Convert-UUlib/UUlib.pm

package Convert::UUlib;

use common::sense;

use Carp;

require Exporter;
require DynaLoader;

our $VERSION = 1.7;

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 { }

# 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.

Lastly, this module uses a very "C-like" interface, which means it doesn't
protect you from invalid points as you might expect from "more perlish"
modules - for example, accessing a file item object after callinbg
C<CleanUp> will likely result in crashes, memory corruption, or worse.

=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:	1.51
Committed:	Sun Mar 1 05:14:55 2020 UTC (4 years, 2 months ago) by root
Branch:	MAIN
CVS Tags:	rel-1_7
Changes since 1.50:	+1 -1 lines
Log Message:	1.7
#	User	Rev	Content
1	root	1.1	package Convert::UUlib;
2
3	root	1.49	use common::sense;
4	root	1.28
5	root	1.1	use Carp;
6
7			require Exporter;
8			require DynaLoader;
9
10	root	1.51	our $VERSION = 1.7;
11	root	1.1
12	root	1.28	our @ISA = qw(Exporter DynaLoader);
13	root	1.1
14	root	1.28	our @_consts = qw(
15	root	1.1	ACT_COPYING ACT_DECODING ACT_ENCODING ACT_IDLE ACT_SCANNING
16
17			FILE_DECODED FILE_ERROR FILE_MISPART FILE_NOBEGIN FILE_NODATA
18			FILE_NOEND FILE_OK FILE_READ FILE_TMPFILE
19
20			MSG_ERROR MSG_FATAL MSG_MESSAGE MSG_NOTE MSG_PANIC MSG_WARNING
21
22	root	1.25	OPT_RBUF OPT_WBUF
23	root	1.1	OPT_BRACKPOL OPT_DEBUG OPT_DESPERATE OPT_DUMBNESS OPT_ENCEXT
24			OPT_ERRNO OPT_FAST OPT_IGNMODE OPT_IGNREPLY OPT_OVERWRITE OPT_PREAMB
25			OPT_PROGRESS OPT_SAVEPATH OPT_TINYB64 OPT_USETEXT OPT_VERBOSE
26	root	1.34	OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT OPT_AUTOCHECK
27	root	1.1
28			RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
29			RET_NOEND RET_NOMEM RET_OK RET_UNSUP
30
31	root	1.11	B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
32	root	1.5	XX_ENCODED UU_ENCODED YENC_ENCODED
33	root	1.1	);
34
35	root	1.28	our @_funcs = qw(
36	root	1.6	Initialize CleanUp GetOption SetOption strerror SetMsgCallback
37			SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
38	root	1.47	FNameFilter LoadFile GetFileListItem GetFileList RenameFile DecodeToTemp
39	root	1.6	RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
40			EncodePartial EncodeToStream EncodeToFile E_PrepSingle
41	root	1.35	E_PrepPartial
42	root	1.1
43			straction strencoding strmsglevel
44			);
45
46	root	1.28	our @EXPORT = @_consts;
47			our @EXPORT_OK = @_funcs;
48			our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);
49	root	1.1
50			bootstrap Convert::UUlib $VERSION;
51
52	root	1.48	# dummy function for compatiiblity with pre-1.7 versions
53			sub Initialize { }
54	root	1.1
55			# action code -> string mapping
56			sub straction($) {
57			return 'copying' if $_[0] == &ACT_COPYING;
58			return 'decoding' if $_[0] == &ACT_DECODING;
59			return 'encoding' if $_[0] == &ACT_ENCODING;
60			return 'idle' if $_[0] == &ACT_IDLE;
61			return 'scanning' if $_[0] == &ACT_SCANNING;
62	root	1.5	'unknown';
63	root	1.1	}
64
65			# encoding type -> string mapping
66			sub strencoding($) {
67	root	1.5	return 'uuencode' if $_[0] == &UU_ENCODED;
68	root	1.11	return 'base64' if $_[0] == &B64_ENCODED;
69	root	1.5	return 'yenc' if $_[0] == &YENC_ENCODED;
70	root	1.1	return 'binhex' if $_[0] == &BH_ENCODED;
71			return 'plaintext' if $_[0] == &PT_ENCODED;
72			return 'quoted-printable' if $_[0] == &QP_ENCODED;
73			return 'xxencode' if $_[0] == &XX_ENCODED;
74	root	1.5	'unknown';
75	root	1.1	}
76
77			sub strmsglevel($) {
78			return 'message' if $_[0] == &MSG_MESSAGE;
79			return 'note' if $_[0] == &MSG_NOTE;
80			return 'warning' if $_[0] == &MSG_WARNING;
81			return 'error' if $_[0] == &MSG_ERROR;
82			return 'panic' if $_[0] == &MSG_PANIC;
83			return 'fatal' if $_[0] == &MSG_FATAL;
84	root	1.5	'unknown';
85	root	1.1	}
86
87			1;
88			__END__
89
90			=head1 NAME
91
92			Convert::UUlib - Perl interface to the uulib library (a.k.a. uudeview/uuenview).
93
