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 | |
28 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $UnzipError); |
29 | |
c70c1701 |
30 | $VERSION = '2.000_12'; |
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 | |
a02d0f6f |
39 | sub new |
40 | { |
41 | my $class = shift ; |
42 | my $obj = createSelfTiedObject($class, \$UnzipError); |
43 | $obj->_create(undef, 0, @_); |
44 | } |
45 | |
46 | sub unzip |
47 | { |
48 | my $obj = createSelfTiedObject(undef, \$UnzipError); |
49 | return $obj->_inf(@_) ; |
50 | } |
51 | |
52 | sub getExtraParams |
53 | { |
54 | use IO::Compress::Base::Common qw(:Parse); |
55 | |
56 | |
57 | return ( |
58 | # # Zip header fields |
59 | 'Name' => [1, 1, Parse_any, undef], |
60 | |
61 | # 'Streaming' => [1, 1, Parse_boolean, 1], |
62 | ); |
63 | } |
64 | |
65 | sub ckParams |
66 | { |
67 | my $self = shift ; |
68 | my $got = shift ; |
69 | |
70 | # unzip always needs crc32 |
71 | $got->value('CRC32' => 1); |
72 | |
73 | *$self->{UnzipData}{Name} = $got->value('Name'); |
74 | |
75 | return 1; |
76 | } |
77 | |
78 | |
79 | sub ckMagic |
80 | { |
81 | my $self = shift; |
82 | |
83 | my $magic ; |
84 | $self->smartReadExact(\$magic, 4); |
85 | |
86 | *$self->{HeaderPending} = $magic ; |
87 | |
88 | return $self->HeaderError("Minimum header size is " . |
89 | 4 . " bytes") |
90 | if length $magic != 4 ; |
91 | |
92 | return $self->HeaderError("Bad Magic") |
93 | if ! _isZipMagic($magic) ; |
94 | |
95 | *$self->{Type} = 'zip'; |
96 | |
97 | return $magic ; |
98 | } |
99 | |
100 | |
101 | |
102 | sub readHeader |
103 | { |
104 | my $self = shift; |
105 | my $magic = shift ; |
106 | |
107 | my $name = *$self->{UnzipData}{Name} ; |
108 | my $hdr = $self->_readZipHeader($magic) ; |
109 | |
110 | while (defined $hdr) |
111 | { |
112 | if (! defined $name || $hdr->{Name} eq $name) |
113 | { |
114 | return $hdr ; |
115 | } |
116 | |
117 | # skip the data |
118 | my $buffer; |
119 | if (*$self->{ZipData}{Streaming}) { |
120 | |
121 | while (1) { |
122 | |
123 | my $b; |
124 | my $status = $self->smartRead(\$b, 1024 * 16); |
125 | return undef |
126 | if $status <= 0 ; |
127 | |
128 | my $temp_buf; |
129 | my $out; |
130 | $status = *$self->{Uncomp}->uncompr(\$b, \$temp_buf, 0, $out); |
131 | |
132 | return $self->saveErrorString(undef, *$self->{Uncomp}{Error}, |
133 | *$self->{Uncomp}{ErrorNo}) |
134 | if $self->saveStatus($status) == STATUS_ERROR; |
135 | |
136 | if ($status == STATUS_ENDSTREAM) { |
137 | *$self->{Uncomp}->reset(); |
138 | $self->pushBack($b) ; |
139 | last; |
140 | } |
141 | } |
142 | |
143 | # skip the trailer |
144 | $self->smartReadExact(\$buffer, $hdr->{TrailerLength}) |
145 | or return $self->saveErrorString(undef, "Truncated file"); |
146 | } |
147 | else { |
148 | my $c = $hdr->{CompressedLength}; |
149 | $self->smartReadExact(\$buffer, $c) |
150 | or return $self->saveErrorString(undef, "Truncated file"); |
151 | $buffer = ''; |
152 | } |
153 | |
154 | $self->chkTrailer($buffer) == STATUS_OK |
155 | or return $self->saveErrorString(undef, "Truncated file"); |
156 | |
157 | $hdr = $self->_readFullZipHeader(); |
158 | |
159 | return $self->saveErrorString(undef, "Cannot find '$name'") |
160 | if $self->smartEof(); |
161 | } |
162 | |
163 | return undef; |
164 | } |
165 | |
166 | sub chkTrailer |
167 | { |
168 | my $self = shift; |
169 | my $trailer = shift; |
170 | |
171 | my ($sig, $CRC32, $cSize, $uSize) ; |
172 | if (*$self->{ZipData}{Streaming}) { |
173 | ($sig, $CRC32, $cSize, $uSize) = unpack("V V V V", $trailer) ; |
174 | return $self->TrailerError("Data Descriptor signature, got $sig") |
c70c1701 |
175 | if $sig != ZIP_DATA_HDR_SIG; |
a02d0f6f |
176 | } |
177 | else { |
178 | ($CRC32, $cSize, $uSize) = |
179 | (*$self->{ZipData}{Crc32}, |
180 | *$self->{ZipData}{CompressedLen}, |
181 | *$self->{ZipData}{UnCompressedLen}); |
182 | } |
183 | |
184 | if (*$self->{Strict}) { |
2b4e0969 |
185 | return $self->TrailerError("CRC mismatch") |
186 | if $CRC32 != *$self->{ZipData}{CRC32} ; |
a02d0f6f |
187 | |
188 | my $exp_isize = *$self->{Uncomp}->compressedBytes(); |
189 | return $self->TrailerError("CSIZE mismatch. Got $cSize" |
190 | . ", expected $exp_isize") |
191 | if $cSize != $exp_isize ; |
192 | |
193 | $exp_isize = *$self->{Uncomp}->uncompressedBytes(); |
194 | return $self->TrailerError("USIZE mismatch. Got $uSize" |
195 | . ", expected $exp_isize") |
196 | if $uSize != $exp_isize ; |
197 | } |
198 | |
199 | my $reachedEnd = STATUS_ERROR ; |
200 | # check for central directory or end of central directory |
201 | while (1) |
202 | { |
203 | my $magic ; |
204 | my $got = $self->smartRead(\$magic, 4); |
205 | |
206 | return $self->saveErrorString(STATUS_ERROR, "Truncated file") |
207 | if $got != 4 && *$self->{Strict}; |
208 | |
209 | if ($got == 0) { |
210 | return STATUS_EOF ; |
211 | } |
212 | elsif ($got < 0) { |
213 | return STATUS_ERROR ; |
214 | } |
