ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/Convert-UUlib/UUlib.pm
(Generate patch)

Comparing Convert-UUlib/UUlib.pm (file contents):
Revision 1.17 by root, Mon Nov 24 16:10:22 2003 UTC vs.
Revision 1.47 by root, Fri Feb 28 16:57:25 2020 UTC

1package Convert::UUlib; 1package Convert::UUlib;
2
3no warnings;
4use strict;
2 5
3use Carp; 6use Carp;
4 7
5require Exporter; 8require Exporter;
6require DynaLoader; 9require DynaLoader;
7 10
8$VERSION = "1.0"; 11our $VERSION = 1.62;
9 12
10@ISA = qw(Exporter DynaLoader); 13our @ISA = qw(Exporter DynaLoader);
11 14
12@_consts = qw( 15our @_consts = qw(
13 ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING 16 ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING
14 17
15 FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA 18 FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA
16 FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE 19 FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE
17 20
18 MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING 21 MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING
19 22
23 OPT_RBUF OPT_WBUF
20 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT 24 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT
21 OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB 25 OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB
22 OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE 26 OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
23 OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT 27 OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT OPT_AUTOCHECK
24 28
25 RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA 29 RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
26 RET_NOEND RET_NOMEM RET_OK RET_UNSUP 30 RET_NOEND RET_NOMEM RET_OK RET_UNSUP
27 31
28 B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED 32 B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
29 XX_ENCODED UU_ENCODED YENC_ENCODED 33 XX_ENCODED UU_ENCODED YENC_ENCODED
30); 34);
31 35
32@_funcs = qw( 36our @_funcs = qw(
33 Initialize CleanUp GetOption SetOption strerror SetMsgCallback 37 Initialize CleanUp GetOption SetOption strerror SetMsgCallback
34 SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback 38 SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
35 FNameFilter LoadFile GetFileListItem RenameFile DecodeToTemp 39 FNameFilter LoadFile GetFileListItem GetFileList RenameFile DecodeToTemp
36 RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti 40 RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
37 EncodePartial EncodeToStream EncodeToFile E_PrepSingle 41 EncodePartial EncodeToStream EncodeToFile E_PrepSingle
38 E_PrepPartial 42 E_PrepPartial
39 43
40 straction strencoding strmsglevel 44 straction strencoding strmsglevel
41); 45);
42 46
43@EXPORT = @_consts; 47our @EXPORT = @_consts;
44@EXPORT_OK = @_funcs; 48our @EXPORT_OK = @_funcs;
45%EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts); 49our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);
46 50
47bootstrap Convert::UUlib $VERSION; 51bootstrap Convert::UUlib $VERSION;
48 52
49Initialize(); 53Initialize();
50 54
51# not when < 5.005_6x 55# not when < 5.005_6x
52# END { CleanUp() } 56# END { CleanUp() }
53 57
54for (@_consts) { 58for (@_consts) {
55 my $constant = constant($_); 59 my $constant = constant($_);
60 no strict 'refs';
56 *$_ = sub () { $constant }; 61 *$_ = sub () { $constant };
57} 62}
58 63
59# action code -> string mapping 64# action code -> string mapping
60sub straction($) { 65sub straction($) {
… …
100 use Convert::UUlib ':all'; 105 use Convert::UUlib ':all';
101 106
102 # read all the files named on the commandline and decode them 107 # read all the files named on the commandline and decode them
103 # into the CURRENT directory. See below for a longer example. 108 # into the CURRENT directory. See below for a longer example.
104 LoadFile $_ for @ARGV; 109 LoadFile $_ for @ARGV;
105 for (my $i = 0; my $uu = GetFileListItem $i; $i++) { 110 for my $uu (GetFileList) {
106 if ($uu->state & FILE_OK) { 111 if ($uu->state & FILE_OK) {
107 $uu->decode; 112 $uu->decode;
108 print $uu->filename, "\n"; 113 print $uu->filename, "\n";
109 } 114 }
110 } 115 }
… …
154 OPT_TINYB64 detect short B64 outside of Mime 159 OPT_TINYB64 detect short B64 outside of Mime
155 OPT_ENCEXT extension for single-part encoded files 160 OPT_ENCEXT extension for single-part encoded files
156 OPT_REMOVE remove input files after decoding (dangerous) 161 OPT_REMOVE remove input files after decoding (dangerous)
157 OPT_MOREMIME strict MIME adherence 162 OPT_MOREMIME strict MIME adherence
158 OPT_DOTDOT ".."-unescaping has not yet been done on input files 163 OPT_DOTDOT ".."-unescaping has not yet been done on input files
164 OPT_RBUF set default read I/O buffer size in bytes
165 OPT_WBUF set default write I/O buffer size in bytes
166 OPT_AUTOCHECK automatically check file list after every loadfile
159 167
160=head2 Result/Error codes 168=head2 Result/Error codes
161 169
162 RET_OK everything went fine 170 RET_OK everything went fine
163 RET_IOERR I/O Error - examine errno 171 RET_IOERR I/O Error - examine errno
… …
206again. 214again.
207 215
208On my machine, a fairly complete decode with DBI backend needs about 10MB 216On my machine, a fairly complete decode with DBI backend needs about 10MB
209RSS to decode 20000 files. 217RSS to decode 20000 files.
210 218
211=over 4 219=over
212 220
213=item Initialize 221=item Initialize
214 222
215Not normally necessary, (re-)initializes the library. 223Not normally necessary, (re-)initializes the library.
216 224
… …
221 229
222=back 230=back
223 231
224=head2 Setting and querying options 232=head2 Setting and querying options
225 233
226=over 4 234=over
227 235
228=item $option = GetOption OPT_xxx 236=item $option = GetOption OPT_xxx
229 237
230=item SetOption OPT_xxx, opt-value 238=item SetOption OPT_xxx, opt-value
231 239
… …
233 241
234See the C<OPT_xxx> constants above to see which options exist. 242See the C<OPT_xxx> constants above to see which options exist.
235 243
236=head2 Setting various callbacks 244=head2 Setting various callbacks
237 245
238=over 4 246=over
239 247
240=item SetMsgCallback [callback-function] 248=item SetMsgCallback [callback-function]
241 249
242=item SetBusyCallback [callback-function] 250=item SetBusyCallback [callback-function]
243 251
… …
247 255
248=back 256=back
249 257
250=head2 Call the currently selected FNameFilter 258=head2 Call the currently selected FNameFilter
251 259
252=over 4 260=over
253 261
254=item $file = FNameFilter $file 262=item $file = FNameFilter $file
255 263
256=back 264=back
257 265
258=head2 Loading sourcefiles, optionally fuzzy merge and start decoding 266=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
259 267
260=over 4 268=over
261 269
262=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]] 270=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
263 271
264Load the given file and scan it for encoded contents. Optionally tag it 272Load the given file and scan it for encoded contents. Optionally tag it
265with the given id, and if C<$delflag> is true, delete the file after it 273with the given id, and if C<$delflag> is true, delete the file after it
266is no longer necessary. If you are certain of the part number, you cna 274is no longer necessary. If you are certain of the part number, you can
267specify it as the lat argument. 275specify it as the last argument.
268 276
269A better (usually faster) way of doing this is using the C<SetFNameFilter> 277A better (usually faster) way of doing this is using the C<SetFNameFilter>
270functionality. 278functionality.
271 279
272=item $retval = Smerge $pass 280=item $retval = Smerge $pass
… …
274If you are desperate, try to call C<Smerge> with increasing C<$pass> 282If you are desperate, try to call C<Smerge> with increasing C<$pass>
275values, beginning at C<0>, to try to merge parts that usually would not 283values, beginning at C<0>, to try to merge parts that usually would not
276have been merged. 284have been merged.
277 285
278Most probably this will result in garbled files, so never do this by 286Most probably this will result in garbled files, so never do this by
279default. 287default, except:
288
289If the C<OPT_AUTOCHECK> option has been disabled (by default it is
290enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
291after loading all files as an additional pre-pass (which is normally done
292by C<LoadFile>).