94			=head1 SYNOPSIS
95
96			use Convert::UUlib ':all';
97
98	root	1.11	# read all the files named on the commandline and decode them
99	root	1.13	# into the CURRENT directory. See below for a longer example.
100			LoadFile $_ for @ARGV;
101	root	1.48
102	root	1.47	for my $uu (GetFileList) {
103	root	1.13	if ($uu->state & FILE_OK) {
104			$uu->decode;
105			print $uu->filename, "\n";
106			}
107	root	1.1	}
108
109	root	1.11	=head1 DESCRIPTION
110	root	1.1
111	root	1.11	Read the file doc/library.pdf from the distribution for in-depth
112			information about the C-library used in this interface, and the rest of
113			this document and especially the non-trivial decoder program at the end.
114
115			=head1 EXPORTED CONSTANTS
116
117			=head2 Action code constants
118
119			ACT_IDLE we don't do anything
120			ACT_SCANNING scanning an input file
121			ACT_DECODING decoding into a temp file
122			ACT_COPYING copying temp to target
123			ACT_ENCODING encoding a file
124
125			=head2 Message severity levels
126
127			MSG_MESSAGE just a message, nothing important
128			MSG_NOTE something that should be noticed
129			MSG_WARNING important msg, processing continues
130			MSG_ERROR processing has been terminated
131			MSG_FATAL decoder cannot process further requests
132			MSG_PANIC recovery impossible, app must terminate
133
134			=head2 Options
135
136			OPT_VERSION version number MAJOR.MINORplPATCH (ro)
137			OPT_FAST assumes only one part per file
138			OPT_DUMBNESS switch off the program's intelligence
139			OPT_BRACKPOL give numbers in [] higher precendence
140			OPT_VERBOSE generate informative messages
141			OPT_DESPERATE try to decode incomplete files
142			OPT_IGNREPLY ignore RE:plies (off by default)
143			OPT_OVERWRITE whether it's OK to overwrite ex. files
144			OPT_SAVEPATH prefix to save-files on disk
145			OPT_IGNMODE ignore the original file mode
146			OPT_DEBUG print messages with FILE/LINE info
147			OPT_ERRNO get last error code for RET_IOERR (ro)
148			OPT_PROGRESS retrieve progress information
149			OPT_USETEXT handle text messages
150			OPT_PREAMB handle Mime preambles/epilogues
151			OPT_TINYB64 detect short B64 outside of Mime
152			OPT_ENCEXT extension for single-part encoded files
153	root	1.14	OPT_REMOVE remove input files after decoding (dangerous)
154	root	1.11	OPT_MOREMIME strict MIME adherence
155	root	1.15	OPT_DOTDOT ".."-unescaping has not yet been done on input files
156	root	1.35	OPT_RBUF set default read I/O buffer size in bytes
157			OPT_WBUF set default write I/O buffer size in bytes
158			OPT_AUTOCHECK automatically check file list after every loadfile
159	root	1.11
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	1.46	=over
212	root	1.13
213			=item CleanUp
214
215	root	1.48	Release memory, file items and clean up files. Should be called after a
216			decoidng run, if you want to start a new one.
217	root	1.13
218			=back
219	root	1.1
220	root	1.11	=head2 Setting and querying options
221	root	1.1
222	root	1.46	=over
223	root	1.13
224			=item $option = GetOption OPT_xxx
225
226			=item SetOption OPT_xxx, opt-value
227
228			=back
229
230			See the C<OPT_xxx> constants above to see which options exist.
231	root	1.1
232	root	1.11	=head2 Setting various callbacks
233	root	1.1
234	root	1.46	=over
235	root	1.13
236			=item SetMsgCallback [callback-function]
237
238			=item SetBusyCallback [callback-function]
239
240			=item SetFileCallback [callback-function]
241
242			=item SetFNameFilter [callback-function]
243
244			=back
245	root	1.1
246	root	1.11	=head2 Call the currently selected FNameFilter
247	root	1.1
248	root	1.46	=over
249	root	1.13
250			=item $file = FNameFilter $file
251
252			=back
253	root	1.1
254	root	1.11	=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
255	root	1.1
256	root	1.46	=over
257	root	1.13
258	root	1.16	=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
259	root	1.13
260			Load the given file and scan it for encoded contents. Optionally tag it
261	root	1.16	with the given id, and if C<$delflag> is true, delete the file after it
262	root	1.18	is no longer necessary. If you are certain of the part number, you can
263			specify it as the last argument.
264	root	1.16
265			A better (usually faster) way of doing this is using the C<SetFNameFilter>
266			functionality.
267	root	1.13
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	root	1.35	default, except:
276
277			If the C<OPT_AUTOCHECK> option has been disabled (by default it is
278			enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
279			after loading all files as an additional pre-pass (which is normally done
280			by C<LoadFile>).
281	root	1.13
282			=item $item = GetFileListItem $item_number
283
284			Return the C<$item> structure for the C<$item_number>'th found file, or
285			C<undef> of no file with that number exists.
286
287			The first file has number C<0>, and the series has no holes, so you can
288			iterate over all files by starting with zero and incrementing until you
289			hit C<undef>.
290
291	root	1.47	This function has to walk the linear list of fils on each access, so
292			if you want to iterate over all items, it is usually faster to use
293			C<GetFileList>.
294
295			=item @items = GetFileList
296
297			Similar to C<GetFileListItem>, but returns all files in one go.
298
299	root	1.13	=back
300
301			=head2 Decoding files
302
303	root	1.46	=over
304	root	1.13
305	root	1.46	=item $retval = $item->rename ($newname)
306	root	1.13
307			Change the ondisk filename where the decoded file will be saved.
308
309			=item $retval = $item->decode_temp
310
311			Decode the file into a temporary location, use C<< $item->infile >> to
312			retrieve the temporary filename.
313
314			=item $retval = $item->remove_temp
315
316			Remove the temporarily decoded file again.
317
318	root	1.46	=item $retval = $item->decode ([$target_path])
319	root	1.13
320	root	1.46	Decode the file to its destination, or the given target path.
321	root	1.13
322	root	1.46	=item $retval = $item->info (callback-function)
323	root	1.13
324			=back
325	root	1.1
326	root	1.11	=head2 Querying (and setting) item attributes
327	root	1.1
328	root	1.46	=over
329	root	1.13
330			=item $state = $item->state
331
332	root	1.46	=item $mode = $item->mode ([newmode])
333	root	1.13
334			=item $uudet = $item->uudet
335
336			=item $size = $item->size
337
338	root	1.46	=item $filename = $item->filename ([newfilename})
339	root	1.13
340			=item $subfname = $item->subfname
341
342			=item $mimeid = $item->mimeid
343
344			=item $mimetype = $item->mimetype
345
346			=item $binfile = $item->binfile
347
348			=back
349
350			=head2 Information about source parts
351
352	root	1.46	=over
353	root	1.13
354			=item $parts = $item->parts
355
356			Return information about all parts (source files) used to decode the file
357			as a list of hashrefs with the following structure:
358
359			{
360			partno => <integer describing the part number, starting with 1>,
361			# the following member sonly exist when they contain useful information
362			sfname => <local pathname of the file where this part is from>,
363			filename => <the ondisk filename of the decoded file>,
364			subfname => <used to cluster postings, possibly the posting filename>,
365			subject => <the subject of the posting/mail>,
366			origin => <the possible source (From) address>,
367			mimetype => <the possible mimetype of the decoded file>,
368			mimeid => <the id part of the Content-Type>,
369			}
370	root	1.1
371	root	1.13	Usually you are interested mostly the C<sfname> and possibly the C<partno>
372			and C<filename> members.
373	root	1.1
374	root	1.13	=back
375	root	1.1
376	root	1.46	=head2 Functions below are not documented and not very well tested - feedback welcome
377	root	1.1
378	root	1.11	QuickDecode
379			EncodeMulti
380			EncodePartial
381			EncodeToStream
382			EncodeToFile
383			E_PrepSingle
384			E_PrepPartial
385	root	1.6
386			=head2 EXTENSION FUNCTIONS
387
388			Functions found in this module but not documented in the uulib documentation:
389
390	root	1.46	=over
391	root	1.6
392	root	1.11	=item $msg = straction ACT_xxx
393
394			Return a human readable string representing the given action code.
395
396			=item $msg = strerror RET_xxx
397
398			Return a human readable string representing the given error code.
399
400			=item $str = strencoding xxx_ENCODED
401
402			Return the name of the encoding type as a string.
403
404			=item $str = strmsglevel MSG_xxx
405
406			Returns the message level as a string.
407
408	root	1.6	=item SetFileNameCallback $cb
409
410			Sets (or queries) the FileNameCallback, which is called whenever the
411			decoding library can't find a filename and wants to extract a filename
412			from the subject line of a posting. The callback will be called with
413			two arguments, the subject line and the current candidate for the
414			filename. The latter argument can be C<undef>, which means that no
415			filename could be found (and likely no one exists, so it is safe to also
416			return C<undef> in this case). If it doesn't return anything (not even
417			C<undef>!), then nothing happens, so this is a no-op callback:
418
419			sub cb {
420			return ();
421			}
422
423			If it returns C<undef>, then this indicates that no filename could be
424			found. In all other cases, the return value is taken to be the filename.
425
426			This is a slightly more useful callback:
427
428			sub cb {
429			return unless $_[1]; # skip "Re:"-plies et al.
430			my ($subject, $filename) = @_;
431			# if we find some *.rar, take it
432			return $1 if $subject =~ /(\w+\.rar)/;
433			# otherwise just pass what we have
434			return ();
435			}
436
437			=back
438	root	1.1
439	root	1.11	=head1 LARGE EXAMPLE DECODER
440
441	root	1.48	The general workflow for decoding is like this:
442
443			=over
444
445			=item 1. Configure options with C<SetOption> or C<SetXXXCallback>.
446
447			=item 2. Load all source files with C<LoadFile>.
448
449			=item 3. Optionally C<Smerge>.
450
451			=item 4. Iterate over all C<GetFileList> items (i.e. result files).
452
453			=item 5. C<CleanUp> to delete files and free items.
454
455			=back
456
457			What follows is the file C<example-decoder> from the distribution that
458			illustrates the above worklfow in a non-trivial example.
459	root	1.11
460	root	1.32	#!/usr/bin/perl
461	root	1.11
462	root	1.32	# decode all the files in the directory uusrc/ and copy
463			# the resulting files to uudst/
464	root	1.11
465	root	1.32	use Convert::UUlib ':all';
466	root	1.11
467	root	1.32	sub namefilter {
468			my ($path) = @_;
469	root	1.11
470	root	1.32	$path=~s/^.*[\/\\]//;
471	root	1.11
472	root	1.32	$path
473			}
474	root	1.11
475	root	1.32	sub busycb {
476			my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
477			$_[0]=straction($action);
478			print "busy_callback(", (join ",",@_), ")\n";
479			0
480			}
481	root	1.11
482	root	1.32	SetOption OPT_RBUF, 128*1024;
483			SetOption OPT_WBUF, 1024*1024;
484			SetOption OPT_IGNMODE, 1;
485			SetOption OPT_IGNMODE, 1;
486			SetOption OPT_VERBOSE, 1;
487
488			# show the three ways you can set callback functions. I normally
489			# prefer the one with the sub inplace.
490			SetFNameFilter \&namefilter;
491
492			SetBusyCallback "busycb", 333;
493
494			SetMsgCallback sub {
495			my ($msg, $level) = @_;
496			print uc strmsglevel $_[1], ": $msg\n";
497			};
498
499			# the following non-trivial FileNameCallback takes care
500			# of some subject lines not detected properly by uulib:
501			SetFileNameCallback sub {
502			return unless $_[1]; # skip "Re:"-plies et al.
503			local $_ = $_[0];
504
505			# the following rules are rather effective on some newsgroups,
506			# like alt.binaries.games.anime, where non-mime, uuencoded data
507			# is very common
508
509			# if we find some *.rar, take it as the filename
510			return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d\|rar))\s/i;
511
512			# one common subject format
513			return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
514
515			# - filename.par (04/55)
516			return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
517
518			# - (xxx) No. 1 sayuri81.jpg 756565 bytes
519			# - (20 files) No.17 Roseanne.jpg [2/2]
520			return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
521
522			# try to detect some common forms of filenames
523			return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
524
525			# otherwise just pass what we have
526			()
527			};
528
529			# now read all files in the directory uusrc/*
530	root	1.47	for (<uusrc/*>) {
531	root	1.32	my ($retval, $count) = LoadFile ($_, $_, 1);
532			print "file($_), status(", strerror $retval, ") parts($count)\n";
533			}
534	root	1.11
535	root	1.32	SetOption OPT_SAVEPATH, "uudst/";
536	root	1.11
537	root	1.32	# now wade through all files and their source parts
538	root	1.47	for my $uu (GetFileList) {
539			print "file ", $uu->filename, "\n";
540			print " state ", $uu->state, "\n";
541			print " mode ", $uu->mode, "\n";
542			print " uudet ", strencoding $uu->uudet, "\n";
543			print " size ", $uu->size, "\n";
544			print " subfname ", $uu->subfname, "\n";
545			print " mimeid ", $uu->mimeid, "\n";
546			print " mimetype ", $uu->mimetype, "\n";
547	root	1.32
548			# print additional info about all parts
549	root	1.47	print " parts";
550	root	1.32	for ($uu->parts) {
551	root	1.47	for my $k (sort keys %$_) {
552			print " $k=$_->{$k}";
553	root	1.32	}
554			print "\n";
555			}
556
557			$uu->remove_temp;
558
559	root	1.47	if (my $err = $uu->decode) {
560			print " ERROR ", strerror $err, "\n";
561	root	1.32	} else {
562	root	1.47	print " successfully saved as uudst/", $uu->filename, "\n";
563	root	1.32	}
564			}
565	root	1.11
566	root	1.32	print "cleanup...\n";
567	root	1.11
568	root	1.32	CleanUp;
569	root	1.11
570	root	1.46	=head1 PERLMULTICORE SUPPORT
571
572			This module supports the perlmulticore standard (see
573			L<http://perlmulticore.schmorp.de/> for more info) for the following
574			functions - generally these are functions accessing the disk and/or using
575			considerable CPU time:
576
577			LoadFile
578			$item->decode
579			$item->decode_temp
580			$item->remove_temp
581			$item->info
582
583			The perl interpreter will be reacquired/released on every callback
584			invocation, so for performance reasons, callbacks should be avoided if
585			that is costly.
586
587			Future versions might enable multicore support for more functions.
588
589	root	1.45	=head1 BUGS AND LIMITATIONS
590
591			The original uulib library this module uses was written at a time where
592			main memory of measured in megabytes and buffer overflows as a security
593			thign didn't exist. While a lot of security fixes have been applied over
594			the years (includign some defense in depth mechanism that can shield
595			against a lot of as-of-yet undetected bugs), using this library for
596			security purposes requires care.
597
598			Likewise, file sizes when the uulib library was written were tiny compared
599			to today, so do not expect this library to handle files larger than 2GB.
600
601	root	1.50	Lastly, this module uses a very "C-like" interface, which means it doesn't
602			protect you from invalid points as you might expect from "more perlish"
603			modules - for example, accessing a file item object after callinbg
604			C<CleanUp> will likely result in crashes, memory corruption, or worse.
605
606	root	1.1	=head1 AUTHOR
607
608	root	1.23	Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
609	root	1.11	by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
610			bugfixed by Marc Lehmann.
611	root	1.1
612			=head1 SEE ALSO
613
614	root	1.45	perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>.
615	root	1.1
616			=cut
617	root	1.45