02d0f6f |
676 | # from Archive::Zip |
677 | sub _dosToUnixTime |
678 | { |
679 | #use Time::Local 'timelocal_nocheck'; |
680 | use Time::Local 'timelocal'; |
681 | |
682 | my $dt = shift; |
683 | |
684 | my $year = ( ( $dt >> 25 ) & 0x7f ) + 80; |
685 | my $mon = ( ( $dt >> 21 ) & 0x0f ) - 1; |
686 | my $mday = ( ( $dt >> 16 ) & 0x1f ); |
687 | |
688 | my $hour = ( ( $dt >> 11 ) & 0x1f ); |
689 | my $min = ( ( $dt >> 5 ) & 0x3f ); |
690 | my $sec = ( ( $dt << 1 ) & 0x3e ); |
691 | |
692 | # catch errors |
693 | my $time_t = |
694 | eval { timelocal( $sec, $min, $hour, $mday, $mon, $year ); }; |
695 | return 0 |
696 | if $@; |
697 | return $time_t; |
698 | } |
699 | |
700 | |
701 | 1; |
702 | |
703 | __END__ |
704 | |
705 | |
706 | =head1 NAME |
707 | |
708 | |
cb7abd7f |
709 | |
710 | IO::Uncompress::Unzip - Read zip files/buffers |
711 | |
a02d0f6f |
712 | |
713 | |
714 | =head1 SYNOPSIS |
715 | |
716 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
717 | |
718 | my $status = unzip $input => $output [,OPTS] |
719 | or die "unzip failed: $UnzipError\n"; |
720 | |
721 | my $z = new IO::Uncompress::Unzip $input [OPTS] |
722 | or die "unzip failed: $UnzipError\n"; |
723 | |
724 | $status = $z->read($buffer) |
725 | $status = $z->read($buffer, $length) |
726 | $status = $z->read($buffer, $length, $offset) |
727 | $line = $z->getline() |
728 | $char = $z->getc() |
729 | $char = $z->ungetc() |
730 | $char = $z->opened() |
731 | |
732 | $status = $z->inflateSync() |
733 | |
e7d45986 |
734 | $data = $z->trailingData() |
735 | $status = $z->nextStream() |
a02d0f6f |
736 | $data = $z->getHeaderInfo() |
737 | $z->tell() |
738 | $z->seek($position, $whence) |
739 | $z->binmode() |
740 | $z->fileno() |
741 | $z->eof() |
742 | $z->close() |
743 | |
744 | $UnzipError ; |
745 | |
746 | # IO::File mode |
747 | |
748 | <$z> |
749 | read($z, $buffer); |
750 | read($z, $buffer, $length); |
751 | read($z, $buffer, $length, $offset); |
752 | tell($z) |
753 | seek($z, $position, $whence) |
754 | binmode($z) |
755 | fileno($z) |
756 | eof($z) |
757 | close($z) |
758 | |
759 | |
760 | =head1 DESCRIPTION |
761 | |
762 | |
763 | |
a02d0f6f |
764 | This module provides a Perl interface that allows the reading of |
765 | zlib files/buffers. |
766 | |
767 | For writing zip files/buffers, see the companion module IO::Compress::Zip. |
768 | |
769 | |
770 | |
cb7abd7f |
771 | |
772 | |
a02d0f6f |
773 | =head1 Functional Interface |
774 | |
775 | A top-level function, C<unzip>, is provided to carry out |
776 | "one-shot" uncompression between buffers and/or files. For finer |
777 | control over the uncompression process, see the L</"OO Interface"> |
778 | section. |
779 | |
780 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
781 | |
782 | unzip $input => $output [,OPTS] |
783 | or die "unzip failed: $UnzipError\n"; |
784 | |
785 | |
786 | |
787 | The functional interface needs Perl5.005 or better. |
788 | |
789 | |
790 | =head2 unzip $input => $output [, OPTS] |
791 | |
792 | |
793 | C<unzip> expects at least two parameters, C<$input> and C<$output>. |
794 | |
795 | =head3 The C<$input> parameter |
796 | |
797 | The parameter, C<$input>, is used to define the source of |
798 | the compressed data. |
799 | |
800 | It can take one of the following forms: |
801 | |
802 | =over 5 |
803 | |
804 | =item A filename |
805 | |
806 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
807 | filename. This file will be opened for reading and the input data |
808 | will be read from it. |
809 | |
810 | =item A filehandle |
811 | |
812 | If the C<$input> parameter is a filehandle, the input data will be |
813 | read from it. |
814 | The string '-' can be used as an alias for standard input. |
815 | |
816 | =item A scalar reference |
817 | |
818 | If C<$input> is a scalar reference, the input data will be read |
819 | from C<$$input>. |
820 | |