280 293
281=item $item = GetFileListItem $item_number 294=item $item = GetFileListItem $item_number
282 295
283Return the C<$item> structure for the C<$item_number>'th found file, or 296Return the C<$item> structure for the C<$item_number>'th found file, or
284C<undef> of no file with that number exists. 297C<undef> of no file with that number exists.
285 298
286The first file has number C<0>, and the series has no holes, so you can 299The first file has number C<0>, and the series has no holes, so you can
287iterate over all files by starting with zero and incrementing until you 300iterate over all files by starting with zero and incrementing until you
288hit C<undef>. 301hit C<undef>.
289 302
303This function has to walk the linear list of fils on each access, so
304if you want to iterate over all items, it is usually faster to use
305C<GetFileList>.
306
307=item @items = GetFileList
308
309Similar to C<GetFileListItem>, but returns all files in one go.
310
290=back 311=back
291 312
292=head2 Decoding files 313=head2 Decoding files
293 314
294=over 4 315=over
295 316
296=item $retval = $item->rename($newname) 317=item $retval = $item->rename ($newname)
297 318
298Change the ondisk filename where the decoded file will be saved. 319Change the ondisk filename where the decoded file will be saved.
299 320
300=item $retval = $item->decode_temp 321=item $retval = $item->decode_temp
301 322
… …
304 325
305=item $retval = $item->remove_temp 326=item $retval = $item->remove_temp
306 327
307Remove the temporarily decoded file again. 328Remove the temporarily decoded file again.
308 329
309=item $retval = $item->decode([$target_path]) 330=item $retval = $item->decode ([$target_path])
310 331
311Decode the file to it's destination, or the given target path. 332Decode the file to its destination, or the given target path.
312 333
313=item $retval = $item->info(callback-function) 334=item $retval = $item->info (callback-function)
314 335
315=back 336=back
316 337
317=head2 Querying (and setting) item attributes 338=head2 Querying (and setting) item attributes
318 339
319=over 4 340=over
320 341
321=item $state = $item->state 342=item $state = $item->state
322 343
323=item $mode = $item->mode([newmode]) 344=item $mode = $item->mode ([newmode])
324 345
325=item $uudet = $item->uudet 346=item $uudet = $item->uudet
326 347
327=item $size = $item->size 348=item $size = $item->size
328 349
329=item $filename = $item->filename([newfilename}) 350=item $filename = $item->filename ([newfilename})
330 351
331=item $subfname = $item->subfname 352=item $subfname = $item->subfname
332 353
333=item $mimeid = $item->mimeid 354=item $mimeid = $item->mimeid
334 355
… …
338 359
339=back 360=back
340 361
341=head2 Information about source parts 362=head2 Information about source parts
342 363
343=over 4 364=over
344 365
345=item $parts = $item->parts 366=item $parts = $item->parts
346 367
347Return information about all parts (source files) used to decode the file 368Return information about all parts (source files) used to decode the file
348as a list of hashrefs with the following structure: 369as a list of hashrefs with the following structure:
… …
362Usually you are interested mostly the C<sfname> and possibly the C<partno> 383Usually you are interested mostly the C<sfname> and possibly the C<partno>
363and C<filename> members. 384and C<filename> members.
364 385
365=back 386=back
366 387
367=head2 Functions below not documented and not very well tested 388=head2 Functions below are not documented and not very well tested - feedback welcome
368 389
369 QuickDecode 390 QuickDecode
370 EncodeMulti 391 EncodeMulti
371 EncodePartial 392 EncodePartial
372 EncodeToStream 393 EncodeToStream
… …
376 397
377=head2 EXTENSION FUNCTIONS 398=head2 EXTENSION FUNCTIONS
378 399
379Functions found in this module but not documented in the uulib documentation: 400Functions found in this module but not documented in the uulib documentation:
380 401
381=over 4 402=over
382 403
383=item $msg = straction ACT_xxx 404=item $msg = straction ACT_xxx
384 405
385Return a human readable string representing the given action code. 406Return a human readable string representing the given action code.
386 407
… …
430=head1 LARGE EXAMPLE DECODER 451=head1 LARGE EXAMPLE DECODER
431 452
432This is the file C<example-decoder> from the distribution, put here 453This is the file C<example-decoder> from the distribution, put here
433instead of more thorough documentation. 454instead of more thorough documentation.
434 455
456 #!/usr/bin/perl
457
435 # decode all the files in the directory uusrc/ and copy 458 # decode all the files in the directory uusrc/ and copy
436 # the resulting files to uudst/ 459 # the resulting files to uudst/
437 460
438 use Convert::UUlib ':all'; 461 use Convert::UUlib ':all';
439 462
440 sub namefilter { 463 sub namefilter {
441 my($path)=@_; 464 my ($path) = @_;
465
442 $path=~s/^.*[\/\\]//; 466 $path=~s/^.*[\/\\]//;
467
443 $path; 468 $path
444 } 469 }
445 470
446 sub busycb { 471 sub busycb {
447 my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_; 472 my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
448 $_[0]=straction($action); 473 $_[0]=straction($action);
449 print "busy_callback(", (join ",",@_), ")\n"; 474 print "busy_callback(", (join ",",@_), ")\n";
450 0; 475 0
451 } 476 }
452 477
478 SetOption OPT_RBUF, 128*1024;
479 SetOption OPT_WBUF, 1024*1024;
453 SetOption OPT_IGNMODE, 1; 480 SetOption OPT_IGNMODE, 1;
481 SetOption OPT_IGNMODE, 1;
454 SetOption OPT_VERBOSE, 1; 482 SetOption OPT_VERBOSE, 1;
455 483
456 # show the three ways you can set callback functions. I normally 484 # show the three ways you can set callback functions. I normally
457 # prefer the one with the sub inplace. 485 # prefer the one with the sub inplace.
458 SetFNameFilter \&namefilter; 486 SetFNameFilter \&namefilter;
459 487
460 SetBusyCallback "busycb", 333; 488 SetBusyCallback "busycb", 333;
461 489
462 SetMsgCallback sub { 490 SetMsgCallback sub {
463 my ($msg, $level) = @_; 491 my ($msg, $level) = @_;
464 print uc strmsglevel $_[1], ": $msg\n"; 492 print uc strmsglevel $_[1], ": $msg\n";
465 }; 493 };
466 494
467 # the following non-trivial FileNameCallback takes care 495 # the following non-trivial FileNameCallback takes care
468 # of some subject lines not detected properly by uulib: 496 # of some subject lines not detected properly by uulib:
469 SetFileNameCallback sub { 497 SetFileNameCallback sub {
470 return unless $_[1]; # skip "Re:"-plies et al. 498 return unless $_[1]; # skip "Re:"-plies et al.
471 local $_ = $_[0]; 499 local $_ = $_[0];
472 500
473 # the following rules are rather effective on some newsgroups, 501 # the following rules are rather effective on some newsgroups,
474 # like alt.binaries.games.anime, where non-mime, uuencoded data 502 # like alt.binaries.games.anime, where non-mime, uuencoded data
475 # is very common 503 # is very common
476 504
477 # if we find some *.rar, take it as the filename 505 # if we find some *.rar, take it as the filename
478 return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i; 506 return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i;
479 507
480 # one common subject format 508 # one common subject format
481 return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i; 509 return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
482 510
483 # - filename.par (04/55) 511 # - filename.par (04/55)
484 return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i; 512 return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
485 513
486 # - (xxx) No. 1 sayuri81.jpg 756565 bytes 514 # - (xxx) No. 1 sayuri81.jpg 756565 bytes
487 # - (20 files) No.17 Roseanne.jpg [2/2] 515 # - (20 files) No.17 Roseanne.jpg [2/2]
488 return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/; 516 return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
489 517
518 # try to detect some common forms of filenames
519 return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
520
490 # otherwise just pass what we have 521 # otherwise just pass what we have
491 return (); 522 ()
492 }; 523 };
493 524
494 # now read all files in the directory uusrc/* 525 # now read all files in the directory uusrc/*
495 for(<uusrc/*>) { 526 for (<uusrc/*>) {
496 my($retval,$count)=LoadFile ($_, $_, 1); 527 my ($retval, $count) = LoadFile ($_, $_, 1);
497 print "file($_), status(", strerror $retval, ") parts($count)\n"; 528 print "file($_), status(", strerror $retval, ") parts($count)\n";
498 } 529 }
499 530
500 SetOption OPT_SAVEPATH, "uudst/"; 531 SetOption OPT_SAVEPATH, "uudst/";
501 532
502 # now wade through all files and their source parts 533 # now wade through all files and their source parts
503 $i = 0; 534 for my $uu (GetFileList) {
504 while ($uu = GetFileListItem($i)) { 535 print "file ", $uu->filename, "\n";
505 $i++;
506 print "file nr. $i";
507 print " state ", $uu->state; 536 print " state ", $uu->state, "\n";
508 print " mode ", $uu->mode; 537 print " mode ", $uu->mode, "\n";
509 print " uudet ", strencoding $uu->uudet; 538 print " uudet ", strencoding $uu->uudet, "\n";
510 print " size ", $uu->size; 539 print " size ", $uu->size, "\n";
511 print " filename ", $uu->filename;
512 print " subfname ", $uu->subfname; 540 print " subfname ", $uu->subfname, "\n";
513 print " mimeid ", $uu->mimeid; 541 print " mimeid ", $uu->mimeid, "\n";
514 print " mimetype ", $uu->mimetype; 542 print " mimetype ", $uu->mimetype, "\n";
515 print "\n";
516 543
517 # print additional info about all parts 544 # print additional info about all parts
545 print " parts";
518 for ($uu->parts) { 546 for ($uu->parts) {
519 while (my ($k, $v) = each %$_) { 547 for my $k (sort keys %$_) {
520 print "$k > $v, "; 548 print " $k=$_->{$k}";
521 } 549 }
522 print "\n"; 550 print "\n";
523 } 551 }
524 552
525 $uu->decode_temp;
526 print " temporarily decoded to ", $uu->binfile, "\n";
527 $uu->remove_temp; 553 $uu->remove_temp;
528 554
529 print strerror $uu->decode; 555 if (my $err = $uu->decode) {
556 print " ERROR ", strerror $err, "\n";
557 } else {
530 print " saved as uudst/", $uu->filename, "\n"; 558 print " successfully saved as uudst/", $uu->filename, "\n";
531 } 559 }
560 }
532 561
533 print "cleanup...\n"; 562 print "cleanup...\n";
534 563
535 CleanUp(); 564 CleanUp;
565
566=head1 PERLMULTICORE SUPPORT
567
568This module supports the perlmulticore standard (see
569L<http://perlmulticore.schmorp.de/> for more info) for the following
570functions - generally these are functions accessing the disk and/or using
571considerable CPU time:
572
573 LoadFile
574 $item->decode
575 $item->decode_temp
576 $item->remove_temp
577 $item->info
578
579The perl interpreter will be reacquired/released on every callback
580invocation, so for performance reasons, callbacks should be avoided if
581that is costly.
582
583Future versions might enable multicore support for more functions.
584
585=head1 BUGS AND LIMITATIONS
586
587The original uulib library this module uses was written at a time where
588main memory of measured in megabytes and buffer overflows as a security
589thign didn't exist. While a lot of security fixes have been applied over
590the years (includign some defense in depth mechanism that can shield
591against a lot of as-of-yet undetected bugs), using this library for
592security purposes requires care.
593
594Likewise, file sizes when the uulib library was written were tiny compared
595to today, so do not expect this library to handle files larger than 2GB.
536 596
537=head1 AUTHOR 597=head1 AUTHOR
538 598
539Marc Lehmann <pcg@goof.com>, the original uulib library was written 599Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
540by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily 600by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
541bugfixed by Marc Lehmann. 601bugfixed by Marc Lehmann.
542 602
543=head1 SEE ALSO 603=head1 SEE ALSO
544 604
545perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/. 605perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>.
546 606
547=cut 607=cut
608

Diff Legend

– Removed lines
+ Added lines
< Changed lines
> Changed lines