Commit | Line | Data |
25f0751f |
1 | |
2 | package IO::Compress::Gzip ; |
3 | |
4 | require 5.004 ; |
5 | |
6 | use strict ; |
7 | use warnings; |
8 | use bytes; |
9 | |
10 | |
a1787f24 |
11 | use IO::Compress::RawDeflate 2.011 ; |
25f0751f |
12 | |
a1787f24 |
13 | use Compress::Raw::Zlib 2.011 ; |
14 | use IO::Compress::Base::Common 2.011 qw(:Status :Parse createSelfTiedObject); |
15 | use IO::Compress::Gzip::Constants 2.011 ; |
16 | use IO::Compress::Zlib::Extra 2.011 ; |
25f0751f |
17 | |
18 | BEGIN |
19 | { |
20 | if (defined &utf8::downgrade ) |
21 | { *noUTF8 = \&utf8::downgrade } |
22 | else |
23 | { *noUTF8 = sub {} } |
24 | } |
25 | |
26 | require Exporter ; |
27 | |
28 | our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, $GzipError); |
29 | |
a1787f24 |
30 | $VERSION = '2.011'; |
25f0751f |
31 | $GzipError = '' ; |
32 | |
33 | @ISA = qw(Exporter IO::Compress::RawDeflate); |
34 | @EXPORT_OK = qw( $GzipError gzip ) ; |
35 | %EXPORT_TAGS = %IO::Compress::RawDeflate::DEFLATE_CONSTANTS ; |
36 | push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; |
37 | Exporter::export_ok_tags('all'); |
38 | |
39 | sub new |
40 | { |
41 | my $class = shift ; |
42 | |
43 | my $obj = createSelfTiedObject($class, \$GzipError); |
44 | |
45 | $obj->_create(undef, @_); |
46 | } |
47 | |
48 | |
49 | sub gzip |
50 | { |
51 | my $obj = createSelfTiedObject(undef, \$GzipError); |
52 | return $obj->_def(@_); |
53 | } |
54 | |
55 | #sub newHeader |
56 | #{ |
57 | # my $self = shift ; |
58 | # #return GZIP_MINIMUM_HEADER ; |
59 | # return $self->mkHeader(*$self->{Got}); |
60 | #} |
61 | |
62 | sub getExtraParams |
63 | { |
64 | my $self = shift ; |
65 | |
66 | return ( |
67 | # zlib behaviour |
68 | $self->getZlibParams(), |
69 | |
70 | # Gzip header fields |
71 | 'Minimal' => [0, 1, Parse_boolean, 0], |
72 | 'Comment' => [0, 1, Parse_any, undef], |
73 | 'Name' => [0, 1, Parse_any, undef], |
74 | 'Time' => [0, 1, Parse_any, undef], |
75 | 'TextFlag' => [0, 1, Parse_boolean, 0], |
76 | 'HeaderCRC' => [0, 1, Parse_boolean, 0], |
77 | 'OS_Code' => [0, 1, Parse_unsigned, $Compress::Raw::Zlib::gzip_os_code], |
c70c1701 |
78 | 'ExtraField'=> [0, 1, Parse_any, undef], |
25f0751f |
79 | 'ExtraFlags'=> [0, 1, Parse_any, undef], |
80 | |
81 | ); |
82 | } |
83 | |
84 | |
85 | sub ckParams |
86 | { |
87 | my $self = shift ; |
88 | my $got = shift ; |
89 | |
90 | # gzip always needs crc32 |
91 | $got->value('CRC32' => 1); |
92 | |
93 | return 1 |
94 | if $got->value('Merge') ; |
95 | |
c70c1701 |
96 | my $strict = $got->value('Strict') ; |
25f0751f |
97 | |
98 | |
99 | { |
100 | if (! $got->parsed('Time') ) { |
101 | # Modification time defaults to now. |
102 | $got->value('Time' => time) ; |
103 | } |
104 | |
105 | # Check that the Name & Comment don't have embedded NULLs |
106 | # Also check that they only contain ISO 8859-1 chars. |
107 | if ($got->parsed('Name') && defined $got->value('Name')) { |
108 | my $name = $got->value('Name'); |
109 | |
110 | return $self->saveErrorString(undef, "Null Character found in Name", |
111 | Z_DATA_ERROR) |
c70c1701 |
112 | if $strict && $name =~ /\x00/ ; |
25f0751f |
113 | |
114 | return $self->saveErrorString(undef, "Non ISO 8859-1 Character found in Name", |
115 | Z_DATA_ERROR) |
c70c1701 |
116 | if $strict && $name =~ /$GZIP_FNAME_INVALID_CHAR_RE/o ; |
25f0751f |
117 | } |
118 | |
119 | if ($got->parsed('Comment') && defined $got->value('Comment')) { |
120 | my $comment = $got->value('Comment'); |
121 | |
122 | return $self->saveErrorString(undef, "Null Character found in Comment", |
123 | Z_DATA_ERROR) |
c70c1701 |
124 | if $strict && $comment =~ /\x00/ ; |
25f0751f |
125 | |
126 | return $self->saveErrorString(undef, "Non ISO 8859-1 Character found in Comment", |
127 | Z_DATA_ERROR) |
c70c1701 |
128 | if $strict && $comment =~ /$GZIP_FCOMMENT_INVALID_CHAR_RE/o; |
25f0751f |
129 | } |
130 | |
131 | if ($got->parsed('OS_Code') ) { |
132 | my $value = $got->value('OS_Code'); |
133 | |
134 | return $self->saveErrorString(undef, "OS_Code must be between 0 and 255, got '$value'") |
135 | if $value < 0 || $value > 255 ; |
136 | |
137 | } |
138 | |
139 | # gzip only supports Deflate at present |
140 | $got->value('Method' => Z_DEFLATED) ; |
141 | |
142 | if ( ! $got->parsed('ExtraFlags')) { |
143 | $got->value('ExtraFlags' => 2) |
144 | if $got->value('Level') == Z_BEST_SPEED ; |
145 | $got->value('ExtraFlags' => 4) |
146 | if $got->value('Level') == Z_BEST_COMPRESSION ; |
147 | } |
148 | |
c70c1701 |
149 | my $data = $got->value('ExtraField') ; |
150 | if (defined $data) { |
151 | my $bad = IO::Compress::Zlib::Extra::parseExtraField($data, $strict, 1) ; |
152 | return $self->saveErrorString(undef, "Error with ExtraField Parameter: $bad", Z_DATA_ERROR) |
25f0751f |
153 | if $bad ; |
154 | |
c70c1701 |
155 | $got->value('ExtraField', $data) ; |
25f0751f |
156 | } |
157 | } |
158 | |
159 | return 1; |
160 | } |
161 | |
162 | sub mkTrailer |
163 | { |
164 | my $self = shift ; |