821 | =item An array reference |
822 | |
823 | If C<$input> is an array reference, each element in the array must be a |
824 | filename. |
825 | |
826 | The input data will be read from each file in turn. |
827 | |
828 | The complete array will be walked to ensure that it only |
829 | contains valid filenames before any data is uncompressed. |
830 | |
831 | |
832 | |
833 | =item An Input FileGlob string |
834 | |
835 | If C<$input> is a string that is delimited by the characters "<" and ">" |
836 | C<unzip> will assume that it is an I<input fileglob string>. The |
837 | input is the list of files that match the fileglob. |
838 | |
839 | If the fileglob does not match any files ... |
840 | |
841 | See L<File::GlobMapper|File::GlobMapper> for more details. |
842 | |
843 | |
844 | =back |
845 | |
846 | If the C<$input> parameter is any other type, C<undef> will be returned. |
847 | |
848 | |
849 | |
850 | =head3 The C<$output> parameter |
851 | |
852 | The parameter C<$output> is used to control the destination of the |
853 | uncompressed data. This parameter can take one of these forms. |
854 | |
855 | =over 5 |
856 | |
857 | =item A filename |
858 | |
859 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
860 | filename. This file will be opened for writing and the uncompressed |
861 | data will be written to it. |
862 | |
863 | =item A filehandle |
864 | |
865 | If the C<$output> parameter is a filehandle, the uncompressed data |
866 | will be written to it. |
867 | The string '-' can be used as an alias for standard output. |
868 | |
869 | |
870 | =item A scalar reference |
871 | |
872 | If C<$output> is a scalar reference, the uncompressed data will be |
873 | stored in C<$$output>. |
874 | |
875 | |
876 | |
877 | =item An Array Reference |
878 | |
879 | If C<$output> is an array reference, the uncompressed data will be |
880 | pushed onto the array. |
881 | |
882 | =item An Output FileGlob |
883 | |
884 | If C<$output> is a string that is delimited by the characters "<" and ">" |
885 | C<unzip> will assume that it is an I<output fileglob string>. The |
886 | output is the list of files that match the fileglob. |
887 | |
888 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
889 | string. Anything else is an error. |
890 | |
891 | =back |
892 | |
893 | If the C<$output> parameter is any other type, C<undef> will be returned. |
894 | |
895 | |
896 | |
897 | =head2 Notes |
898 | |
c70c1701 |
899 | |
900 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
901 | a single file/buffer, after uncompression C<$output> will contain a |
902 | concatenation of all the uncompressed data from each of the input |
903 | files/buffers. |
904 | |
905 | |
a02d0f6f |
906 | |
907 | |
908 | |
909 | =head2 Optional Parameters |
910 | |
911 | Unless specified below, the optional parameters for C<unzip>, |
912 | C<OPTS>, are the same as those used with the OO interface defined in the |
913 | L</"Constructor Options"> section below. |
914 | |
915 | =over 5 |
916 | |
e7d45986 |
917 | =item C<< AutoClose => 0|1 >> |
a02d0f6f |
918 | |
919 | This option applies to any input or output data streams to |
920 | C<unzip> that are filehandles. |
921 | |
922 | If C<AutoClose> is specified, and the value is true, it will result in all |
923 | input and/or output filehandles being closed once C<unzip> has |
924 | completed. |
925 | |
926 | This parameter defaults to 0. |
927 | |
928 | |
e7d45986 |
929 | =item C<< BinModeOut => 0|1 >> |
a02d0f6f |
930 | |
931 | When writing to a file or filehandle, set C<binmode> before writing to the |
932 | file. |
933 | |
934 | Defaults to 0. |
935 | |
936 | |
937 | |
938 | |
939 | |
e7d45986 |
940 | =item C<< Append => 0|1 >> |
a02d0f6f |
941 | |
942 | TODO |
943 | |
e7d45986 |
944 | =item C<< MultiStream => 0|1 >> |
a02d0f6f |
945 | |
258133d1 |
946 | |
e7d45986 |
947 | If the input file/buffer contains multiple compressed data streams, this |
948 | option will uncompress the whole lot as a single data stream. |
a02d0f6f |
949 | |
e7d45986 |
950 | Defaults to 0. |
a02d0f6f |
951 | |
952 | |
953 | |
258133d1 |
954 | |
955 | |
956 | =item C<< TrailingData => $scalar >> |
957 | |
958 | Returns the data, if any, that is present immediately after the compressed |
959 | data stream once uncompression is complete. |
960 | |
961 | This option can be used when there is useful information immediately |
962 | following the compressed data stream, and you don't know the length of the |
963 | compressed data stream. |
964 | |
965 | If the input is a buffer, C<trailingData> will return everything from the |
966 | end of the compressed data stream to the end of the buffer. |
967 | |
968 | If the input is a filehandle, C<trailingData> will return the data that is |
969 | left in the filehandle input buffer once the end of the compressed data |
970 | stream has been reached. You can then use the filehandle to read the rest |
971 | of the input file. |
972 | |
973 | Don't bother using C<trailingData> if the input is a filename. |
974 | |
975 | |
976 | |
977 | If you know the length of the compressed data stream before you start |
978 | uncompressing, you can avoid having to use C<trailingData> by setting the |
979 | C<InputLength> option. |
980 | |
981 | |
982 | |
a02d0f6f |
983 | =back |
984 | |
985 | |
986 | |
987 | |
988 | =head2 Examples |
989 | |
990 | To read the contents of the file C<file1.txt.zip> and write the |
991 | compressed data to the file C<file1.txt>. |
992 | |
993 | use strict ; |
994 | use warnings ; |
995 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
996 | |
997 | my $input = "file1.txt.zip"; |
998 | my $output = "file1.txt"; |
999 | unzip $input => $output |
1000 | or die "unzip failed: $UnzipError\n"; |
1001 | |
1002 | |
1003 | To read from an existing Perl filehandle, C<$input>, and write the |
1004 | uncompressed data to a buffer, C<$buffer>. |
1005 | |
1006 | use strict ; |
1007 | use warnings ; |
1008 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
1009 | use IO::File ; |
1010 | |
1011 | my $input = new IO::File "<file1.txt.zip" |
1012 | or die "Cannot open 'file1.txt.zip': $!\n" ; |
1013 | my $buffer ; |
1014 | unzip $input => \$buffer |
1015 | or die "unzip failed: $UnzipError\n"; |
1016 | |
1017 | To uncompress all files in the directory "/my/home" that match "*.txt.zip" and store the compressed data in the same directory |
1018 | |
1019 | use strict ; |
1020 | use warnings ; |
1021 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
1022 | |
1023 | unzip '</my/home/*.txt.zip>' => '</my/home/#1.txt>' |
1024 | or die "unzip failed: $UnzipError\n"; |
1025 | |
1026 | and if you want to compress each file one at a time, this will do the trick |
1027 | |
1028 | use strict ; |
1029 | use warnings ; |
1030 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
1031 | |
1032 | for my $input ( glob "/my/home/*.txt.zip" ) |
1033 | { |
1034 | my $output = $input; |
1035 | $output =~ s/.zip// ; |
1036 | unzip $input => $output |
1037 | or die "Error compressing '$input': $UnzipError\n"; |
1038 | } |
1039 | |
1040 | =head1 OO Interface |
1041 | |
1042 | =head2 Constructor |
1043 | |
1044 | The format of the constructor for IO::Uncompress::Unzip is shown below |
1045 | |
1046 | |
1047 | my $z = new IO::Uncompress::Unzip $input [OPTS] |
1048 | or die "IO::Uncompress::Unzip failed: $UnzipError\n"; |
1049 | |
1050 | Returns an C<IO::Uncompress::Unzip> object on success and undef on failure. |
1051 | The variable C<$UnzipError> will contain an error message on failure. |
1052 | |
1053 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
1054 | IO::Uncompress::Unzip can be used exactly like an L<IO::File|IO::File> filehandle. |
1055 | This means that all normal input file operations can be carried out with |
1056 | C<$z>. For example, to read a line from a compressed file/buffer you can |
1057 | use either of these forms |
1058 | |
1059 | $line = $z->getline(); |
1060 | $line = <$z>; |
1061 | |
1062 | The mandatory parameter C<$input> is used to determine the source of the |
1063 | compressed data. This parameter can take one of three forms. |
1064 | |
1065 | =over 5 |
1066 | |
1067 | =item A filename |
1068 | |
1069 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
1070 | file will be opened for reading and the compressed data will be read from it. |
1071 | |
1072 | =item A filehandle |
1073 | |
1074 | If the C<$input> parameter is a filehandle, the compressed data will be |
1075 | read from it. |
1076 | The string '-' can be used as an alias for standard input. |
1077 | |
1078 | |
1079 | =item A scalar reference |
1080 | |
1081 | If C<$input> is a scalar reference, the compressed data will be read from |
1082 | C<$$output>. |
1083 | |
1084 | =back |
1085 | |
1086 | =head2 Constructor Options |
1087 | |
1088 | |
1089 | The option names defined below are case insensitive and can be optionally |
1090 | prefixed by a '-'. So all of the following are valid |
1091 | |
1092 | -AutoClose |
1093 | -autoclose |
1094 | AUTOCLOSE |
1095 | autoclose |
1096 | |
1097 | OPTS is a combination of the following options: |
1098 | |
1099 | =over 5 |
1100 | |
e7d45986 |
1101 | =item C<< AutoClose => 0|1 >> |
a02d0f6f |
1102 | |
1103 | This option is only valid when the C<$input> parameter is a filehandle. If |
1104 | specified, and the value is true, it will result in the file being closed once |
1105 | either the C<close> method is called or the IO::Uncompress::Unzip object is |
1106 | destroyed. |
1107 | |
1108 | This parameter defaults to 0. |
1109 | |
e7d45986 |
1110 | =item C<< MultiStream => 0|1 >> |
a02d0f6f |
1111 | |
1112 | |
1113 | |
e7d45986 |
1114 | Treats the complete zip file/buffer as a single compressed data |
1115 | stream. When reading in multi-stream mode each member of the zip |
1116 | file/buffer will be uncompressed in turn until the end of the file/buffer |
1117 | is encountered. |
a02d0f6f |
1118 | |
1119 | This parameter defaults to 0. |
1120 | |
1121 | |
e7d45986 |
1122 | =item C<< Prime => $string >> |
a02d0f6f |
1123 | |
1124 | This option will uncompress the contents of C<$string> before processing the |
1125 | input file/buffer. |
1126 | |
1127 | This option can be useful when the compressed data is embedded in another |
1128 | file/data structure and it is not possible to work out where the compressed |
1129 | data begins without having to read the first few bytes. If this is the |
1130 | case, the uncompression can be I<primed> with these bytes using this |
1131 | option. |
1132 | |
e7d45986 |
1133 | =item C<< Transparent => 0|1 >> |
a02d0f6f |
1134 | |
1135 | If this option is set and the input file or buffer is not compressed data, |
1136 | the module will allow reading of it anyway. |
1137 | |
1138 | This option defaults to 1. |
1139 | |
e7d45986 |
1140 | =item C<< BlockSize => $num >> |
a02d0f6f |
1141 | |
1142 | When reading the compressed input data, IO::Uncompress::Unzip will read it in |
1143 | blocks of C<$num> bytes. |
1144 | |
1145 | This option defaults to 4096. |
1146 | |
e7d45986 |
1147 | =item C<< InputLength => $size >> |
a02d0f6f |
1148 | |
1149 | When present this option will limit the number of compressed bytes read |
1150 | from the input file/buffer to C<$size>. This option can be used in the |
1151 | situation where there is useful data directly after the compressed data |
1152 | stream and you know beforehand the exact length of the compressed data |
1153 | stream. |
1154 | |
1155 | This option is mostly used when reading from a filehandle, in which case |
1156 | the file pointer will be left pointing to the first byte directly after the |
1157 | compressed data stream. |
1158 | |
1159 | |
1160 | |
1161 | This option defaults to off. |
1162 | |
e7d45986 |
1163 | =item C<< Append => 0|1 >> |
a02d0f6f |
1164 | |
1165 | This option controls what the C<read> method does with uncompressed data. |
1166 | |
1167 | If set to 1, all uncompressed data will be appended to the output parameter |
1168 | of the C<read> method. |
1169 | |
1170 | If set to 0, the contents of the output parameter of the C<read> method |
1171 | will be overwritten by the uncompressed data. |
1172 | |
1173 | Defaults to 0. |
1174 | |
e7d45986 |
1175 | =item C<< Strict => 0|1 >> |
a02d0f6f |
1176 | |
1177 | |
1178 | |
1179 | This option controls whether the extra checks defined below are used when |
1180 | carrying out the decompression. When Strict is on, the extra tests are |
1181 | carried out, when Strict is off they are not. |
1182 | |
1183 | The default for this option is off. |
1184 | |
1185 | |
1186 | |
1187 | |
1188 | |
1189 | |
1190 | |
1191 | |
1192 | |
1193 | |
1194 | |
1195 | |
1196 | |
1197 | |
258133d1 |
1198 | |
a02d0f6f |
1199 | =back |
1200 | |
1201 | =head2 Examples |
1202 | |
1203 | TODO |
1204 | |
1205 | =head1 Methods |
1206 | |
1207 | =head2 read |
1208 | |
1209 | Usage is |
1210 | |
1211 | $status = $z->read($buffer) |
1212 | |
1213 | Reads a block of compressed data (the size the the compressed block is |
1214 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1215 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
1216 | set in the constructor, the uncompressed data will be appended to the |
1217 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
1218 | |
1219 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
1220 | or a negative number on error. |
1221 | |
1222 | =head2 read |
1223 | |
1224 | Usage is |
1225 | |
1226 | $status = $z->read($buffer, $length) |
1227 | $status = $z->read($buffer, $length, $offset) |
1228 | |
1229 | $status = read($z, $buffer, $length) |
1230 | $status = read($z, $buffer, $length, $offset) |
1231 | |
1232 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
1233 | |
1234 | The main difference between this form of the C<read> method and the |
1235 | previous one, is that this one will attempt to return I<exactly> C<$length> |
1236 | bytes. The only circumstances that this function will not is if end-of-file |
1237 | or an IO error is encountered. |
1238 | |
1239 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
1240 | or a negative number on error. |
1241 | |
1242 | |
1243 | =head2 getline |
1244 | |
1245 | Usage is |
1246 | |
1247 | $line = $z->getline() |
1248 | $line = <$z> |
1249 | |
1250 | Reads a single line. |
1251 | |
258133d1 |
1252 | This method fully supports the use of of the variable C<$/> (or |
1253 | C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
1254 | determine what constitutes an end of line. Paragraph mode, record mode and |
1255 | file slurp mode are all supported. |
a02d0f6f |
1256 | |
1257 | |
1258 | =head2 getc |
1259 | |
1260 | Usage is |
1261 | |
1262 | $char = $z->getc() |
1263 | |
1264 | Read a single character. |
1265 | |
1266 | =head2 ungetc |
1267 | |
1268 | Usage is |
1269 | |
1270 | $char = $z->ungetc($string) |
1271 | |
1272 | |
1273 | |
1274 | =head2 inflateSync |
1275 | |
1276 | Usage is |
1277 | |
1278 | $status = $z->inflateSync() |
1279 | |
1280 | TODO |
1281 | |
1282 | |
1283 | =head2 getHeaderInfo |
1284 | |
1285 | Usage is |
1286 | |
1287 | $hdr = $z->getHeaderInfo(); |
1288 | @hdrs = $z->getHeaderInfo(); |
1289 | |
1290 | This method returns either a hash reference (in scalar context) or a list |
1291 | or hash references (in array context) that contains information about each |
1292 | of the header fields in the compressed data stream(s). |
1293 | |
1294 | |
1295 | |
1296 | |
1297 | =head2 tell |
1298 | |
1299 | Usage is |
1300 | |
1301 | $z->tell() |
1302 | tell $z |
1303 | |
