Convert-UUlib/UUlib.pm

package Convert::UUlib;

use common::sense;

use Carp;

require Exporter;
require DynaLoader;

our $VERSION = 1.8;

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 - decode uu/xx/b64/mime/yenc/etc-encoded data from a massive number of files

=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

This module started as an interface to the uulib/uudeview library by Frank
Pilhofer that can be used to decode all kinds of usenet (and other)
binary messages.

After upstream abondoned the project, the library was continuously bugfixed
and improved in this module, with major focuses on security fixes,
correctness and speed (that does not mean that this library is considered
safe with untrusted data, but it surely is safer than the original
uudeview).

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 precedence
  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, which is
very much faster for large number of items, and has no drawbacks when used
for a small number of items.

=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;
   SetOption OPT_AUTOCHK, 0;

   # 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";
   }

   Smerge -1;

   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 was measured in megabytes and buffer overflows as a security
thing didn't exist. While a lot of security fixes have been applied over
the years (including 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,
certainly not on a 32 bit host.

Lastly, this module uses a very "C-like" interface, which means it doesn't
protect you from invalid pointers as you might expect from "more perlish"
modules - for example, accessing a file item object after calling
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:	1.58
Committed:	Sun Jan 29 05:04:51 2023 UTC (3 years, 3 months ago) by root
Branch:	MAIN
CVS Tags:	HEAD
Changes since 1.57:	+6 -6 lines
Log Message:	* empty log message *
#	Content
1	package Convert::UUlib;
2
3	use common::sense;
4
5	use Carp;
6
7	require Exporter;
8	require DynaLoader;
9
10	our $VERSION = 1.8;
11
12	our @ISA = qw(Exporter DynaLoader);
13
14	our @_consts = qw(
15	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	OPT_RBUF OPT_WBUF
23	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	OPT_VERSION OPT_REMOVE OPT_MOREMIME OPT_DOTDOT OPT_AUTOCHECK
27
28	RET_CANCEL RET_CONT RET_EXISTS RET_ILLVAL RET_IOERR RET_NODATA
29	RET_NOEND RET_NOMEM RET_OK RET_UNSUP
30
31	B64_ENCODED BH_ENCODED PT_ENCODED QP_ENCODED
32	XX_ENCODED UU_ENCODED YENC_ENCODED
33	);
34
35	our @_funcs = qw(
36	Initialize CleanUp GetOption SetOption strerror SetMsgCallback
37	SetBusyCallback SetFileCallback SetFNameFilter SetFileNameCallback
38	FNameFilter LoadFile GetFileListItem GetFileList RenameFile DecodeToTemp
39	RemoveTemp DecodeFile InfoFile Smerge QuickDecode EncodeMulti
40	EncodePartial EncodeToStream EncodeToFile E_PrepSingle
41	E_PrepPartial
42
43	straction strencoding strmsglevel
44	);
45
46	our @EXPORT = @_consts;
47	our @EXPORT_OK = @_funcs;
48	our %EXPORT_TAGS = (all => [@_consts,@_funcs], constants => \@_consts);
49
50	bootstrap Convert::UUlib $VERSION;
51
52	# dummy function for compatiiblity with pre-1.7 versions
53	sub Initialize { }
54
55	# action code -> string mapping
56	sub straction($) {
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 $_[0] == &ACT_SCANNING;
62	'unknown';
63	}
64
65	# encoding type -> string mapping
66	sub strencoding($) {
67	return 'uuencode' if $_[0] == &UU_ENCODED;
68	return 'base64' if $_[0] == &B64_ENCODED;
69	return 'yenc' if $_[0] == &YENC_ENCODED;
70	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 $_[0] == &XX_ENCODED;
74	'unknown';
75	}
76
77	sub strmsglevel($) {
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	'unknown';
85	}
86
87	1;
88	__END__
89
90	=head1 NAME
91
