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 1.25 by root, Mon May 2 19:58:40 2005 UTC vs.
Revision 1.48 by root, Fri Feb 28 17:19:02 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 = "1.06"; 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
19 22
20 OPT_RBUF OPT_WBUF 23 OPT_RBUF OPT_WBUF
21 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT 24 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT
22 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
23 OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE 26 OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
24 OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT 27 OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT OPT_AUTOCHECK
25 28
26 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
27 RET_NOEND RET_NOMEM RET_OK RET_UNSUP 30 RET_NOEND RET_NOMEM RET_OK RET_UNSUP
28 31
29 B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED 32 B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
30 XX_ENCODED UU_ENCODED YENC_ENCODED 33 XX_ENCODED UU_ENCODED YENC_ENCODED
31); 34);
32 35
33@_funcs = qw( 36our @_funcs = qw(
34 Initialize CleanUp GetOption SetOption strerror SetMsgCallback 37 Initialize CleanUp GetOption SetOption strerror SetMsgCallback
35 SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback 38 SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
36 FNameFilter LoadFile GetFileListItem RenameFile DecodeToTemp 39 FNameFilter LoadFile GetFileListItem GetFileList RenameFile DecodeToTemp
37 RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti 40 RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
38 EncodePartial EncodeToStream EncodeToFile E_PrepSingle 41 EncodePartial EncodeToStream EncodeToFile E_PrepSingle
39 E_PrepPartial 42 E_PrepPartial
40 43
41 straction strencoding strmsglevel 44 straction strencoding strmsglevel
42); 45);
43 46
44@EXPORT = @_consts; 47our @EXPORT = @_consts;
45@EXPORT_OK = @_funcs; 48our @EXPORT_OK = @_funcs;
46%EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts); 49our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);
47 50
48bootstrap Convert::UUlib $VERSION; 51bootstrap Convert::UUlib $VERSION;
49 52
50Initialize(); 53# dummy function for compatiiblity with pre-1.7 versions
51 54sub Initialize { }
52# not when < 5.005_6x
53# END { CleanUp() }
54 55
55for (@_consts) { 56for (@_consts) {
56 my $constant = constant($_); 57 my $constant = constant ($_);
58 no strict 'refs';
57 *$_ = sub () { $constant }; 59 *$_ = sub () { $constant };
58} 60}
59 61
60# action code -> string mapping 62# action code -> string mapping
61sub straction($) { 63sub straction($) {
101 use Convert::UUlib ':all'; 103 use Convert::UUlib ':all';
102 104
103 # read all the files named on the commandline and decode them 105 # read all the files named on the commandline and decode them
104 # into the CURRENT directory. See below for a longer example. 106 # into the CURRENT directory. See below for a longer example.
105 LoadFile $_ for @ARGV; 107 LoadFile $_ for @ARGV;
106 for (my $i = 0; my $uu = GetFileListItem $i; $i++) { 108
109 for my $uu (GetFileList) {
107 if ($uu->state & FILE_OK) { 110 if ($uu->state & FILE_OK) {
108 $uu->decode; 111 $uu->decode;
109 print $uu->filename, "\n"; 112 print $uu->filename, "\n";
110 } 113 }
111 } 114 }
155 OPT_TINYB64 detect short B64 outside of Mime 158 OPT_TINYB64 detect short B64 outside of Mime
156 OPT_ENCEXT extension for single-part encoded files 159 OPT_ENCEXT extension for single-part encoded files
157 OPT_REMOVE remove input files after decoding (dangerous) 160 OPT_REMOVE remove input files after decoding (dangerous)
158 OPT_MOREMIME strict MIME adherence 161 OPT_MOREMIME strict MIME adherence
159 OPT_DOTDOT ".."-unescaping has not yet been done on input files 162 OPT_DOTDOT ".."-unescaping has not yet been done on input files
160 OPT_RBUF set default read I/O buffer size in bytes *EXPERIMENTAL* 163 OPT_RBUF set default read I/O buffer size in bytes
161 OPT_WBUF set default write I/O buffer size in bytes *EXPERIMENTAL* 164 OPT_WBUF set default write I/O buffer size in bytes
165 OPT_AUTOCHECK automatically check file list after every loadfile
162 166
163=head2 Result/Error codes 167=head2 Result/Error codes
164 168
165 RET_OK everything went fine 169 RET_OK everything went fine
166 RET_IOERR I/O Error - examine errno 170 RET_IOERR I/O Error - examine errno
209again. 213again.
