Convert-UUlib/UUlib.pm

package Convert::UUlib;

no warnings;
use strict;

use Carp;

require Exporter;
require DynaLoader;

our $VERSION = 1.62;

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 OPT_AUTOCHECK

        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 GetFileList 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;

# dummy function for compatiiblity with pre-1.7 versions
sub Initialize { }

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 $uu (GetFileList) {
    if ($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
  OPT_WBUF      set default write I/O buffer size in bytes
  OPT_AUTOCHECK automatically check file list after every loadfile

=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

=item CleanUp

Release memory, file items and clean up files. Should be called after a
decoidng run, if you want to start a new one.

=back

=head2 Setting and querying options

=over

=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

=item SetMsgCallback [callback-function]

=item SetBusyCallback [callback-function]

=item SetFileCallback [callback-function]

=item SetFNameFilter [callback-function]

=back

=head2 Call the currently selected FNameFilter

=over

=item $file = FNameFilter $file

=back

=head2 Loading sourcefiles, optionally fuzzy merge and start decoding

=over

=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, except:

If the C<OPT_AUTOCHECK> option has been disabled (by default it is
enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
after loading all files as an additional pre-pass (which is normally done
by C<LoadFile>).

=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>.

This function has to walk the linear list of fils on each access, so
if you want to iterate over all items, it is usually faster to use
C<GetFileList>.

=item @items = GetFileList

Similar to C<GetFileListItem>, but returns all files in one go.

=back

=head2 Decoding files

=over

=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 its destination, or the given target path.

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

=back

=head2 Querying (and setting) item attributes

=over

=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

=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 are not documented and not very well tested - feedback welcome

  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

=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

The general workflow for decoding is like this:

=over

=item 1. Configure options with C<SetOption> or C<SetXXXCallback>.

=item 2. Load all source files with C<LoadFile>.

=item 3. Optionally C<Smerge>.

=item 4. Iterate over all C<GetFileList> items (i.e. result files).

=item 5. C<CleanUp> to delete files and free items.

=back

What follows is the file C<example-decoder> from the distribution that
illustrates the above worklfow in a non-trivial example.

   #!/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];

      # 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
   for my $uu (GetFileList) {
      print "file ", $uu->filename, "\n";
      print " state ", $uu->state, "\n";
      print " mode ", $uu->mode, "\n";
      print " uudet ", strencoding $uu->uudet, "\n";
      print " size ", $uu->size, "\n";
      print " subfname ", $uu->subfname, "\n";
      print " mimeid ", $uu->mimeid, "\n";
      print " mimetype ", $uu->mimetype, "\n";

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

      $uu->remove_temp;

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

   print "cleanup...\n";

   CleanUp;

=head1 PERLMULTICORE SUPPORT

This module supports the perlmulticore standard (see
L<http://perlmulticore.schmorp.de/> for more info) for the following
functions - generally these are functions accessing the disk and/or using
considerable CPU time:

   LoadFile
   $item->decode
   $item->decode_temp
   $item->remove_temp
   $item->info

The perl interpreter will be reacquired/released on every callback
invocation, so for performance reasons, callbacks should be avoided if
that is costly.

Future versions might enable multicore support for more functions.

=head1 BUGS AND LIMITATIONS

The original uulib library this module uses was written at a time where
main memory of measured in megabytes and buffer overflows as a security
thign didn't exist. While a lot of security fixes have been applied over
the years (includign some defense in depth mechanism that can shield
against a lot of as-of-yet undetected bugs), using this library for
security purposes requires care.

Likewise, file sizes when the uulib library was written were tiny compared
to today, so do not expect this library to handle files larger than 2GB.

=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 L<http://www.fpx.de/fp/Software/UUDeview/>.

=cut

Revision:	1.48
Committed:	Fri Feb 28 17:19:02 2020 UTC (4 years, 2 months ago) by root
Branch:	MAIN
Changes since 1.47:	+24 -13 lines
Log Message:	* empty log message *
#	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 = 1.62;
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 OPT_AUTOCHECK
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 GetFileList 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	# dummy function for compatiiblity with pre-1.7 versions
54	sub Initialize { }
55
56	for (@_consts) {
57	my $constant = constant ($_);
58	no strict 'refs';
59	*$_ = sub () { $constant };
60	}
61
62	# action code -> string mapping
63	sub straction($) {
64	return 'copying' if $_[0] == &ACT_COPYING;
65	return 'decoding' if $_[0] == &ACT_DECODING;
66	return 'encoding' if $_[0] == &ACT_ENCODING;
67	return 'idle' if $_[0] == &ACT_IDLE;
68	return 'scanning' if $_[0] == &ACT_SCANNING;
69	'unknown';
70	}
71
72	# encoding type -> string mapping
73	sub strencoding($) {
74	return 'uuencode' if $_[0] == &UU_ENCODED;
75	return 'base64' if $_[0] == &B64_ENCODED;
76	return 'yenc' if $_[0] == &YENC_ENCODED;
77	return 'binhex' if $_[0] == &BH_ENCODED;
78	return 'plaintext' if $_[0] == &PT_ENCODED;
79	return 'quoted-printable' if $_[0] == &QP_ENCODED;
80	return 'xxencode' if $_[0] == &XX_ENCODED;
81	'unknown';
82	}
83
84	sub strmsglevel($) {
85	return 'message' if $_[0] == &MSG_MESSAGE;
86	return 'note' if $_[0] == &MSG_NOTE;
87	return 'warning' if $_[0] == &MSG_WARNING;
88	return 'error' if $_[0] == &MSG_ERROR;
89	return 'panic' if $_[0] == &MSG_PANIC;
90	return 'fatal' if $_[0] == &MSG_FATAL;
91	'unknown';
92	}
93
94	1;
95	__END__
96
97	=head1 NAME
98
99	Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).
100
101	=head1 SYNOPSIS
102
103	use Convert::UUlib ':all';
104
105	# read all the files named on the commandline and decode them
106	# into the CURRENT directory. See below for a longer example.
107	LoadFile $_ for @ARGV;
108
109	for my $uu (GetFileList) {
110	if ($uu->state & FILE_OK) {
111	$uu->decode;
112	print $uu->filename, "\n";
113	}
114	}
115
116	=head1 DESCRIPTION
117
118	Read the file doc/library.pdf from the distribution for in-depth
119	information about the C-library used in this interface, and the rest of
120	this document and especially the non-trivial decoder program at the end.
121
122	=head1 EXPORTED CONSTANTS
123
124	=head2 Action code constants
125
126	ACT_IDLE we don't do anything
127	ACT_SCANNING scanning an input file
128	ACT_DECODING decoding into a temp file
129	ACT_COPYING copying temp to target
130	ACT_ENCODING encoding a file
131
132	=head2 Message severity levels
133
134	MSG_MESSAGE just a message, nothing important
135	MSG_NOTE something that should be noticed
136	MSG_WARNING important msg, processing continues
137	MSG_ERROR processing has been terminated
138	MSG_FATAL decoder cannot process further requests
139	MSG_PANIC recovery impossible, app must terminate
140
141	=head2 Options
142
143	OPT_VERSION version number MAJOR.MINORplPATCH (ro)
144	OPT_FAST assumes only one part per file
145	OPT_DUMBNESS switch off the program's intelligence
146	OPT_BRACKPOL give numbers in [] higher precendence
147	OPT_VERBOSE generate informative messages
148	OPT_DESPERATE try to decode incomplete files
149	OPT_IGNREPLY ignore RE:plies (off by default)
150	OPT_OVERWRITE whether it's OK to overwrite ex. files
151	OPT_SAVEPATH prefix to save-files on disk
152	OPT_IGNMODE ignore the original file mode
153	OPT_DEBUG print messages with FILE/LINE info
154	OPT_ERRNO get last error code for RET_IOERR (ro)
155	OPT_PROGRESS retrieve progress information
156	OPT_USETEXT handle text messages
157	OPT_PREAMB handle Mime preambles/epilogues
158	OPT_TINYB64 detect short B64 outside of Mime
159	OPT_ENCEXT extension for single-part encoded files
160	OPT_REMOVE remove input files after decoding (dangerous)
161	OPT_MOREMIME strict MIME adherence
162	OPT_DOTDOT ".."-unescaping has not yet been done on input files
163	OPT_RBUF set default read I/O buffer size in bytes
164	OPT_WBUF set default write I/O buffer size in bytes
165	OPT_AUTOCHECK automatically check file list after every loadfile
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
219
220	=item CleanUp
221
222	Release memory, file items and clean up files. Should be called after a
223	decoidng run, if you want to start a new one.
224
225	=back
226
227	=head2 Setting and querying options
228
229	=over
230
231	=item $option = GetOption OPT_xxx
232
233	=item SetOption OPT_xxx, opt-value
234
235	=back
236
237	See the C<OPT_xxx> constants above to see which options exist.
238
239	=head2 Setting various callbacks
240
241	=over
242
243	=item SetMsgCallback [callback-function]
244
245	=item SetBusyCallback [callback-function]
246
247	=item SetFileCallback [callback-function]
248
249	=item SetFNameFilter [callback-function]
250
251	=back
252
253	=head2 Call the currently selected FNameFilter
254
255	=over
256
257	=item $file = FNameFilter $file
258
259	=back
260
261	=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
262
263	=over
264
265	=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
266
267	Load the given file and scan it for encoded contents. Optionally tag it
268	with the given id, and if C<$delflag> is true, delete the file after it
269	is no longer necessary. If you are certain of the part number, you can
270	specify it as the last argument.
271
272	A better (usually faster) way of doing this is using the C<SetFNameFilter>
273	functionality.
274
275	=item $retval = Smerge $pass
276
277	If you are desperate, try to call C<Smerge> with increasing C<$pass>
278	values, beginning at C<0>, to try to merge parts that usually would not
279	have been merged.
280
281	Most probably this will result in garbled files, so never do this by
282	default, except:
283
284	If the C<OPT_AUTOCHECK> option has been disabled (by default it is
285	enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
286	after loading all files as an additional pre-pass (which is normally done
287	by C<LoadFile>).
288
289	=item $item = GetFileListItem $item_number
290
291	Return the C<$item> structure for the C<$item_number>'th found file, or
292	C<undef> of no file with that number exists.
293
294	The first file has number C<0>, and the series has no holes, so you can
295	iterate over all files by starting with zero and incrementing until you
296	hit C<undef>.
297
298	This function has to walk the linear list of fils on each access, so
299	if you want to iterate over all items, it is usually faster to use
300	C<GetFileList>.
301
302	=item @items = GetFileList
303
304	Similar to C<GetFileListItem>, but returns all files in one go.
305
306	=back
307
308	=head2 Decoding files
309
310	=over
311
312	=item $retval = $item->rename ($newname)
313
314	Change the ondisk filename where the decoded file will be saved.
315
316	=item $retval = $item->decode_temp
317
318	Decode the file into a temporary location, use C<< $item->infile >> to
319	retrieve the temporary filename.
320
321	=item $retval = $item->remove_temp
322
323	Remove the temporarily decoded file again.
324
325	=item $retval = $item->decode ([$target_path])
326
327	Decode the file to its destination, or the given target path.
328
329	=item $retval = $item->info (callback-function)
330
331	=back
332
333	=head2 Querying (and setting) item attributes
334
335	=over
336
337	=item $state = $item->state
338
339	=item $mode = $item->mode ([newmode])
340
341	=item $uudet = $item->uudet
342
343	=item $size = $item->size
344
345	=item $filename = $item->filename ([newfilename})
346
347	=item $subfname = $item->subfname
348
349	=item $mimeid = $item->mimeid
350
351	=item $mimetype = $item->mimetype
352
353	=item $binfile = $item->binfile
354
355	=back
356
357	=head2 Information about source parts
358
359	=over
360
361	=item $parts = $item->parts
362
363	Return information about all parts (source files) used to decode the file
364	as a list of hashrefs with the following structure:
365
366	{
367	partno => <integer describing the part number, starting with 1>,
368	# the following member sonly exist when they contain useful information
369	sfname => <local pathname of the file where this part is from>,
370	filename => <the ondisk filename of the decoded file>,
371	subfname => <used to cluster postings, possibly the posting filename>,
372	subject => <the subject of the posting/mail>,
373	origin => <the possible source (From) address>,
374	mimetype => <the possible mimetype of the decoded file>,
375	mimeid => <the id part of the Content-Type>,
376	}
377
378	Usually you are interested mostly the C<sfname> and possibly the C<partno>
379	and C<filename> members.
380
381	=back
382
383	=head2 Functions below are not documented and not very well tested - feedback welcome
384
385	QuickDecode
386	EncodeMulti
387	EncodePartial
388	EncodeToStream
389	EncodeToFile
390	E_PrepSingle
391	E_PrepPartial
392
393	=head2 EXTENSION FUNCTIONS
394
395	Functions found in this module but not documented in the uulib documentation:
396
397	=over
398
399	=item $msg = straction ACT_xxx
400
401	Return a human readable string representing the given action code.
402
403	=item $msg = strerror RET_xxx
404
405	Return a human readable string representing the given error code.
406
407	=item $str = strencoding xxx_ENCODED
408
409	Return the name of the encoding type as a string.
410
411	=item $str = strmsglevel MSG_xxx
412
413	Returns the message level as a string.
414
415	=item SetFileNameCallback $cb
416
417	Sets (or queries) the FileNameCallback, which is called whenever the
418	decoding library can't find a filename and wants to extract a filename
419	from the subject line of a posting. The callback will be called with
420	two arguments, the subject line and the current candidate for the
421	filename. The latter argument can be C<undef>, which means that no
422	filename could be found (and likely no one exists, so it is safe to also
423	return C<undef> in this case). If it doesn't return anything (not even
424	C<undef>!), then nothing happens, so this is a no-op callback:
425
426	sub cb {
427	return ();
428	}
429
430	If it returns C<undef>, then this indicates that no filename could be
431	found. In all other cases, the return value is taken to be the filename.
432
433	This is a slightly more useful callback:
434
435	sub cb {
436	return unless $_[1]; # skip "Re:"-plies et al.
437	my ($subject, $filename) = @_;
438	# if we find some *.rar, take it
439	return $1 if $subject =~ /(\w+\.rar)/;
440	# otherwise just pass what we have
441	return ();
442	}
443
444	=back
445
446	=head1 LARGE EXAMPLE DECODER
447
448	The general workflow for decoding is like this:
449
450	=over
451
452	=item 1. Configure options with C<SetOption> or C<SetXXXCallback>.
453
454	=item 2. Load all source files with C<LoadFile>.
455
456	=item 3. Optionally C<Smerge>.
457
458	=item 4. Iterate over all C<GetFileList> items (i.e. result files).
459
460	=item 5. C<CleanUp> to delete files and free items.
461
462	=back
463
464	What follows is the file C<example-decoder> from the distribution that
465	illustrates the above worklfow in a non-trivial example.
466
467	#!/usr/bin/perl
468
469	# decode all the files in the directory uusrc/ and copy
470	# the resulting files to uudst/
471
472	use Convert::UUlib ':all';
473
474	sub namefilter {
475	my ($path) = @_;
476
477	$path=~s/^.*[\/\\]//;
478
479	$path
480	}
481
482	sub busycb {
483	my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
484	$_[0]=straction($action);
485	print "busy_callback(", (join ",",@_), ")\n";
486	0
487	}
488
489	SetOption OPT_RBUF, 128*1024;
490	SetOption OPT_WBUF, 1024*1024;
491	SetOption OPT_IGNMODE, 1;
492	SetOption OPT_IGNMODE, 1;
493	SetOption OPT_VERBOSE, 1;
494