92	Convert::UUlib - decode uu/xx/b64/mime/yenc/etc-encoded data from a massive number of files
93
94	=head1 SYNOPSIS
95
96	use Convert::UUlib ':all';
97
98	# read all the files named on the commandline and decode them
99	# into the CURRENT directory. See below for a longer example.
100	LoadFile $_ for @ARGV;
101
102	for my $uu (GetFileList) {
103	if ($uu->state & FILE_OK) {
104	$uu->decode;
105	print $uu->filename, "\n";
106	}
107	}
108
109	=head1 DESCRIPTION
110
111	This module started as an interface to the uulib/uudeview library by Frank
112	Pilhofer that can be used to decode all kinds of usenet (and other)
113	binary messages.
114
115	After upstream abondoned the project, the library was continuously bugfixed
116	and improved in this module, with major focuses on security fixes,
117	correctness and speed (that does not mean that this library is considered
118	safe with untrusted data, but it surely is safer than the original
119	uudeview).
120
121	Read the file doc/library.pdf from the distribution for in-depth
122	information about the C-library used in this interface, and the rest of
123	this document and especially the non-trivial decoder program at the end.
124
125	=head1 EXPORTED CONSTANTS
126
127	=head2 Action code constants
128
129	ACT_IDLE we don't do anything
130	ACT_SCANNING scanning an input file
131	ACT_DECODING decoding into a temp file
132	ACT_COPYING copying temp to target
133	ACT_ENCODING encoding a file
134
135	=head2 Message severity levels
136
137	MSG_MESSAGE just a message, nothing important
138	MSG_NOTE something that should be noticed
139	MSG_WARNING important msg, processing continues
140	MSG_ERROR processing has been terminated
141	MSG_FATAL decoder cannot process further requests
142	MSG_PANIC recovery impossible, app must terminate
143
144	=head2 Options
145
146	OPT_VERSION version number MAJOR.MINORplPATCH (ro)
147	OPT_FAST assumes only one part per file
148	OPT_DUMBNESS switch off the program's intelligence
149	OPT_BRACKPOL give numbers in [] higher precedence
150	OPT_VERBOSE generate informative messages
151	OPT_DESPERATE try to decode incomplete files
152	OPT_IGNREPLY ignore RE:plies (off by default)
153	OPT_OVERWRITE whether it's OK to overwrite ex. files
154	OPT_SAVEPATH prefix to save-files on disk
155	OPT_IGNMODE ignore the original file mode
156	OPT_DEBUG print messages with FILE/LINE info
157	OPT_ERRNO get last error code for RET_IOERR (ro)
158	OPT_PROGRESS retrieve progress information
159	OPT_USETEXT handle text messages
160	OPT_PREAMB handle Mime preambles/epilogues
161	OPT_TINYB64 detect short B64 outside of Mime
162	OPT_ENCEXT extension for single-part encoded files
163	OPT_REMOVE remove input files after decoding (dangerous)
164	OPT_MOREMIME strict MIME adherence
165	OPT_DOTDOT ".."-unescaping has not yet been done on input files
166	OPT_RBUF set default read I/O buffer size in bytes
167	OPT_WBUF set default write I/O buffer size in bytes
168	OPT_AUTOCHECK automatically check file list after every loadfile
169
170	=head2 Result/Error codes
171
172	RET_OK everything went fine
173	RET_IOERR I/O Error - examine errno
174	RET_NOMEM not enough memory
175	RET_ILLVAL illegal value for operation
176	RET_NODATA decoder didn't find any data
177	RET_NOEND encoded data wasn't ended properly
178	RET_UNSUP unsupported function (encoding)
179	RET_EXISTS file exists (decoding)
180	RET_CONT continue -- special from ScanPart
181	RET_CANCEL operation canceled
182
183	=head2 File States
184
185	This code is zero, i.e. "false":
186
187	UUFILE_READ Read in, but not further processed
188
189	The following state codes are or'ed together:
190
191	FILE_MISPART Missing Part(s) detected
192	FILE_NOBEGIN No 'begin' found
193	FILE_NOEND No 'end' found
194	FILE_NODATA File does not contain valid uudata
195	FILE_OK All Parts found, ready to decode