1304 | Returns the uncompressed file offset. |
1305 | |
1306 | =head2 eof |
1307 | |
1308 | Usage is |
1309 | |
1310 | $z->eof(); |
1311 | eof($z); |
1312 | |
1313 | |
1314 | |
1315 | Returns true if the end of the compressed input stream has been reached. |
1316 | |
1317 | |
1318 | |
1319 | =head2 seek |
1320 | |
1321 | $z->seek($position, $whence); |
1322 | seek($z, $position, $whence); |
1323 | |
1324 | |
1325 | |
1326 | |
1327 | Provides a sub-set of the C<seek> functionality, with the restriction |
1328 | that it is only legal to seek forward in the input file/buffer. |
1329 | It is a fatal error to attempt to seek backward. |
1330 | |
1331 | |
1332 | |
1333 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
1334 | SEEK_CUR or SEEK_END. |
1335 | |
1336 | Returns 1 on success, 0 on failure. |
1337 | |
1338 | =head2 binmode |
1339 | |
1340 | Usage is |
1341 | |
1342 | $z->binmode |
1343 | binmode $z ; |
1344 | |
1345 | This is a noop provided for completeness. |
1346 | |
1347 | =head2 opened |
1348 | |
1349 | $z->opened() |
1350 | |
1351 | Returns true if the object currently refers to a opened file/buffer. |
1352 | |
1353 | =head2 autoflush |
1354 | |
1355 | my $prev = $z->autoflush() |
1356 | my $prev = $z->autoflush(EXPR) |
1357 | |
1358 | If the C<$z> object is associated with a file or a filehandle, this method |
1359 | returns the current autoflush setting for the underlying filehandle. If |
1360 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
1361 | write/print operation. |
1362 | |
1363 | If C<$z> is associated with a buffer, this method has no effect and always |
1364 | returns C<undef>. |
1365 | |
1366 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
1367 | retrieve the autoflush setting. |
1368 | |
1369 | =head2 input_line_number |
1370 | |
1371 | $z->input_line_number() |
1372 | $z->input_line_number(EXPR) |
1373 | |
1374 | |
1375 | |
1376 | Returns the current uncompressed line number. If C<EXPR> is present it has |
1377 | the effect of setting the line number. Note that setting the line number |
1378 | does not change the current position within the file/buffer being read. |
1379 | |
1380 | The contents of C<$/> are used to to determine what constitutes a line |
1381 | terminator. |
1382 | |
1383 | |
1384 | |
1385 | =head2 fileno |
1386 | |
1387 | $z->fileno() |
1388 | fileno($z) |
1389 | |
1390 | If the C<$z> object is associated with a file or a filehandle, this method |
1391 | will return the underlying file descriptor. |
1392 | |
1393 | If the C<$z> object is is associated with a buffer, this method will |
1394 | return undef. |
1395 | |
1396 | =head2 close |
1397 | |
1398 | $z->close() ; |
1399 | close $z ; |
1400 | |
1401 | |
1402 | |
1403 | Closes the output file/buffer. |
1404 | |
1405 | |
1406 | |
1407 | For most versions of Perl this method will be automatically invoked if |
1408 | the IO::Uncompress::Unzip object is destroyed (either explicitly or by the |
1409 | variable with the reference to the object going out of scope). The |
1410 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
1411 | these cases, the C<close> method will be called automatically, but |
1412 | not until global destruction of all live objects when the program is |
1413 | terminating. |
1414 | |
1415 | Therefore, if you want your scripts to be able to run on all versions |
1416 | of Perl, you should call C<close> explicitly and not rely on automatic |
1417 | closing. |
1418 | |
1419 | Returns true on success, otherwise 0. |
1420 | |
1421 | If the C<AutoClose> option has been enabled when the IO::Uncompress::Unzip |
1422 | object was created, and the object is associated with a file, the |
1423 | underlying file will also be closed. |
1424 | |
1425 | |
1426 | |
1427 | |
e7d45986 |
1428 | =head2 nextStream |
1429 | |
1430 | Usage is |
1431 | |
1432 | my $status = $z->nextStream(); |
1433 | |
