Convert-UUlib/UUlib.pm

package Convert::UUlib;

use Carp;

require Exporter;
require DynaLoader;

$VERSION = 0.31;

@ISA = qw(Exporter DynaLoader);

@_consts = qw(
        ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING

        FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA
        FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE

        MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING

        OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT
        OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB
        OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
        OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT

        RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
        RET_NOEND RET_NOMEM RET_OK RET_UNSUP

        B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
        XX_ENCODED UU_ENCODED YENC_ENCODED
);

@_funcs = qw(
        Initialize CleanUp GetOption SetOption strerror SetMsgCallback
        SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
        FNameFilter LoadFile GetFileListItem RenameFile DecodeToTemp
        RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
        EncodePartial EncodeToStream EncodeToFile E_PrepSingle
        E_PrepPartial

        straction strencoding strmsglevel
);

@EXPORT = @_consts;
@EXPORT_OK = @_funcs;
%EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);

bootstrap Convert::UUlib $VERSION;

Initialize();

# not when < 5.005_6x
# END { CleanUp() }

for (@_consts) {
   my $constant = constant($_);
   *$_ = sub () { $constant };
}

# action code -> string mapping
sub straction($) {
   return 'copying'     if $_[0] == &ACT_COPYING;
   return 'decoding'    if $_[0] == &ACT_DECODING;
   return 'encoding'    if $_[0] == &ACT_ENCODING;
   return 'idle'        if $_[0] == &ACT_IDLE;
   return 'scanning'    if $_[0] == &ACT_SCANNING;
   'unknown';
}

# encoding type -> string mapping
sub strencoding($) {
   return 'uuencode'            if $_[0] == &UU_ENCODED;
   return 'base64'              if $_[0] == &B64_ENCODED;
   return 'yenc'                if $_[0] == &YENC_ENCODED;
   return 'binhex'              if $_[0] == &BH_ENCODED;
   return 'plaintext'           if $_[0] == &PT_ENCODED;
   return 'quoted-printable'    if $_[0] == &QP_ENCODED;
   return 'xxencode'            if $_[0] == &XX_ENCODED;
   'unknown';
}

sub strmsglevel($) {
   return 'message'     if $_[0] == &MSG_MESSAGE;
   return 'note'        if $_[0] == &MSG_NOTE;
   return 'warning'     if $_[0] == &MSG_WARNING;
   return 'error'       if $_[0] == &MSG_ERROR;
   return 'panic'       if $_[0] == &MSG_PANIC;
   return 'fatal'       if $_[0] == &MSG_FATAL;
   'unknown';
}

1;
__END__

=head1 NAME

Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).

=head1 SYNOPSIS

 use Convert::UUlib ':all';
 
 # read all the files named on the commandline and decode them
 # into the CURRENT directory. See below for a longer example.
 LoadFile $_ for @ARGV;
 for (my $i = 0; my $uu = GetFileListItem $i; $i++) {
    if ($uu->state & FILE_OK) {
      $uu->decode;
      print $uu->filename, "\n";
    }
 }

=head1 DESCRIPTION

Read the file doc/library.pdf from the distribution for in-depth
information about the C-library used in this interface, and the rest of
this document and especially the non-trivial decoder program at the end.

=head1 EXPORTED CONSTANTS

=head2 Action code constants

  ACT_IDLE      we don't do anything
  ACT_SCANNING  scanning an input file
  ACT_DECODING  decoding into a temp file
  ACT_COPYING   copying temp to target
  ACT_ENCODING  encoding a file

=head2 Message severity levels

  MSG_MESSAGE   just a message, nothing important
  MSG_NOTE      something that should be noticed
  MSG_WARNING   important msg, processing continues
  MSG_ERROR     processing has been terminated
  MSG_FATAL     decoder cannot process further requests
  MSG_PANIC     recovery impossible, app must terminate