196	FILE_ERROR Error while decoding
197	FILE_DECODED Successfully decoded
198	FILE_TMPFILE Temporary decoded file exists
199
200	=head2 Encoding types
201
202	UU_ENCODED UUencoded data
203	B64_ENCODED Mime-Base64 data
204	XX_ENCODED XXencoded data
205	BH_ENCODED Binhex encoded
206	PT_ENCODED Plain-Text encoded (MIME)
207	QP_ENCODED Quoted-Printable (MIME)
208	YENC_ENCODED yEnc encoded (non-MIME)
209
210	=head1 EXPORTED FUNCTIONS
211
212	=head2 Initializing and cleanup
213
214	Initialize is automatically called when the module is loaded and allocates
215	quite a small amount of memory for todays machines ;) CleanUp releases that
216	again.
217
218	On my machine, a fairly complete decode with DBI backend needs about 10MB
219	RSS to decode 20000 files.
220
221	=over
222
223	=item CleanUp
224
225	Release memory, file items and clean up files. Should be called after a
226	decoidng run, if you want to start a new one.
227
228	=back
229
230	=head2 Setting and querying options
231
232	=over
233
234	=item $option = GetOption OPT_xxx
235
236	=item SetOption OPT_xxx, opt-value
237
238	=back
239
240	See the C<OPT_xxx> constants above to see which options exist.
241
242	=head2 Setting various callbacks
243
244	=over
245
246	=item SetMsgCallback [callback-function]
247
248	=item SetBusyCallback [callback-function]
249
250	=item SetFileCallback [callback-function]
251
252	=item SetFNameFilter [callback-function]
253
254	=back
255
256	=head2 Call the currently selected FNameFilter
257
258	=over
259
260	=item $file = FNameFilter $file
261
262	=back
263
264	=head2 Loading sourcefiles, optionally fuzzy merge and start decoding
265
266	=over
267
268	=item ($retval, $count) = LoadFile $fname, [$id, [$delflag, [$partno]]]
269
270	Load the given file and scan it for encoded contents. Optionally tag it
271	with the given id, and if C<$delflag> is true, delete the file after it
272	is no longer necessary. If you are certain of the part number, you can
273	specify it as the last argument.
274
275	A better (usually faster) way of doing this is using the C<SetFNameFilter>
276	functionality.
277
278	=item $retval = Smerge $pass
279
280	If you are desperate, try to call C<Smerge> with increasing C<$pass>
281	values, beginning at C<0>, to try to merge parts that usually would not
282	have been merged.
283
284	Most probably this will result in garbled files, so never do this by
285	default, except:
286
287	If the C<OPT_AUTOCHECK> option has been disabled (by default it is
288	enabled) to speed up file loading, then you I<have> to call C<Smerge -1>
289	after loading all files as an additional pre-pass (which is normally done
290	by C<LoadFile>).
291
292	=item $item = GetFileListItem $item_number
293
294	Return the C<$item> structure for the C<$item_number>'th found file, or
295	C<undef> of no file with that number exists.
296
297	The first file has number C<0>, and the series has no holes, so you can
298	iterate over all files by starting with zero and incrementing until you
299	hit C<undef>.
300
301	This function has to walk the linear list of fils on each access, so
302	if you want to iterate over all items, it is usually faster to use
303	C<GetFileList>.
304
305	=item @items = GetFileList
306
307	Similar to C<GetFileListItem>, but returns all files in one go, which is
308	very much faster for large number of items, and has no drawbacks when used
309	for a small number of items.
310
311	=back
312
313	=head2 Decoding files
314
315	=over
316
317	=item $retval = $item->rename ($newname)
318
319	Change the ondisk filename where the decoded file will be saved.
320
321	=item $retval = $item->decode_temp
322
323	Decode the file into a temporary location, use C<< $item->infile >> to
324	retrieve the temporary filename.
325
326	=item $retval = $item->remove_temp
327