215 | elsif ($got < 4) { |
216 | $self->pushBack($magic) ; |
217 | return STATUS_OK ; |
218 | } |
219 | |
220 | my $sig = unpack("V", $magic) ; |
221 | |
c70c1701 |
222 | if ($sig == ZIP_CENTRAL_HDR_SIG) |
a02d0f6f |
223 | { |
224 | if ($self->skipCentralDirectory($magic) != STATUS_OK ) { |
225 | if (*$self->{Strict}) { |
226 | return STATUS_ERROR ; |
227 | } |
228 | else { |
229 | $self->clearError(); |
230 | return STATUS_OK ; |
231 | } |
232 | } |
233 | } |
c70c1701 |
234 | elsif ($sig == ZIP_END_CENTRAL_HDR_SIG) |
a02d0f6f |
235 | { |
236 | if ($self->skipEndCentralDirectory($magic) != STATUS_OK) { |
237 | if (*$self->{Strict}) { |
238 | return STATUS_ERROR ; |
239 | } |
240 | else { |
241 | $self->clearError(); |
242 | return STATUS_OK ; |
243 | } |
244 | } |
245 | # $reachedEnd = STATUS_OK ; |
246 | return STATUS_OK ; |
247 | last; |
248 | } |
c70c1701 |
249 | elsif ($sig == ZIP_LOCAL_HDR_SIG) |
a02d0f6f |
250 | { |
251 | $self->pushBack($magic) ; |
252 | return STATUS_OK ; |
253 | } |
254 | else |
255 | { |
256 | # put the data back |
257 | $self->pushBack($magic) ; |
258 | last; |
259 | } |
260 | } |
261 | |
262 | return $reachedEnd ; |
263 | } |
264 | |
265 | sub skipCentralDirectory |
266 | { |
267 | my $self = shift; |
268 | my $magic = shift ; |
269 | |
270 | my $buffer; |
271 | $self->smartReadExact(\$buffer, 46 - 4) |
272 | or return $self->TrailerError("Minimum header size is " . |
273 | 46 . " bytes") ; |
274 | |
275 | my $keep = $magic . $buffer ; |
276 | *$self->{HeaderPending} = $keep ; |
277 | |
278 | #my $versionMadeBy = unpack ("v", substr($buffer, 4-4, 2)); |
279 | #my $extractVersion = unpack ("v", substr($buffer, 6-4, 2)); |
280 | #my $gpFlag = unpack ("v", substr($buffer, 8-4, 2)); |
281 | #my $compressedMethod = unpack ("v", substr($buffer, 10-4, 2)); |
282 | #my $lastModTime = unpack ("V", substr($buffer, 12-4, 4)); |
283 | #my $crc32 = unpack ("V", substr($buffer, 16-4, 4)); |
284 | #my $compressedLength = unpack ("V", substr($buffer, 20-4, 4)); |
285 | #my $uncompressedLength = unpack ("V", substr($buffer, 24-4, 4)); |
286 | my $filename_length = unpack ("v", substr($buffer, 28-4, 2)); |
287 | my $extra_length = unpack ("v", substr($buffer, 30-4, 2)); |
288 | my $comment_length = unpack ("v", substr($buffer, 32-4, 2)); |
289 | #my $disk_start = unpack ("v", substr($buffer, 34-4, 2)); |
290 | #my $int_file_attrib = unpack ("v", substr($buffer, 36-4, 2)); |
291 | #my $ext_file_attrib = unpack ("V", substr($buffer, 38-4, 2)); |
292 | #my $lcl_hdr_offset = unpack ("V", substr($buffer, 42-4, 2)); |
293 | |
294 | |
295 | my $filename; |
296 | my $extraField; |
297 | my $comment ; |
298 | if ($filename_length) |
299 | { |
300 | $self->smartReadExact(\$filename, $filename_length) |
2b4e0969 |
301 | or return $self->TruncatedTrailer("filename"); |
a02d0f6f |
302 | $keep .= $filename ; |
303 | } |
304 | |
305 | if ($extra_length) |
306 | { |
307 | $self->smartReadExact(\$extraField, $extra_length) |
2b4e0969 |
308 | or return $self->TruncatedTrailer("extra"); |
a02d0f6f |
309 | $keep .= $extraField ; |
310 | } |
311 | |
312 | if ($comment_length) |
313 | { |
314 | $self->smartReadExact(\$comment, $comment_length) |
2b4e0969 |
315 | or return $self->TruncatedTrailer("comment"); |
a02d0f6f |
316 | $keep .= $comment ; |
317 | } |
318 | |
319 | return STATUS_OK ; |
320 | } |
321 | |
322 | sub skipEndCentralDirectory |
323 | { |
324 | my $self = shift; |
325 | my $magic = shift ; |
326 | |
327 | my $buffer; |
328 | $self->smartReadExact(\$buffer, 22 - 4) |
329 | or return $self->TrailerError("Minimum header size is " . |
330 | 22 . " bytes") ; |
331 | |
332 | my $keep = $magic . $buffer ; |
333 | *$self->{HeaderPending} = $keep ; |
334 | |
335 | #my $diskNumber = unpack ("v", substr($buffer, 4-4, 2)); |
336 | #my $cntrlDirDiskNo = unpack ("v", substr($buffer, 6-4, 2)); |
337 | #my $entriesInThisCD = unpack ("v", substr($buffer, 8-4, 2)); |
338 | #my $entriesInCD = unpack ("v", substr($buffer, 10-4, 2)); |
339 | #my $sizeOfCD = unpack ("V", substr($buffer, 12-4, 2)); |
340 | #my $offsetToCD = unpack ("V", substr($buffer, 16-4, 2)); |
341 | my $comment_length = unpack ("v", substr($buffer, 20-4, 2)); |
342 | |
343 | |
344 | my $comment ; |
345 | if ($comment_length) |
346 | { |
347 | $self->smartReadExact(\$comment, $comment_length) |
2b4e0969 |
348 | or return $self->TruncatedTrailer("comment"); |
a02d0f6f |
349 | $keep .= $comment ; |
350 | } |
351 | |
352 | return STATUS_OK ; |
353 | } |
354 | |
355 | |
356 | |
357 | |
358 | sub _isZipMagic |
359 | { |
360 | my $buffer = shift ; |
361 | return 0 if length $buffer < 4 ; |
362 | my $sig = unpack("V", $buffer) ; |
c70c1701 |
363 | return $sig == ZIP_LOCAL_HDR_SIG ; |
a02d0f6f |
364 | } |
365 | |
366 | |
367 | sub _readFullZipHeader($) |
368 | { |
369 | my ($self) = @_ ; |
370 | my $magic = '' ; |
371 | |
372 | $self->smartReadExact(\$magic, 4); |
373 | |
374 | *$self->{HeaderPending} = $magic ; |
