Convert-UUlib/UUlib.pm

package Convert::UUlib;

no warnings;
use strict;

use Carp;

require Exporter;
require DynaLoader;

our $VERSION = '1.12';

our @ISA = qw(Exporter DynaLoader);

our @_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_RBUF OPT_WBUF
        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
);

our @_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
);

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

bootstrap Convert::UUlib $VERSION;

Initialize();

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

for (@_consts) {
   my $constant = constant($_);
   no strict 'refs';
   *$_ = 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
  OPT_RBUF      set default read I/O buffer size in bytes *EXPERIMENTAL*
  OPT_WBUF      set default write I/O buffer size in bytes *EXPERIMENTAL*

=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, [$delflag, [$partno]]]

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. If you are certain of the part number, you can
specify it as the last argument.

A better (usually faster) way of doing this is using the C<SetFNameFilter>
functionality.

=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.

   #!/usr/bin/perl

   # 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_RBUF, 128*1024;
   SetOption OPT_WBUF, 1024*1024;
   SetOption OPT_IGNMODE, 1;
   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];

         return $1 if /(\S+\s+IMG_\d+.jpg)/i;

      # 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 )?\[/;

      # try to detect some common forms of filenames
      return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;

      # otherwise just pass what we have
      ()
   };

   # 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";
      }

      print $uu->filename;

      $uu->remove_temp;

      if (my $err = $uu->decode ()) {
         print ", ", strerror $err, "\n";
      } else {
         print ", saved as uudst/", $uu->filename, "\n";
      }
   }

   print "cleanup...\n";

   CleanUp;