328	Remove the temporarily decoded file again.
329
330	=item $retval = $item->decode ([$target_path])
331
332	Decode the file to its destination, or the given target path.
333
334	=item $retval = $item->info (callback-function)
335
336	=back
337
338	=head2 Querying (and setting) item attributes
339
340	=over
341
342	=item $state = $item->state
343
344	=item $mode = $item->mode ([newmode])
345
346	=item $uudet = $item->uudet
347
348	=item $size = $item->size
349
350	=item $filename = $item->filename ([newfilename})
351
352	=item $subfname = $item->subfname
353
354	=item $mimeid = $item->mimeid
355
356	=item $mimetype = $item->mimetype
357
358	=item $binfile = $item->binfile
359
360	=back
361
362	=head2 Information about source parts
363
364	=over
365
366	=item $parts = $item->parts
367
368	Return information about all parts (source files) used to decode the file
369	as a list of hashrefs with the following structure:
370
371	{
372	partno => <integer describing the part number, starting with 1>,
373	# the following member sonly exist when they contain useful information
374	sfname => <local pathname of the file where this part is from>,
375	filename => <the ondisk filename of the decoded file>,
376	subfname => <used to cluster postings, possibly the posting filename>,
377	subject => <the subject of the posting/mail>,
378	origin => <the possible source (From) address>,
379	mimetype => <the possible mimetype of the decoded file>,
380	mimeid => <the id part of the Content-Type>,
381	}
382
383	Usually you are interested mostly the C<sfname> and possibly the C<partno>
384	and C<filename> members.
385
386	=back
387
388	=head2 Functions below are not documented and not very well tested - feedback welcome
389
390	QuickDecode
391	EncodeMulti
392	EncodePartial
393	EncodeToStream
394	EncodeToFile
395	E_PrepSingle
396	E_PrepPartial
397
398	=head2 EXTENSION FUNCTIONS
399
400	Functions found in this module but not documented in the uulib documentation:
401
402	=over
403
404	=item $msg = straction ACT_xxx
405
406	Return a human readable string representing the given action code.
407
408	=item $msg = strerror RET_xxx
409
410	Return a human readable string representing the given error code.
411
412	=item $str = strencoding xxx_ENCODED
413
414	Return the name of the encoding type as a string.
415
416	=item $str = strmsglevel MSG_xxx
417
418	Returns the message level as a string.
419
420	=item SetFileNameCallback $cb
421
422	Sets (or queries) the FileNameCallback, which is called whenever the
423	decoding library can't find a filename and wants to extract a filename
424	from the subject line of a posting. The callback will be called with
425	two arguments, the subject line and the current candidate for the
426	filename. The latter argument can be C<undef>, which means that no
427	filename could be found (and likely no one exists, so it is safe to also
428	return C<undef> in this case). If it doesn't return anything (not even
429	C<undef>!), then nothing happens, so this is a no-op callback:
430
431	sub cb {
432	return ();
433	}
434
435	If it returns C<undef>, then this indicates that no filename could be
436	found. In all other cases, the return value is taken to be the filename.
437
438	This is a slightly more useful callback:
439
440	sub cb {
441	return unless $_[1]; # skip "Re:"-plies et al.
442	my ($subject, $filename) = @_;
443	# if we find some *.rar, take it
444	return $1 if $subject =~ /(\w+\.rar)/;
445	# otherwise just pass what we have
446	return ();
447	}
448
449	=back
450
451	=head1 LARGE EXAMPLE DECODER
452
453	The general workflow for decoding is like this:
454
455	=over
456
457	=item 1. Configure options with C<SetOption> or C<SetXXXCallback>.
458
459	=item 2. Load all source files with C<LoadFile>.
460
461	=item 3. Optionally C<Smerge>.
462
463	=item 4. