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 1.6 by root, Sun Mar 31 21:42:35 2002 UTC vs.
Revision 1.51 by root, Sun Mar 1 05:14:55 2020 UTC

1package Convert::UUlib; 1package Convert::UUlib;
2
3use common::sense;
2 4
3use Carp; 5use Carp;
4 6
5require Exporter; 7require Exporter;
6require DynaLoader; 8require DynaLoader;
7use AutoLoader;
8 9
9$VERSION = 0.21; 10our $VERSION = 1.7;
10 11
11@ISA = qw(Exporter DynaLoader); 12our @ISA = qw(Exporter DynaLoader);
12 13
13@_consts = qw( 14our @_consts = qw(
14 ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING 15 ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING
15 16
16 FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA 17 FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA
17 FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE 18 FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE
18 19
19 MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING 20 MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING
20 21
22 OPT_RBUF OPT_WBUF
21 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT 23 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT
22 OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB 24 OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB
23 OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE 25 OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
24 OPT_VERSION OPT_REMOVE OPT_MOREMIME 26 OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT OPT_AUTOCHECK
25 27
26 RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA 28 RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
27 RET_NOEND RET_NOMEM RET_OK RET_UNSUP 29 RET_NOEND RET_NOMEM RET_OK RET_UNSUP
28 30
29 B64ENCODED BH_ENCODED PT_ENCODED QP_ENCODED 31 B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
30 XX_ENCODED UU_ENCODED YENC_ENCODED 32 XX_ENCODED UU_ENCODED YENC_ENCODED
31); 33);
32 34
33@_funcs = qw( 35our @_funcs = qw(
34 Initialize CleanUp GetOption SetOption strerror SetMsgCallback 36 Initialize CleanUp GetOption SetOption strerror SetMsgCallback
35 SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback 37 SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
36 FNameFilter LoadFile GetFileListItem RenameFile DecodeToTemp 38 FNameFilter LoadFile GetFileListItem GetFileList RenameFile DecodeToTemp
37 RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti 39 RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
38 EncodePartial EncodeToStream EncodeToFile E_PrepSingle 40 EncodePartial EncodeToStream EncodeToFile E_PrepSingle
39 E_PrepPartial 41 E_PrepPartial
40 42
41 straction strencoding strmsglevel 43 straction strencoding strmsglevel
42); 44);
43 45
44@EXPORT = @_consts; 46our @EXPORT = @_consts;
45@EXPORT_OK = @_funcs; 47our @EXPORT_OK = @_funcs;
46%EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts); 48our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);
47 49
48bootstrap Convert::UUlib $VERSION; 50bootstrap Convert::UUlib $VERSION;
49 51
50Initialize(); 52# dummy function for compatiiblity with pre-1.7 versions
51 53sub Initialize { }
52# not when < 5.005_6x
53# END { CleanUp() }
54
55for (@_consts) {
56 my $constant = constant($_);
57 *$_ = sub () { $constant };
58}
59 54
60# action code -> string mapping 55# action code -> string mapping
61sub straction($) { 56sub straction($) {
62 return 'copying' if $_[0] == &ACT_COPYING; 57 return 'copying' if $_[0] == &ACT_COPYING;
63 return 'decoding' if $_[0] == &ACT_DECODING; 58 return 'decoding' if $_[0] == &ACT_DECODING;
68} 63}
69 64
70# encoding type -> string mapping 65# encoding type -> string mapping
71sub strencoding($) { 66sub strencoding($) {
72 return 'uuencode' if $_[0] == &UU_ENCODED; 67 return 'uuencode' if $_[0] == &UU_ENCODED;
73 return 'base64' if $_[0] == &B64ENCODED; 68 return 'base64' if $_[0] == &B64_ENCODED;
74 return 'yenc' if $_[0] == &YENC_ENCODED; 69 return 'yenc' if $_[0] == &YENC_ENCODED;
75 return 'binhex' if $_[0] == &BH_ENCODED; 70 return 'binhex' if $_[0] == &BH_ENCODED;
76 return 'plaintext' if $_[0] == &PT_ENCODED; 71 return 'plaintext' if $_[0] == &PT_ENCODED;
77 return 'quoted-printable' if $_[0] == &QP_ENCODED; 72 return 'quoted-printable' if $_[0] == &QP_ENCODED;
78 return 'xxencode' if $_[0] == &XX_ENCODED; 73 return 'xxencode' if $_[0] == &XX_ENCODED;
96 91
97Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview). 92Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).