=head1 AUTHOR

Marc Lehmann <schmorp@schmorp.de>, 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:	1.32
Committed:	Mon Oct 13 12:12:56 2008 UTC (15 years, 7 months ago) by root
Branch:	MAIN
CVS Tags:	rel-1_12
Changes since 1.31:	+106 -91 lines
Log Message:	1.12
#	Content
1	package Convert::UUlib;
2
3	no warnings;
4	use strict;
5
6	use Carp;
7
8	require Exporter;
9	require DynaLoader;
10
11	our $VERSION = '1.12';
12
13	our @ISA = qw(Exporter DynaLoader);
14
15	our @_consts = qw(
16	ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING
17
18	FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA
19	FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE
20
21	MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING
22
23	OPT_RBUF OPT_WBUF
24	OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT
25	OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB
26	OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
27	OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT
28
29	RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
30	RET_NOEND RET_NOMEM RET_OK RET_UNSUP
31
32	B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
33	XX_ENCODED UU_ENCODED YENC_ENCODED
34	);
35
36	our @_funcs = qw(
37	Initialize CleanUp GetOption SetOption strerror SetMsgCallback
38	SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
39	FNameFilter LoadFile GetFileListItem RenameFile DecodeToTemp
40	RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
41	EncodePartial EncodeToStream EncodeToFile E_PrepSingle
42	E_PrepPartial
43
44	straction strencoding strmsglevel
45	);
46
47	our @EXPORT = @_consts;
48	our @EXPORT_OK = @_funcs;
49	our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);
50
51	bootstrap Convert::UUlib $VERSION;
52
53	Initialize();
54
55	# not when < 5.005_6x
56	# END { CleanUp() }
57
58	for (@_consts) {
59	my $constant = constant($_);
60	no strict 'refs';
61	*$_ = sub () { $constant };
62	}
63
64	# action code -> string mapping
65	sub straction($) {
66	return 'copying' if $_[0] == &ACT_COPYING;
67	return 'decoding' if $_[0] == &ACT_DECODING;
68	return 'encoding' if $_[0] == &ACT_ENCODING;
69	return 'idle' if $_[0] == &ACT_IDLE;
70	return 'scanning' if $_[0] == &ACT_SCANNING;
71	'unknown';
72	}
73
74	# encoding type -> string mapping
75	sub strencoding($) {
76	return 'uuencode' if $_[0] == &UU_ENCODED;
77	return 'base64' if $_[0] == &B64_ENCODED;
78	return 'yenc' if $_[0] == &YENC_ENCODED;
79	return 'binhex' if $_[0] == &BH_ENCODED;
80	return 'plaintext' if $_[0] == &PT_ENCODED;
81	return 'quoted-printable' if $_[0] == &QP_ENCODED;
82	return 'xxencode' if $_[0] == &XX_ENCODED;
83	'unknown';
84	}
85
86	sub strmsglevel($) {
87	return 'message' if $_[0] == &MSG_MESSAGE;
88	return 'note' if $_[0] == &MSG_NOTE;
89	return 'warning' if $_[0] == &MSG_WARNING;
90	return 'error' if $_[0] == &MSG_ERROR;
91	return 'panic' if $_[0] == &MSG_PANIC;
92	return 'fatal' if $_[0] == &MSG_FATAL;
93	'unknown';
94	}
95
96	1;
97	__END__
98
99	=head1 NAME
100
101	Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).
102
103	=head1 SYNOPSIS
104
105	use Convert::UUlib ':all';
106
107	# read all the files named on the commandline and decode them
108	# into the CURRENT directory. See below for a longer example.
109	LoadFile $_ for @ARGV;
110	for (my $i = 0; my $uu = GetFileListItem $i; $i++) {
111	if ($uu->state & FILE_OK) {
112	$uu->decode;
113	print $uu->filename, "\n";
114	}
115	}
116
117	=head1 DESCRIPTION
118
119	Read the file doc/library.pdf from the distribution for in-depth
120	information about the C-library used in this interface, and the rest of
121	this document and especially the non-trivial decoder program at the end.
122
123	=head1 EXPORTED CONSTANTS
124
125	=head2 Action code constants
126
127	ACT_IDLE we don't do anything
128	ACT_SCANNING scanning an input file
129	ACT_DECODING decoding into a temp file
130	ACT_COPYING copying temp to target
131	ACT_ENCODING encoding a file
132
133	=head2 Message severity levels
134
135	MSG_MESSAGE just a message, nothing important
136	MSG_NOTE something that should be noticed
137	MSG_WARNING important msg, processing continues
138	MSG_ERROR processing has been terminated
139	MSG_FATAL decoder cannot process further requests
140	MSG_PANIC recovery impossible, app must terminate
141
142	=head2 Options
143
144	OPT_VERSION version number MAJOR.MINORplPATCH (ro)
145	OPT_FAST assumes only one part per file
146	OPT_DUMBNESS switch off the program's intelligence
147	OPT_BRACKPOL give numbers in [] higher precendence
148	OPT_VERBOSE generate informative messages
149	OPT_DESPERATE try to decode incomplete files
150	OPT_IGNREPLY ignore RE:plies (off by default)
151	OPT_OVERWRITE whether it's OK to overwrite ex. files
152	OPT_SAVEPATH prefix to save-files on disk
153	OPT_IGNMODE ignore the original file mode
154	OPT_DEBUG print messages with FILE/LINE info
155	OPT_ERRNO get last error code for RET_IOERR (ro)
156	OPT_PROGRESS retrieve progress information
157	OPT_USETEXT handle text messages
158	OPT_PREAMB handle Mime preambles/epilogues
159	OPT_TINYB64 detect short B64 outside of Mime
160	OPT_ENCEXT extension for single-part encoded files
161	OPT_REMOVE remove input files after decoding (dangerous)
162	OPT_MOREMIME strict MIME adherence
163	OPT_DOTDOT ".."-unescaping has not yet been done on input files
164	OPT_RBUF set default read I/O buffer size in bytes EXPERIMENTAL
165	OPT_WBUF set default write I/O buffer size in bytes EXPERIMENTAL
166
167	=head2 Result/Error codes
168
169	RET_OK everything went fine
170	RET_IOERR I/O Error - examine errno
171	RET_NOMEM not enough memory
172	RET_ILLVAL illegal value for operation
173	RET_NODATA decoder didn't find any data
174	RET_NOEND encoded data wasn't ended properly
175	RET_UNSUP unsupported function (encoding)
176	RET_EXISTS file exists (decoding)
177	RET_CONT continue -- special from ScanPart
178	RET_CANCEL operation canceled
179
180	=head2 File States
181
182	This code is zero, i.e. "false":
183
184	UUFILE_READ Read in, but not further processed
185
186	The following state codes are or'ed together:
187
188	FILE_MISPART Missing Part(s) detected
189	FILE_NOBEGIN No 'begin' found
190	FILE_NOEND No 'end' found
191	FILE_NODATA File does not contain valid uudata
192	FILE_OK All Parts found, ready to decode
193	FILE_ERROR Error while decoding
194	FILE_DECODED Successfully decoded
195	FILE_TMPFILE Temporary decoded file exists
196
197	=head2 Encoding types
198
199	UU_ENCODED UUencoded data
200	B64_ENCODED Mime-Base64 data
201	XX_ENCODED XXencoded data
202	BH_ENCODED Binhex encoded
203	PT_ENCODED Plain-Text encoded (MIME)
204	QP_ENCODED Quoted-Printable (MIME)
205	YENC_ENCODED yEnc encoded (non-MIME)
206
207	=head1 EXPORTED FUNCTIONS
208
209	=head2 Initializing and cleanup
210
211	Initialize is automatically called when the module is loaded and allocates
212	quite a small amount of memory for todays machines ;) CleanUp releases that
213	again.
214
215	On my machine, a fairly complete decode with DBI backend needs about 10MB
216	RSS to decode 20000 files.
217
218	=over 4
219
220	=item Initialize
221
222	Not normally necessary, (re-)initializes the library.
223
224	=item CleanUp
225
226	Not normally necessary, could be called at the end to release memory
227	before starting a new decoding round.
228
229	=back
230
231	=head2 Setting and querying options
232
233	=over 4
234
235	=item $option = GetOption OPT_xxx
236
237	=item SetOption OPT_xxx, opt-value
238
239	=back
240
241	See the C<OPT_xxx> constants above to see which options exist.
242
243	=head2 Setting various callbacks
244
245	=over 4
246
247	=item SetMsgCallback [callback-function]
248
249	=item SetBusyCallback [callback-function]
250
251	=item SetFileCallback [callback-function]
252
253	=item SetFNameFilter [callback-function]
254
255	=back
256
257	=head2 Call the currently selected FNameFilter
258
259	=over 4
260
261	=item $file = FNameFilter $file
262
263	=back
264
265	=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
266
267	=over 4
268
269	=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
270
271	Load the given file and scan it for encoded contents. Optionally tag it
272	with the given id, and if C<$delflag> is true, delete the file after it
273	is no longer necessary. If you are certain of the part number, you can
274	specify it as the last argument.
275
276	A better (usually faster) way of doing this is using the C<SetFNameFilter>
277	functionality.
278
279	=item $retval = Smerge $pass
280
281	If you are desperate, try to call C<Smerge> with increasing C<$pass>
282	values, beginning at C<0>, to try to merge parts that usually would not
283	have been merged.
284
285	Most probably this will result in garbled files, so never do this by
286	default.
287
288	=item $item = GetFileListItem $item_number
289
290	Return the C<$item> structure for the C<$item_number>'th found file, or
291	C<undef> of no file with that number exists.
292
293	The first file has number C<0>, and the series has no holes, so you can
294	iterate over all files by starting with zero and incrementing until you
295	hit C<undef>.
296
297	=back
298
299	=head2 Decoding files
300
301	=over 4
302
303	=item $retval = $item->rename($newname)
304
305	Change the ondisk filename where the decoded file will be saved.
306
307	=item $retval = $item->decode_temp
308
309	Decode the file into a temporary location, use C<< $item->infile >> to
310	retrieve the temporary filename.
311
312	=item $retval = $item->remove_temp
313
314	Remove the temporarily decoded file again.
315
316	=item $retval = $item->decode([$target_path])
317
318	Decode the file to it's destination, or the given target path.
319
320	=item $retval = $item->info(callback-function)
321
322	=back
323
324	=head2 Querying (and setting) item attributes
325
326	=over 4
327
328	=item $state = $item->state
329
330	=item $mode = $item->mode([newmode])
331
332	=item $uudet = $item->uudet
333
334	=item $size = $item->size
335
336	=item $filename = $item->filename([newfilename})
337
338	=item $subfname = $item->subfname
339
340	=item $mimeid = $item->mimeid
341
342	=item $mimetype = $item->mimetype
343
344	=item $binfile = $item->binfile
345
346	=back
347
348	=head2 Information about source parts
349
350	=over 4
351
352	=item $parts = $item->parts
353
354	Return information about all parts (source files) used to decode the file
355	as a list of hashrefs with the following structure:
356
357	{
358	partno => <integer describing the part number, starting with 1>,
359	# the following member sonly exist when they contain useful information
360	sfname => <local pathname of the file where this part is from>,
361	filename => <the ondisk filename of the decoded file>,
362	subfname => <used to cluster postings, possibly the posting filename>,
363	subject => <the subject of the posting/mail>,
364	origin => <the possible source (From) address>,
365	mimetype => <the possible mimetype of the decoded file>,
366	mimeid => <the id part of the Content-Type>,
367	}
368
369	Usually you are interested mostly the C<sfname> and possibly the C<partno>
370	and C<filename> members.
371
372	=back
373
374	=head2 Functions below not documented and not very well tested
375
376	QuickDecode
377	EncodeMulti
378	EncodePartial
379	EncodeToStream
380	EncodeToFile
381	E_PrepSingle
382	E_PrepPartial
383
384	=head2 EXTENSION FUNCTIONS
385
386	Functions found in this module but not documented in the uulib documentation:
387
388	=over 4
389
390	=item $msg = straction ACT_xxx
391
392	Return a human readable string representing the given action code.
393
394	=item $msg = strerror RET_xxx
395
396	Return a human readable string representing the given error code.
397
398	=item $str = strencoding xxx_ENCODED
399
400	Return the name of the encoding type as a string.
401
402	=item $str = strmsglevel MSG_xxx
403
404	Returns the message level as a string.
405
406	=item SetFileNameCallback $cb
407
408	Sets (or queries) the FileNameCallback, which is called whenever the
409	decoding library can't find a filename and wants to extract a filename
410	from the subject line of a posting. The callback will be called with
411	two arguments, the subject line and the current candidate for the
412	filename. The latter argument can be C<undef>, which means that no
413	filename could be found (and likely no one exists, so it is safe to also
414	return C<undef> in this case). If it doesn't return anything (not even
415	C<undef>!), then nothing happens, so this is a no-op callback:
416
417	sub cb {
418	return ();
419	}
420
421	If it returns C<undef>, then this indicates that no filename could be
422	found. In all other cases, the return value is taken to be the filename.
423
424	This is a slightly more useful callback:
425
426	sub cb {
427	return unless $_[1]; # skip "Re:"-plies et al.
428	my ($subject, $filename) = @_;
429	# if we find some *.rar, take it
430	return $1 if $subject =~ /(\w+\.rar)/;
431	# otherwise just pass what we have
432	return ();
433	}
434
435	=back
436
437	=head1 LARGE EXAMPLE DECODER
438
439	This is the file C<example-decoder> from the distribution, put here
440	instead of more thorough documentation.
441
442	#!/usr/bin/perl
443
444	# decode all the files in the directory uusrc/ and copy
445	# the resulting files to uudst/
446
447	use Convert::UUlib ':all';
448
449	sub namefilter {
450	my ($path) = @_;
451
452	$path=~s/^.*[\/\\]//;
453
454	$path
455	}
456
457	sub busycb {
458	my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
459	$_[0]=straction($action);
460	print "busy_callback(", (join ",",@_), ")\n";
461	0
462	}
463
464	SetOption OPT_RBUF, 128*1024;
465	SetOption OPT_WBUF, 1024*1024;
466	SetOption OPT_IGNMODE, 1;
467	SetOption OPT_IGNMODE, 1;
468	SetOption OPT_VERBOSE, 1;
469
470	# show the three ways you can set callback functions. I normally
471	# prefer the one with the sub inplace.
472	SetFNameFilter \&namefilter;
473
474	SetBusyCallback "busycb", 333;
475
476	SetMsgCallback sub {
477	my ($msg, $level) = @_;
478	print uc strmsglevel $_[1], ": $msg\n";
479	};
480
481	# the following non-trivial FileNameCallback takes care
482	# of some subject lines not detected properly by uulib:
483	SetFileNameCallback sub {
484	return unless $_[1]; # skip "Re:"-plies et al.
485	local $_ = $_[0];
486
487	return $1 if /(\S+\s+IMG_\d+.jpg)/i;
488
489	# the following rules are rather effective on some newsgroups,
490	# like alt.binaries.games.anime, where non-mime, uuencoded data
491	# is very common
492
493	# if we find some *.rar, take it as the filename
494	return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d\|rar))\s/i;
495
496	# one common subject format
497	return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
498
499	# - filename.par (04/55)
500	return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
501
502	# - (xxx) No. 1 sayuri81.jpg 756565 bytes
503	# - (20 files) No.17 Roseanne.jpg [2/2]
504	return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
505
506	# try to detect some common forms of filenames
507	return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
508
509	# otherwise just pass what we have
510	()
511	};
512
513	# now read all files in the directory uusrc/*
514	for(<uusrc/*>) {
515	my ($retval, $count) = LoadFile ($_, $_, 1);
516	print "file($_), status(", strerror $retval, ") parts($count)\n";
517	}
518
519	SetOption OPT_SAVEPATH, "uudst/";
520
521	# now wade through all files and their source parts
522	$i = 0;
523	while ($uu = GetFileListItem $i) {
524	$i++;
525	print "file nr. $i";
526	print " state ", $uu->state;
527	print " mode ", $uu->mode;
528	print " uudet ", strencoding $uu->uudet;
529	print " size ", $uu->size;
530	print " filename ", $uu->filename;
531	print " subfname ", $uu->subfname;
532	print " mimeid ", $uu->mimeid;
533	print " mimetype ", $uu->mimetype;
534	print "\n";
535
536	# print additional info about all parts
537	for ($uu->parts) {
538	while (my ($k, $v) = each %$_) {
539	print "$k > $v, ";
540	}
541	print "\n";
542	}
543
544	print $uu->filename;
545
546	$uu->remove_temp;
547
548	if (my $err = $uu->decode ()) {
549	print ", ", strerror $err, "\n";
550	} else {
551	print ", saved as uudst/", $uu->filename, "\n";
552	}
553	}
554
555	print "cleanup...\n";
556
557	CleanUp;
558
559	=head1 AUTHOR
560
561	Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
562	by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
563	bugfixed by Marc Lehmann.
564
565	=head1 SEE ALSO
566
567	perl(1), uudeview homepage at http://www.uni-frankfurt.de/~fp/uudeview/.
568
569	=cut