1 |
package Convert::UUlib; |
2 |
|
3 |
use Carp; |
4 |
|
5 |
require Exporter; |
6 |
require DynaLoader; |
7 |
|
8 |
$VERSION = "1.01"; |
9 |
|
10 |
@ISA = qw(Exporter DynaLoader); |
11 |
|
12 |
@_consts = qw( |
13 |
ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING |
14 |
|
15 |
FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA |
16 |
FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE |
17 |
|
18 |
MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING |
19 |
|
20 |
OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT |
21 |
OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB |
22 |
OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE |
23 |
OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT |
24 |
|
25 |
RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA |
26 |
RET_NOEND RET_NOMEM RET_OK RET_UNSUP |
27 |
|
28 |
B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED |
29 |
XX_ENCODED UU_ENCODED YENC_ENCODED |
30 |
); |
31 |
|
32 |
@_funcs = qw( |
33 |
Initialize CleanUp GetOption SetOption strerror SetMsgCallback |
34 |
SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback |
35 |
FNameFilter LoadFile GetFileListItem RenameFile DecodeToTemp |
36 |
RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti |
37 |
EncodePartial EncodeToStream EncodeToFile E_PrepSingle |
38 |
E_PrepPartial |
39 |
|
40 |
straction strencoding strmsglevel |
41 |
); |
42 |
|
43 |
@EXPORT = @_consts; |
44 |
@EXPORT_OK = @_funcs; |
45 |
%EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts); |
46 |
|
47 |
bootstrap Convert::UUlib $VERSION; |
48 |
|
49 |
Initialize(); |
50 |
|
51 |
# not when < 5.005_6x |
52 |
# END { CleanUp() } |
53 |
|
54 |
for (@_consts) { |
55 |
my $constant = constant($_); |
56 |
*$_ = sub () { $constant }; |
57 |
} |
58 |
|
59 |
# action code -> string mapping |
60 |
sub straction($) { |
61 |
return 'copying' if $_[0] == &ACT_COPYING; |
62 |
return 'decoding' if $_[0] == &ACT_DECODING; |
63 |
return 'encoding' if $_[0] == &ACT_ENCODING; |
64 |
return 'idle' if $_[0] == &ACT_IDLE; |
65 |
return 'scanning' if $_[0] == &ACT_SCANNING; |
66 |
'unknown'; |
67 |
} |
68 |
|
69 |
# encoding type -> string mapping |
70 |
sub strencoding($) { |
71 |
return 'uuencode' if $_[0] == &UU_ENCODED; |
72 |
return 'base64' if $_[0] == &B64_ENCODED; |
73 |
return 'yenc' if $_[0] == &YENC_ENCODED; |
74 |
return 'binhex' if $_[0] == &BH_ENCODED; |
75 |
return 'plaintext' if $_[0] == &PT_ENCODED; |
76 |
return 'quoted-printable' if $_[0] == &QP_ENCODED; |
77 |
return 'xxencode' if $_[0] == &XX_ENCODED; |
78 |
'unknown'; |
79 |
} |
80 |
|
81 |
sub strmsglevel($) { |
82 |
return 'message' if $_[0] == &MSG_MESSAGE; |
83 |
return 'note' if $_[0] == &MSG_NOTE; |
84 |
return 'warning' if $_[0] == &MSG_WARNING; |
85 |
return 'error' if $_[0] == &MSG_ERROR; |
86 |
return 'panic' if $_[0] == &MSG_PANIC; |
87 |
return 'fatal' if $_[0] == &MSG_FATAL; |
88 |
'unknown'; |
89 |
} |
90 |
|
91 |
1; |
92 |
__END__ |
93 |
|
94 |
=head1 NAME |
95 |
|
96 |
Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview). |
97 |
|
98 |
=head1 SYNOPSIS |
99 |
|
100 |
use Convert::UUlib ':all'; |
101 |
|
102 |
# read all the files named on the commandline and decode them |
103 |
# into the CURRENT directory. See below for a longer example. |
104 |
LoadFile $_ for @ARGV; |
105 |
for (my $i = 0; my $uu = GetFileListItem $i; $i++) { |
106 |
if ($uu->state & FILE_OK) { |
107 |
$uu->decode; |
108 |
print $uu->filename, "\n"; |
109 |
} |
110 |
} |
111 |
|
112 |
=head1 DESCRIPTION |
113 |
|
114 |
Read the file doc/library.pdf from the distribution for in-depth |
115 |
information about the C-library used in this interface, and the rest of |
116 |
this document and especially the non-trivial decoder program at the end. |
117 |
|
118 |
=head1 EXPORTED CONSTANTS |
119 |
|
120 |
=head2 Action code constants |
121 |
|
122 |
ACT_IDLE we don't do anything |
123 |
ACT_SCANNING scanning an input file |
124 |
ACT_DECODING decoding into a temp file |
125 |
ACT_COPYING copying temp to target |
126 |
ACT_ENCODING encoding a file |
127 |
|
128 |
=head2 Message severity levels |