98 93
99=head1 SYNOPSIS 94=head1 SYNOPSIS
100 95
101 use Convert::UUlib;
102
103=head1 DESCRIPTION
104
105Read the file uulibdoc.dvi.gz and the example-decoder source. Sorry - more
106to come once people use me ;)
107
108=head1 SMALL EXAMPLE DECODER
109
110The following code excerpt is a minimal decoder program. It reads all
111files given on the commandline and decodes any files in it.
112
113 use Convert::UUlib ':all'; 96 use Convert::UUlib ':all';
114 97
98 # read all the files named on the commandline and decode them
99 # into the CURRENT directory. See below for a longer example.
115 LoadFile($_) for @ARGV; 100 LoadFile $_ for @ARGV;
116 101
117 for($i=0; $uu=GetFileListItem($i); $i++) { 102 for my $uu (GetFileList) {
118 $uu->decode if $uu->state & FILE_OK; 103 if ($uu->state & FILE_OK) {
104 $uu->decode;
105 print $uu->filename, "\n";
106 }
119 } 107 }
120 108
121=head1 LARGE EXAMPLE DECODER 109=head1 DESCRIPTION
122 110
123This is the file C<example-decoder> from the distribution, put here 111Read the file doc/library.pdf from the distribution for in-depth
124instead of more thorough documentation. 112information about the C-library used in this interface, and the rest of
113this document and especially the non-trivial decoder program at the end.
125 114
126 # decode all the files in the directory uusrc/ and copy 115=head1 EXPORTED CONSTANTS
127 # the resulting files to uudst/
128 116
129 use Convert::UUlib ':all'; 117=head2 Action code constants
130 118
131 sub namefilter { 119 ACT_IDLE we don't do anything
132 my($path)=@_; 120 ACT_SCANNING scanning an input file
133 $path=~s/^.*[\/\\]//; 121 ACT_DECODING decoding into a temp file
134 $path; 122 ACT_COPYING copying temp to target
123 ACT_ENCODING encoding a file
124
125=head2 Message severity levels
126
127 MSG_MESSAGE just a message, nothing important
128 MSG_NOTE something that should be noticed
129 MSG_WARNING important msg, processing continues
130 MSG_ERROR processing has been terminated
131 MSG_FATAL decoder cannot process further requests
132 MSG_PANIC recovery impossible, app must terminate
133
134=head2 Options
135
136 OPT_VERSION version number MAJOR.MINORplPATCH (ro)
137 OPT_FAST assumes only one part per file
138 OPT_DUMBNESS switch off the program's intelligence
139 OPT_BRACKPOL give numbers in [] higher precendence
140 OPT_VERBOSE generate informative messages
141 OPT_DESPERATE try to decode incomplete files
142 OPT_IGNREPLY ignore RE:plies (off by default)
143 OPT_OVERWRITE whether it's OK to overwrite ex. files
144 OPT_SAVEPATH prefix to save-files on disk
145 OPT_IGNMODE ignore the original file mode
146 OPT_DEBUG print messages with FILE/LINE info
147 OPT_ERRNO get last error code for RET_IOERR (ro)
148 OPT_PROGRESS retrieve progress information
149 OPT_USETEXT handle text messages
150 OPT_PREAMB handle Mime preambles/epilogues
151 OPT_TINYB64 detect short B64 outside of Mime
152 OPT_ENCEXT extension for single-part encoded files
153 OPT_REMOVE remove input files after decoding (dangerous)
154 OPT_MOREMIME strict MIME adherence
155 OPT_DOTDOT ".."-unescaping has not yet been done on input files
156 OPT_RBUF set default read I/O buffer size in bytes
157 OPT_WBUF set default write I/O buffer size in bytes
158 OPT_AUTOCHECK automatically check file list after every loadfile
159
160=head2 Result/Error codes
161
162 RET_OK everything went fine
163 RET_IOERR I/O Error - examine errno
164 RET_NOMEM not enough memory
165 RET_ILLVAL illegal value for operation
166 RET_NODATA decoder didn't find any data
167 RET_NOEND encoded data wasn't ended properly
168 RET_UNSUP unsupported function (encoding)
169 RET_EXISTS file exists (decoding)
170 RET_CONT continue -- special from ScanPart
171 RET_CANCEL operation canceled
172
173=head2 File States
174
175 This code is zero, i.e. "false":
176
177 UUFILE_READ Read in, but not further processed
178
179 The following state codes are or'ed together:
180
181 FILE_MISPART Missing Part(s) detected
182 FILE_NOBEGIN No 'begin' found
183 FILE_NOEND No 'end' found
184 FILE_NODATA File does not contain valid uudata
185 FILE_OK All Parts found, ready to decode
186 FILE_ERROR Error while decoding
187 FILE_DECODED Successfully decoded
188 FILE_TMPFILE Temporary decoded file exists
189
190=head2 Encoding types
191
192 UU_ENCODED UUencoded data
193 B64_ENCODED Mime-Base64 data
194 XX_ENCODED XXencoded data
195 BH_ENCODED Binhex encoded
196 PT_ENCODED Plain-Text encoded (MIME)
197 QP_ENCODED Quoted-Printable (MIME)
198 YENC_ENCODED yEnc encoded (non-MIME)
199
200=head1 EXPORTED FUNCTIONS
201
202=head2 Initializing and cleanup
203
204Initialize is automatically called when the module is loaded and allocates
205quite a small amount of memory for todays machines ;) CleanUp releases that
206again.
207
208On my machine, a fairly complete decode with DBI backend needs about 10MB
209RSS to decode 20000 files.
210
211=over
212
213=item CleanUp
214
215Release memory, file items and clean up files. Should be called after a
216decoidng run, if you want to start a new one.
217
218=back
219
220=head2 Setting and querying options
221
222=over
223
224=item $option = GetOption OPT_xxx
225
226=item SetOption OPT_xxx, opt-value
227
228=back
229
230See the C<OPT_xxx> constants above to see which options exist.
231
232=head2 Setting various callbacks
233
234=over
235
236=item SetMsgCallback [callback-function]
237
238=item SetBusyCallback [callback-function]
239
240=item SetFileCallback [callback-function]
241
242=item SetFNameFilter [callback-function]
243
244=back
245
246=head2 Call the currently selected FNameFilter
247
248=over
249
250=item $file = FNameFilter $file
251
252=back
253
254=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
255
256=over
257
258=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
259
260Load the given file and scan it for encoded contents. Optionally tag it
261with the given id, and if C<$delflag> is true, delete the file after it
262is no longer necessary. If you are certain of the part number, you can
263specify it as the last argument.
264
265A better (usually faster) way of doing this is using the C<SetFNameFilter>
266functionality.
267
268=item $retval = Smerge $pass
269
270If you are desperate, try to call C<Smerge> with increasing C<$pass>
271values, beginning at C<0>, to try to merge parts that usually would not
272have been merged.
273
274Most probably this will result in garbled files, so never do this by
275default, except:
276
277If the C<OPT_AUTOCHECK> option has been disabled (by default it is
278enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
279after loading all files as an additional pre-pass (which is normally done
280by C<LoadFile>).
281
282=item $item = GetFileListItem $item_number
283
284Return the C<$item> structure for the C<$item_number>'th found file, or
285C<undef> of no file with that number exists.
286
287The first file has number C<0>, and the series has no holes, so you can
288iterate over all files by starting with zero and incrementing until you
289hit C<undef>.
290
291This function has to walk the linear list of fils on each access, so
292if you want to iterate over all items, it is usually faster to use
293C<GetFileList>.
294
295=item @items = GetFileList
296
297Similar to C<GetFileListItem>, but returns all files in one go.
298
299=back
300
301=head2 Decoding files
302
303=over
304
305=item $retval = $item->rename ($newname)
306
307Change the ondisk filename where the decoded file will be saved.
308
309=item $retval = $item->decode_temp
310
311Decode the file into a temporary location, use C<< $item->infile >> to
312retrieve the temporary filename.
313
314=item $retval = $item->remove_temp
315
316Remove the temporarily decoded file again.
317
318=item $retval = $item->decode ([$target_path])
319
320Decode the file to its destination, or the given target path.
321
322=item $retval = $item->info (callback-function)
323
324=back
325
326=head2 Querying (and setting) item attributes
327
328=over
329
330=item $state = $item->state
331
332=item $mode = $item->mode ([newmode])
333
334=item $uudet = $item->uudet
335
336=item $size = $item->size
337
338=item $filename = $item->filename ([newfilename})
339
340=item $subfname = $item->subfname
341
342=item $mimeid = $item->mimeid
343
344=item $mimetype = $item->mimetype
345
346=item $binfile = $item->binfile
347
348=back
349
350=head2 Information about source parts
351
352=over
353
354=item $parts = $item->parts
355
356Return information about all parts (source files) used to decode the file
357as a list of hashrefs with the following structure:
358
359 {
360 partno => <integer describing the part number, starting with 1>,
361 # the following member sonly exist when they contain useful information
362 sfname => <local pathname of the file where this part is from>,
363 filename => <the ondisk filename of the decoded file>,
364 subfname => <used to cluster postings, possibly the posting filename>,
365 subject => <the subject of the posting/mail>,
366 origin => <the possible source (From) address>,
367 mimetype => <the possible mimetype of the decoded file>,
368 mimeid => <the id part of the Content-Type>,
135 } 369 }
136 370
137 sub busycb { 371Usually you are interested mostly the C<sfname> and possibly the C<partno>
138 my($action,$curfile,$partno,$numparts,$percent,$fsize)=@_; 372and C<filename> members.
139 $_[0]=straction($action);
140 print "busy_callback(",join(",",@_),")\n";
141 0;
142 }
143 373
144 SetOption (OPT_IGNMODE, 1); 374=back
145 SetOption (OPT_VERBOSE, 1);
146 375
147 # show the three ways you can set callback functions
148 SetFNameFilter (\&namefilter);
149
150 SetBusyCallback ("busycb",333);
151
152 SetMsgCallback (sub {
153 my($msg,$level)=@_;
154 print uc(strmsglevel($_[1])),": $msg\n";
155 });
156
157 for(<uusrc/*>) {
158 my($retval,$count)=LoadFile ($_,$_,1);
159 print "file($_), status(",strerror($retval),") parts($count)\n";
160 }
161
162 SetOption (OPT_SAVEPATH, "uudst/");
163
164 $i=0;
165 while($uu=GetFileListItem($i)) {
166 $i++;
167 print "file nr. $i";
168 print " state ",$uu->state;
169 print " mode ",$uu->mode;
170 print " uudet ",strencoding($uu->uudet);
171 print " size ",$uu->size;
172 print " filename ",$uu->filename;
173 print " subfname ",$uu->subfname;
174 print " mimeid ",$uu->mimeid;
175 print " mimetype ",$uu->mimetype;
176 print "\n";
177
178 # print additional info about all parts
179 for($uu->parts) {
180 while(my($k,$v)=each(%$_)) {
181 print "$k > $v, ";
182 }
183 print "\n";
184 }
185
186 $uu->decode_temp;
187 print " temporarily decoded to ",$uu->binfile,"\n";
188 $uu->remove_temp;
189
190 print strerror($uu->decode);
191 print " saved as uudst/",$uu->filename,"\n";
192 }
193
194 print "cleanup...\n";
195
196 CleanUp();
197
198=head1 Exported constants
199
200Action code constants:
201
202 ACT_COPYING ACT_DECODING ACT_ENCODING
203 ACT_IDLE ACT_SCANNING
204
205File status flags:
206
207 FILE_DECODED FILE_ERROR FILE_MISPART
208 FILE_NOBEGIN FILE_NODATA FILE_NOEND
209 FILE_OK FILE_READ FILE_TMPFILE
210
211Message severity levels:
212
213 MSG_ERROR MSG_FATAL MSG_MESSAGE
214 MSG_NOTE MSG_PANIC MSG_WARNING
215
216Options:
217
218 OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS
219 OPT_ENCEXT OPT_ERRNO OPT_FAST OPT_IGNMODE
220 OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB OPT_PROGRESS
221 OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
222 OPT_VERSION OPT_REMOVE OPT_MOREMIME
223
224Error/Result codes:
225
226 RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR
227 RET_NODATA RET_NOEND RET_NOMEM RET_OK RET_UNSUP
228
229Encoding types:
230
231 B64ENCODED BH_ENCODED PT_ENCODED QP_ENCODED XX_ENCODED
232 UU_ENCODED YENC_ENCODED
233
234=head1 Exported functions
235
236Initializing and cleanup (Initialize is automatically called when the
237module is loaded and allocates quite a bit of memory. CleanUp releases
238that again).