=head2 Options

  OPT_VERSION   version number MAJOR.MINORplPATCH (ro)
  OPT_FAST      assumes only one part per file
  OPT_DUMBNESS  switch off the program's intelligence
  OPT_BRACKPOL  give numbers in [] higher precendence
  OPT_VERBOSE   generate informative messages
  OPT_DESPERATE try to decode incomplete files
  OPT_IGNREPLY  ignore RE:plies (off by default)
  OPT_OVERWRITE whether it's OK to overwrite ex. files
  OPT_SAVEPATH  prefix to save-files on disk
  OPT_IGNMODE   ignore the original file mode
  OPT_DEBUG     print messages with FILE/LINE info
  OPT_ERRNO     get last error code for RET_IOERR (ro)
  OPT_PROGRESS  retrieve progress information
  OPT_USETEXT   handle text messages
  OPT_PREAMB    handle Mime preambles/epilogues
  OPT_TINYB64   detect short B64 outside of Mime
  OPT_ENCEXT    extension for single-part encoded files
  OPT_REMOVE    remove input files after decoding (dangerous)
  OPT_MOREMIME  strict MIME adherence
  OPT_DOTDOT    .. unescaping has not yet been done on input files

=head2 Result/Error codes

  RET_OK        everything went fine
  RET_IOERR     I/O Error - examine errno
  RET_NOMEM     not enough memory
  RET_ILLVAL    illegal value for operation
  RET_NODATA    decoder didn't find any data
  RET_NOEND     encoded data wasn't ended properly
  RET_UNSUP     unsupported function (encoding)
  RET_EXISTS    file exists (decoding)
  RET_CONT      continue -- special from ScanPart
  RET_CANCEL    operation canceled

=head2 File States

 This code is zero, i.e. "false":

  UUFILE_READ   Read in, but not further processed

 The following state codes are or'ed together:

  FILE_MISPART  Missing Part(s) detected
  FILE_NOBEGIN  No 'begin' found
  FILE_NOEND    No 'end' found
  FILE_NODATA   File does not contain valid uudata
  FILE_OK       All Parts found, ready to decode
  FILE_ERROR    Error while decoding
  FILE_DECODED  Successfully decoded
  FILE_TMPFILE  Temporary decoded file exists

=head2 Encoding types

  UU_ENCODED    UUencoded data
  B64_ENCODED   Mime-Base64 data
  XX_ENCODED    XXencoded data
  BH_ENCODED    Binhex encoded
  PT_ENCODED    Plain-Text encoded (MIME)
  QP_ENCODED    Quoted-Printable (MIME)
  YENC_ENCODED  yEnc encoded (non-MIME)

=head1 EXPORTED FUNCTIONS

=head2 Initializing and cleanup

Initialize is automatically called when the module is loaded and allocates
quite a small amount of memory for todays machines ;) CleanUp releases that
again.

On my machine, a fairly complete decode with DBI backend needs about 10MB
RSS to decode 20000 files.

=over 4

=item Initialize

Not normally necessary, (re-)initializes the library.

=item CleanUp

Not normally necessary, could be called at the end to release memory
before starting a new decoding round.

=back

=head2 Setting and querying options

=over 4

=item $option = GetOption OPT_xxx

=item SetOption OPT_xxx, opt-value

=back

See the C<OPT_xxx> constants above to see which options exist.

=head2 Setting various callbacks

=over 4

=item SetMsgCallback [callback-function]

=item SetBusyCallback [callback-function]

=item SetFileCallback [callback-function]

=item SetFNameFilter [callback-function]

=back

=head2 Call the currently selected FNameFilter

=over 4

=item $file = FNameFilter $file

=back

=head2 Loading sourcefiles, optionally fuzzy merge and start decoding

=over 4

=item ($retval, $count) = LoadFile $fname, [$id, [$delflag]]

Load the given file and scan it for encoded contents. Optionally tag it
with the given id, and if C<$delflag> is true, delete the file after it is
no longer necessary.

=item $retval = Smerge $pass

If you are desperate, try to call C<Smerge> with increasing C<$pass>
values, beginning at C<0>, to try to merge parts that usually would not
have been merged.

Most probably this will result in garbled files, so never do this by
default.

=item $item = GetFileListItem $item_number

Return the C<$item> structure for the C<$item_number>'th found file, or
C<undef> of no file with that number exists.

The first file has number C<0>, and the series has no holes, so you can
iterate over all files by starting with zero and incrementing until you
hit C<undef>.

=back

=head2 Decoding files

=over 4

=item $retval = $item->rename($newname)

Change the ondisk filename where the decoded file will be saved.

=item $retval = $item->decode_temp

Decode the file into a temporary location, use C<< $item->infile >> to
retrieve the temporary filename.