375 | |
376 | return $self->HeaderError("Minimum header size is " . |
377 | 30 . " bytes") |
378 | if length $magic != 4 ; |
379 | |
380 | |
381 | return $self->HeaderError("Bad Magic") |
382 | if ! _isZipMagic($magic) ; |
383 | |
384 | my $status = $self->_readZipHeader($magic); |
385 | delete *$self->{Transparent} if ! defined $status ; |
386 | return $status ; |
387 | } |
388 | |
389 | sub _readZipHeader($) |
390 | { |
391 | my ($self, $magic) = @_ ; |
392 | my ($HeaderCRC) ; |
393 | my ($buffer) = '' ; |
394 | |
395 | $self->smartReadExact(\$buffer, 30 - 4) |
396 | or return $self->HeaderError("Minimum header size is " . |
397 | 30 . " bytes") ; |
398 | |
399 | my $keep = $magic . $buffer ; |
400 | *$self->{HeaderPending} = $keep ; |
401 | |
402 | my $extractVersion = unpack ("v", substr($buffer, 4-4, 2)); |
403 | my $gpFlag = unpack ("v", substr($buffer, 6-4, 2)); |
404 | my $compressedMethod = unpack ("v", substr($buffer, 8-4, 2)); |
405 | my $lastModTime = unpack ("V", substr($buffer, 10-4, 4)); |
406 | my $crc32 = unpack ("V", substr($buffer, 14-4, 4)); |
407 | my $compressedLength = unpack ("V", substr($buffer, 18-4, 4)); |
408 | my $uncompressedLength = unpack ("V", substr($buffer, 22-4, 4)); |
409 | my $filename_length = unpack ("v", substr($buffer, 26-4, 2)); |
410 | my $extra_length = unpack ("v", substr($buffer, 28-4, 2)); |
411 | |
412 | my $filename; |
413 | my $extraField; |
c70c1701 |
414 | my @EXTRA = (); |
415 | my $streamingMode = ($gpFlag & ZIP_GP_FLAG_STREAMING_MASK) ? 1 : 0 ; |
a02d0f6f |
416 | |
417 | return $self->HeaderError("Streamed Stored content not supported") |
418 | if $streamingMode && $compressedMethod == 0 ; |
419 | |
420 | *$self->{ZipData}{Streaming} = $streamingMode; |
421 | |
422 | if (! $streamingMode) { |
423 | *$self->{ZipData}{Streaming} = 0; |
424 | *$self->{ZipData}{Crc32} = $crc32; |
425 | *$self->{ZipData}{CompressedLen} = $compressedLength; |
426 | *$self->{ZipData}{UnCompressedLen} = $uncompressedLength; |
427 | *$self->{CompressedInputLengthRemaining} = |
428 | *$self->{CompressedInputLength} = $compressedLength; |
429 | } |
430 | |
431 | |
432 | if ($filename_length) |
433 | { |
434 | $self->smartReadExact(\$filename, $filename_length) |
c70c1701 |
435 | or return $self->TruncatedHeader("Filename"); |
a02d0f6f |
436 | $keep .= $filename ; |
437 | } |
438 | |
439 | if ($extra_length) |
440 | { |
441 | $self->smartReadExact(\$extraField, $extra_length) |
c70c1701 |
442 | or return $self->TruncatedHeader("Extra Field"); |
443 | |
444 | my $bad = IO::Compress::Zlib::Extra::parseRawExtra($extraField, |
445 | \@EXTRA, 1, 0); |
446 | return $self->HeaderError($bad) |
447 | if defined $bad; |
448 | |
a02d0f6f |
449 | $keep .= $extraField ; |
450 | } |
451 | |
2b4e0969 |
452 | *$self->{ZipData}{Method} = $compressedMethod; |
c70c1701 |
453 | if ($compressedMethod == ZIP_CM_DEFLATE) |
a02d0f6f |
454 | { |
2b4e0969 |
455 | *$self->{Type} = 'zip-deflate'; |
456 | } |
c70c1701 |
457 | elsif ($compressedMethod == ZIP_CM_BZIP2) |
2b4e0969 |
458 | { |
459 | #if (! defined $IO::Uncompress::Adapter::Bunzip2::VERSION) |
460 | |
461 | *$self->{Type} = 'zip-bzip2'; |
462 | |
463 | my $obj = IO::Uncompress::Adapter::Bunzip2::mkUncompObject( |
464 | ); |
465 | |
466 | *$self->{Uncomp} = $obj; |
467 | *$self->{ZipData}{CRC32} = crc32(undef); |
468 | |
a02d0f6f |
469 | } |
c70c1701 |
470 | elsif ($compressedMethod == ZIP_CM_STORE) |
a02d0f6f |
471 | { |
472 | # TODO -- add support for reading uncompressed |
473 | |
2b4e0969 |
474 | *$self->{Type} = 'zip-stored'; |
a02d0f6f |
475 | |
476 | my $obj = IO::Uncompress::Adapter::Identity::mkUncompObject(# $got->value('CRC32'), |
477 | # $got->value('ADLER32'), |
478 | ); |
479 | |
480 | *$self->{Uncomp} = $obj; |
481 | |
482 | } |
483 | else |
484 | { |
485 | return $self->HeaderError("Unsupported Compression format $compressedMethod"); |
486 | } |
487 | |
488 | return { |
489 | 'Type' => 'zip', |
490 | 'FingerprintLength' => 4, |
491 | #'HeaderLength' => $compressedMethod == 8 ? length $keep : 0, |
492 | 'HeaderLength' => length $keep, |
493 | 'TrailerLength' => $streamingMode ? 16 : 0, |
494 | 'Header' => $keep, |
495 | 'CompressedLength' => $compressedLength , |
496 | 'UncompressedLength' => $uncompressedLength , |
497 | 'CRC32' => $crc32 , |
498 | 'Name' => $filename, |
499 | 'Time' => _dosToUnixTime($lastModTime), |
500 | 'Stream' => $streamingMode, |
501 | |
502 | 'MethodID' => $compressedMethod, |
c70c1701 |
503 | 'MethodName' => $compressedMethod == ZIP_CM_DEFLATE |
a02d0f6f |
504 | ? "Deflated" |
c70c1701 |
505 | : $compressedMethod == ZIP_CM_BZIP2 |
506 | ? "Bzip2" |
507 | : $compressedMethod == ZIP_CM_STORE |
508 | ? "Stored" |
509 | : "Unknown" , |
a02d0f6f |
510 | |
511 | # 'TextFlag' => $flag & GZIP_FLG_FTEXT ? 1 : 0, |
512 | # 'HeaderCRCFlag' => $flag & GZIP_FLG_FHCRC ? 1 : 0, |
513 | # 'NameFlag' => $flag & GZIP_FLG_FNAME ? 1 : 0, |