129 |
|
130 |
MSG_MESSAGE just a message, nothing important |
131 |
MSG_NOTE something that should be noticed |
132 |
MSG_WARNING important msg, processing continues |
133 |
MSG_ERROR processing has been terminated |
134 |
MSG_FATAL decoder cannot process further requests |
135 |
MSG_PANIC recovery impossible, app must terminate |
136 |
|
137 |
=head2 Options |
138 |
|
139 |
OPT_VERSION version number MAJOR.MINORplPATCH (ro) |
140 |
OPT_FAST assumes only one part per file |
141 |
OPT_DUMBNESS switch off the program's intelligence |
142 |
OPT_BRACKPOL give numbers in [] higher precendence |
143 |
OPT_VERBOSE generate informative messages |
144 |
OPT_DESPERATE try to decode incomplete files |
145 |
OPT_IGNREPLY ignore RE:plies (off by default) |
146 |
OPT_OVERWRITE whether it's OK to overwrite ex. files |
147 |
OPT_SAVEPATH prefix to save-files on disk |
148 |
OPT_IGNMODE ignore the original file mode |
149 |
OPT_DEBUG print messages with FILE/LINE info |
150 |
OPT_ERRNO get last error code for RET_IOERR (ro) |
151 |
OPT_PROGRESS retrieve progress information |
152 |
OPT_USETEXT handle text messages |
153 |
OPT_PREAMB handle Mime preambles/epilogues |
154 |
OPT_TINYB64 detect short B64 outside of Mime |
155 |
OPT_ENCEXT extension for single-part encoded files |
156 |
OPT_REMOVE remove input files after decoding (dangerous) |
157 |
OPT_MOREMIME strict MIME adherence |
158 |
OPT_DOTDOT ".."-unescaping has not yet been done on input files |
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 |
|
204 |
Initialize is automatically called when the module is loaded and allocates |
205 |
quite a small amount of memory for todays machines ;) CleanUp releases that |
206 |
again. |
207 |
|
208 |
On my machine, a fairly complete decode with DBI backend needs about 10MB |
209 |
RSS to decode 20000 files. |
210 |
|
211 |
=over 4 |
212 |
|
213 |
=item Initialize |
214 |
|
215 |
Not normally necessary, (re-)initializes the library. |
216 |
|
217 |
=item CleanUp |
218 |
|
219 |
Not normally necessary, could be called at the end to release memory |
220 |
before starting a new decoding round. |
221 |
|
222 |
=back |
223 |
|
224 |
=head2 Setting and querying options |
225 |
|
226 |
=over 4 |
227 |
|
228 |
=item $option = GetOption OPT_xxx |
229 |
|
230 |
=item SetOption OPT_xxx, opt-value |
231 |
|
232 |
=back |
233 |
|
234 |
See the C<OPT_xxx> constants above to see which options exist. |
235 |
|
236 |
=head2 Setting various callbacks |
237 |
|
238 |
=over 4 |
239 |
|
240 |
=item SetMsgCallback [callback-function] |
241 |
|
242 |
=item SetBusyCallback [callback-function] |
243 |
|
244 |
=item SetFileCallback [callback-function] |
245 |
|
246 |
=item SetFNameFilter [callback-function] |
247 |
|
248 |
=back |
249 |
|
250 |
=head2 Call the currently selected FNameFilter |
251 |
|
252 |
=over 4 |
253 |
|
254 |
=item $file = FNameFilter $file |
255 |
|
256 |
=back |
257 |
|
258 |
=head2 Loading sourcefiles, optionally fuzzy merge and start decoding |
259 |
|
260 |
=over 4 |
261 |
|
262 |
=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]] |
263 |
|
264 |
Load the given file and scan it for encoded contents. Optionally tag it |
265 |
with the given id, and if C<$delflag> is true, delete the file after it |
266 |
is no longer necessary. If you are certain of the part number, you can |
267 |
specify it as the last argument. |
268 |
|
269 |
A better (usually faster) way of doing this is using the C<SetFNameFilter> |
270 |
functionality. |
271 |
|
272 |
=item $retval = Smerge $pass |
273 |
|
274 |
If you are desperate, try to call C<Smerge> with increasing C<$pass> |
275 |
values, beginning at C<0>, to try to merge parts that usually would not |
276 |
have been merged. |
277 |
|
278 |
Most probably this will result in garbled files, so never do this by |
279 |
default. |
280 |
|
281 |
=item $item = GetFileListItem $item_number |
282 |
|
283 |
Return the C<$item> structure for the C<$item_number>'th found file, or |
284 |
C<undef> of no file with that number exists. |
285 |
|
286 |
The first file has number C<0>, and the series has no holes, so you can |
287 |