=item $retval = $item->remove_temp

Remove the temporarily decoded file again.

=item $retval = $item->decode([$target_path])

Decode the file to it's destination, or the given target path.

=item $retval = $item->info(callback-function)

=back

=head2 Querying (and setting) item attributes

=over 4

=item $state    = $item->state

=item $mode     = $item->mode([newmode])

=item $uudet    = $item->uudet

=item $size     = $item->size

=item $filename = $item->filename([newfilename})

=item $subfname = $item->subfname

=item $mimeid   = $item->mimeid

=item $mimetype = $item->mimetype

=item $binfile  = $item->binfile

=back

=head2 Information about source parts

=over 4

=item $parts = $item->parts

Return information about all parts (source files) used to decode the file
as a list of hashrefs with the following structure:

 {
   partno   => <integer describing the part number, starting with 1>,
   # the following member sonly exist when they contain useful information
   sfname   => <local pathname of the file where this part is from>,
   filename => <the ondisk filename of the decoded file>,
   subfname => <used to cluster postings, possibly the posting filename>,
   subject  => <the subject of the posting/mail>,
   origin   => <the possible source (From) address>,
   mimetype => <the possible mimetype of the decoded file>,
   mimeid   => <the id part of the Content-Type>,
 }

Usually you are interested mostly the C<sfname> and possibly the C<partno>
and C<filename> members.

=back

=head2 Functions below not documented and not very well tested

  QuickDecode
  EncodeMulti
  EncodePartial
  EncodeToStream
  EncodeToFile
  E_PrepSingle
  E_PrepPartial

=head2 EXTENSION FUNCTIONS

Functions found in this module but not documented in the uulib documentation:

=over 4

=item $msg = straction ACT_xxx

Return a human readable string representing the given action code.

=item $msg = strerror RET_xxx

Return a human readable string representing the given error code.

=item $str = strencoding xxx_ENCODED

Return the name of the encoding type as a string.

=item $str = strmsglevel MSG_xxx

Returns the message level as a string.

=item SetFileNameCallback $cb

Sets (or queries) the FileNameCallback, which is called whenever the
decoding library can't find a filename and wants to extract a filename
from the subject line of a posting. The callback will be called with
two arguments, the subject line and the current candidate for the
filename. The latter argument can be C<undef>, which means that no
filename could be found (and likely no one exists, so it is safe to also
return C<undef> in this case). If it doesn't return anything (not even
C<undef>!), then nothing happens, so this is a no-op callback:

   sub cb {
      return ();
   }

If it returns C<undef>, then this indicates that no filename could be
found. In all other cases, the return value is taken to be the filename.

This is a slightly more useful callback:

  sub cb {
     return unless $_[1]; # skip "Re:"-plies et al.
     my ($subject, $filename) = @_;
     # if we find some *.rar, take it
     return $1 if $subject =~ /(\w+\.rar)/;
     # otherwise just pass what we have
     return ();
  }

=back

=head1 LARGE EXAMPLE DECODER

This is the file C<example-decoder> from the distribution, put here
instead of more thorough documentation.

 # decode all the files in the directory uusrc/ and copy
 # the resulting files to uudst/

 use Convert::UUlib ':all';

 sub namefilter {
    my($path)=@_;
    $path=~s/^.*[\/\\]//;
    $path;
 }

 sub busycb {
    my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
    $_[0]=straction($action);
    print "busy_callback(", (join ",",@_), ")\n";
    0;
 }

 SetOption OPT_IGNMODE, 1;
 SetOption OPT_VERBOSE, 1;

 # show the three ways you can set callback functions. I normally
 # prefer the one with the sub inplace.
 SetFNameFilter \&namefilter;

 SetBusyCallback "busycb", 333;

 SetMsgCallback sub {
    my ($msg, $level) = @_;
    print uc strmsglevel $_[1], ": $msg\n";
 };

 # the following non-trivial FileNameCallback takes care
 # of some subject lines not detected properly by uulib:
 SetFileNameCallback sub {
    return unless $_[1]; # skip "Re:"-plies et al.
    local $_ = $_[0];

    # the following rules are rather effective on some newsgroups,
    # like alt.binaries.games.anime, where non-mime, uuencoded data
    # is very common