165 | return pack("V V", *$self->{Compress}->crc32(), |
e7d45986 |
166 | *$self->{UnCompSize}->get32bit()); |
25f0751f |
167 | } |
168 | |
169 | sub getInverseClass |
170 | { |
171 | return ('IO::Uncompress::Gunzip', |
172 | \$IO::Uncompress::Gunzip::GunzipError); |
173 | } |
174 | |
175 | sub getFileInfo |
176 | { |
177 | my $self = shift ; |
178 | my $params = shift; |
179 | my $filename = shift ; |
180 | |
181 | my $defaultTime = (stat($filename))[9] ; |
182 | |
183 | $params->value('Name' => $filename) |
184 | if ! $params->parsed('Name') ; |
185 | |
186 | $params->value('Time' => $defaultTime) |
187 | if ! $params->parsed('Time') ; |
188 | } |
189 | |
190 | |
191 | sub mkHeader |
192 | { |
193 | my $self = shift ; |
194 | my $param = shift ; |
195 | |
196 | # stort-circuit if a minimal header is requested. |
197 | return GZIP_MINIMUM_HEADER if $param->value('Minimal') ; |
198 | |
199 | # METHOD |
200 | my $method = $param->valueOrDefault('Method', GZIP_CM_DEFLATED) ; |
201 | |
202 | # FLAGS |
203 | my $flags = GZIP_FLG_DEFAULT ; |
204 | $flags |= GZIP_FLG_FTEXT if $param->value('TextFlag') ; |
205 | $flags |= GZIP_FLG_FHCRC if $param->value('HeaderCRC') ; |
206 | $flags |= GZIP_FLG_FEXTRA if $param->wantValue('ExtraField') ; |
207 | $flags |= GZIP_FLG_FNAME if $param->wantValue('Name') ; |
208 | $flags |= GZIP_FLG_FCOMMENT if $param->wantValue('Comment') ; |
209 | |
210 | # MTIME |
211 | my $time = $param->valueOrDefault('Time', GZIP_MTIME_DEFAULT) ; |
212 | |
213 | # EXTRA FLAGS |
214 | my $extra_flags = $param->valueOrDefault('ExtraFlags', GZIP_XFL_DEFAULT); |
215 | |
216 | # OS CODE |
217 | my $os_code = $param->valueOrDefault('OS_Code', GZIP_OS_DEFAULT) ; |
218 | |
219 | |
220 | my $out = pack("C4 V C C", |
221 | GZIP_ID1, # ID1 |
222 | GZIP_ID2, # ID2 |
223 | $method, # Compression Method |
224 | $flags, # Flags |
225 | $time, # Modification Time |
226 | $extra_flags, # Extra Flags |
227 | $os_code, # Operating System Code |
228 | ) ; |
229 | |
230 | # EXTRA |
231 | if ($flags & GZIP_FLG_FEXTRA) { |
232 | my $extra = $param->value('ExtraField') ; |
233 | $out .= pack("v", length $extra) . $extra ; |
234 | } |
235 | |
236 | # NAME |
237 | if ($flags & GZIP_FLG_FNAME) { |
238 | my $name .= $param->value('Name') ; |
239 | $name =~ s/\x00.*$//; |
240 | $out .= $name ; |
241 | # Terminate the filename with NULL unless it already is |
242 | $out .= GZIP_NULL_BYTE |
243 | if !length $name or |
244 | substr($name, 1, -1) ne GZIP_NULL_BYTE ; |
245 | } |
246 | |
247 | # COMMENT |
248 | if ($flags & GZIP_FLG_FCOMMENT) { |
249 | my $comment .= $param->value('Comment') ; |
250 | $comment =~ s/\x00.*$//; |
251 | $out .= $comment ; |
252 | # Terminate the comment with NULL unless it already is |
253 | $out .= GZIP_NULL_BYTE |
254 | if ! length $comment or |
255 | substr($comment, 1, -1) ne GZIP_NULL_BYTE; |
256 | } |
257 | |
258 | # HEADER CRC |
259 | $out .= pack("v", crc32($out) & 0x00FF ) if $param->value('HeaderCRC') ; |
260 | |
261 | noUTF8($out); |
262 | |
263 | return $out ; |
264 | } |
265 | |
25f0751f |
266 | sub mkFinalTrailer |
267 | { |
268 | return ''; |
269 | } |
270 | |
271 | 1; |
272 | |
273 | __END__ |
274 | |
275 | =head1 NAME |
276 | |
cb7abd7f |
277 | IO::Compress::Gzip - Write RFC 1952 files/buffers |
278 | |
25f0751f |
279 | |
280 | |
281 | =head1 SYNOPSIS |
282 | |
283 | use IO::Compress::Gzip qw(gzip $GzipError) ; |
284 | |
25f0751f |
285 | my $status = gzip $input => $output [,OPTS] |
286 | or die "gzip failed: $GzipError\n"; |
287 | |
288 | my $z = new IO::Compress::Gzip $output [,OPTS] |
289 | or die "gzip failed: $GzipError\n"; |
290 | |
291 | $z->print($string); |
292 | $z->printf($format, $string); |
293 | $z->write($string); |
294 | $z->syswrite($string [, $length, $offset]); |
295 | $z->flush(); |
296 | $z->tell(); |
297 | $z->eof(); |
298 | $z->seek($position, $whence); |
299 | $z->binmode(); |
300 | $z->fileno(); |
301 | $z->opened(); |
302 | $z->autoflush(); |
303 | $z->input_line_number(); |
304 | $z->newStream( [OPTS] ); |
305 | |
306 | $z->deflateParams(); |
307 | |
308 | $z->close() ; |
309 | |
310 | $GzipError ; |
311 | |
312 | # IO::File mode |
313 | |
314 | print $z $string; |
315 | printf $z $format, $string; |
316 | tell $z |
317 | eof $z |
318 | seek $z, $position, $whence |
319 | binmode $z |
320 | fileno $z |
321 | close $z ; |
322 | |
323 | |
324 | =head1 DESCRIPTION |
325 | |
25f0751f |
326 | This module provides a Perl interface that allows writing compressed |
327 | data to files or buffer as defined in RFC 1952. |
328 | |
25f0751f |
329 | All the gzip headers defined in RFC 1952 can be created using |
330 | this module. |
331 | |
25f0751f |
332 | For reading RFC 1952 files/buffers, see the companion module |
333 | L<IO::Uncompress::Gunzip|IO::Uncompress::Gunzip>. |
334 | |
25f0751f |
335 | =head1 Functional Interface |
336 | |
337 | A top-level function, C<gzip>, is provided to carry out |
338 | "one-shot" compression between buffers and/or files. For finer |
339 | control over the compression process, see the L</"OO Interface"> |
340 | section. |
341 | |
342 | use IO::Compress::Gzip qw(gzip $GzipError) ; |
343 | |
344 | gzip $input => $output [,OPTS] |
345 | or die "gzip failed: $GzipError\n"; |
346 | |
25f0751f |
347 | The functional interface needs Perl5.005 or better. |
348 | |
25f0751f |
349 | =head2 gzip $input => $output [, OPTS] |
350 | |
25f0751f |
351 | C<gzip> expects at least two parameters, C<$input> and C<$output>. |
352 | |
353 | =head3 The C<$input> parameter |
354 | |
355 | The parameter, C<$input>, is used to define the source of |
356 | the uncompressed data. |
357 | |
358 | It can take one of the following forms: |
359 | |
360 | =over 5 |
361 | |
362 | =item A filename |
363 | |
364 | If the C<$input> parameter is a simple scalar, it is assumed to be a |
365 | filename. This file will be opened for reading and the input data |
366 | will be read from it. |
367 | |
368 | =item A filehandle |
369 | |
370 | If the C<$input> parameter is a filehandle, the input data will be |
371 | read from it. |
372 | The string '-' can be used as an alias for standard input. |
373 | |
374 | =item A scalar reference |
375 | |
376 | If C<$input> is a scalar reference, the input data will be read |
377 | from C<$$input>. |
378 | |
379 | =item An array reference |
380 | |
381 | If C<$input> is an array reference, each element in the array must be a |
382 | filename. |
383 | |
384 | The input data will be read from each file in turn. |
385 | |
386 | The complete array will be walked to ensure that it only |
387 | contains valid filenames before any data is compressed. |
388 | |
25f0751f |
389 | =item An Input FileGlob string |
390 | |
391 | If C<$input> is a string that is delimited by the characters "<" and ">" |
392 | C<gzip> will assume that it is an I<input fileglob string>. The |
393 | input is the list of files that match the fileglob. |
394 | |
395 | If the fileglob does not match any files ... |
396 | |
397 | See L<File::GlobMapper|File::GlobMapper> for more details. |
398 | |
25f0751f |
399 | =back |
400 | |
401 | If the C<$input> parameter is any other type, C<undef> will be returned. |
402 | |
25f0751f |
403 | In addition, if C<$input> is a simple filename, the default values for |
cb7abd7f |
404 | the C<Name> and C<Time> options will be sourced from that file. |
25f0751f |
405 | |
406 | If you do not want to use these defaults they can be overridden by |
407 | explicitly setting the C<Name> and C<Time> options or by setting the |
408 | C<Minimal> parameter. |
409 | |
25f0751f |
410 | =head3 The C<$output> parameter |
411 | |
412 | The parameter C<$output> is used to control the destination of the |
413 | compressed data. This parameter can take one of these forms. |
414 | |
415 | =over 5 |
416 | |
417 | =item A filename |
418 | |
419 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
420 | filename. This file will be opened for writing and the compressed |
421 | data will be written to it. |
422 | |
423 | =item A filehandle |
424 | |
425 | If the C<$output> parameter is a filehandle, the compressed data |
426 | will be written to it. |
427 | The string '-' can be used as an alias for standard output. |
428 | |
25f0751f |
429 | =item A scalar reference |
430 | |
431 | If C<$output> is a scalar reference, the compressed data will be |
432 | stored in C<$$output>. |
433 | |
25f0751f |
434 | =item An Array Reference |
435 | |
436 | If C<$output> is an array reference, the compressed data will be |
437 | pushed onto the array. |
438 | |
439 | =item An Output FileGlob |
440 | |
441 | If C<$output> is a string that is delimited by the characters "<" and ">" |
442 | C<gzip> will assume that it is an I<output fileglob string>. The |
443 | output is the list of files that match the fileglob. |
444 | |
445 | When C<$output> is an fileglob string, C<$input> must also be a fileglob |
446 | string. Anything else is an error. |
447 | |
448 | =back |
449 | |
450 | If the C<$output> parameter is any other type, C<undef> will be returned. |
451 | |
25f0751f |
452 | =head2 Notes |
453 | |
454 | When C<$input> maps to multiple files/buffers and C<$output> is a single |
c70c1701 |
455 | file/buffer the input files/buffers will be stored |
456 | in C<$output> as a concatenated series of compressed data streams. |
457 | |
25f0751f |
458 | =head2 Optional Parameters |
459 | |
460 | Unless specified below, the optional parameters for C<gzip>, |
461 | C<OPTS>, are the same as those used with the OO interface defined in the |
462 | L</"Constructor Options"> section below. |
463 | |
464 | =over 5 |
465 | |
e7d45986 |
466 | =item C<< AutoClose => 0|1 >> |
25f0751f |
467 | |
468 | This option applies to any input or output data streams to |
469 | C<gzip> that are filehandles. |
470 | |
471 | If C<AutoClose> is specified, and the value is true, it will result in all |
472 | input and/or output filehandles being closed once C<gzip> has |