514 | # 'CommentFlag' => $flag & GZIP_FLG_FCOMMENT ? 1 : 0, |
515 | # 'ExtraFlag' => $flag & GZIP_FLG_FEXTRA ? 1 : 0, |
516 | # 'Comment' => $comment, |
517 | # 'OsID' => $os, |
518 | # 'OsName' => defined $GZIP_OS_Names{$os} |
519 | # ? $GZIP_OS_Names{$os} : "Unknown", |
520 | # 'HeaderCRC' => $HeaderCRC, |
521 | # 'Flags' => $flag, |
522 | # 'ExtraFlags' => $xfl, |
c70c1701 |
523 | 'ExtraFieldRaw' => $extraField, |
524 | 'ExtraField' => [ @EXTRA ], |
a02d0f6f |
525 | |
526 | |
527 | } |
528 | } |
529 | |
2b4e0969 |
530 | sub filterUncompressed |
531 | { |
532 | my $self = shift ; |
533 | |
534 | if (*$self->{ZipData}{Method} == 12) { |
535 | *$self->{ZipData}{CRC32} = crc32(${$_[0]}, *$self->{ZipData}{CRC32}); |
536 | } |
537 | else { |
538 | *$self->{ZipData}{CRC32} = *$self->{Uncomp}->crc32() ; |
539 | } |
540 | } |
541 | |
542 | |
a02d0f6f |
543 | # from Archive::Zip |
544 | sub _dosToUnixTime |
545 | { |
546 | #use Time::Local 'timelocal_nocheck'; |
547 | use Time::Local 'timelocal'; |
548 | |
549 | my $dt = shift; |
550 | |
551 | my $year = ( ( $dt >> 25 ) & 0x7f ) + 80; |
552 | my $mon = ( ( $dt >> 21 ) & 0x0f ) - 1; |
553 | my $mday = ( ( $dt >> 16 ) & 0x1f ); |
554 | |
555 | my $hour = ( ( $dt >> 11 ) & 0x1f ); |
556 | my $min = ( ( $dt >> 5 ) & 0x3f ); |
557 | my $sec = ( ( $dt << 1 ) & 0x3e ); |
558 | |
559 | # catch errors |
560 | my $time_t = |
561 | eval { timelocal( $sec, $min, $hour, $mday, $mon, $year ); }; |
562 | return 0 |
563 | if $@; |
564 | return $time_t; |
565 | } |
566 | |
567 | |
568 | 1; |
569 | |
570 | __END__ |
571 | |
572 | |
573 | =head1 NAME |
574 | |
575 | |
cb7abd7f |
576 | |
577 | IO::Uncompress::Unzip - Read zip files/buffers |
578 | |
a02d0f6f |
579 | |
580 | |
581 | =head1 SYNOPSIS |
582 | |
583 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
584 | |
585 | my $status = unzip $input => $output [,OPTS] |
586 | or die "unzip failed: $UnzipError\n"; |
587 | |
588 | my $z = new IO::Uncompress::Unzip $input [OPTS] |
589 | or die "unzip failed: $UnzipError\n"; |
590 | |
591 | $status = $z->read($buffer) |
592 | $status = $z->read($buffer, $length) |
593 | $status = $z->read($buffer, $length, $offset) |
594 | $line = $z->getline() |
595 | $char = $z->getc() |
596 | $char = $z->ungetc() |
597 | $char = $z->opened() |
598 | |
599 | $status = $z->inflateSync() |
600 | |
601 | $z->trailingData() |
602 | $data = $z->getHeaderInfo() |
603 | $z->tell() |
604 | $z->seek($position, $whence) |
605 | $z->binmode() |
606 | $z->fileno() |
607 | $z->eof() |
608 | $z->close() |
609 | |
610 | $UnzipError ; |
611 | |
612 | # IO::File mode |
613 | |
614 | <$z> |
615 | read($z, $buffer); |
616 | read($z, $buffer, $length); |
617 | read($z, $buffer, $length, $offset); |
618 | tell($z) |
619 | seek($z, $position, $whence) |
620 | binmode($z) |
621 | fileno($z) |
622 | eof($z) |
623 | close($z) |
624 | |
625 | |
626 | =head1 DESCRIPTION |
627 | |
628 | |
629 | |
630 | B<WARNING -- This is a Beta release>. |
631 | |
632 | =over 5 |
633 | |
634 | =item * DO NOT use in production code. |
635 | |
636 | =item * The documentation is incomplete in places. |
637 | |
638 | =item * Parts of the interface defined here are tentative. |
639 | |
640 | =item * Please report any problems you find. |
641 | |
642 | =back |
643 | |
644 | |
645 | |
646 | |
647 | |
648 | This module provides a Perl interface that allows the reading of |
649 | zlib files/buffers. |
650 | |
651 | For writing zip files/buffers, see the companion module IO::Compress::Zip. |
652 | |
653 | |
654 | |
cb7abd7f |
655 | |
656 | |
657 | |
a02d0f6f |
658 | =head1 Functional Interface |
659 | |
660 | A top-level function, C<unzip>, is provided to carry out |
661 | "one-shot" uncompression between buffers and/or files. For finer |
662 | control over the uncompression process, see the L</"OO Interface"> |
663 | section. |
664 | |
665 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
666 | |
667 | unzip $input => $output [,OPTS] |
668 | or die "unzip failed: $UnzipError\n"; |
669 | |
670 | |
671 | |
672 | The functional interface needs Perl5.005 or better. |
673 | |
674 | |
675 | =head2 unzip $input => $output [, OPTS] |
676 | |
677 | |
678 | C<unzip> expects at least two parameters, C<$input> and C<$output>. |
679 | |
680 | =head3 The C<$input> parameter |
681 | |
682 | The parameter, C<$input>, is used to define the source of |
683 | the compressed data. |
684 | |
685 | It can take one of the following forms: |
686 | |
687 | =over 5 |
688 | |
689 | =item A filename |
690 | |
691 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
692 | filename. This file will be opened for reading and the input data |
693 | will be read from it. |
694 | |
695 | =item A filehandle |
696 | |
697 | If the C<$input> parameter is a filehandle, the input data will be |
698 | read from it. |
699 | The string '-' can be used as an alias for standard input. |
700 | |
701 | =item A scalar reference |