    # if we find some *.rar, take it as the filename
    return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d|rar))\s/i;

    # one common subject format
    return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;

    # - filename.par (04/55)
    return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;

    # - (xxx) No. 1 sayuri81.jpg 756565 bytes
    # - (20 files) No.17 Roseanne.jpg [2/2]
    return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;

    # otherwise just pass what we have
    return ();
 };

 # now read all files in the directory uusrc/*
 for(<uusrc/*>) {
    my($retval,$count)=LoadFile ($_, $_, 1);
    print "file($_), status(", strerror $retval, ") parts($count)\n";
 }

 SetOption OPT_SAVEPATH, "uudst/";

 # now wade through all files and their source parts
 $i = 0;
 while ($uu = GetFileListItem($i)) {
    $i++;
    print "file nr. $i";
    print " state ", $uu->state;
    print " mode ", $uu->mode;
    print " uudet ", strencoding $uu->uudet;
    print " size ", $uu->size;
    print " filename ", $uu->filename;
    print " subfname ", $uu->subfname;
    print " mimeid ", $uu->mimeid;
    print " mimetype ", $uu->mimetype;
    print "\n";

    # print additional info about all parts
    for ($uu->parts) {
       while (my ($k, $v) = each %$_) {
          print "$k > $v, ";
       }
       print "\n";
    }

    $uu->decode_temp;
    print " temporarily decoded to ", $uu->binfile, "\n";
    $uu->remove_temp;

    print strerror $uu->decode;
    print " saved as uudst/", $uu->filename, "\n";
 }

 print "cleanup...\n";

 CleanUp();

=head1 AUTHOR

Marc Lehmann <pcg@goof.com>, the original uulib library was written
by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
bugfixed by Marc Lehmann.

=head1 SEE ALSO

perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/.