473 | completed. |
474 | |
475 | This parameter defaults to 0. |
476 | |
e7d45986 |
477 | =item C<< BinModeIn => 0|1 >> |
25f0751f |
478 | |
479 | When reading from a file or filehandle, set C<binmode> before reading. |
480 | |
481 | Defaults to 0. |
482 | |
e7d45986 |
483 | =item C<< Append => 0|1 >> |
25f0751f |
484 | |
485 | TODO |
486 | |
25f0751f |
487 | =back |
488 | |
25f0751f |
489 | =head2 Examples |
490 | |
491 | To read the contents of the file C<file1.txt> and write the compressed |
492 | data to the file C<file1.txt.gz>. |
493 | |
494 | use strict ; |
495 | use warnings ; |
496 | use IO::Compress::Gzip qw(gzip $GzipError) ; |
497 | |
498 | my $input = "file1.txt"; |
499 | gzip $input => "$input.gz" |
500 | or die "gzip failed: $GzipError\n"; |
501 | |
25f0751f |
502 | To read from an existing Perl filehandle, C<$input>, and write the |
503 | compressed data to a buffer, C<$buffer>. |
504 | |
505 | use strict ; |
506 | use warnings ; |
507 | use IO::Compress::Gzip qw(gzip $GzipError) ; |
508 | use IO::File ; |
509 | |
510 | my $input = new IO::File "<file1.txt" |
511 | or die "Cannot open 'file1.txt': $!\n" ; |
512 | my $buffer ; |
513 | gzip $input => \$buffer |
514 | or die "gzip failed: $GzipError\n"; |
515 | |
516 | To compress all files in the directory "/my/home" that match "*.txt" |
517 | and store the compressed data in the same directory |
518 | |
519 | use strict ; |
520 | use warnings ; |
521 | use IO::Compress::Gzip qw(gzip $GzipError) ; |
522 | |
523 | gzip '</my/home/*.txt>' => '<*.gz>' |
524 | or die "gzip failed: $GzipError\n"; |
525 | |
526 | and if you want to compress each file one at a time, this will do the trick |
527 | |
528 | use strict ; |
529 | use warnings ; |
530 | use IO::Compress::Gzip qw(gzip $GzipError) ; |
531 | |
532 | for my $input ( glob "/my/home/*.txt" ) |
533 | { |
534 | my $output = "$input.gz" ; |
535 | gzip $input => $output |
536 | or die "Error compressing '$input': $GzipError\n"; |
537 | } |
538 | |
25f0751f |
539 | =head1 OO Interface |
540 | |
541 | =head2 Constructor |
542 | |
543 | The format of the constructor for C<IO::Compress::Gzip> is shown below |
544 | |
545 | my $z = new IO::Compress::Gzip $output [,OPTS] |
546 | or die "IO::Compress::Gzip failed: $GzipError\n"; |
547 | |
548 | It returns an C<IO::Compress::Gzip> object on success and undef on failure. |
549 | The variable C<$GzipError> will contain an error message on failure. |
550 | |
551 | If you are running Perl 5.005 or better the object, C<$z>, returned from |
552 | IO::Compress::Gzip can be used exactly like an L<IO::File|IO::File> filehandle. |
553 | This means that all normal output file operations can be carried out |
554 | with C<$z>. |
555 | For example, to write to a compressed file/buffer you can use either of |
556 | these forms |
557 | |
558 | $z->print("hello world\n"); |
559 | print $z "hello world\n"; |
560 | |
561 | The mandatory parameter C<$output> is used to control the destination |
562 | of the compressed data. This parameter can take one of these forms. |
563 | |
564 | =over 5 |
565 | |
566 | =item A filename |
567 | |
568 | If the C<$output> parameter is a simple scalar, it is assumed to be a |
569 | filename. This file will be opened for writing and the compressed data |
570 | will be written to it. |
571 | |
572 | =item A filehandle |
573 | |
574 | If the C<$output> parameter is a filehandle, the compressed data will be |
575 | written to it. |
576 | The string '-' can be used as an alias for standard output. |
577 | |
25f0751f |
578 | =item A scalar reference |
579 | |
580 | If C<$output> is a scalar reference, the compressed data will be stored |
581 | in C<$$output>. |
582 | |
583 | =back |
584 | |
585 | If the C<$output> parameter is any other type, C<IO::Compress::Gzip>::new will |
586 | return undef. |
587 | |
588 | =head2 Constructor Options |
589 | |
590 | C<OPTS> is any combination of the following options: |
591 | |
592 | =over 5 |
593 | |
e7d45986 |
594 | =item C<< AutoClose => 0|1 >> |
25f0751f |
595 | |
596 | This option is only valid when the C<$output> parameter is a filehandle. If |
597 | specified, and the value is true, it will result in the C<$output> being |
598 | closed once either the C<close> method is called or the C<IO::Compress::Gzip> |
599 | object is destroyed. |
600 | |
601 | This parameter defaults to 0. |
602 | |
e7d45986 |
603 | =item C<< Append => 0|1 >> |
25f0751f |
604 | |
605 | Opens C<$output> in append mode. |
606 | |
607 | The behaviour of this option is dependent on the type of C<$output>. |
608 | |
609 | =over 5 |
610 | |
611 | =item * A Buffer |
612 | |
613 | If C<$output> is a buffer and C<Append> is enabled, all compressed data |
614 | will be append to the end if C<$output>. Otherwise C<$output> will be |
615 | cleared before any data is written to it. |
616 | |
617 | =item * A Filename |
618 | |
619 | If C<$output> is a filename and C<Append> is enabled, the file will be |