702 | |
703 | If C<$input> is a scalar reference, the input data will be read |
704 | from C<$$input>. |
705 | |
706 | =item An array reference |
707 | |
708 | If C<$input> is an array reference, each element in the array must be a |
709 | filename. |
710 | |
711 | The input data will be read from each file in turn. |
712 | |
713 | The complete array will be walked to ensure that it only |
714 | contains valid filenames before any data is uncompressed. |
715 | |
716 | |
717 | |
718 | =item An Input FileGlob string |
719 | |
720 | If C<$input> is a string that is delimited by the characters "<" and ">" |
721 | C<unzip> will assume that it is an I<input fileglob string>. The |
722 | input is the list of files that match the fileglob. |
723 | |
724 | If the fileglob does not match any files ... |
725 | |
726 | See L<File::GlobMapper|File::GlobMapper> for more details. |
727 | |
728 | |
729 | =back |
730 | |
731 | If the C<$input> parameter is any other type, C<undef> will be returned. |
732 | |
733 | |
734 | |
735 | =head3 The C<$output> parameter |
736 | |
737 | The parameter C<$output> is used to control the destination of the |
738 | uncompressed data. This parameter can take one of these forms. |
739 | |
740 | =over 5 |
741 | |
742 | =item A filename |
743 | |
744 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
745 | filename. This file will be opened for writing and the uncompressed |
746 | data will be written to it. |
747 | |
748 | =item A filehandle |
749 | |
750 | If the C<$output> parameter is a filehandle, the uncompressed data |
751 | will be written to it. |
752 | The string '-' can be used as an alias for standard output. |
753 | |
754 | |
755 | =item A scalar reference |
756 | |
757 | If C<$output> is a scalar reference, the uncompressed data will be |
758 | stored in C<$$output>. |
759 | |
760 | |
761 | |
762 | =item An Array Reference |
763 | |
764 | If C<$output> is an array reference, the uncompressed data will be |
765 | pushed onto the array. |
766 | |
767 | =item An Output FileGlob |
768 | |
769 | If C<$output> is a string that is delimited by the characters "<" and ">" |
770 | C<unzip> will assume that it is an I<output fileglob string>. The |
771 | output is the list of files that match the fileglob. |
772 | |
773 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
774 | string. Anything else is an error. |
775 | |
776 | =back |
777 | |
778 | If the C<$output> parameter is any other type, C<undef> will be returned. |
779 | |
780 | |
781 | |
782 | =head2 Notes |
783 | |
c70c1701 |
784 | |
785 | When C<$input> maps to multiple compressed files/buffers and C<$output> is |
786 | a single file/buffer, after uncompression C<$output> will contain a |
787 | concatenation of all the uncompressed data from each of the input |
788 | files/buffers. |
789 | |
790 | |
a02d0f6f |
791 | |
792 | |
793 | |
794 | =head2 Optional Parameters |
795 | |
796 | Unless specified below, the optional parameters for C<unzip>, |
797 | C<OPTS>, are the same as those used with the OO interface defined in the |
798 | L</"Constructor Options"> section below. |
799 | |
800 | =over 5 |
801 | |
802 | =item AutoClose =E<gt> 0|1 |
803 | |
804 | This option applies to any input or output data streams to |
805 | C<unzip> that are filehandles. |
806 | |
807 | If C<AutoClose> is specified, and the value is true, it will result in all |
808 | input and/or output filehandles being closed once C<unzip> has |
809 | completed. |
810 | |
811 | This parameter defaults to 0. |
812 | |
813 | |
814 | |
815 | =item BinModeOut =E<gt> 0|1 |
816 | |
817 | When writing to a file or filehandle, set C<binmode> before writing to the |
818 | file. |
819 | |
820 | Defaults to 0. |
821 | |
822 | |
823 | |
824 | |
825 | |
826 | =item -Append =E<gt> 0|1 |
827 | |
828 | TODO |
829 | |
830 | =item -MultiStream =E<gt> 0|1 |
831 | |
832 | Creates a new stream after each file. |
833 | |
834 | Defaults to 1. |
835 | |
836 | |
837 | |
838 | =back |
839 | |
840 | |
841 | |
842 | |
843 | =head2 Examples |
844 | |
845 | To read the contents of the file C<file1.txt.zip> and write the |
846 | compressed data to the file C<file1.txt>. |
847 | |
848 | use strict ; |
849 | use warnings ; |
850 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
851 | |
852 | my $input = "file1.txt.zip"; |
853 | my $output = "file1.txt"; |
854 | unzip $input => $output |
855 | or die "unzip failed: $UnzipError\n"; |
856 | |
857 | |
858 | To read from an existing Perl filehandle, C<$input>, and write the |
859 | uncompressed data to a buffer, C<$buffer>. |
860 | |
861 | use strict ; |
862 | use warnings ; |
863 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
864 | use IO::File ; |
865 | |
866 | my $input = new IO::File "<file1.txt.zip" |
867 | or die "Cannot open 'file1.txt.zip': $!\n" ; |
868 | my $buffer ; |
869 | unzip $input => \$buffer |
870 | or die "unzip failed: $UnzipError\n"; |
871 | |
872 | To uncompress all files in the directory "/my/home" that match "*.txt.zip" and store the compressed data in the same directory |
873 | |
874 | use strict ; |
875 | use warnings ; |
876 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
877 | |
878 | unzip '</my/home/*.txt.zip>' => '</my/home/#1.txt>' |
879 | or die "unzip failed: $UnzipError\n"; |
880 | |
881 | and if you want to compress each file one at a time, this will do the trick |
882 | |
883 | use strict ; |
884 | use warnings ; |
885 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
886 | |
887 | for my $input ( glob "/my/home/*.txt.zip" ) |
888 | { |
889 | my $output = $input; |
890 | $output =~ s/.zip// ; |
891 | unzip $input => $output |
892 | or die "Error compressing '$input': $UnzipError\n"; |
893 | } |
894 | |
895 | =head1 OO Interface |
896 | |
897 | =head2 Constructor |
898 | |
899 | The format of the constructor for IO::Uncompress::Unzip is shown below |
900 | |
901 | |
902 | my $z = new IO::Uncompress::Unzip $input [OPTS] |
903 | or die "IO::Uncompress::Unzip failed: $UnzipError\n"; |
904 | |
905 | Returns an C<IO::Uncompress::Unzip> object on success and undef on failure. |
906 | The variable C<$UnzipError> will contain an error message on failure. |
907 | |
908 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
909 | IO::Uncompress::Unzip can be used exactly like an L<IO::File|IO::File> filehandle. |
910 | This means that all normal input file operations can be carried out with |
911 | C<$z>. For example, to read a line from a compressed file/buffer you can |
912 | use either of these forms |
913 | |
914 | $line = $z->getline(); |
915 | $line = <$z>; |
916 | |
917 | The mandatory parameter C<$input> is used to determine the source of the |
918 | compressed data. This parameter can take one of three forms. |
919 | |
920 | =over 5 |
921 | |
922 | =item A filename |
923 | |
924 | If the C<$input> parameter is a scalar, it is assumed to be a filename. This |
925 | file will be opened for reading and the compressed data will be read from it. |
926 | |
927 | =item A filehandle |
928 | |
929 | If the C<$input> parameter is a filehandle, the compressed data will be |
930 | read from it. |
931 | The string '-' can be used as an alias for standard input. |
932 | |
933 | |
934 | =item A scalar reference |
935 | |
936 | If C<$input> is a scalar reference, the compressed data will be read from |
937 | C<$$output>. |
938 | |
939 | =back |
940 | |
941 | =head2 Constructor Options |
942 | |
943 | |
944 | The option names defined below are case insensitive and can be optionally |
945 | prefixed by a '-'. So all of the following are valid |
946 | |
947 | -AutoClose |
948 | -autoclose |
949 | AUTOCLOSE |
950 | autoclose |
951 | |
952 | OPTS is a combination of the following options: |
953 | |
954 | =over 5 |
955 | |
956 | =item -AutoClose =E<gt> 0|1 |
957 | |
958 | This option is only valid when the C<$input> parameter is a filehandle. If |
959 | specified, and the value is true, it will result in the file being closed once |
960 | either the C<close> method is called or the IO::Uncompress::Unzip object is |
961 | destroyed. |
962 | |
963 | This parameter defaults to 0. |
964 | |
965 | =item -MultiStream =E<gt> 0|1 |
966 | |
967 | |
968 | |
969 | Allows multiple concatenated compressed streams to be treated as a single |
970 | compressed stream. Decompression will stop once either the end of the |
971 | file/buffer is reached, an error is encountered (premature eof, corrupt |
972 | compressed data) or the end of a stream is not immediately followed by the |
973 | start of another stream. |
974 | |
975 | This parameter defaults to 0. |
976 | |
977 | |
978 | |
979 | =item -Prime =E<gt> $string |
980 | |
981 | This option will uncompress the contents of C<$string> before processing the |
982 | input file/buffer. |
983 | |
984 | This option can be useful when the compressed data is embedded in another |
985 | file/data structure and it is not possible to work out where the compressed |
986 | data begins without having to read the first few bytes. If this is the |
987 | case, the uncompression can be I<primed> with these bytes using this |
988 | option. |
989 | |
990 | =item -Transparent =E<gt> 0|1 |
991 | |
992 | If this option is set and the input file or buffer is not compressed data, |
993 | the module will allow reading of it anyway. |
994 | |
995 | This option defaults to 1. |
996 | |
997 | =item -BlockSize =E<gt> $num |
998 | |
999 | When reading the compressed input data, IO::Uncompress::Unzip will read it in |
1000 | blocks of C<$num> bytes. |
1001 | |
1002 | This option defaults to 4096. |
1003 | |
1004 | =item -InputLength =E<gt> $size |
1005 | |
1006 | When present this option will limit the number of compressed bytes read |
1007 | from the input file/buffer to C<$size>. This option can be used in the |
1008 | situation where there is useful data directly after the compressed data |