=cut
Revision:	1.14
Committed:	Tue Oct 15 23:34:41 2002 UTC (21 years, 7 months ago) by root
Branch:	MAIN
Changes since 1.13:	+4 -1 lines
Log Message:	* empty log message *
#	User	Rev	Content
1	root	1.1	package Convert::UUlib;
2
3			use Carp;
4
5			require Exporter;
6			require DynaLoader;
7
8	root	1.13	$VERSION = 0.31;
9	root	1.1
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	root	1.8	OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT
24	root	1.1
25			RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
26			RET_NOEND RET_NOMEM RET_OK RET_UNSUP
27
28	root	1.11	B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
29	root	1.5	XX_ENCODED UU_ENCODED YENC_ENCODED
30	root	1.1	);
31
32			@_funcs = qw(
33	root	1.6	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	root	1.1
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 $_[0] == &ACT_SCANNING;
66	root	1.5	'unknown';
67	root	1.1	}
68
69			# encoding type -> string mapping
70			sub strencoding($) {
71	root	1.5	return 'uuencode' if $_[0] == &UU_ENCODED;
72	root	1.11	return 'base64' if $_[0] == &B64_ENCODED;
73	root	1.5	return 'yenc' if $_[0] == &YENC_ENCODED;
74	root	1.1	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 $_[0] == &XX_ENCODED;
78	root	1.5	'unknown';
79	root	1.1	}
80
81			sub strmsglevel($) {
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	root	1.5	'unknown';
89	root	1.1	}
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	root	1.11	# read all the files named on the commandline and decode them
103	root	1.13	# 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	root	1.1	}
111
112	root	1.11	=head1 DESCRIPTION
113	root	1.1
114	root	1.11	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	root	1.14	OPT_REMOVE remove input files after decoding (dangerous)
157	root	1.11	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	root	1.13	The following state codes are or'ed together:
180	root	1.11
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	root	1.1
200	root	1.11	=head1 EXPORTED FUNCTIONS
201	root	1.1
202	root	1.11	=head2 Initializing and cleanup
203	root	1.1
204	root	1.11	Initialize is automatically called when the module is loaded and allocates
205	root	1.13	quite a small amount of memory for todays machines ;) CleanUp releases that
206			again.
207	root	1.14
208			On my machine, a fairly complete decode with DBI backend needs about 10MB
209			RSS to decode 20000 files.
210	root	1.1
211	root	1.13	=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	root	1.1
224	root	1.11	=head2 Setting and querying options
225	root	1.1
226	root	1.13	=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	root	1.1
236	root	1.11	=head2 Setting various callbacks
237	root	1.1
238	root	1.13	=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	root	1.1
250	root	1.11	=head2 Call the currently selected FNameFilter
251	root	1.1
252	root	1.13	=over 4
253
254			=item $file = FNameFilter $file
255
256			=back
257	root	1.1
258	root	1.11	=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
259	root	1.1
260	root	1.13	=over 4
261
262			=item ($retval, $count) = LoadFile $fname, [$id, [$delflag]]
263
264			Load the given file and scan it for encoded contents. Optionally tag it
265			with the given id, and if C<$delflag> is true, delete the file after it is
266			no longer necessary.
267
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.
276
277			=item $item = GetFileListItem $item_number
278
279			Return the C<$item> structure for the C<$item_number>'th found file, or
280			C<undef> of no file with that number exists.
281
282			The first file has number C<0>, and the series has no holes, so you can
283			iterate over all files by starting with zero and incrementing until you
284			hit C<undef>.
285
286			=back
287
288			=head2 Decoding files
289
290			=over 4
291
292			=item $retval = $item->rename($newname)
293
294			Change the ondisk filename where the decoded file will be saved.
295
296			=item $retval = $item->decode_temp
297
298			Decode the file into a temporary location, use C<< $item->infile >> to
299			retrieve the temporary filename.
300
301			=item $retval = $item->remove_temp
302
303			Remove the temporarily decoded file again.
304
305			=item $retval = $item->decode([$target_path])
306
307			Decode the file to it's destination, or the given target path.
308
309			=item $retval = $item->info(callback-function)
310
311			=back
312	root	1.1
313	root	1.11	=head2 Querying (and setting) item attributes
314	root	1.1
315	root	1.13	=over 4
316
317			=item $state = $item->state
318
319			=item $mode = $item->mode([newmode])
320
321			=item $uudet = $item->uudet
322
323			=item $size = $item->size
324
325			=item $filename = $item->filename([newfilename})
326
327			=item $subfname = $item->subfname
328
329			=item $mimeid = $item->mimeid
330
331			=item $mimetype = $item->mimetype
332
333			=item $binfile = $item->binfile
334
335			=back
336
337			=head2 Information about source parts
338
339			=over 4
340
341			=item $parts = $item->parts
342
343			Return information about all parts (source files) used to decode the file
344			as a list of hashrefs with the following structure:
345
346			{
347			partno => <integer describing the part number, starting with 1>,
348			# the following member sonly exist when they contain useful information
349			sfname => <local pathname of the file where this part is from>,
350			filename => <the ondisk filename of the decoded file>,
351			subfname => <used to cluster postings, possibly the posting filename>,
352			subject => <the subject of the posting/mail>,
353			origin => <the possible source (From) address>,
354			mimetype => <the possible mimetype of the decoded file>,