620 | opened in append mode. Otherwise the contents of the file, if any, will be |
621 | truncated before any compressed data is written to it. |
622 | |
623 | =item * A Filehandle |
624 | |
625 | If C<$output> is a filehandle, the file pointer will be positioned to the |
626 | end of the file via a call to C<seek> before any compressed data is written |
627 | to it. Otherwise the file pointer will not be moved. |
628 | |
629 | =back |
630 | |
631 | This parameter defaults to 0. |
632 | |
e7d45986 |
633 | =item C<< Merge => 0|1 >> |
25f0751f |
634 | |
635 | This option is used to compress input data and append it to an existing |
636 | compressed data stream in C<$output>. The end result is a single compressed |
637 | data stream stored in C<$output>. |
638 | |
25f0751f |
639 | It is a fatal error to attempt to use this option when C<$output> is not an |
640 | RFC 1952 data stream. |
641 | |
25f0751f |
642 | There are a number of other limitations with the C<Merge> option: |
643 | |
644 | =over 5 |
645 | |
646 | =item 1 |
647 | |
648 | This module needs to have been built with zlib 1.2.1 or better to work. A |
649 | fatal error will be thrown if C<Merge> is used with an older version of |
650 | zlib. |
651 | |
652 | =item 2 |
653 | |
654 | If C<$output> is a file or a filehandle, it must be seekable. |
655 | |
656 | =back |
657 | |
25f0751f |
658 | This parameter defaults to 0. |
659 | |
25f0751f |
660 | =item -Level |
661 | |
662 | Defines the compression level used by zlib. The value should either be |
663 | a number between 0 and 9 (0 means no compression and 9 is maximum |
664 | compression), or one of the symbolic constants defined below. |
665 | |
666 | Z_NO_COMPRESSION |
667 | Z_BEST_SPEED |
668 | Z_BEST_COMPRESSION |
669 | Z_DEFAULT_COMPRESSION |
670 | |
671 | The default is Z_DEFAULT_COMPRESSION. |
672 | |
673 | Note, these constants are not imported by C<IO::Compress::Gzip> by default. |
674 | |
675 | use IO::Compress::Gzip qw(:strategy); |
676 | use IO::Compress::Gzip qw(:constants); |
677 | use IO::Compress::Gzip qw(:all); |
678 | |
679 | =item -Strategy |
680 | |
681 | Defines the strategy used to tune the compression. Use one of the symbolic |
682 | constants defined below. |
683 | |
684 | Z_FILTERED |
685 | Z_HUFFMAN_ONLY |
686 | Z_RLE |
687 | Z_FIXED |
688 | Z_DEFAULT_STRATEGY |
689 | |
690 | The default is Z_DEFAULT_STRATEGY. |
691 | |
e7d45986 |
692 | =item C<< Minimal => 0|1 >> |
25f0751f |
693 | |
694 | If specified, this option will force the creation of the smallest possible |
695 | compliant gzip header (which is exactly 10 bytes long) as defined in |
696 | RFC 1952. |
697 | |
698 | See the section titled "Compliance" in RFC 1952 for a definition |
699 | of the values used for the fields in the gzip header. |
700 | |
701 | All other parameters that control the content of the gzip header will |
702 | be ignored if this parameter is set to 1. |
703 | |
704 | This parameter defaults to 0. |
705 | |
e7d45986 |
706 | =item C<< Comment => $comment >> |
25f0751f |
707 | |
708 | Stores the contents of C<$comment> in the COMMENT field in |
709 | the gzip header. |
710 | By default, no comment field is written to the gzip file. |
711 | |
712 | If the C<-Strict> option is enabled, the comment can only consist of ISO |
713 | 8859-1 characters plus line feed. |
714 | |
715 | If the C<-Strict> option is disabled, the comment field can contain any |
716 | character except NULL. If any null characters are present, the field |
717 | will be truncated at the first NULL. |
718 | |
e7d45986 |
719 | =item C<< Name => $string >> |
25f0751f |
720 | |
721 | Stores the contents of C<$string> in the gzip NAME header field. If |
722 | C<Name> is not specified, no gzip NAME field will be created. |
723 | |
724 | If the C<-Strict> option is enabled, C<$string> can only consist of ISO |
725 | 8859-1 characters. |
726 | |
727 | If C<-Strict> is disabled, then C<$string> can contain any character |
728 | except NULL. If any null characters are present, the field will be |
729 | truncated at the first NULL. |
730 | |
e7d45986 |
731 | =item C<< Time => $number >> |
25f0751f |
732 | |
733 | Sets the MTIME field in the gzip header to $number. |
734 | |
735 | This field defaults to the time the C<IO::Compress::Gzip> object was created |
736 | if this option is not specified. |
737 | |
e7d45986 |
738 | =item C<< TextFlag => 0|1 >> |
25f0751f |
739 | |
740 | This parameter controls the setting of the FLG.FTEXT bit in the gzip |
741 | header. It is used to signal that the data stored in the gzip file/buffer |
742 | is probably text. |
743 | |
744 | The default is 0. |
745 | |
e7d45986 |
746 | =item C<< HeaderCRC => 0|1 >> |
25f0751f |
747 | |
748 | When true this parameter will set the FLG.FHCRC bit to 1 in the gzip header |
749 | and set the CRC16 header field to the CRC of the complete gzip header |
750 | except the CRC16 field itself. |
751 | |
752 | B<Note> that gzip files created with the C<HeaderCRC> flag set to 1 cannot |