iterate over all files by starting with zero and incrementing until you |
288 |
hit C<undef>. |
289 |
|
290 |
=back |
291 |
|
292 |
=head2 Decoding files |
293 |
|
294 |
=over 4 |
295 |
|
296 |
=item $retval = $item->rename($newname) |
297 |
|
298 |
Change the ondisk filename where the decoded file will be saved. |
299 |
|
300 |
=item $retval = $item->decode_temp |
301 |
|
302 |
Decode the file into a temporary location, use C<< $item->infile >> to |
303 |
retrieve the temporary filename. |
304 |
|
305 |
=item $retval = $item->remove_temp |
306 |
|
307 |
Remove the temporarily decoded file again. |
308 |
|
309 |
=item $retval = $item->decode([$target_path]) |
310 |
|
311 |
Decode the file to it's destination, or the given target path. |
312 |
|
313 |
=item $retval = $item->info(callback-function) |
314 |
|
315 |
=back |
316 |
|
317 |
=head2 Querying (and setting) item attributes |
318 |
|
319 |
=over 4 |
320 |
|
321 |
=item $state = $item->state |
322 |
|
323 |
=item $mode = $item->mode([newmode]) |
324 |
|
325 |
=item $uudet = $item->uudet |
326 |
|
327 |
=item $size = $item->size |
328 |
|
329 |
=item $filename = $item->filename([newfilename}) |
330 |
|
331 |
=item $subfname = $item->subfname |
332 |
|
333 |
=item $mimeid = $item->mimeid |
334 |
|
335 |
=item $mimetype = $item->mimetype |
336 |
|
337 |
=item $binfile = $item->binfile |
338 |
|
339 |
=back |
340 |
|
341 |
=head2 Information about source parts |
342 |
|
343 |
=over 4 |
344 |
|
345 |
=item $parts = $item->parts |
346 |
|
347 |
Return information about all parts (source files) used to decode the file |
348 |
as a list of hashrefs with the following structure: |
349 |
|
350 |
{ |
351 |
partno => <integer describing the part number, starting with 1>, |
352 |
# the following member sonly exist when they contain useful information |
353 |
sfname => <local pathname of the file where this part is from>, |
354 |
filename => <the ondisk filename of the decoded file>, |
355 |
subfname => <used to cluster postings, possibly the posting filename>, |
356 |
subject => <the subject of the posting/mail>, |
357 |
origin => <the possible source (From) address>, |
358 |
mimetype => <the possible mimetype of the decoded file>, |
359 |
mimeid => <the id part of the Content-Type>, |
360 |
} |
361 |
|
362 |
Usually you are interested mostly the C<sfname> and possibly the C<partno> |
363 |
and C<filename> members. |
364 |
|
365 |
=back |
366 |
|
367 |
=head2 Functions below not documented and not very well tested |
368 |
|
369 |
QuickDecode |
370 |
EncodeMulti |
371 |
EncodePartial |
372 |
EncodeToStream |
373 |
EncodeToFile |
374 |
E_PrepSingle |
375 |
E_PrepPartial |
376 |
|
377 |
=head2 EXTENSION FUNCTIONS |
378 |
|
379 |
Functions found in this module but not documented in the uulib documentation: |
380 |
|
381 |
=over 4 |
382 |
|
383 |
=item $msg = straction ACT_xxx |
384 |
|
385 |
Return a human readable string representing the given action code. |
386 |
|
387 |
=item $msg = strerror RET_xxx |
388 |
|
389 |
Return a human readable string representing the given error code. |
390 |
|
391 |
=item $str = strencoding xxx_ENCODED |
392 |
|
393 |
Return the name of the encoding type as a string. |
394 |
|
395 |
=item $str = strmsglevel MSG_xxx |
396 |
|
397 |
Returns the message level as a string. |
398 |
|
399 |
=item SetFileNameCallback $cb |
400 |
|
401 |
Sets (or queries) the FileNameCallback, which is called whenever the |
402 |
decoding library can't find a filename and wants to extract a filename |
403 |
from the subject line of a posting. The callback will be called with |
404 |
two arguments, the subject line and the current candidate for the |
405 |
filename. The latter argument can be C<undef>, which means that no |
406 |
filename could be found (and likely no one exists, so it is safe to also |
407 |
return C<undef> in this case). If it doesn't return anything (not even |
408 |
C<undef>!), then nothing happens, so this is a no-op callback: |
409 |
|
410 |
sub cb { |
411 |
return (); |
412 |
} |
413 |
|
414 |
If it returns C<undef>, then this indicates that no filename could be |
415 |