355			mimeid => <the id part of the Content-Type>,
356			}
357	root	1.1
358	root	1.13	Usually you are interested mostly the C<sfname> and possibly the C<partno>
359			and C<filename> members.
360	root	1.1
361	root	1.13	=back
362	root	1.1
363	root	1.11	=head2 Functions below not documented and not very well tested
364	root	1.1
365	root	1.11	QuickDecode
366			EncodeMulti
367			EncodePartial
368			EncodeToStream
369			EncodeToFile
370			E_PrepSingle
371			E_PrepPartial
372	root	1.6
373			=head2 EXTENSION FUNCTIONS
374
375			Functions found in this module but not documented in the uulib documentation:
376
377			=over 4
378
379	root	1.11	=item $msg = straction ACT_xxx
380
381			Return a human readable string representing the given action code.
382
383			=item $msg = strerror RET_xxx
384
385			Return a human readable string representing the given error code.
386
387			=item $str = strencoding xxx_ENCODED
388
389			Return the name of the encoding type as a string.
390
391			=item $str = strmsglevel MSG_xxx
392
393			Returns the message level as a string.
394
395	root	1.6	=item SetFileNameCallback $cb
396
397			Sets (or queries) the FileNameCallback, which is called whenever the
398			decoding library can't find a filename and wants to extract a filename
399			from the subject line of a posting. The callback will be called with
400			two arguments, the subject line and the current candidate for the
401			filename. The latter argument can be C<undef>, which means that no
402			filename could be found (and likely no one exists, so it is safe to also
403			return C<undef> in this case). If it doesn't return anything (not even
404			C<undef>!), then nothing happens, so this is a no-op callback:
405
406			sub cb {
407			return ();
408			}
409
410			If it returns C<undef>, then this indicates that no filename could be
411			found. In all other cases, the return value is taken to be the filename.
412
413			This is a slightly more useful callback:
414
415			sub cb {
416			return unless $_[1]; # skip "Re:"-plies et al.
417			my ($subject, $filename) = @_;
418			# if we find some *.rar, take it
419			return $1 if $subject =~ /(\w+\.rar)/;
420			# otherwise just pass what we have
421			return ();
422			}
423
424			=back
425	root	1.1
426	root	1.11	=head1 LARGE EXAMPLE DECODER
427
428			This is the file C<example-decoder> from the distribution, put here
429			instead of more thorough documentation.
430
431			# decode all the files in the directory uusrc/ and copy
432			# the resulting files to uudst/
433
434			use Convert::UUlib ':all';
435
436			sub namefilter {
437			my($path)=@_;
438			$path=~s/^.*[\/\\]//;
439			$path;
440			}
441
442			sub busycb {
443			my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
444			$_[0]=straction($action);
445			print "busy_callback(", (join ",",@_), ")\n";
446			0;
447			}
448
449			SetOption OPT_IGNMODE, 1;
450			SetOption OPT_VERBOSE, 1;
451
452			# show the three ways you can set callback functions. I normally
453			# prefer the one with the sub inplace.
454			SetFNameFilter \&namefilter;
455
456			SetBusyCallback "busycb", 333;
457
458			SetMsgCallback sub {
459			my ($msg, $level) = @_;
460			print uc strmsglevel $_[1], ": $msg\n";
461			};
462
463			# the following non-trivial FileNameCallback takes care
464			# of some subject lines not detected properly by uulib:
465			SetFileNameCallback sub {
466			return unless $_[1]; # skip "Re:"-plies et al.
467			local $_ = $_[0];
468
469			# the following rules are rather effective on some newsgroups,
470			# like alt.binaries.games.anime, where non-mime, uuencoded data
471			# is very common
472
473			# if we find some *.rar, take it as the filename
474			return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d\|rar))\s/i;
475
476			# one common subject format
477			return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
478
479			# - filename.par (04/55)
480			return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
481
482			# - (xxx) No. 1 sayuri81.jpg 756565 bytes
483			# - (20 files) No.17 Roseanne.jpg [2/2]
484			return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
485
486			# otherwise just pass what we have
487			return ();
488			};
489
490			# now read all files in the directory uusrc/*
491			for(<uusrc/*>) {
492			my($retval,$count)=LoadFile ($_, $_, 1);
493			print "file($_), status(", strerror $retval, ") parts($count)\n";
494			}
495
496			SetOption OPT_SAVEPATH, "uudst/";
497
498			# now wade through all files and their source parts
499			$i = 0;
500			while ($uu = GetFileListItem($i)) {
501			$i++;
502			print "file nr. $i";
503			print " state ", $uu->state;
504			print " mode ", $uu->mode;
505			print " uudet ", strencoding $uu->uudet;
506			print " size ", $uu->size;
507			print " filename ", $uu->filename;
508			print " subfname ", $uu->subfname;
509			print " mimeid ", $uu->mimeid;
510			print " mimetype ", $uu->mimetype;
511			print "\n";
512
513			# print additional info about all parts
514			for ($uu->parts) {
515			while (my ($k, $v) = each %$_) {
516			print "$k > $v, ";
517			}
518			print "\n";
519			}
520
521			$uu->decode_temp;
522			print " temporarily decoded to ", $uu->binfile, "\n";
523			$uu->remove_temp;
524
525			print strerror $uu->decode;
526			print " saved as uudst/", $uu->filename, "\n";
527			}
528
529			print "cleanup...\n";
530
531			CleanUp();
532
533	root	1.1	=head1 AUTHOR
534
535	root	1.11	Marc Lehmann <pcg@goof.com>, the original uulib library was written
536			by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
537			bugfixed by Marc Lehmann.
538	root	1.1
539			=head1 SEE ALSO
540
541			perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/.
542
543			=cut