239
240 Initialize; # not normally necessary
241 CleanUp; # could be called at the end to release memory
242
243Setting and querying options:
244
245 $option = GetOption OPT_xxx;
246 SetOption OPT_xxx, opt-value;
247
248Error and action values => stringified:
249
250 $msg = straction ACT_xxx;
251 $msg = strerror RET_xxx;
252
253Setting various callbacks:
254
255 SetMsgCallback [callback-function];
256 SetBusyCallback [callback-function];
257 SetFileCallback [callback-function];
258 SetFNameFilter [callback-function];
259
260Call the currently selected FNameFilter:
261
262 $file = FNameFilter $file;
263
264Loading sourcefiles, optionally fuzzy merge and start decoding:
265
266 ($retval, $count) = LoadFile $fname, [$id, [$delflag]];
267 $retval = Smerge $pass;
268 $item = GetFileListItem $item_number;
269
270The procedural interface is undocumented, use the following methods instead:
271
272 $retval = $item->rename($newname);
273 $retval = $item->decode_temp;
274 $retval = $item->remove_temp;
275 $retval = $item->decode([$target_path]);
276 $retval = $item->info(callback-function);
277
278Querying (and setting) item attributes:
279
280 $state = $item->state;
281 $mode = $item->mode([newmode]);
282 $uudet = $item->uudet;
283 $size = $item->size;
284 $filename = $item->filename([newfilename});
285 $subfname = $item->subfname;
286 $mimeid = $item->mimeid;
287 $mimetype = $item->mimetype;
288 $binfile = $item->binfile;
289
290Totally undocumented and unsupported(!):
291
292 $parts = $item->parts;
293
294Functions below not documented and not very well tested: 376=head2 Functions below are not documented and not very well tested - feedback welcome
295 377
296 int QuickDecode () ; 378 QuickDecode
297 int EncodeMulti () ; 379 EncodeMulti
298 int EncodePartial () ; 380 EncodePartial
299 int EncodeToStream () ; 381 EncodeToStream
300 int EncodeToFile () ; 382 EncodeToFile
301 int E_PrepSingle () ; 383 E_PrepSingle
302 int E_PrepPartial () ; 384 E_PrepPartial
303 385
304=head2 EXTENSION FUNCTIONS 386=head2 EXTENSION FUNCTIONS
305 387
306Functions found in this module but not documented in the uulib documentation: 388Functions found in this module but not documented in the uulib documentation:
307 389
308=over 4 390=over
391
392=item $msg = straction ACT_xxx
393
394Return a human readable string representing the given action code.
395
396=item $msg = strerror RET_xxx
397
398Return a human readable string representing the given error code.
399
400=item $str = strencoding xxx_ENCODED
401
402Return the name of the encoding type as a string.
403
404=item $str = strmsglevel MSG_xxx
405
406Returns the message level as a string.
309 407
310=item SetFileNameCallback $cb 408=item SetFileNameCallback $cb
311 409
312Sets (or queries) the FileNameCallback, which is called whenever the 410Sets (or queries) the FileNameCallback, which is called whenever the
313decoding library can't find a filename and wants to extract a filename 411decoding library can't find a filename and wants to extract a filename
336 return (); 434 return ();
337 } 435 }
338 436
339=back 437=back
340 438
439=head1 LARGE EXAMPLE DECODER
440
441The general workflow for decoding is like this:
442
443=over
444
445=item 1. Configure options with C<SetOption> or C<SetXXXCallback>.
446
447=item 2. Load all source files with C<LoadFile>.
448
449=item 3. Optionally C<Smerge>.
450
451=item 4. Iterate over all C<GetFileList> items (i.e. result files).
452
453=item 5. C<CleanUp> to delete files and free items.
454
455=back
456
457What follows is the file C<example-decoder> from the distribution that
458illustrates the above worklfow in a non-trivial example.
459
460 #!/usr/bin/perl
461
462 # decode all the files in the directory uusrc/ and copy
463 # the resulting files to uudst/
464
465 use Convert::UUlib ':all';
466
467 sub namefilter {
468 my ($path) = @_;
469
470 $path=~s/^.*[\/\\]//;
471
472 $path
473 }
474
475 sub busycb {
476 my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
477 $_[0]=straction($action);
478 print "busy_callback(", (join ",",@_), ")\n";
479 0
480 }
481
482 SetOption OPT_RBUF, 128*1024;
483 SetOption OPT_WBUF, 1024*1024;
484 SetOption OPT_IGNMODE, 1;
485 SetOption OPT_IGNMODE, 1;
486 SetOption OPT_VERBOSE, 1;
487
488 # show the three ways you can set callback functions. I normally
489 # prefer the one with the sub inplace.