1009 | stream and you know beforehand the exact length of the compressed data |
1010 | stream. |
1011 | |
1012 | This option is mostly used when reading from a filehandle, in which case |
1013 | the file pointer will be left pointing to the first byte directly after the |
1014 | compressed data stream. |
1015 | |
1016 | |
1017 | |
1018 | This option defaults to off. |
1019 | |
1020 | =item -Append =E<gt> 0|1 |
1021 | |
1022 | This option controls what the C<read> method does with uncompressed data. |
1023 | |
1024 | If set to 1, all uncompressed data will be appended to the output parameter |
1025 | of the C<read> method. |
1026 | |
1027 | If set to 0, the contents of the output parameter of the C<read> method |
1028 | will be overwritten by the uncompressed data. |
1029 | |
1030 | Defaults to 0. |
1031 | |
1032 | =item -Strict =E<gt> 0|1 |
1033 | |
1034 | |
1035 | |
1036 | This option controls whether the extra checks defined below are used when |
1037 | carrying out the decompression. When Strict is on, the extra tests are |
1038 | carried out, when Strict is off they are not. |
1039 | |
1040 | The default for this option is off. |
1041 | |
1042 | |
1043 | |
1044 | |
1045 | |
1046 | |
1047 | |
1048 | |
1049 | |
1050 | |
1051 | |
1052 | |
1053 | |
1054 | |
1055 | =back |
1056 | |
1057 | =head2 Examples |
1058 | |
1059 | TODO |
1060 | |
1061 | =head1 Methods |
1062 | |
1063 | =head2 read |
1064 | |
1065 | Usage is |
1066 | |
1067 | $status = $z->read($buffer) |
1068 | |
1069 | Reads a block of compressed data (the size the the compressed block is |
1070 | determined by the C<Buffer> option in the constructor), uncompresses it and |
1071 | writes any uncompressed data into C<$buffer>. If the C<Append> parameter is |
1072 | set in the constructor, the uncompressed data will be appended to the |
1073 | C<$buffer> parameter. Otherwise C<$buffer> will be overwritten. |
1074 | |
1075 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
1076 | or a negative number on error. |
1077 | |
1078 | =head2 read |
1079 | |
1080 | Usage is |
1081 | |
1082 | $status = $z->read($buffer, $length) |
1083 | $status = $z->read($buffer, $length, $offset) |
1084 | |
1085 | $status = read($z, $buffer, $length) |
1086 | $status = read($z, $buffer, $length, $offset) |
1087 | |
1088 | Attempt to read C<$length> bytes of uncompressed data into C<$buffer>. |
1089 | |
1090 | The main difference between this form of the C<read> method and the |
1091 | previous one, is that this one will attempt to return I<exactly> C<$length> |
1092 | bytes. The only circumstances that this function will not is if end-of-file |
1093 | or an IO error is encountered. |
1094 | |
1095 | Returns the number of uncompressed bytes written to C<$buffer>, zero if eof |
1096 | or a negative number on error. |
1097 | |
1098 | |
1099 | =head2 getline |
1100 | |
1101 | Usage is |
1102 | |
1103 | $line = $z->getline() |
1104 | $line = <$z> |
1105 | |
1106 | Reads a single line. |
1107 | |
1108 | This method fully supports the use of of the variable C<$/> |
1109 | (or C<$INPUT_RECORD_SEPARATOR> or C<$RS> when C<English> is in use) to |
1110 | determine what constitutes an end of line. Both paragraph mode and file |
1111 | slurp mode are supported. |
1112 | |
1113 | |
1114 | =head2 getc |
1115 | |
1116 | Usage is |
1117 | |
1118 | $char = $z->getc() |
1119 | |
1120 | Read a single character. |
1121 | |
1122 | =head2 ungetc |
1123 | |
1124 | Usage is |
1125 | |
1126 | $char = $z->ungetc($string) |
1127 | |
1128 | |
1129 | |
1130 | =head2 inflateSync |
1131 | |
1132 | Usage is |
1133 | |
1134 | $status = $z->inflateSync() |
1135 | |
1136 | TODO |
1137 | |
1138 | |
1139 | =head2 getHeaderInfo |
1140 | |
1141 | Usage is |
1142 | |
1143 | $hdr = $z->getHeaderInfo(); |
1144 | @hdrs = $z->getHeaderInfo(); |
1145 | |
1146 | This method returns either a hash reference (in scalar context) or a list |
1147 | or hash references (in array context) that contains information about each |
1148 | of the header fields in the compressed data stream(s). |
1149 | |
1150 | |
1151 | |
1152 | |
1153 | =head2 tell |
1154 | |
1155 | Usage is |
1156 | |
1157 | $z->tell() |
1158 | tell $z |
1159 | |
1160 | Returns the uncompressed file offset. |
1161 | |
1162 | =head2 eof |
1163 | |
1164 | Usage is |
1165 | |
1166 | $z->eof(); |
1167 | eof($z); |
1168 | |
1169 | |
1170 | |
1171 | Returns true if the end of the compressed input stream has been reached. |
1172 | |
1173 | |
1174 | |
1175 | =head2 seek |
1176 | |
1177 | $z->seek($position, $whence); |
1178 | seek($z, $position, $whence); |
1179 | |
1180 | |
1181 | |
1182 | |
1183 | Provides a sub-set of the C<seek> functionality, with the restriction |
1184 | that it is only legal to seek forward in the input file/buffer. |
1185 | It is a fatal error to attempt to seek backward. |
1186 | |
1187 | |
1188 | |
1189 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
1190 | SEEK_CUR or SEEK_END. |
1191 | |
1192 | Returns 1 on success, 0 on failure. |
1193 | |
1194 | =head2 binmode |
1195 | |
1196 | Usage is |
1197 | |
1198 | $z->binmode |
1199 | binmode $z ; |
1200 | |
1201 | This is a noop provided for completeness. |
1202 | |
1203 | =head2 opened |
1204 | |
1205 | $z->opened() |
1206 | |
1207 | Returns true if the object currently refers to a opened file/buffer. |
1208 | |
1209 | =head2 autoflush |
1210 | |
1211 | my $prev = $z->autoflush() |
1212 | my $prev = $z->autoflush(EXPR) |
1213 | |
1214 | If the C<$z> object is associated with a file or a filehandle, this method |
1215 | returns the current autoflush setting for the underlying filehandle. If |
1216 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
1217 | write/print operation. |
1218 | |
1219 | If C<$z> is associated with a buffer, this method has no effect and always |
1220 | returns C<undef>. |
1221 | |
1222 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
1223 | retrieve the autoflush setting. |
1224 | |
1225 | =head2 input_line_number |
1226 | |
1227 | $z->input_line_number() |
1228 | $z->input_line_number(EXPR) |
1229 | |
1230 | |
1231 | |
1232 | Returns the current uncompressed line number. If C<EXPR> is present it has |
1233 | the effect of setting the line number. Note that setting the line number |
1234 | does not change the current position within the file/buffer being read. |
1235 | |
1236 | The contents of C<$/> are used to to determine what constitutes a line |
1237 | terminator. |
1238 | |
1239 | |
1240 | |
1241 | =head2 fileno |
1242 | |
1243 | $z->fileno() |
1244 | fileno($z) |
1245 | |
1246 | If the C<$z> object is associated with a file or a filehandle, this method |
1247 | will return the underlying file descriptor. |
1248 | |
1249 | If the C<$z> object is is associated with a buffer, this method will |
1250 | return undef. |
1251 | |
1252 | =head2 close |
1253 | |
1254 | $z->close() ; |
1255 | close $z ; |
1256 | |
1257 | |
1258 | |
1259 | Closes the output file/buffer. |
1260 | |
1261 | |
1262 | |
1263 | For most versions of Perl this method will be automatically invoked if |
1264 | the IO::Uncompress::Unzip object is destroyed (either explicitly or by the |
1265 | variable with the reference to the object going out of scope). The |
1266 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
1267 | these cases, the C<close> method will be called automatically, but |
1268 | not until global destruction of all live objects when the program is |
1269 | terminating. |
1270 | |
1271 | Therefore, if you want your scripts to be able to run on all versions |
1272 | of Perl, you should call C<close> explicitly and not rely on automatic |
1273 | closing. |
1274 | |
1275 | Returns true on success, otherwise 0. |
1276 | |
1277 | If the C<AutoClose> option has been enabled when the IO::Uncompress::Unzip |
1278 | object was created, and the object is associated with a file, the |
1279 | underlying file will also be closed. |
1280 | |
1281 | |
1282 | |
1283 | |
1284 | =head1 Importing |
1285 | |
1286 | No symbolic constants are required by this IO::Uncompress::Unzip at present. |
1287 | |
1288 | =over 5 |
1289 | |
1290 | =item :all |
1291 | |
1292 | Imports C<unzip> and C<$UnzipError>. |
1293 | Same as doing this |
1294 | |
1295 | use IO::Uncompress::Unzip qw(unzip $UnzipError) ; |
1296 | |
1297 | =back |
1298 | |
1299 | =head1 EXAMPLES |
1300 | |
1301 | |
1302 | |
1303 | |
1304 | =head1 SEE ALSO |
1305 | |
1306 | 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::Uncompress::AnyInflate>, L<IO::Uncompress::AnyUncompress> |
1307 | |
1308 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
1309 | |
1310 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1311 | L<Archive::Tar|Archive::Tar>, |
1312 | L<IO::Zlib|IO::Zlib> |
1313 | |
1314 | |
1315 | For RFC 1950, 1951 and 1952 see |
1316 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
1317 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
1318 | F<http://www.faqs.org/rfcs/rfc1952.html> |
1319 | |
1320 | The I<zlib> compression library was written by Jean-loup Gailly |
1321 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
1322 | |
1323 | The primary site for the I<zlib> compression library is |
1324 | F<http://www.zlib.org>. |
1325 | |
1326 | The primary site for gzip is F<http://www.gzip.org>. |
1327 | |
1328 | |
1329 | |
1330 | |
a02d0f6f |
1331 | =head1 AUTHOR |
1332 | |
cb7abd7f |
1333 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
a02d0f6f |
1334 | |
1335 | |
1336 | |
1337 | =head1 MODIFICATION HISTORY |
1338 | |
1339 | See the Changes file. |
1340 | |
1341 | =head1 COPYRIGHT AND LICENSE |
a02d0f6f |
1342 | |
1343 | Copyright (c) 2005-2006 Paul Marquess. All rights reserved. |
1344 | |
1345 | This program is free software; you can redistribute it and/or |
1346 | modify it under the same terms as Perl itself. |
1347 | |