1434 | Skips to the next compressed data stream in the input file/buffer. If a new |
258133d1 |
1435 | compressed data stream is found, the eof marker will be cleared and C<$.> |
1436 | will be reset to 0. |
e7d45986 |
1437 | |
1438 | Returns 1 if a new stream was found, 0 if none was found, and -1 if an |
1439 | error was encountered. |
1440 | |
1441 | =head2 trailingData |
1442 | |
1443 | Usage is |
1444 | |
1445 | my $data = $z->trailingData(); |
1446 | |
258133d1 |
1447 | Returns the data, if any, that is present immediately after the compressed |
1448 | data stream once uncompression is complete. It only makes sense to call |
1449 | this method once the end of the compressed data stream has been |
1450 | encountered. |
1451 | |
1452 | This option can be used when there is useful information immediately |
1453 | following the compressed data stream, and you don't know the length of the |
1454 | compressed data stream. |
1455 | |
1456 | If the input is a buffer, C<trailingData> will return everything from the |
1457 | end of the compressed data stream to the end of the buffer. |
1458 | |
1459 | If the input is a filehandle, C<trailingData> will return the data that is |
1460 | left in the filehandle input buffer once the end of the compressed data |
1461 | stream has been reached. You can then use the filehandle to read the rest |
1462 | of the input file. |
1463 | |
1464 | Don't bother using C<trailingData> if the input is a filename. |
1465 | |
1466 | |
1467 | |
1468 | If you know the length of the compressed data stream before you start |
1469 | uncompressing, you can avoid having to use C<trailingData> by setting the |
1470 | C<InputLength> option in the constructor. |
e7d45986 |
1471 | |
a02d0f6f |
1472 | =head1 Importing |
1473 | |
1474 | No symbolic constants are required by this IO::Uncompress::Unzip at present. |
1475 | |
1476 | =over 5 |
1477 | |
1478 | =item :all |
1479 | |
1480 | Imports C<unzip> and C<$UnzipError>. |
1481 | Same as doing this |
1482 | |
1483 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
1484 | |
1485 | =back |
1486 | |
1487 | =head1 EXAMPLES |
1488 | |
1489 | |
1490 | |
1491 | |
1492 | =head1 SEE ALSO |
1493 | |
258133d1 |
1494 | L<Compress::Zlib>, L<IO::Compress::Gzip>, L<IO::Uncompress::Gunzip>, L<IO::Compress::Deflate>, L<IO::Uncompress::Inflate>, L<IO::Compress::RawDeflate>, L<IO::Uncompress::RawInflate>, L<IO::Compress::Bzip2>, L<IO::Uncompress::Bunzip2>, L<IO::Compress::Lzop>, L<IO::Uncompress::UnLzop>, L<IO::Compress::Lzf>, L<IO::Uncompress::UnLzf>, L<IO::Uncompress::AnyInflate>, L<IO::Uncompress::AnyUncompress> |
a02d0f6f |
1495 | |
1496 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
1497 | |
1498 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1499 | L<Archive::Tar|Archive::Tar>, |
1500 | L<IO::Zlib|IO::Zlib> |
1501 | |
1502 | |
1503 | For RFC 1950, 1951 and 1952 see |
1504 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
1505 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
1506 | F<http://www.faqs.org/rfcs/rfc1952.html> |
1507 | |
1508 | The I<zlib> compression library was written by Jean-loup Gailly |
1509 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
1510 | |
1511 | The primary site for the I<zlib> compression library is |
1512 | F<http://www.zlib.org>. |
1513 | |
1514 | The primary site for gzip is F<http://www.gzip.org>. |
1515 | |
1516 | |
1517 | |
1518 | |
a02d0f6f |
1519 | =head1 AUTHOR |
1520 | |
cb7abd7f |
1521 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
a02d0f6f |
1522 | |
1523 | |
1524 | |
1525 | =head1 MODIFICATION HISTORY |
1526 | |
1527 | See the Changes file. |
1528 | |
1529 | =head1 COPYRIGHT AND LICENSE |
a02d0f6f |
1530 | |
1531 | Copyright (c) 2005-2006 Paul Marquess. All rights reserved. |
1532 | |
1533 | This program is free software; you can redistribute it and/or |
1534 | modify it under the same terms as Perl itself. |
1535 | |