495	# show the three ways you can set callback functions. I normally
496	# prefer the one with the sub inplace.
497	SetFNameFilter \&namefilter;
498
499	SetBusyCallback "busycb", 333;
500
501	SetMsgCallback sub {
502	my ($msg, $level) = @_;
503	print uc strmsglevel $_[1], ": $msg\n";
504	};
505
506	# the following non-trivial FileNameCallback takes care
507	# of some subject lines not detected properly by uulib:
508	SetFileNameCallback sub {
509	return unless $_[1]; # skip "Re:"-plies et al.
510	local $_ = $_[0];
511
512	# the following rules are rather effective on some newsgroups,
513	# like alt.binaries.games.anime, where non-mime, uuencoded data
514	# is very common
515
516	# if we find some *.rar, take it as the filename
517	return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d\|rar))\s/i;
518
519	# one common subject format
520	return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
521
522	# - filename.par (04/55)
523	return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
524
525	# - (xxx) No. 1 sayuri81.jpg 756565 bytes
526	# - (20 files) No.17 Roseanne.jpg [2/2]
527	return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
528
529	# try to detect some common forms of filenames
530	return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
531
532	# otherwise just pass what we have
533	()
534	};
535
536	# now read all files in the directory uusrc/*
537	for (<uusrc/*>) {
538	my ($retval, $count) = LoadFile ($_, $_, 1);
539	print "file($_), status(", strerror $retval, ") parts($count)\n";
540	}
541
542	SetOption OPT_SAVEPATH, "uudst/";
543
544	# now wade through all files and their source parts
545	for my $uu (GetFileList) {
546	print "file ", $uu->filename, "\n";
547	print " state ", $uu->state, "\n";
548	print " mode ", $uu->mode, "\n";
549	print " uudet ", strencoding $uu->uudet, "\n";
550	print " size ", $uu->size, "\n";
551	print " subfname ", $uu->subfname, "\n";
552	print " mimeid ", $uu->mimeid, "\n";
553	print " mimetype ", $uu->mimetype, "\n";
554
555	# print additional info about all parts
556	print " parts";
557	for ($uu->parts) {
558	for my $k (sort keys %$_) {
559	print " $k=$_->{$k}";
560	}
561	print "\n";
562	}
563
564	$uu->remove_temp;
565
566	if (my $err = $uu->decode) {
567	print " ERROR ", strerror $err, "\n";
568	} else {
569	print " successfully saved as uudst/", $uu->filename, "\n";
570	}
571	}
572
573	print "cleanup...\n";
574
575	CleanUp;
576
577	=head1 PERLMULTICORE SUPPORT
578
579	This module supports the perlmulticore standard (see
580	L<http://perlmulticore.schmorp.de/> for more info) for the following
581	functions - generally these are functions accessing the disk and/or using
582	considerable CPU time:
583
584	LoadFile
585	$item->decode
586	$item->decode_temp
587	$item->remove_temp
588	$item->info
589
590	The perl interpreter will be reacquired/released on every callback
591	invocation, so for performance reasons, callbacks should be avoided if
592	that is costly.
593
594	Future versions might enable multicore support for more functions.
595
596	=head1 BUGS AND LIMITATIONS
597
598	The original uulib library this module uses was written at a time where
599	main memory of measured in megabytes and buffer overflows as a security
600	thign didn't exist. While a lot of security fixes have been applied over
601	the years (includign some defense in depth mechanism that can shield
602	against a lot of as-of-yet undetected bugs), using this library for
603	security purposes requires care.
604
605	Likewise, file sizes when the uulib library was written were tiny compared
606	to today, so do not expect this library to handle files larger than 2GB.
607
608	=head1 AUTHOR
609
610	Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
611	by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
612	bugfixed by Marc Lehmann.
613
614	=head1 SEE ALSO
615
616	perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>.
617
618	=cut
619