found. In all other cases, the return value is taken to be the filename. |
416 |
|
417 |
This is a slightly more useful callback: |
418 |
|
419 |
sub cb { |
420 |
return unless $_[1]; # skip "Re:"-plies et al. |
421 |
my ($subject, $filename) = @_; |
422 |
# if we find some *.rar, take it |
423 |
return $1 if $subject =~ /(\w+\.rar)/; |
424 |
# otherwise just pass what we have |
425 |
return (); |
426 |
} |
427 |
|
428 |
=back |
429 |
|
430 |
=head1 LARGE EXAMPLE DECODER |
431 |
|
432 |
This is the file C<example-decoder> from the distribution, put here |
433 |
instead of more thorough documentation. |
434 |
|
435 |
# decode all the files in the directory uusrc/ and copy |
436 |
# the resulting files to uudst/ |
437 |
|
438 |
use Convert::UUlib ':all'; |
439 |
|
440 |
sub namefilter { |
441 |
my($path)=@_; |
442 |
$path=~s/^.*[\/\\]//; |
443 |
$path; |
444 |
} |
445 |
|
446 |
sub busycb { |
447 |
my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_; |
448 |
$_[0]=straction($action); |
449 |
print "busy_callback(", (join ",",@_), ")\n"; |
450 |
0; |
451 |
} |
452 |
|
453 |
SetOption OPT_IGNMODE, 1; |
454 |
SetOption OPT_VERBOSE, 1; |
455 |
|
456 |
# show the three ways you can set callback functions. I normally |
457 |
# prefer the one with the sub inplace. |
458 |
SetFNameFilter \&namefilter; |
459 |
|
460 |
SetBusyCallback "busycb", 333; |
461 |
|
462 |
SetMsgCallback sub { |
463 |
my ($msg, $level) = @_; |
464 |
print uc strmsglevel $_[1], ": $msg\n"; |
465 |
}; |
466 |
|
467 |
# the following non-trivial FileNameCallback takes care |
468 |
# of some subject lines not detected properly by uulib: |
469 |
SetFileNameCallback sub { |
470 |
return unless $_[1]; # skip "Re:"-plies et al. |
471 |
local $_ = $_[0]; |
472 |
|
473 |
# the following rules are rather effective on some newsgroups, |
474 |
# like alt.binaries.games.anime, where non-mime, uuencoded data |
475 |
# is very common |
476 |
|
477 |
# if we find some *.rar, take it as the filename |
478 |
return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i; |
479 |
|
480 |
# one common subject format |
481 |
return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i; |
482 |
|
483 |
# - filename.par (04/55) |
484 |
return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i; |
485 |
|
486 |
# - (xxx) No. 1 sayuri81.jpg 756565 bytes |
487 |
# - (20 files) No.17 Roseanne.jpg [2/2] |
488 |
return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/; |
489 |
|
490 |
# otherwise just pass what we have |
491 |
return (); |
492 |
}; |
493 |
|
494 |
# now read all files in the directory uusrc/* |
495 |
for(<uusrc/*>) { |
496 |
my($retval,$count)=LoadFile ($_, $_, 1); |
497 |
print "file($_), status(", strerror $retval, ") parts($count)\n"; |
498 |
} |
499 |
|
500 |
SetOption OPT_SAVEPATH, "uudst/"; |
501 |
|
502 |
# now wade through all files and their source parts |
503 |
$i = 0; |
504 |
while ($uu = GetFileListItem($i)) { |
505 |
$i++; |
506 |
print "file nr. $i"; |
507 |
print " state ", $uu->state; |
508 |
print " mode ", $uu->mode; |
509 |
print " uudet ", strencoding $uu->uudet; |
510 |
print " size ", $uu->size; |
511 |
print " filename ", $uu->filename; |
512 |
print " subfname ", $uu->subfname; |
513 |
print " mimeid ", $uu->mimeid; |
514 |
print " mimetype ", $uu->mimetype; |
515 |
print "\n"; |
516 |
|
517 |
# print additional info about all parts |
518 |
for ($uu->parts) { |
519 |
while (my ($k, $v) = each %$_) { |
520 |
print "$k > $v, "; |
521 |
} |
522 |
print "\n"; |
523 |
} |
524 |
|
525 |
$uu->decode_temp; |
526 |
print " temporarily decoded to ", $uu->binfile, "\n"; |
527 |
$uu->remove_temp; |
528 |
|
529 |
print strerror $uu->decode; |
530 |
print " saved as uudst/", $uu->filename, "\n"; |
531 |
} |
532 |
|
533 |
print "cleanup...\n"; |
534 |
|
535 |
CleanUp(); |
536 |
|
537 |
=head1 AUTHOR |
538 |
|
539 |
Marc Lehmann <pcg@goof.com>, the original uulib library was written |
540 |
by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily |
541 |
bugfixed by Marc Lehmann. |
542 |
|
543 |
=head1 SEE ALSO |
544 |
|
545 |
perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/. |
546 |
|
547 |
=cut |