490 SetFNameFilter \&namefilter;
491
492 SetBusyCallback "busycb", 333;
493
494 SetMsgCallback sub {
495 my ($msg, $level) = @_;
496 print uc strmsglevel $_[1], ": $msg\n";
497 };
498
499 # the following non-trivial FileNameCallback takes care
500 # of some subject lines not detected properly by uulib:
501 SetFileNameCallback sub {
502 return unless $_[1]; # skip "Re:"-plies et al.
503 local $_ = $_[0];
504
505 # the following rules are rather effective on some newsgroups,
506 # like alt.binaries.games.anime, where non-mime, uuencoded data
507 # is very common
508
509 # if we find some *.rar, take it as the filename
510 return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i;
511
512 # one common subject format
513 return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
514
515 # - filename.par (04/55)
516 return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
517
518 # - (xxx) No. 1 sayuri81.jpg 756565 bytes
519 # - (20 files) No.17 Roseanne.jpg [2/2]
520 return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
521
522 # try to detect some common forms of filenames
523 return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
524
525 # otherwise just pass what we have
526 ()
527 };
528
529 # now read all files in the directory uusrc/*
530 for (<uusrc/*>) {
531 my ($retval, $count) = LoadFile ($_, $_, 1);
532 print "file($_), status(", strerror $retval, ") parts($count)\n";
533 }
534
535 SetOption OPT_SAVEPATH, "uudst/";
536
537 # now wade through all files and their source parts
538 for my $uu (GetFileList) {
539 print "file ", $uu->filename, "\n";
540 print " state ", $uu->state, "\n";
541 print " mode ", $uu->mode, "\n";
542 print " uudet ", strencoding $uu->uudet, "\n";
543 print " size ", $uu->size, "\n";
544 print " subfname ", $uu->subfname, "\n";
545 print " mimeid ", $uu->mimeid, "\n";
546 print " mimetype ", $uu->mimetype, "\n";
547
548 # print additional info about all parts
549 print " parts";
550 for ($uu->parts) {
551 for my $k (sort keys %$_) {
552 print " $k=$_->{$k}";
553 }
554 print "\n";
555 }
556
557 $uu->remove_temp;
558
559 if (my $err = $uu->decode) {
560 print " ERROR ", strerror $err, "\n";
561 } else {
562 print " successfully saved as uudst/", $uu->filename, "\n";
563 }
564 }
565
566 print "cleanup...\n";
567
568 CleanUp;
569
570=head1 PERLMULTICORE SUPPORT
571
572This module supports the perlmulticore standard (see
573L<http://perlmulticore.schmorp.de/> for more info) for the following
574functions - generally these are functions accessing the disk and/or using
575considerable CPU time:
576
577 LoadFile
578 $item->decode
579 $item->decode_temp
580 $item->remove_temp
581 $item->info
582
583The perl interpreter will be reacquired/released on every callback
584invocation, so for performance reasons, callbacks should be avoided if
585that is costly.
586
587Future versions might enable multicore support for more functions.
588
589=head1 BUGS AND LIMITATIONS
590
591The original uulib library this module uses was written at a time where
592main memory of measured in megabytes and buffer overflows as a security
593thign didn't exist. While a lot of security fixes have been applied over
594the years (includign some defense in depth mechanism that can shield
595against a lot of as-of-yet undetected bugs), using this library for
596security purposes requires care.
597
598Likewise, file sizes when the uulib library was written were tiny compared
599to today, so do not expect this library to handle files larger than 2GB.
600
601Lastly, this module uses a very "C-like" interface, which means it doesn't
602protect you from invalid points as you might expect from "more perlish"
603modules - for example, accessing a file item object after callinbg
604C<CleanUp> will likely result in crashes, memory corruption, or worse.
605
341=head1 AUTHOR 606=head1 AUTHOR
342 607
343Marc Lehmann <pcg@goof.com>, the original uulib library was written by 608Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
344Frank Pilhofer <fp@informatik.uni-frankfurt.de>. 609by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
610bugfixed by Marc Lehmann.
345 611
346=head1 SEE ALSO 612=head1 SEE ALSO
347 613
348perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/. 614perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>.
349 615
350=cut 616=cut
617

Diff Legend

Removed lines
+ Added lines
< Changed lines
> Changed lines