753 | be read by most, if not all, of the the standard gunzip utilities, most |
754 | notably gzip version 1.2.4. You should therefore avoid using this option if |
755 | you want to maximize the portability of your gzip files. |
756 | |
757 | This parameter defaults to 0. |
758 | |
e7d45986 |
759 | =item C<< OS_Code => $value >> |
25f0751f |
760 | |
761 | Stores C<$value> in the gzip OS header field. A number between 0 and 255 is |
762 | valid. |
763 | |
764 | If not specified, this parameter defaults to the OS code of the Operating |
765 | System this module was built on. The value 3 is used as a catch-all for all |
766 | Unix variants and unknown Operating Systems. |
767 | |
e7d45986 |
768 | =item C<< ExtraField => $data >> |
25f0751f |
769 | |
770 | This parameter allows additional metadata to be stored in the ExtraField in |
771 | the gzip header. An RFC 1952 compliant ExtraField consists of zero or more |
772 | subfields. Each subfield consists of a two byte header followed by the |
773 | subfield data. |
774 | |
775 | The list of subfields can be supplied in any of the following formats |
776 | |
777 | -ExtraField => [$id1, $data1, |
778 | $id2, $data2, |
779 | ... |
780 | ] |
781 | -ExtraField => [ [$id1 => $data1], |
782 | [$id2 => $data2], |
783 | ... |
784 | ] |
785 | -ExtraField => { $id1 => $data1, |
786 | $id2 => $data2, |
787 | ... |
788 | } |
789 | |
790 | Where C<$id1>, C<$id2> are two byte subfield ID's. The second byte of |
791 | the ID cannot be 0, unless the C<Strict> option has been disabled. |
792 | |
793 | If you use the hash syntax, you have no control over the order in which |
794 | the ExtraSubFields are stored, plus you cannot have SubFields with |
795 | duplicate ID. |
796 | |
797 | Alternatively the list of subfields can by supplied as a scalar, thus |
798 | |
799 | -ExtraField => $rawdata |
800 | |
801 | If you use the raw format, and the C<Strict> option is enabled, |
802 | C<IO::Compress::Gzip> will check that C<$rawdata> consists of zero or more |
803 | conformant sub-fields. When C<Strict> is disabled, C<$rawdata> can |
804 | consist of any arbitrary byte stream. |
805 | |
806 | The maximum size of the Extra Field 65535 bytes. |
807 | |
e7d45986 |
808 | =item C<< ExtraFlags => $value >> |
25f0751f |
809 | |
810 | Sets the XFL byte in the gzip header to C<$value>. |
811 | |
812 | If this option is not present, the value stored in XFL field will be |
813 | determined by the setting of the C<Level> option. |
814 | |
e7d45986 |
815 | If C<< Level => Z_BEST_SPEED >> has been specified then XFL is set to 2. |
816 | If C<< Level => Z_BEST_COMPRESSION >> has been specified then XFL is set to 4. |
25f0751f |
817 | Otherwise XFL is set to 0. |
818 | |
e7d45986 |
819 | =item C<< Strict => 0|1 >> |
25f0751f |
820 | |
25f0751f |
821 | C<Strict> will optionally police the values supplied with other options |
822 | to ensure they are compliant with RFC1952. |
823 | |
824 | This option is enabled by default. |
825 | |
826 | If C<Strict> is enabled the following behaviour will be policed: |
827 | |
828 | =over 5 |
829 | |
830 | =item * |
831 | |
832 | The value supplied with the C<Name> option can only contain ISO 8859-1 |
833 | characters. |
834 | |
835 | =item * |
836 | |
837 | The value supplied with the C<Comment> option can only contain ISO 8859-1 |
838 | characters plus line-feed. |
839 | |
840 | =item * |
841 | |
842 | The values supplied with the C<-Name> and C<-Comment> options cannot |
843 | contain multiple embedded nulls. |
844 | |
845 | =item * |
846 | |
847 | If an C<ExtraField> option is specified and it is a simple scalar, |
848 | it must conform to the sub-field structure as defined in RFC 1952. |
849 | |
850 | =item * |
851 | |
852 | If an C<ExtraField> option is specified the second byte of the ID will be |
853 | checked in each subfield to ensure that it does not contain the reserved |
854 | value 0x00. |
855 | |
856 | =back |
857 | |
858 | When C<Strict> is disabled the following behaviour will be policed: |
859 | |
860 | =over 5 |
861 | |
862 | =item * |
863 | |
864 | The value supplied with C<-Name> option can contain |
865 | any character except NULL. |
866 | |
867 | =item * |
868 | |
869 | The value supplied with C<-Comment> option can contain any character |
870 | except NULL. |
871 | |
872 | =item * |
873 | |
874 | The values supplied with the C<-Name> and C<-Comment> options can contain |
875 | multiple embedded nulls. The string written to the gzip header will |
876 | consist of the characters up to, but not including, the first embedded |
877 | NULL. |
878 | |
879 | =item * |
880 | |
881 | If an C<ExtraField> option is specified and it is a simple scalar, the |
882 | structure will not be checked. The only error is if the length is too big. |
883 | |
884 | =item * |
885 | |
886 | The ID header in an C<ExtraField> sub-field can consist of any two bytes. |
887 | |
888 | =back |
889 | |
25f0751f |
890 | =back |
891 | |
892 | =head2 Examples |
893 | |
894 | TODO |
895 | |
896 | =head1 Methods |
897 | |
898 | =head2 print |
899 | |
900 | Usage is |
901 | |
902 | $z->print($data) |
903 | print $z $data |
904 | |
905 | Compresses and outputs the contents of the C<$data> parameter. This |
906 | has the same behaviour as the C<print> built-in. |
907 | |
908 | Returns true if successful. |
909 | |
910 | =head2 printf |
911 | |
912 | Usage is |
913 | |
914 | $z->printf($format, $data) |
915 | printf $z $format, $data |
916 | |
917 | Compresses and outputs the contents of the C<$data> parameter. |
918 | |
919 | Returns true if successful. |
920 | |
921 | =head2 syswrite |
922 | |
923 | Usage is |
924 | |
925 | $z->syswrite $data |
926 | $z->syswrite $data, $length |
927 | $z->syswrite $data, $length, $offset |
928 | |
929 | Compresses and outputs the contents of the C<$data> parameter. |
930 | |
931 | Returns the number of uncompressed bytes written, or C<undef> if |
932 | unsuccessful. |
933 | |
934 | =head2 write |
935 | |
936 | Usage is |
937 | |
938 | $z->write $data |
939 | $z->write $data, $length |
940 | $z->write $data, $length, $offset |
941 | |
942 | Compresses and outputs the contents of the C<$data> parameter. |
943 | |
944 | Returns the number of uncompressed bytes written, or C<undef> if |
945 | unsuccessful. |
946 | |
947 | =head2 flush |
948 | |
949 | Usage is |
950 | |
25f0751f |
951 | $z->flush; |
952 | $z->flush($flush_type); |
953 | |
25f0751f |
954 | Flushes any pending compressed data to the output file/buffer. |
955 | |
25f0751f |
956 | This method takes an optional parameter, C<$flush_type>, that controls |
957 | how the flushing will be carried out. By default the C<$flush_type> |
958 | used is C<Z_FINISH>. Other valid values for C<$flush_type> are |
959 | C<Z_NO_FLUSH>, C<Z_SYNC_FLUSH>, C<Z_FULL_FLUSH> and C<Z_BLOCK>. It is |
960 | strongly recommended that you only set the C<flush_type> parameter if |
961 | you fully understand the implications of what it does - overuse of C<flush> |
962 | can seriously degrade the level of compression achieved. See the C<zlib> |
963 | documentation for details. |
964 | |
25f0751f |
965 | Returns true on success. |
966 | |
25f0751f |
967 | =head2 tell |
968 | |
969 | Usage is |
970 | |
971 | $z->tell() |
972 | tell $z |
973 | |
974 | Returns the uncompressed file offset. |
975 | |
976 | =head2 eof |
977 | |
978 | Usage is |
979 | |
980 | $z->eof(); |
981 | eof($z); |
982 | |
25f0751f |
983 | Returns true if the C<close> method has been called. |
984 | |
25f0751f |
985 | =head2 seek |
986 | |
987 | $z->seek($position, $whence); |
988 | seek($z, $position, $whence); |
989 | |
25f0751f |
990 | Provides a sub-set of the C<seek> functionality, with the restriction |
991 | that it is only legal to seek forward in the output file/buffer. |
992 | It is a fatal error to attempt to seek backward. |
993 | |
994 | Empty parts of the file/buffer will have NULL (0x00) bytes written to them. |
995 | |
25f0751f |
996 | The C<$whence> parameter takes one the usual values, namely SEEK_SET, |
997 | SEEK_CUR or SEEK_END. |
998 | |
999 | Returns 1 on success, 0 on failure. |
1000 | |
1001 | =head2 binmode |
1002 | |
1003 | Usage is |
1004 | |
1005 | $z->binmode |
1006 | binmode $z ; |
1007 | |
1008 | This is a noop provided for completeness. |
1009 | |
1010 | =head2 opened |
1011 | |
1012 | $z->opened() |
1013 | |
1014 | Returns true if the object currently refers to a opened file/buffer. |
1015 | |
1016 | =head2 autoflush |
1017 | |
1018 | my $prev = $z->autoflush() |
1019 | my $prev = $z->autoflush(EXPR) |
1020 | |
1021 | If the C<$z> object is associated with a file or a filehandle, this method |
1022 | returns the current autoflush setting for the underlying filehandle. If |
1023 | C<EXPR> is present, and is non-zero, it will enable flushing after every |
1024 | write/print operation. |
1025 | |
1026 | If C<$z> is associated with a buffer, this method has no effect and always |
1027 | returns C<undef>. |
1028 | |
1029 | B<Note> that the special variable C<$|> B<cannot> be used to set or |
1030 | retrieve the autoflush setting. |
1031 | |
1032 | =head2 input_line_number |
1033 | |
1034 | $z->input_line_number() |
1035 | $z->input_line_number(EXPR) |
1036 | |
25f0751f |
1037 | This method always returns C<undef> when compressing. |
1038 | |
25f0751f |
1039 | =head2 fileno |
1040 | |
1041 | $z->fileno() |
1042 | fileno($z) |
1043 | |
d54256af |
1044 | If the C<$z> object is associated with a file or a filehandle, C<fileno> |
1045 | will return the underlying file descriptor. Once the C<close> method is |
1046 | called C<fileno> will return C<undef>. |
25f0751f |
1047 | |
d54256af |
1048 | If the C<$z> object is is associated with a buffer, this method will return |
1049 | C<undef>. |
25f0751f |
1050 | |
1051 | =head2 close |
1052 | |
1053 | $z->close() ; |
1054 | close $z ; |
1055 | |
25f0751f |
1056 | Flushes any pending compressed data and then closes the output file/buffer. |
1057 | |
25f0751f |
1058 | For most versions of Perl this method will be automatically invoked if |
1059 | the IO::Compress::Gzip object is destroyed (either explicitly or by the |
1060 | variable with the reference to the object going out of scope). The |
1061 | exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In |
1062 | these cases, the C<close> method will be called automatically, but |
1063 | not until global destruction of all live objects when the program is |
1064 | terminating. |
1065 | |
1066 | Therefore, if you want your scripts to be able to run on all versions |
1067 | of Perl, you should call C<close> explicitly and not rely on automatic |
1068 | closing. |
1069 | |
1070 | Returns true on success, otherwise 0. |
1071 | |
1072 | If the C<AutoClose> option has been enabled when the IO::Compress::Gzip |
1073 | object was created, and the object is associated with a file, the |
1074 | underlying file will also be closed. |
1075 | |
25f0751f |
1076 | =head2 newStream([OPTS]) |
1077 | |
1078 | Usage is |
1079 | |
1080 | $z->newStream( [OPTS] ) |
1081 | |
1082 | Closes the current compressed data stream and starts a new one. |
1083 | |
e7d45986 |
1084 | OPTS consists of any of the the options that are available when creating |
1085 | the C<$z> object. |
25f0751f |
1086 | |
e7d45986 |
1087 | See the L</"Constructor Options"> section for more details. |
25f0751f |
1088 | |
25f0751f |
1089 | =head2 deflateParams |
1090 | |
1091 | Usage is |
1092 | |
1093 | $z->deflateParams |
1094 | |
1095 | TODO |
1096 | |
25f0751f |
1097 | =head1 Importing |
1098 | |
25f0751f |
1099 | A number of symbolic constants are required by some methods in |
1100 | C<IO::Compress::Gzip>. None are imported by default. |
1101 | |
25f0751f |
1102 | =over 5 |
1103 | |
1104 | =item :all |
1105 | |
25f0751f |
1106 | Imports C<gzip>, C<$GzipError> and all symbolic |
1107 | constants that can be used by C<IO::Compress::Gzip>. Same as doing this |
1108 | |
1109 | use IO::Compress::Gzip qw(gzip $GzipError :constants) ; |
1110 | |
1111 | =item :constants |
1112 | |
1113 | Import all symbolic constants. Same as doing this |
1114 | |
1115 | use IO::Compress::Gzip qw(:flush :level :strategy) ; |
1116 | |
1117 | =item :flush |
1118 | |
1119 | These symbolic constants are used by the C<flush> method. |
1120 | |
1121 | Z_NO_FLUSH |
1122 | Z_PARTIAL_FLUSH |
1123 | Z_SYNC_FLUSH |
1124 | Z_FULL_FLUSH |
1125 | Z_FINISH |
1126 | Z_BLOCK |
1127 | |
1128 | =item :level |
1129 | |
1130 | These symbolic constants are used by the C<Level> option in the constructor. |
1131 | |
1132 | Z_NO_COMPRESSION |
1133 | Z_BEST_SPEED |
1134 | Z_BEST_COMPRESSION |
1135 | Z_DEFAULT_COMPRESSION |
1136 | |
25f0751f |
1137 | =item :strategy |
1138 | |
1139 | These symbolic constants are used by the C<Strategy> option in the constructor. |
1140 | |
1141 | Z_FILTERED |
1142 | Z_HUFFMAN_ONLY |
1143 | Z_RLE |
1144 | Z_FIXED |
1145 | Z_DEFAULT_STRATEGY |
2b4e0969 |
1146 | |
1147 | |
25f0751f |
1148 | |
1149 | |
1150 | =back |
1151 | |
25f0751f |
1152 | =head1 EXAMPLES |
1153 | |
d54256af |
1154 | =head2 Apache::GZip Revisited |
e7d45986 |
1155 | |
d54256af |
1156 | See L<IO::Compress::Zlib::FAQ|IO::Compress::Zlib::FAQ/"Apache::GZip Revisited"> |
e7d45986 |
1157 | |
d54256af |
1158 | |
e7d45986 |
1159 | |
d54256af |
1160 | =head2 Working with Net::FTP |
e7d45986 |
1161 | |
d54256af |
1162 | See L<IO::Compress::Zlib::FAQ|IO::Compress::Zlib::FAQ/"Compressed files and Net::FTP"> |
e7d45986 |
1163 | |
25f0751f |
1164 | =head1 SEE ALSO |
1165 | |
258133d1 |
1166 | L<Compress::Zlib>, 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> |
25f0751f |
1167 | |
1168 | L<Compress::Zlib::FAQ|Compress::Zlib::FAQ> |
1169 | |
1170 | L<File::GlobMapper|File::GlobMapper>, L<Archive::Zip|Archive::Zip>, |
1171 | L<Archive::Tar|Archive::Tar>, |
1172 | L<IO::Zlib|IO::Zlib> |
1173 | |
25f0751f |
1174 | For RFC 1950, 1951 and 1952 see |
1175 | F<http://www.faqs.org/rfcs/rfc1950.html>, |
1176 | F<http://www.faqs.org/rfcs/rfc1951.html> and |
1177 | F<http://www.faqs.org/rfcs/rfc1952.html> |
1178 | |
1179 | The I<zlib> compression library was written by Jean-loup Gailly |
1180 | F<gzip@prep.ai.mit.edu> and Mark Adler F<madler@alumni.caltech.edu>. |
1181 | |
1182 | The primary site for the I<zlib> compression library is |
1183 | F<http://www.zlib.org>. |
1184 | |
1185 | The primary site for gzip is F<http://www.gzip.org>. |
1186 | |
25f0751f |
1187 | =head1 AUTHOR |
1188 | |
cb7abd7f |
1189 | This module was written by Paul Marquess, F<pmqs@cpan.org>. |
25f0751f |
1190 | |
25f0751f |
1191 | =head1 MODIFICATION HISTORY |
1192 | |
1193 | See the Changes file. |
1194 | |
1195 | =head1 COPYRIGHT AND LICENSE |
25f0751f |
1196 | |
d54256af |
1197 | Copyright (c) 2005-2008 Paul Marquess. All rights reserved. |
25f0751f |
1198 | |
1199 | This program is free software; you can redistribute it and/or |
1200 | modify it under the same terms as Perl itself. |
1201 | |