[ViewVC] Diff of: cvs/Convert-UUlib/UUlib.pm

Comparing Convert-UUlib/UUlib.pm (file contents):
Revision 1.9 by root, Sat Apr 6 02:28:35 2002 UTC vs.
Revision 1.13 by root, Tue Oct 15 23:20:29 2002 UTC

…		…
2		2
3	use Carp;	3	use Carp;
4		4
5	require Exporter;	5	require Exporter;
6	require DynaLoader;	6	require DynaLoader;
7	use AutoLoader;
8		7
9	$VERSION = 0.212;	8	$VERSION = 0.31;
10		9
11	@ISA = qw(Exporter DynaLoader);	10	@ISA = qw(Exporter DynaLoader);
12		11
13	@_consts = qw(	12	@_consts = qw(
14	ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING	13	ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING
…		…
24	OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT	23	OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT
25		24
26	RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA	25	RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
27	RET_NOEND RET_NOMEM RET_OK RET_UNSUP	26	RET_NOEND RET_NOMEM RET_OK RET_UNSUP
28		27
29	B64ENCODED BH_ENCODED PT_ENCODED QP_ENCODED	28	B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
30	XX_ENCODED UU_ENCODED YENC_ENCODED	29	XX_ENCODED UU_ENCODED YENC_ENCODED
31	);	30	);
32		31
33	@_funcs = qw(	32	@_funcs = qw(
34	Initialize CleanUp GetOption SetOption strerror SetMsgCallback	33	Initialize CleanUp GetOption SetOption strerror SetMsgCallback
…		…
68	}	67	}
69		68
70	# encoding type -> string mapping	69	# encoding type -> string mapping
71	sub strencoding($) {	70	sub strencoding($) {
72	return 'uuencode' if $_[0] == &UU_ENCODED;	71	return 'uuencode' if $_[0] == &UU_ENCODED;
73	return 'base64' if $_[0] == &B64ENCODED;	72	return 'base64' if $_[0] == &B64_ENCODED;
74	return 'yenc' if $_[0] == &YENC_ENCODED;	73	return 'yenc' if $_[0] == &YENC_ENCODED;
75	return 'binhex' if $_[0] == &BH_ENCODED;	74	return 'binhex' if $_[0] == &BH_ENCODED;
76	return 'plaintext' if $_[0] == &PT_ENCODED;	75	return 'plaintext' if $_[0] == &PT_ENCODED;
77	return 'quoted-printable' if $_[0] == &QP_ENCODED;	76	return 'quoted-printable' if $_[0] == &QP_ENCODED;
78	return 'xxencode' if $_[0] == &XX_ENCODED;	77	return 'xxencode' if $_[0] == &XX_ENCODED;
…		…
96		95
97	Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).	96	Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).
98		97
99	=head1 SYNOPSIS	98	=head1 SYNOPSIS
100		99
101	use Convert::UUlib;
102
103	=head1 DESCRIPTION
104
105	Read the file uulibdoc.dvi.gz and the example-decoder source. Sorry - more
106	to come once people use me ;)
107
108	=head1 SMALL EXAMPLE DECODER
109
110	The following code excerpt is a minimal decoder program. It reads all
111	files given on the commandline and decodes any files in it.
112
113	use Convert::UUlib ':all';	100	use Convert::UUlib ':all';
114		101
		102	# read all the files named on the commandline and decode them
		103	# into the CURRENT directory. See below for a longer example.
115	LoadFile($_) for @ARGV;	104	LoadFile $_ for @ARGV;
116
117	for($i=0; $uu=GetFileListItem($i); $i++) {	105	for (my $i = 0; my $uu = GetFileListItem $i; $i++) {
118	$uu->decode if $uu->state & FILE_OK;	106	if ($uu->state & FILE_OK) {
		107	$uu->decode;
		108	print $uu->filename, "\n";
		109	}
119	}	110	}
120		111
121	=head1 LARGE EXAMPLE DECODER	112	=head1 DESCRIPTION
122		113
123	This is the file C<example-decoder> from the distribution, put here	114	Read the file doc/library.pdf from the distribution for in-depth
124	instead of more thorough documentation.	115	information about the C-library used in this interface, and the rest of
		116	this document and especially the non-trivial decoder program at the end.
125		117
126	# decode all the files in the directory uusrc/ and copy	118	=head1 EXPORTED CONSTANTS
127	# the resulting files to uudst/
128		119
129	use Convert::UUlib ':all';	120	=head2 Action code constants
130		121
131	sub namefilter {	122	ACT_IDLE we don't do anything
132	my($path)=@_;	123	ACT_SCANNING scanning an input file
133	$path=~s/^.*[\/\\]//;	124	ACT_DECODING decoding into a temp file
134	$path;	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
		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	=over 4
		209
		210	=item Initialize
		211
		212	Not normally necessary, (re-)initializes the library.
		213
		214	=item CleanUp
		215
		216	Not normally necessary, could be called at the end to release memory
		217	before starting a new decoding round.
		218
		219	=back
		220
		221	=head2 Setting and querying options
		222
		223	=over 4
		224
		225	=item $option = GetOption OPT_xxx
		226
		227	=item SetOption OPT_xxx, opt-value
		228
		229	=back
		230
		231	See the C<OPT_xxx> constants above to see which options exist.
		232
		233	=head2 Setting various callbacks
		234
		235	=over 4
		236
		237	=item SetMsgCallback [callback-function]
		238
		239	=item SetBusyCallback [callback-function]
		240
		241	=item SetFileCallback [callback-function]
		242
		243	=item SetFNameFilter [callback-function]
		244
		245	=back
		246
		247	=head2 Call the currently selected FNameFilter
		248
		249	=over 4
		250
		251	=item $file = FNameFilter $file
		252
		253	=back
		254
		255	=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
		256
		257	=over 4
		258
		259	=item ($retval, $count) = LoadFile $fname, [$id, [$delflag]]
		260
		261	Load the given file and scan it for encoded contents. Optionally tag it
		262	with the given id, and if C<$delflag> is true, delete the file after it is
		263	no longer necessary.
		264
		265	=item $retval = Smerge $pass
		266
		267	If you are desperate, try to call C<Smerge> with increasing C<$pass>
		268	values, beginning at C<0>, to try to merge parts that usually would not
		269	have been merged.
		270
		271	Most probably this will result in garbled files, so never do this by
		272	default.
		273
		274	=item $item = GetFileListItem $item_number
		275
		276	Return the C<$item> structure for the C<$item_number>'th found file, or
		277	C<undef> of no file with that number exists.
		278
		279	The first file has number C<0>, and the series has no holes, so you can
		280	iterate over all files by starting with zero and incrementing until you
		281	hit C<undef>.
		282
		283	=back
		284
		285	=head2 Decoding files
		286
		287	=over 4
		288
		289	=item $retval = $item->rename($newname)
		290
		291	Change the ondisk filename where the decoded file will be saved.
		292
		293	=item $retval = $item->decode_temp
		294
		295	Decode the file into a temporary location, use C<< $item->infile >> to
		296	retrieve the temporary filename.
		297
		298	=item $retval = $item->remove_temp
		299
		300	Remove the temporarily decoded file again.
		301
		302	=item $retval = $item->decode([$target_path])
		303
		304	Decode the file to it's destination, or the given target path.
		305
		306	=item $retval = $item->info(callback-function)
		307
		308	=back
		309
		310	=head2 Querying (and setting) item attributes
		311
		312	=over 4
		313
		314	=item $state = $item->state
		315
		316	=item $mode = $item->mode([newmode])
		317
		318	=item $uudet = $item->uudet
		319
		320	=item $size = $item->size
		321
		322	=item $filename = $item->filename([newfilename})
		323
		324	=item $subfname = $item->subfname
		325
		326	=item $mimeid = $item->mimeid
		327
		328	=item $mimetype = $item->mimetype
		329
		330	=item $binfile = $item->binfile
		331
		332	=back
		333
		334	=head2 Information about source parts
		335
		336	=over 4
		337
		338	=item $parts = $item->parts
		339
		340	Return information about all parts (source files) used to decode the file
		341	as a list of hashrefs with the following structure:
		342
		343	{
		344	partno => <integer describing the part number, starting with 1>,
		345	# the following member sonly exist when they contain useful information
		346	sfname => <local pathname of the file where this part is from>,
		347	filename => <the ondisk filename of the decoded file>,
		348	subfname => <used to cluster postings, possibly the posting filename>,
		349	subject => <the subject of the posting/mail>,
		350	origin => <the possible source (From) address>,
		351	mimetype => <the possible mimetype of the decoded file>,
		352	mimeid => <the id part of the Content-Type>,
135	}	353	}
136		354
137	sub busycb {	355	Usually you are interested mostly the C<sfname> and possibly the C<partno>
138	my($action,$curfile,$partno,$numparts,$percent,$fsize)=@_;	356	and C<filename> members.
139	$_[0]=straction($action);
140	print "busy_callback(",join(",",@_),")\n";
141	0;
142	}
143		357
144	SetOption (OPT_IGNMODE, 1);	358	=back
145	SetOption (OPT_VERBOSE, 1);
146		359
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
200	Action code constants:
201
202	ACT_COPYING ACT_DECODING ACT_ENCODING
203	ACT_IDLE ACT_SCANNING
204
205	File 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
211	Message severity levels:
212
213	MSG_ERROR MSG_FATAL MSG_MESSAGE
214	MSG_NOTE MSG_PANIC MSG_WARNING
215
216	Options:
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
224	Error/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
229	Encoding types:
230
231	B64ENCODED BH_ENCODED PT_ENCODED QP_ENCODED XX_ENCODED
232	UU_ENCODED YENC_ENCODED
233
234	=head1 Exported functions
235
236	Initializing and cleanup (Initialize is automatically called when the
237	module is loaded and allocates quite a bit of memory. CleanUp releases
238	that again).
239
240	Initialize; # not normally necessary
241	CleanUp; # could be called at the end to release memory
242
243	Setting and querying options:
244
245	$option = GetOption OPT_xxx;
246	SetOption OPT_xxx, opt-value;
247
248	Error and action values => stringified:
249
250	$msg = straction ACT_xxx;
251	$msg = strerror RET_xxx;
252
253	Setting various callbacks:
254
255	SetMsgCallback [callback-function];
256	SetBusyCallback [callback-function];
257	SetFileCallback [callback-function];
258	SetFNameFilter [callback-function];
259
260	Call the currently selected FNameFilter:
261
262	$file = FNameFilter $file;
263
264	Loading sourcefiles, optionally fuzzy merge and start decoding:
265
266	($retval, $count) = LoadFile $fname, [$id, [$delflag]];
267	$retval = Smerge $pass;
268	$item = GetFileListItem $item_number;
269
270	The 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
278	Querying (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
290	Totally undocumented and unsupported(!):
291
292	$parts = $item->parts;
293
294	Functions below not documented and not very well tested:	360	=head2 Functions below not documented and not very well tested
295		361
296	int QuickDecode () ;	362	QuickDecode
297	int EncodeMulti () ;	363	EncodeMulti
298	int EncodePartial () ;	364	EncodePartial
299	int EncodeToStream () ;	365	EncodeToStream
300	int EncodeToFile () ;	366	EncodeToFile
301	int E_PrepSingle () ;	367	E_PrepSingle
302	int E_PrepPartial () ;	368	E_PrepPartial
303		369
304	=head2 EXTENSION FUNCTIONS	370	=head2 EXTENSION FUNCTIONS
305		371
306	Functions found in this module but not documented in the uulib documentation:	372	Functions found in this module but not documented in the uulib documentation:
307		373
308	=over 4	374	=over 4
		375
		376	=item $msg = straction ACT_xxx
		377
		378	Return a human readable string representing the given action code.
		379
		380	=item $msg = strerror RET_xxx
		381
		382	Return a human readable string representing the given error code.
		383
		384	=item $str = strencoding xxx_ENCODED
		385
		386	Return the name of the encoding type as a string.
		387
		388	=item $str = strmsglevel MSG_xxx
		389
		390	Returns the message level as a string.
309		391
310	=item SetFileNameCallback $cb	392	=item SetFileNameCallback $cb
311		393
312	Sets (or queries) the FileNameCallback, which is called whenever the	394	Sets (or queries) the FileNameCallback, which is called whenever the
313	decoding library can't find a filename and wants to extract a filename	395	decoding library can't find a filename and wants to extract a filename
…		…
336	return ();	418	return ();
337	}	419	}
338		420
339	=back	421	=back
340		422
		423	=head1 LARGE EXAMPLE DECODER
		424
		425	This is the file C<example-decoder> from the distribution, put here
		426	instead of more thorough documentation.
		427
		428	# decode all the files in the directory uusrc/ and copy
		429	# the resulting files to uudst/
		430
		431	use Convert::UUlib ':all';
		432
		433	sub namefilter {
		434	my($path)=@_;
		435	$path=~s/^.*[\/\\]//;
		436	$path;
		437	}
		438
		439	sub busycb {
		440	my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
		441	$_[0]=straction($action);
		442	print "busy_callback(", (join ",",@_), ")\n";
		443	0;
		444	}
		445
		446	SetOption OPT_IGNMODE, 1;
		447	SetOption OPT_VERBOSE, 1;
		448
		449	# show the three ways you can set callback functions. I normally
		450	# prefer the one with the sub inplace.
		451	SetFNameFilter \&namefilter;
		452
		453	SetBusyCallback "busycb", 333;
		454
		455	SetMsgCallback sub {
		456	my ($msg, $level) = @_;
		457	print uc strmsglevel $_[1], ": $msg\n";
		458	};
		459
		460	# the following non-trivial FileNameCallback takes care
		461	# of some subject lines not detected properly by uulib:
		462	SetFileNameCallback sub {
		463	return unless $_[1]; # skip "Re:"-plies et al.
		464	local $_ = $_[0];
		465
		466	# the following rules are rather effective on some newsgroups,
		467	# like alt.binaries.games.anime, where non-mime, uuencoded data
		468	# is very common
		469
		470	# if we find some *.rar, take it as the filename
		471	return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d\|rar))\s/i;
		472
		473	# one common subject format
		474	return $1 if /- "(.{2,}?\..+?)" (?:yenc )?$\d+\/\d+$/i;
		475
		476	# - filename.par (04/55)
		477	return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?$\d+\/\d+$/i;
		478
		479	# - (xxx) No. 1 sayuri81.jpg 756565 bytes
		480	# - (20 files) No.17 Roseanne.jpg [2/2]
		481	return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
		482
		483	# otherwise just pass what we have
		484	return ();
		485	};
		486
		487	# now read all files in the directory uusrc/*
		488	for(<uusrc/*>) {
		489	my($retval,$count)=LoadFile ($_, $_, 1);
		490	print "file($_), status(", strerror $retval, ") parts($count)\n";
		491	}
		492
		493	SetOption OPT_SAVEPATH, "uudst/";
		494
		495	# now wade through all files and their source parts
		496	$i = 0;
		497	while ($uu = GetFileListItem($i)) {
		498	$i++;
		499	print "file nr. $i";
		500	print " state ", $uu->state;
		501	print " mode ", $uu->mode;
		502	print " uudet ", strencoding $uu->uudet;
		503	print " size ", $uu->size;
		504	print " filename ", $uu->filename;
		505	print " subfname ", $uu->subfname;
		506	print " mimeid ", $uu->mimeid;
		507	print " mimetype ", $uu->mimetype;
		508	print "\n";
		509
		510	# print additional info about all parts
		511	for ($uu->parts) {
		512	while (my ($k, $v) = each %$_) {
		513	print "$k > $v, ";
		514	}
		515	print "\n";
		516	}
		517
		518	$uu->decode_temp;
		519	print " temporarily decoded to ", $uu->binfile, "\n";
		520	$uu->remove_temp;
		521
		522	print strerror $uu->decode;
		523	print " saved as uudst/", $uu->filename, "\n";
		524	}
		525
		526	print "cleanup...\n";
		527
		528	CleanUp();
		529
341	=head1 AUTHOR	530	=head1 AUTHOR
342		531
343	Marc Lehmann <pcg@goof.com>, the original uulib library was written by	532	Marc Lehmann <pcg@goof.com>, the original uulib library was written
344	Frank Pilhofer <fp@informatik.uni-frankfurt.de>.	533	by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
		534	bugfixed by Marc Lehmann.
345		535
346	=head1 SEE ALSO	536	=head1 SEE ALSO
347		537
348	perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/.	538	perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/.
349		539

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing Convert-UUlib/UUlib.pm (file contents): Revision 1.9 by root, Sat Apr 6 02:28:35 2002 UTC vs. Revision 1.13 by root, Tue Oct 15 23:20:29 2002 UTC

Diff Legend

Comparing Convert-UUlib/UUlib.pm (file contents):
Revision 1.9 by root, Sat Apr 6 02:28:35 2002 UTC vs.
Revision 1.13 by root, Tue Oct 15 23:20:29 2002 UTC