1 | package Convert::UUlib; |
1 | package Convert::UUlib; |
|
|
2 | |
|
|
3 | use common::sense; |
2 | |
4 | |
3 | use Carp; |
5 | use Carp; |
4 | |
6 | |
5 | require Exporter; |
7 | require Exporter; |
6 | require DynaLoader; |
8 | require DynaLoader; |
7 | use AutoLoader; |
|
|
8 | |
9 | |
9 | $VERSION = 0.3; |
10 | our $VERSION = 1.71; |
10 | |
11 | |
11 | @ISA = qw(Exporter DynaLoader); |
12 | our @ISA = qw(Exporter DynaLoader); |
12 | |
13 | |
13 | @_consts = qw( |
14 | our @_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 OPT_DOTDOT |
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 | B64_ENCODED 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( |
35 | our @_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; |
46 | our @EXPORT = @_consts; |
45 | @EXPORT_OK = @_funcs; |
47 | our @EXPORT_OK = @_funcs; |
46 | %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts); |
48 | our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts); |
47 | |
49 | |
48 | bootstrap Convert::UUlib $VERSION; |
50 | bootstrap Convert::UUlib $VERSION; |
49 | |
51 | |
50 | Initialize(); |
52 | # dummy function for compatiiblity with pre-1.7 versions |
51 | |
53 | sub Initialize { } |
52 | # not when < 5.005_6x |
|
|
53 | # END { CleanUp() } |
|
|
54 | |
|
|
55 | for (@_consts) { |
|
|
56 | my $constant = constant($_); |
|
|
57 | *$_ = sub () { $constant }; |
|
|
58 | } |
|
|
59 | |
54 | |
60 | # action code -> string mapping |
55 | # action code -> string mapping |
61 | sub straction($) { |
56 | sub 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 $_[0] == &ACT_DECODING; |
… | |
… | |
99 | =head1 SYNOPSIS |
94 | =head1 SYNOPSIS |
100 | |
95 | |
101 | use Convert::UUlib ':all'; |
96 | use Convert::UUlib ':all'; |
102 | |
97 | |
103 | # read all the files named on the commandline and decode them |
98 | # read all the files named on the commandline and decode them |
|
|
99 | # into the CURRENT directory. See below for a longer example. |
104 | LoadFile($_) for @ARGV; |
100 | LoadFile $_ for @ARGV; |
105 | for($i=0; $uu=GetFileListItem($i); $i++) { |
101 | |
|
|
102 | for my $uu (GetFileList) { |
106 | $uu->decode if $uu->state & FILE_OK; |
103 | if ($uu->state & FILE_OK) { |
|
|
104 | $uu->decode; |
|
|
105 | print $uu->filename, "\n"; |
|
|
106 | } |
107 | } |
107 | } |
108 | |
108 | |
109 | =head1 DESCRIPTION |
109 | =head1 DESCRIPTION |
110 | |
110 | |
111 | Read the file doc/library.pdf from the distribution for in-depth |
111 | Read the file doc/library.pdf from the distribution for in-depth |
… | |
… | |
148 | OPT_PROGRESS retrieve progress information |
148 | OPT_PROGRESS retrieve progress information |
149 | OPT_USETEXT handle text messages |
149 | OPT_USETEXT handle text messages |
150 | OPT_PREAMB handle Mime preambles/epilogues |
150 | OPT_PREAMB handle Mime preambles/epilogues |
151 | OPT_TINYB64 detect short B64 outside of Mime |
151 | OPT_TINYB64 detect short B64 outside of Mime |
152 | OPT_ENCEXT extension for single-part encoded files |
152 | OPT_ENCEXT extension for single-part encoded files |
153 | OPT_REMOVE remove input files after decoding |
153 | OPT_REMOVE remove input files after decoding (dangerous) |
154 | OPT_MOREMIME strict MIME adherence |
154 | OPT_MOREMIME strict MIME adherence |
155 | OPT_DOTDOT .. unescaping has not yet been done on input files |
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 |
156 | |
159 | |
157 | =head2 Result/Error codes |
160 | =head2 Result/Error codes |
158 | |
161 | |
159 | RET_OK everything went fine |
162 | RET_OK everything went fine |
160 | RET_IOERR I/O Error - examine errno |
163 | RET_IOERR I/O Error - examine errno |
… | |
… | |
171 | |
174 | |
172 | This code is zero, i.e. "false": |
175 | This code is zero, i.e. "false": |
173 | |
176 | |
174 | UUFILE_READ Read in, but not further processed |
177 | UUFILE_READ Read in, but not further processed |
175 | |
178 | |
176 | The following state codes are ored together: |
179 | The following state codes are or'ed together: |
177 | |
180 | |
178 | FILE_MISPART Missing Part(s) detected |
181 | FILE_MISPART Missing Part(s) detected |
179 | FILE_NOBEGIN No 'begin' found |
182 | FILE_NOBEGIN No 'begin' found |
180 | FILE_NOEND No 'end' found |
183 | FILE_NOEND No 'end' found |
181 | FILE_NODATA File does not contain valid uudata |
184 | FILE_NODATA File does not contain valid uudata |
… | |
… | |
197 | =head1 EXPORTED FUNCTIONS |
200 | =head1 EXPORTED FUNCTIONS |
198 | |
201 | |
199 | =head2 Initializing and cleanup |
202 | =head2 Initializing and cleanup |
200 | |
203 | |
201 | Initialize is automatically called when the module is loaded and allocates |
204 | Initialize is automatically called when the module is loaded and allocates |
202 | quite a bit of memory. CleanUp releases that again. |
205 | quite a small amount of memory for todays machines ;) CleanUp releases that |
|
|
206 | again. |
203 | |
207 | |
204 | Initialize; # not normally necessary |
208 | On my machine, a fairly complete decode with DBI backend needs about 10MB |
205 | CleanUp; # could be called at the end to release memory |
209 | RSS to decode 20000 files. |
|
|
210 | |
|
|
211 | =over |
|
|
212 | |
|
|
213 | =item CleanUp |
|
|
214 | |
|
|
215 | Release memory, file items and clean up files. Should be called after a |
|
|
216 | decoidng run, if you want to start a new one. |
|
|
217 | |
|
|
218 | =back |
206 | |
219 | |
207 | =head2 Setting and querying options |
220 | =head2 Setting and querying options |
208 | |
221 | |
|
|
222 | =over |
|
|
223 | |
209 | $option = GetOption OPT_xxx; |
224 | =item $option = GetOption OPT_xxx |
|
|
225 | |
210 | SetOption OPT_xxx, opt-value; |
226 | =item SetOption OPT_xxx, opt-value |
|
|
227 | |
|
|
228 | =back |
|
|
229 | |
|
|
230 | See the C<OPT_xxx> constants above to see which options exist. |
211 | |
231 | |
212 | =head2 Setting various callbacks |
232 | =head2 Setting various callbacks |
213 | |
233 | |
|
|
234 | =over |
|
|
235 | |
214 | SetMsgCallback [callback-function]; |
236 | =item SetMsgCallback [callback-function] |
|
|
237 | |
215 | SetBusyCallback [callback-function]; |
238 | =item SetBusyCallback [callback-function] |
|
|
239 | |
216 | SetFileCallback [callback-function]; |
240 | =item SetFileCallback [callback-function] |
|
|
241 | |
217 | SetFNameFilter [callback-function]; |
242 | =item SetFNameFilter [callback-function] |
|
|
243 | |
|
|
244 | =back |
218 | |
245 | |
219 | =head2 Call the currently selected FNameFilter |
246 | =head2 Call the currently selected FNameFilter |
220 | |
247 | |
|
|
248 | =over |
|
|
249 | |
221 | $file = FNameFilter $file; |
250 | =item $file = FNameFilter $file |
|
|
251 | |
|
|
252 | =back |
222 | |
253 | |
223 | =head2 Loading sourcefiles, optionally fuzzy merge and start decoding |
254 | =head2 Loading sourcefiles, optionally fuzzy merge and start decoding |
224 | |
255 | |
|
|
256 | =over |
|
|
257 | |
225 | ($retval, $count) = LoadFile $fname, [$id, [$delflag]]; |
258 | =item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]] |
|
|
259 | |
|
|
260 | Load the given file and scan it for encoded contents. Optionally tag it |
|
|
261 | with the given id, and if C<$delflag> is true, delete the file after it |
|
|
262 | is no longer necessary. If you are certain of the part number, you can |
|
|
263 | specify it as the last argument. |
|
|
264 | |
|
|
265 | A better (usually faster) way of doing this is using the C<SetFNameFilter> |
|
|
266 | functionality. |
|
|
267 | |
226 | $retval = Smerge $pass; |
268 | =item $retval = Smerge $pass |
|
|
269 | |
|
|
270 | If you are desperate, try to call C<Smerge> with increasing C<$pass> |
|
|
271 | values, beginning at C<0>, to try to merge parts that usually would not |
|
|
272 | have been merged. |
|
|
273 | |
|
|
274 | Most probably this will result in garbled files, so never do this by |
|
|
275 | default, except: |
|
|
276 | |
|
|
277 | If the C<OPT_AUTOCHECK> option has been disabled (by default it is |
|
|
278 | enabled) to speed up file loading, then you I<have> to call C<Smerge -1> |
|
|
279 | after loading all files as an additional pre-pass (which is normally done |
|
|
280 | by C<LoadFile>). |
|
|
281 | |
227 | $item = GetFileListItem $item_number; |
282 | =item $item = GetFileListItem $item_number |
228 | |
283 | |
229 | =head2 The procedural interface is undocumented, use the following methods instead |
284 | Return the C<$item> structure for the C<$item_number>'th found file, or |
|
|
285 | C<undef> of no file with that number exists. |
230 | |
286 | |
|
|
287 | The first file has number C<0>, and the series has no holes, so you can |
|
|
288 | iterate over all files by starting with zero and incrementing until you |
|
|
289 | hit C<undef>. |
|
|
290 | |
|
|
291 | This function has to walk the linear list of fils on each access, so |
|
|
292 | if you want to iterate over all items, it is usually faster to use |
|
|
293 | C<GetFileList>. |
|
|
294 | |
|
|
295 | =item @items = GetFileList |
|
|
296 | |
|
|
297 | Similar to C<GetFileListItem>, but returns all files in one go. |
|
|
298 | |
|
|
299 | =back |
|
|
300 | |
|
|
301 | =head2 Decoding files |
|
|
302 | |
|
|
303 | =over |
|
|
304 | |
231 | $retval = $item->rename($newname); |
305 | =item $retval = $item->rename ($newname) |
|
|
306 | |
|
|
307 | Change the ondisk filename where the decoded file will be saved. |
|
|
308 | |
232 | $retval = $item->decode_temp; |
309 | =item $retval = $item->decode_temp |
|
|
310 | |
|
|
311 | Decode the file into a temporary location, use C<< $item->infile >> to |
|
|
312 | retrieve the temporary filename. |
|
|
313 | |
233 | $retval = $item->remove_temp; |
314 | =item $retval = $item->remove_temp |
|
|
315 | |
|
|
316 | Remove the temporarily decoded file again. |
|
|
317 | |
234 | $retval = $item->decode([$target_path]); |
318 | =item $retval = $item->decode ([$target_path]) |
|
|
319 | |
|
|
320 | Decode the file to its destination, or the given target path. |
|
|
321 | |
235 | $retval = $item->info(callback-function); |
322 | =item $retval = $item->info (callback-function) |
|
|
323 | |
|
|
324 | =back |
236 | |
325 | |
237 | =head2 Querying (and setting) item attributes |
326 | =head2 Querying (and setting) item attributes |
238 | |
327 | |
|
|
328 | =over |
|
|
329 | |
239 | $state = $item->state; |
330 | =item $state = $item->state |
|
|
331 | |
240 | $mode = $item->mode([newmode]); |
332 | =item $mode = $item->mode ([newmode]) |
|
|
333 | |
241 | $uudet = $item->uudet; |
334 | =item $uudet = $item->uudet |
|
|
335 | |
242 | $size = $item->size; |
336 | =item $size = $item->size |
|
|
337 | |
243 | $filename = $item->filename([newfilename}); |
338 | =item $filename = $item->filename ([newfilename}) |
|
|
339 | |
244 | $subfname = $item->subfname; |
340 | =item $subfname = $item->subfname |
|
|
341 | |
245 | $mimeid = $item->mimeid; |
342 | =item $mimeid = $item->mimeid |
|
|
343 | |
246 | $mimetype = $item->mimetype; |
344 | =item $mimetype = $item->mimetype |
|
|
345 | |
247 | $binfile = $item->binfile; |
346 | =item $binfile = $item->binfile |
248 | |
347 | |
249 | =head2 Totally undocumented but well tested ;) |
348 | =back |
250 | |
349 | |
|
|
350 | =head2 Information about source parts |
|
|
351 | |
|
|
352 | =over |
|
|
353 | |
251 | $parts = $item->parts; |
354 | =item $parts = $item->parts |
252 | |
355 | |
|
|
356 | Return information about all parts (source files) used to decode the file |
|
|
357 | as 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>, |
|
|
369 | } |
|
|
370 | |
|
|
371 | Usually you are interested mostly the C<sfname> and possibly the C<partno> |
|
|
372 | and C<filename> members. |
|
|
373 | |
|
|
374 | =back |
|
|
375 | |
253 | =head2 Functions below not documented and not very well tested |
376 | =head2 Functions below are not documented and not very well tested - feedback welcome |
254 | |
377 | |
255 | QuickDecode |
378 | QuickDecode |
256 | EncodeMulti |
379 | EncodeMulti |
257 | EncodePartial |
380 | EncodePartial |
258 | EncodeToStream |
381 | EncodeToStream |
… | |
… | |
262 | |
385 | |
263 | =head2 EXTENSION FUNCTIONS |
386 | =head2 EXTENSION FUNCTIONS |
264 | |
387 | |
265 | Functions found in this module but not documented in the uulib documentation: |
388 | Functions found in this module but not documented in the uulib documentation: |
266 | |
389 | |
267 | =over 4 |
390 | =over |
268 | |
391 | |
269 | =item $msg = straction ACT_xxx |
392 | =item $msg = straction ACT_xxx |
270 | |
393 | |
271 | Return a human readable string representing the given action code. |
394 | Return a human readable string representing the given action code. |
272 | |
395 | |
… | |
… | |
313 | |
436 | |
314 | =back |
437 | =back |
315 | |
438 | |
316 | =head1 LARGE EXAMPLE DECODER |
439 | =head1 LARGE EXAMPLE DECODER |
317 | |
440 | |
|
|
441 | The general workflow for decoding is like this: |
|
|
442 | |
|
|
443 | =over |
|
|
444 | |
|
|
445 | =item 1. Configure options with C<SetOption> or C<SetXXXCallback>. |
|
|
446 | |
|
|
447 | =item 2. Load all source files with C<LoadFile>. |
|
|
448 | |
|
|
449 | =item 3. Optionally C<Smerge>. |
|
|
450 | |
|
|
451 | =item 4. Iterate over all C<GetFileList> items (i.e. result files). |
|
|
452 | |
|
|
453 | =item 5. C<CleanUp> to delete files and free items. |
|
|
454 | |
|
|
455 | =back |
|
|
456 | |
318 | This is the file C<example-decoder> from the distribution, put here |
457 | What follows is the file C<example-decoder> from the distribution that |
319 | instead of more thorough documentation. |
458 | illustrates the above worklfow in a non-trivial example. |
320 | |
459 | |
|
|
460 | #!/usr/bin/perl |
|
|
461 | |
321 | # decode all the files in the directory uusrc/ and copy |
462 | # decode all the files in the directory uusrc/ and copy |
322 | # the resulting files to uudst/ |
463 | # the resulting files to uudst/ |
323 | |
464 | |
324 | use Convert::UUlib ':all'; |
465 | use Convert::UUlib ':all'; |
325 | |
466 | |
326 | sub namefilter { |
467 | sub namefilter { |
327 | my($path)=@_; |
468 | my ($path) = @_; |
|
|
469 | |
328 | $path=~s/^.*[\/\\]//; |
470 | $path=~s/^.*[\/\\]//; |
|
|
471 | |
329 | $path; |
472 | $path |
330 | } |
473 | } |
331 | |
474 | |
332 | sub busycb { |
475 | sub busycb { |
333 | my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_; |
476 | my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_; |
334 | $_[0]=straction($action); |
477 | $_[0]=straction($action); |
335 | print "busy_callback(", (join ",",@_), ")\n"; |
478 | print "busy_callback(", (join ",",@_), ")\n"; |
336 | 0; |
479 | 0 |
337 | } |
480 | } |
338 | |
481 | |
|
|
482 | SetOption OPT_RBUF, 128*1024; |
|
|
483 | SetOption OPT_WBUF, 1024*1024; |
339 | SetOption OPT_IGNMODE, 1; |
484 | SetOption OPT_IGNMODE, 1; |
|
|
485 | SetOption OPT_IGNMODE, 1; |
340 | SetOption OPT_VERBOSE, 1; |
486 | SetOption OPT_VERBOSE, 1; |
341 | |
487 | |
342 | # show the three ways you can set callback functions. I normally |
488 | # show the three ways you can set callback functions. I normally |
343 | # prefer the one with the sub inplace. |
489 | # prefer the one with the sub inplace. |
344 | SetFNameFilter \&namefilter; |
490 | SetFNameFilter \&namefilter; |
345 | |
491 | |
346 | SetBusyCallback "busycb", 333; |
492 | SetBusyCallback "busycb", 333; |
347 | |
493 | |
348 | SetMsgCallback sub { |
494 | SetMsgCallback sub { |
349 | my ($msg, $level) = @_; |
495 | my ($msg, $level) = @_; |
350 | print uc strmsglevel $_[1], ": $msg\n"; |
496 | print uc strmsglevel $_[1], ": $msg\n"; |
351 | }; |
497 | }; |
352 | |
498 | |
353 | # the following non-trivial FileNameCallback takes care |
499 | # the following non-trivial FileNameCallback takes care |
354 | # of some subject lines not detected properly by uulib: |
500 | # of some subject lines not detected properly by uulib: |
355 | SetFileNameCallback sub { |
501 | SetFileNameCallback sub { |
356 | return unless $_[1]; # skip "Re:"-plies et al. |
502 | return unless $_[1]; # skip "Re:"-plies et al. |
357 | local $_ = $_[0]; |
503 | local $_ = $_[0]; |
358 | |
504 | |
359 | # the following rules are rather effective on some newsgroups, |
505 | # the following rules are rather effective on some newsgroups, |
360 | # like alt.binaries.games.anime, where non-mime, uuencoded data |
506 | # like alt.binaries.games.anime, where non-mime, uuencoded data |
361 | # is very common |
507 | # is very common |
362 | |
508 | |
363 | # if we find some *.rar, take it as the filename |
509 | # if we find some *.rar, take it as the filename |
364 | return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i; |
510 | return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i; |
365 | |
511 | |
366 | # one common subject format |
512 | # one common subject format |
367 | return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i; |
513 | return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i; |
368 | |
514 | |
369 | # - filename.par (04/55) |
515 | # - filename.par (04/55) |
370 | return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i; |
516 | return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i; |
371 | |
517 | |
372 | # - (xxx) No. 1 sayuri81.jpg 756565 bytes |
518 | # - (xxx) No. 1 sayuri81.jpg 756565 bytes |
373 | # - (20 files) No.17 Roseanne.jpg [2/2] |
519 | # - (20 files) No.17 Roseanne.jpg [2/2] |
374 | return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/; |
520 | return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/; |
375 | |
521 | |
|
|
522 | # try to detect some common forms of filenames |
|
|
523 | return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i; |
|
|
524 | |
376 | # otherwise just pass what we have |
525 | # otherwise just pass what we have |
377 | return (); |
526 | () |
378 | }; |
527 | }; |
379 | |
528 | |
380 | # now read all files in the directory uusrc/* |
529 | # now read all files in the directory uusrc/* |
381 | for(<uusrc/*>) { |
530 | for (<uusrc/*>) { |
382 | my($retval,$count)=LoadFile ($_, $_, 1); |
531 | my ($retval, $count) = LoadFile ($_, $_, 1); |
383 | print "file($_), status(", strerror $retval, ") parts($count)\n"; |
532 | print "file($_), status(", strerror $retval, ") parts($count)\n"; |
384 | } |
533 | } |
385 | |
534 | |
386 | SetOption OPT_SAVEPATH, "uudst/"; |
535 | SetOption OPT_SAVEPATH, "uudst/"; |
387 | |
536 | |
388 | # now wade through all files and their source parts |
537 | # now wade through all files and their source parts |
389 | $i = 0; |
538 | for my $uu (GetFileList) { |
390 | while ($uu = GetFileListItem($i)) { |
539 | print "file ", $uu->filename, "\n"; |
391 | $i++; |
|
|
392 | print "file nr. $i"; |
|
|
393 | print " state ", $uu->state; |
540 | print " state ", $uu->state, "\n"; |
394 | print " mode ", $uu->mode; |
541 | print " mode ", $uu->mode, "\n"; |
395 | print " uudet ", strencoding $uu->uudet; |
542 | print " uudet ", strencoding $uu->uudet, "\n"; |
396 | print " size ", $uu->size; |
543 | print " size ", $uu->size, "\n"; |
397 | print " filename ", $uu->filename; |
|
|
398 | print " subfname ", $uu->subfname; |
544 | print " subfname ", $uu->subfname, "\n"; |
399 | print " mimeid ", $uu->mimeid; |
545 | print " mimeid ", $uu->mimeid, "\n"; |
400 | print " mimetype ", $uu->mimetype; |
546 | print " mimetype ", $uu->mimetype, "\n"; |
401 | print "\n"; |
|
|
402 | |
547 | |
403 | # print additional info about all parts |
548 | # print additional info about all parts |
|
|
549 | print " parts"; |
404 | for ($uu->parts) { |
550 | for ($uu->parts) { |
405 | while (my ($k, $v) = each %$_) { |
551 | for my $k (sort keys %$_) { |
406 | print "$k > $v, "; |
552 | print " $k=$_->{$k}"; |
407 | } |
553 | } |
408 | print "\n"; |
554 | print "\n"; |
409 | } |
555 | } |
410 | |
556 | |
411 | $uu->decode_temp; |
|
|
412 | print " temporarily decoded to ", $uu->binfile, "\n"; |
|
|
413 | $uu->remove_temp; |
557 | $uu->remove_temp; |
414 | |
558 | |
415 | print strerror $uu->decode; |
559 | if (my $err = $uu->decode) { |
|
|
560 | print " ERROR ", strerror $err, "\n"; |
|
|
561 | } else { |
416 | print " saved as uudst/", $uu->filename, "\n"; |
562 | print " successfully saved as uudst/", $uu->filename, "\n"; |
417 | } |
563 | } |
|
|
564 | } |
418 | |
565 | |
419 | print "cleanup...\n"; |
566 | print "cleanup...\n"; |
420 | |
567 | |
421 | CleanUp(); |
568 | CleanUp; |
|
|
569 | |
|
|
570 | =head1 PERLMULTICORE SUPPORT |
|
|
571 | |
|
|
572 | This module supports the perlmulticore standard (see |
|
|
573 | L<http://perlmulticore.schmorp.de/> for more info) for the following |
|
|
574 | functions - generally these are functions accessing the disk and/or using |
|
|
575 | considerable CPU time: |
|
|
576 | |
|
|
577 | LoadFile |
|
|
578 | $item->decode |
|
|
579 | $item->decode_temp |
|
|
580 | $item->remove_temp |
|
|
581 | $item->info |
|
|
582 | |
|
|
583 | The perl interpreter will be reacquired/released on every callback |
|
|
584 | invocation, so for performance reasons, callbacks should be avoided if |
|
|
585 | that is costly. |
|
|
586 | |
|
|
587 | Future versions might enable multicore support for more functions. |
|
|
588 | |
|
|
589 | =head1 BUGS AND LIMITATIONS |
|
|
590 | |
|
|
591 | The original uulib library this module uses was written at a time where |
|
|
592 | main memory of measured in megabytes and buffer overflows as a security |
|
|
593 | thign didn't exist. While a lot of security fixes have been applied over |
|
|
594 | the years (includign some defense in depth mechanism that can shield |
|
|
595 | against a lot of as-of-yet undetected bugs), using this library for |
|
|
596 | security purposes requires care. |
|
|
597 | |
|
|
598 | Likewise, file sizes when the uulib library was written were tiny compared |
|
|
599 | to today, so do not expect this library to handle files larger than 2GB. |
|
|
600 | |
|
|
601 | Lastly, this module uses a very "C-like" interface, which means it doesn't |
|
|
602 | protect you from invalid points as you might expect from "more perlish" |
|
|
603 | modules - for example, accessing a file item object after callinbg |
|
|
604 | C<CleanUp> will likely result in crashes, memory corruption, or worse. |
422 | |
605 | |
423 | =head1 AUTHOR |
606 | =head1 AUTHOR |
424 | |
607 | |
425 | Marc Lehmann <pcg@goof.com>, the original uulib library was written |
608 | Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written |
426 | by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily |
609 | by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily |
427 | bugfixed by Marc Lehmann. |
610 | bugfixed by Marc Lehmann. |
428 | |
611 | |
429 | =head1 SEE ALSO |
612 | =head1 SEE ALSO |
430 | |
613 | |
431 | perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/. |
614 | perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>. |
432 | |
615 | |
433 | =cut |
616 | =cut |
|
|
617 | |