1 |
NAME |
2 |
Convert::UUlib - Perl interface to the uulib library (a.k.a. |
3 |
uudeview/uuenview). |
4 |
|
5 |
SYNOPSIS |
6 |
use Convert::UUlib ':all'; |
7 |
|
8 |
# read all the files named on the commandline and decode them |
9 |
# into the CURRENT directory. See below for a longer example. |
10 |
LoadFile $_ for @ARGV; |
11 |
for (my $i = 0; my $uu = GetFileListItem $i; $i++) { |
12 |
if ($uu->state & FILE_OK) { |
13 |
$uu->decode; |
14 |
print $uu->filename, "\n"; |
15 |
} |
16 |
} |
17 |
|
18 |
DESCRIPTION |
19 |
Read the file doc/library.pdf from the distribution for in-depth |
20 |
information about the C-library used in this interface, and the rest of |
21 |
this document and especially the non-trivial decoder program at the end. |
22 |
|
23 |
EXPORTED CONSTANTS |
24 |
Action code constants |
25 |
ACT_IDLE we don't do anything |
26 |
ACT_SCANNING scanning an input file |
27 |
ACT_DECODING decoding into a temp file |
28 |
ACT_COPYING copying temp to target |
29 |
ACT_ENCODING encoding a file |
30 |
|
31 |
Message severity levels |
32 |
MSG_MESSAGE just a message, nothing important |
33 |
MSG_NOTE something that should be noticed |
34 |
MSG_WARNING important msg, processing continues |
35 |
MSG_ERROR processing has been terminated |
36 |
MSG_FATAL decoder cannot process further requests |
37 |
MSG_PANIC recovery impossible, app must terminate |
38 |
|
39 |
Options |
40 |
OPT_VERSION version number MAJOR.MINORplPATCH (ro) |
41 |
OPT_FAST assumes only one part per file |
42 |
OPT_DUMBNESS switch off the program's intelligence |
43 |
OPT_BRACKPOL give numbers in [] higher precendence |
44 |
OPT_VERBOSE generate informative messages |
45 |
OPT_DESPERATE try to decode incomplete files |
46 |
OPT_IGNREPLY ignore RE:plies (off by default) |
47 |
OPT_OVERWRITE whether it's OK to overwrite ex. files |
48 |
OPT_SAVEPATH prefix to save-files on disk |
49 |
OPT_IGNMODE ignore the original file mode |
50 |
OPT_DEBUG print messages with FILE/LINE info |
51 |
OPT_ERRNO get last error code for RET_IOERR (ro) |
52 |
OPT_PROGRESS retrieve progress information |
53 |
OPT_USETEXT handle text messages |
54 |
OPT_PREAMB handle Mime preambles/epilogues |
55 |
OPT_TINYB64 detect short B64 outside of Mime |
56 |
OPT_ENCEXT extension for single-part encoded files |
57 |
OPT_REMOVE remove input files after decoding (dangerous) |
58 |
OPT_MOREMIME strict MIME adherence |
59 |
OPT_DOTDOT ".."-unescaping has not yet been done on input files |
60 |
OPT_RBUF set default read I/O buffer size in bytes *EXPERIMENTAL* |
61 |
OPT_WBUF set default write I/O buffer size in bytes *EXPERIMENTAL* |
62 |
|
63 |
Result/Error codes |
64 |
RET_OK everything went fine |
65 |
RET_IOERR I/O Error - examine errno |
66 |
RET_NOMEM not enough memory |
67 |
RET_ILLVAL illegal value for operation |
68 |
RET_NODATA decoder didn't find any data |
69 |
RET_NOEND encoded data wasn't ended properly |
70 |
RET_UNSUP unsupported function (encoding) |
71 |
RET_EXISTS file exists (decoding) |
72 |
RET_CONT continue -- special from ScanPart |
73 |
RET_CANCEL operation canceled |
74 |
|
75 |
File States |
76 |
This code is zero, i.e. "false": |
77 |
|
78 |
UUFILE_READ Read in, but not further processed |
79 |
|
80 |
The following state codes are or'ed together: |
81 |
|
82 |
FILE_MISPART Missing Part(s) detected |
83 |
FILE_NOBEGIN No 'begin' found |
84 |
FILE_NOEND No 'end' found |
85 |
FILE_NODATA File does not contain valid uudata |
86 |
FILE_OK All Parts found, ready to decode |
87 |
FILE_ERROR Error while decoding |
88 |
FILE_DECODED Successfully decoded |
89 |
FILE_TMPFILE Temporary decoded file exists |
90 |
|
91 |
Encoding types |
92 |
UU_ENCODED UUencoded data |
93 |
B64_ENCODED Mime-Base64 data |
94 |
XX_ENCODED XXencoded data |
95 |
BH_ENCODED Binhex encoded |
96 |
PT_ENCODED Plain-Text encoded (MIME) |
97 |
QP_ENCODED Quoted-Printable (MIME) |
98 |
YENC_ENCODED yEnc encoded (non-MIME) |
99 |
|
100 |
EXPORTED FUNCTIONS |
101 |
Initializing and cleanup |
102 |
Initialize is automatically called when the module is loaded and |
103 |
allocates quite a small amount of memory for todays machines ;) CleanUp |
104 |
releases that again. |
105 |
|
106 |
On my machine, a fairly complete decode with DBI backend needs about |
107 |
10MB RSS to decode 20000 files. |
108 |
|
109 |
Initialize |
110 |
Not normally necessary, (re-)initializes the library. |
111 |
|
112 |
CleanUp |
113 |
Not normally necessary, could be called at the end to release memory |
114 |
before starting a new decoding round. |
115 |
|
116 |
Setting and querying options |
117 |
$option = GetOption OPT_xxx |
118 |
SetOption OPT_xxx, opt-value |
119 |
|
120 |
See the "OPT_xxx" constants above to see which options exist. |
121 |
|
122 |
Setting various callbacks |
123 |
SetMsgCallback [callback-function] |
124 |
SetBusyCallback [callback-function] |
125 |
SetFileCallback [callback-function] |
126 |
SetFNameFilter [callback-function] |
127 |
|
128 |
Call the currently selected FNameFilter |
129 |
$file = FNameFilter $file |
130 |
|
131 |
Loading sourcefiles, optionally fuzzy merge and start decoding |
132 |
($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]] |
133 |
Load the given file and scan it for encoded contents. Optionally tag |
134 |
it with the given id, and if $delflag is true, delete the file after |
135 |
it is no longer necessary. If you are certain of the part number, |
136 |
you can specify it as the last argument. |
137 |
|
138 |
A better (usually faster) way of doing this is using the |
139 |
"SetFNameFilter" functionality. |
140 |
|
141 |
$retval = Smerge $pass |
142 |
If you are desperate, try to call "Smerge" with increasing $pass |
143 |
values, beginning at 0, to try to merge parts that usually would not |
144 |
have been merged. |
145 |
|
146 |
Most probably this will result in garbled files, so never do this by |
147 |
default. |
148 |
|
149 |
$item = GetFileListItem $item_number |
150 |
Return the $item structure for the $item_number'th found file, or |
151 |
"undef" of no file with that number exists. |
152 |
|
153 |
The first file has number 0, and the series has no holes, so you can |
154 |
iterate over all files by starting with zero and incrementing until |
155 |
you hit "undef". |
156 |
|
157 |
Decoding files |
158 |
$retval = $item->rename($newname) |
159 |
Change the ondisk filename where the decoded file will be saved. |
160 |
|
161 |
$retval = $item->decode_temp |
162 |
Decode the file into a temporary location, use "$item->infile" to |
163 |
retrieve the temporary filename. |
164 |
|
165 |
$retval = $item->remove_temp |
166 |
Remove the temporarily decoded file again. |
167 |
|
168 |
$retval = $item->decode([$target_path]) |
169 |
Decode the file to it's destination, or the given target path. |
170 |
|
171 |
$retval = $item->info(callback-function) |
172 |
|
173 |
Querying (and setting) item attributes |
174 |
$state = $item->state |
175 |
$mode = $item->mode([newmode]) |
176 |
$uudet = $item->uudet |
177 |
$size = $item->size |
178 |
$filename = $item->filename([newfilename}) |
179 |
$subfname = $item->subfname |
180 |
$mimeid = $item->mimeid |
181 |
$mimetype = $item->mimetype |
182 |
$binfile = $item->binfile |
183 |
|
184 |
Information about source parts |
185 |
$parts = $item->parts |
186 |
Return information about all parts (source files) used to decode the |
187 |
file as a list of hashrefs with the following structure: |
188 |
|
189 |
{ |
190 |
partno => <integer describing the part number, starting with 1>, |
191 |
# the following member sonly exist when they contain useful information |
192 |
sfname => <local pathname of the file where this part is from>, |
193 |
filename => <the ondisk filename of the decoded file>, |
194 |
subfname => <used to cluster postings, possibly the posting filename>, |
195 |
subject => <the subject of the posting/mail>, |
196 |
origin => <the possible source (From) address>, |
197 |
mimetype => <the possible mimetype of the decoded file>, |
198 |
mimeid => <the id part of the Content-Type>, |
199 |
} |
200 |
|
201 |
Usually you are interested mostly the "sfname" and possibly the |
202 |
"partno" and "filename" members. |
203 |
|
204 |
Functions below not documented and not very well tested |
205 |
QuickDecode |
206 |
EncodeMulti |
207 |
EncodePartial |
208 |
EncodeToStream |
209 |
EncodeToFile |
210 |
E_PrepSingle |
211 |
E_PrepPartial |
212 |
|
213 |
EXTENSION FUNCTIONS |
214 |
Functions found in this module but not documented in the uulib |
215 |
documentation: |
216 |
|
217 |
$msg = straction ACT_xxx |
218 |
Return a human readable string representing the given action code. |
219 |
|
220 |
$msg = strerror RET_xxx |
221 |
Return a human readable string representing the given error code. |
222 |
|
223 |
$str = strencoding xxx_ENCODED |
224 |
Return the name of the encoding type as a string. |
225 |
|
226 |
$str = strmsglevel MSG_xxx |
227 |
Returns the message level as a string. |
228 |
|
229 |
SetFileNameCallback $cb |
230 |
Sets (or queries) the FileNameCallback, which is called whenever the |
231 |
decoding library can't find a filename and wants to extract a |
232 |
filename from the subject line of a posting. The callback will be |
233 |
called with two arguments, the subject line and the current |
234 |
candidate for the filename. The latter argument can be "undef", |
235 |
which means that no filename could be found (and likely no one |
236 |
exists, so it is safe to also return "undef" in this case). If it |
237 |
doesn't return anything (not even "undef"!), then nothing happens, |
238 |
so this is a no-op callback: |
239 |
|
240 |
sub cb { |
241 |
return (); |
242 |
} |
243 |
|
244 |
If it returns "undef", then this indicates that no filename could be |
245 |
found. In all other cases, the return value is taken to be the |
246 |
filename. |
247 |
|
248 |
This is a slightly more useful callback: |
249 |
|
250 |
sub cb { |
251 |
return unless $_[1]; # skip "Re:"-plies et al. |
252 |
my ($subject, $filename) = @_; |
253 |
# if we find some *.rar, take it |
254 |
return $1 if $subject =~ /(\w+\.rar)/; |
255 |
# otherwise just pass what we have |
256 |
return (); |
257 |
} |
258 |
|
259 |
LARGE EXAMPLE DECODER |
260 |
This is the file "example-decoder" from the distribution, put here |
261 |
instead of more thorough documentation. |
262 |
|
263 |
# decode all the files in the directory uusrc/ and copy |
264 |
# the resulting files to uudst/ |
265 |
|
266 |
use Convert::UUlib ':all'; |
267 |
|
268 |
sub namefilter { |
269 |
my($path)=@_; |
270 |
$path=~s/^.*[\/\\]//; |
271 |
$path; |
272 |
} |
273 |
|
274 |
sub busycb { |
275 |
my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_; |
276 |
$_[0]=straction($action); |
277 |
print "busy_callback(", (join ",",@_), ")\n"; |
278 |
0; |
279 |
} |
280 |
|
281 |
SetOption OPT_IGNMODE, 1; |
282 |
SetOption OPT_VERBOSE, 1; |
283 |
|
284 |
# show the three ways you can set callback functions. I normally |
285 |
# prefer the one with the sub inplace. |
286 |
SetFNameFilter \&namefilter; |
287 |
|
288 |
SetBusyCallback "busycb", 333; |
289 |
|
290 |
SetMsgCallback sub { |
291 |
my ($msg, $level) = @_; |
292 |
print uc strmsglevel $_[1], ": $msg\n"; |
293 |
}; |
294 |
|
295 |
# the following non-trivial FileNameCallback takes care |
296 |
# of some subject lines not detected properly by uulib: |
297 |
SetFileNameCallback sub { |
298 |
return unless $_[1]; # skip "Re:"-plies et al. |
299 |
local $_ = $_[0]; |
300 |
|
301 |
# the following rules are rather effective on some newsgroups, |
302 |
# like alt.binaries.games.anime, where non-mime, uuencoded data |
303 |
# is very common |
304 |
|
305 |
# if we find some *.rar, take it as the filename |
306 |
return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i; |
307 |
|
308 |
# one common subject format |
309 |
return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i; |
310 |
|
311 |
# - filename.par (04/55) |
312 |
return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i; |
313 |
|
314 |
# - (xxx) No. 1 sayuri81.jpg 756565 bytes |
315 |
# - (20 files) No.17 Roseanne.jpg [2/2] |
316 |
return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/; |
317 |
|
318 |
# otherwise just pass what we have |
319 |
return (); |
320 |
}; |
321 |
|
322 |
# now read all files in the directory uusrc/* |
323 |
for(<uusrc/*>) { |
324 |
my($retval,$count)=LoadFile ($_, $_, 1); |
325 |
print "file($_), status(", strerror $retval, ") parts($count)\n"; |
326 |
} |
327 |
|
328 |
SetOption OPT_SAVEPATH, "uudst/"; |
329 |
|
330 |
# now wade through all files and their source parts |
331 |
$i = 0; |
332 |
while ($uu = GetFileListItem($i)) { |
333 |
$i++; |
334 |
print "file nr. $i"; |
335 |
print " state ", $uu->state; |
336 |
print " mode ", $uu->mode; |
337 |
print " uudet ", strencoding $uu->uudet; |
338 |
print " size ", $uu->size; |
339 |
print " filename ", $uu->filename; |
340 |
print " subfname ", $uu->subfname; |
341 |
print " mimeid ", $uu->mimeid; |
342 |
print " mimetype ", $uu->mimetype; |
343 |
print "\n"; |
344 |
|
345 |
# print additional info about all parts |
346 |
for ($uu->parts) { |
347 |
while (my ($k, $v) = each %$_) { |
348 |
print "$k > $v, "; |
349 |
} |
350 |
print "\n"; |
351 |
} |
352 |
|
353 |
$uu->decode_temp; |
354 |
print " temporarily decoded to ", $uu->binfile, "\n"; |
355 |
$uu->remove_temp; |
356 |
|
357 |
print strerror $uu->decode; |
358 |
print " saved as uudst/", $uu->filename, "\n"; |
359 |
} |
360 |
|
361 |
print "cleanup...\n"; |
362 |
|
363 |
CleanUp(); |
364 |
|
365 |
AUTHOR |
366 |
Marc Lehmann <schmorp@schmorp.de>, the original uulib library was |
367 |
written by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later |
368 |
heavily bugfixed by Marc Lehmann. |
369 |
|
370 |
SEE ALSO |
371 |
perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/. |
372 |
|