210 214
211On my machine, a fairly complete decode with DBI backend needs about 10MB 215On my machine, a fairly complete decode with DBI backend needs about 10MB
212RSS to decode 20000 files. 216RSS to decode 20000 files.
213 217
214=over 4 218=over
215
216=item Initialize
217
218Not normally necessary, (re-)initializes the library.
219 219
220=item CleanUp 220=item CleanUp
221 221
222Not normally necessary, could be called at the end to release memory 222Release memory, file items and clean up files. Should be called after a
223before starting a new decoding round. 223decoidng run, if you want to start a new one.
224 224
225=back 225=back
226 226
227=head2 Setting and querying options 227=head2 Setting and querying options
228 228
229=over 4 229=over
230 230
231=item $option = GetOption OPT_xxx 231=item $option = GetOption OPT_xxx
232 232
233=item SetOption OPT_xxx, opt-value 233=item SetOption OPT_xxx, opt-value
234 234
236 236
237See the C<OPT_xxx> constants above to see which options exist. 237See the C<OPT_xxx> constants above to see which options exist.
238 238
239=head2 Setting various callbacks 239=head2 Setting various callbacks
240 240
241=over 4 241=over
242 242
243=item SetMsgCallback [callback-function] 243=item SetMsgCallback [callback-function]
244 244
245=item SetBusyCallback [callback-function] 245=item SetBusyCallback [callback-function]
246 246
250 250
251=back 251=back
252 252
253=head2 Call the currently selected FNameFilter 253=head2 Call the currently selected FNameFilter
254 254
255=over 4 255=over
256 256
257=item $file = FNameFilter $file 257=item $file = FNameFilter $file
258 258
259=back 259=back
260 260
261=head2 Loading sourcefiles, optionally fuzzy merge and start decoding 261=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
262 262
263=over 4 263=over
264 264
265=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]] 265=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
266 266
267Load the given file and scan it for encoded contents. Optionally tag it 267Load the given file and scan it for encoded contents. Optionally tag it
268with the given id, and if C<$delflag> is true, delete the file after it 268with the given id, and if C<$delflag> is true, delete the file after it
277If you are desperate, try to call C<Smerge> with increasing C<$pass> 277If you are desperate, try to call C<Smerge> with increasing C<$pass>
278values, beginning at C<0>, to try to merge parts that usually would not 278values, beginning at C<0>, to try to merge parts that usually would not
279have been merged. 279have been merged.
280 280
281Most probably this will result in garbled files, so never do this by 281Most probably this will result in garbled files, so never do this by
282default. 282default, except:
283
284If the C<OPT_AUTOCHECK> option has been disabled (by default it is
285enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
286after loading all files as an additional pre-pass (which is normally done
287by C<LoadFile>).
283 288
284=item $item = GetFileListItem $item_number 289=item $item = GetFileListItem $item_number
285 290
286Return the C<$item> structure for the C<$item_number>'th found file, or 291Return the C<$item> structure for the C<$item_number>'th found file, or
287C<undef> of no file with that number exists. 292C<undef> of no file with that number exists.
288 293
289The first file has number C<0>, and the series has no holes, so you can 294The first file has number C<0>, and the series has no holes, so you can
290iterate over all files by starting with zero and incrementing until you 295iterate over all files by starting with zero and incrementing until you
291hit C<undef>. 296hit C<undef>.
292 297
298This function has to walk the linear list of fils on each access, so
299if you want to iterate over all items, it is usually faster to use
300C<GetFileList>.
301
302=item @items = GetFileList
303
304Similar to C<GetFileListItem>, but returns all files in one go.
305
293=back 306=back
294 307
295=head2 Decoding files 308=head2 Decoding files
296 309
297=over 4 310=over
298 311
299=item $retval = $item->rename($newname) 312=item $retval = $item->rename ($newname)
300 313
301Change the ondisk filename where the decoded file will be saved. 314Change the ondisk filename where the decoded file will be saved.
302 315
303=item $retval = $item->decode_temp 316=item $retval = $item->decode_temp
304 317
307 320
308=item $retval = $item->remove_temp 321=item $retval = $item->remove_temp
309 322
310Remove the temporarily decoded file again. 323Remove the temporarily decoded file again.
311 324
312=item $retval = $item->decode([$target_path]) 325=item $retval = $item->decode ([$target_path])
313 326
314Decode the file to it's destination, or the given target path. 327Decode the file to its destination, or the given target path.
315 328
316=item $retval = $item->info(callback-function) 329=item $retval = $item->info (callback-function)
317 330
318=back 331=back
319 332
320=head2 Querying (and setting) item attributes 333=head2 Querying (and setting) item attributes
321 334
322=over 4 335=over
323 336
324=item $state = $item->state 337=item $state = $item->state
325 338
326=item $mode = $item->mode([newmode]) 339=item $mode = $item->mode ([newmode])
327 340
328=item $uudet = $item->uudet 341=item $uudet = $item->uudet
329 342
330=item $size = $item->size 343=item $size = $item->size
331 344
332=item $filename = $item->filename([newfilename}) 345=item $filename = $item->filename ([newfilename})
333 346
334=item $subfname = $item->subfname 347=item $subfname = $item->subfname
335 348
336=item $mimeid = $item->mimeid 349=item $mimeid = $item->mimeid
337 350
341 354
342=back 355=back
343 356
344=head2 Information about source parts 357=head2 Information about source parts
345 358
346=over 4 359=over
347 360
348=item $parts = $item->parts 361=item $parts = $item->parts
349 362
350Return information about all parts (source files) used to decode the file 363Return information about all parts (source files) used to decode the file
351as a list of hashrefs with the following structure: 364as a list of hashrefs with the following structure:
365Usually you are interested mostly the C<sfname> and possibly the C<partno> 378Usually you are interested mostly the C<sfname> and possibly the C<partno>
366and C<filename> members. 379and C<filename> members.
367 380
368=back 381=back
369 382
370=head2 Functions below not documented and not very well tested 383=head2 Functions below are not documented and not very well tested - feedback welcome
371 384
372 QuickDecode 385 QuickDecode
373 EncodeMulti 386 EncodeMulti
374 EncodePartial 387 EncodePartial
375 EncodeToStream 388 EncodeToStream
379 392
380=head2 EXTENSION FUNCTIONS 393=head2 EXTENSION FUNCTIONS
381 394
382Functions found in this module but not documented in the uulib documentation: 395Functions found in this module but not documented in the uulib documentation:
383 396
384=over 4 397=over
385 398
386=item $msg = straction ACT_xxx 399=item $msg = straction ACT_xxx
387 400
388Return a human readable string representing the given action code. 401Return a human readable string representing the given action code.
389 402
430 443
431=back 444=back
432 445
433=head1 LARGE EXAMPLE DECODER 446=head1 LARGE EXAMPLE DECODER
434 447
448The general workflow for decoding is like this:
449
450=over
451
452=item 1. Configure options with C<SetOption> or C<SetXXXCallback>.
453
454=item 2. Load all source files with C<LoadFile>.
455
456=item 3. Optionally C<Smerge>.
457
458=item 4. Iterate over all C<GetFileList> items (i.e. result files).
459
460=item 5. C<CleanUp> to delete files and free items.
461
462=back
463
435This is the file C<example-decoder> from the distribution, put here 464What follows is the file C<example-decoder> from the distribution that
436instead of more thorough documentation. 465illustrates the above worklfow in a non-trivial example.
437 466
467 #!/usr/bin/perl
468
438 # decode all the files in the directory uusrc/ and copy 469 # decode all the files in the directory uusrc/ and copy
439 # the resulting files to uudst/ 470 # the resulting files to uudst/
440 471
441 use Convert::UUlib ':all'; 472 use Convert::UUlib ':all';
442 473
443 sub namefilter { 474 sub namefilter {
444 my($path)=@_; 475 my ($path) = @_;
476
445 $path=~s/^.*[\/\\]//; 477 $path=~s/^.*[\/\\]//;
478
446 $path; 479 $path
447 } 480 }
448 481
449 sub busycb { 482 sub busycb {
450 my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_; 483 my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
451 $_[0]=straction($action); 484 $_[0]=straction($action);
452 print "busy_callback(", (join ",",@_), ")\n"; 485 print "busy_callback(", (join ",",@_), ")\n";
453 0; 486 0
454 } 487 }
455 488
489 SetOption OPT_RBUF, 128*1024;
490 SetOption OPT_WBUF, 1024*1024;
456 SetOption OPT_IGNMODE, 1; 491 SetOption OPT_IGNMODE, 1;
492 SetOption OPT_IGNMODE, 1;
457 SetOption OPT_VERBOSE, 1; 493 SetOption OPT_VERBOSE, 1;
458 494
459 # show the three ways you can set callback functions. I normally 495 # show the three ways you can set callback functions. I normally
460 # prefer the one with the sub inplace. 496 # prefer the one with the sub inplace.
461 SetFNameFilter \&namefilter; 497 SetFNameFilter \&namefilter;
462 498
463 SetBusyCallback "busycb", 333; 499 SetBusyCallback "busycb", 333;
464 500
465 SetMsgCallback sub { 501 SetMsgCallback sub {
466 my ($msg, $level) = @_; 502 my ($msg, $level) = @_;
467 print uc strmsglevel $_[1], ": $msg\n"; 503 print uc strmsglevel $_[1], ": $msg\n";
468 }; 504 };
469 505
470 # the following non-trivial FileNameCallback takes care 506 # the following non-trivial FileNameCallback takes care
471 # of some subject lines not detected properly by uulib: 507 # of some subject lines not detected properly by uulib:
472 SetFileNameCallback sub { 508 SetFileNameCallback sub {
473 return unless $_[1]; # skip "Re:"-plies et al. 509 return unless $_[1]; # skip "Re:"-plies et al.
474 local $_ = $_[0]; 510 local $_ = $_[0];
475 511
476 # the following rules are rather effective on some newsgroups, 512 # the following rules are rather effective on some newsgroups,
477 # like alt.binaries.games.anime, where non-mime, uuencoded data 513 # like alt.binaries.games.anime, where non-mime, uuencoded data
478 # is very common 514 # is very common
479 515
480 # if we find some *.rar, take it as the filename 516 # if we find some *.rar, take it as the filename
481 return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i; 517 return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i;
482 518
483 # one common subject format 519 # one common subject format
484 return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i; 520 return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
485 521
486 # - filename.par (04/55) 522 # - filename.par (04/55)
487 return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i; 523 return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
488 524
489 # - (xxx) No. 1 sayuri81.jpg 756565 bytes 525 # - (xxx) No. 1 sayuri81.jpg 756565 bytes
490 # - (20 files) No.17 Roseanne.jpg [2/2] 526 # - (20 files) No.17 Roseanne.jpg [2/2]
491 return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/; 527 return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
492 528
529 # try to detect some common forms of filenames
530 return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
531
493 # otherwise just pass what we have 532 # otherwise just pass what we have
494 return (); 533 ()
495 }; 534 };
496 535
497 # now read all files in the directory uusrc/* 536 # now read all files in the directory uusrc/*
498 for(<uusrc/*>) { 537 for (<uusrc/*>) {
499 my($retval,$count)=LoadFile ($_, $_, 1); 538 my ($retval, $count) = LoadFile ($_, $_, 1);
500 print "file($_), status(", strerror $retval, ") parts($count)\n"; 539 print "file($_), status(", strerror $retval, ") parts($count)\n";
501 } 540 }
502 541
503 SetOption OPT_SAVEPATH, "uudst/"; 542 SetOption OPT_SAVEPATH, "uudst/";
504 543
505 # now wade through all files and their source parts 544 # now wade through all files and their source parts
506 $i = 0; 545 for my $uu (GetFileList) {
507 while ($uu = GetFileListItem($i)) { 546 print "file ", $uu->filename, "\n";
508 $i++;
509 print "file nr. $i";
510 print " state ", $uu->state; 547 print " state ", $uu->state, "\n";
511 print " mode ", $uu->mode; 548 print " mode ", $uu->mode, "\n";
512 print " uudet ", strencoding $uu->uudet; 549 print " uudet ", strencoding $uu->uudet, "\n";
513 print " size ", $uu->size; 550 print " size ", $uu->size, "\n";
514 print " filename ", $uu->filename;
515 print " subfname ", $uu->subfname; 551 print " subfname ", $uu->subfname, "\n";
516 print " mimeid ", $uu->mimeid; 552 print " mimeid ", $uu->mimeid, "\n";
517 print " mimetype ", $uu->mimetype; 553 print " mimetype ", $uu->mimetype, "\n";
518 print "\n";
519 554
520 # print additional info about all parts 555 # print additional info about all parts
556 print " parts";
521 for ($uu->parts) { 557 for ($uu->parts) {
522 while (my ($k, $v) = each %$_) { 558 for my $k (sort keys %$_) {
523 print "$k > $v, "; 559 print " $k=$_->{$k}";
524 } 560 }
525 print "\n"; 561 print "\n";
526 } 562 }
527 563
528 $uu->decode_temp;
529 print " temporarily decoded to ", $uu->binfile, "\n";
530 $uu->remove_temp; 564 $uu->remove_temp;
531 565
532 print strerror $uu->decode; 566 if (my $err = $uu->decode) {
567 print " ERROR ", strerror $err, "\n";
568 } else {
533 print " saved as uudst/", $uu->filename, "\n"; 569 print " successfully saved as uudst/", $uu->filename, "\n";
534 } 570 }
571 }
535 572
536 print "cleanup...\n"; 573 print "cleanup...\n";
537 574
538 CleanUp(); 575 CleanUp;
576
577=head1 PERLMULTICORE SUPPORT
578
579This module supports the perlmulticore standard (see
580L<http://perlmulticore.schmorp.de/> for more info) for the following
581functions - generally these are functions accessing the disk and/or using
582considerable CPU time:
583
584 LoadFile
585 $item->decode
586 $item->decode_temp
587 $item->remove_temp
588 $item->info
589
590The perl interpreter will be reacquired/released on every callback
591invocation, so for performance reasons, callbacks should be avoided if
592that is costly.
593
594Future versions might enable multicore support for more functions.
595
596=head1 BUGS AND LIMITATIONS
597
598The original uulib library this module uses was written at a time where
599main memory of measured in megabytes and buffer overflows as a security
600thign didn't exist. While a lot of security fixes have been applied over
601the years (includign some defense in depth mechanism that can shield
602against a lot of as-of-yet undetected bugs), using this library for
603security purposes requires care.
604
605Likewise, file sizes when the uulib library was written were tiny compared
606to today, so do not expect this library to handle files larger than 2GB.
539 607
540=head1 AUTHOR 608=head1 AUTHOR
541 609
542Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written 610Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
543by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily 611by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
544bugfixed by Marc Lehmann. 612bugfixed by Marc Lehmann.
545 613
546=head1 SEE ALSO 614=head1 SEE ALSO
547 615
548perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/. 616perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>.
549 617
550=cut 618=cut
619

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines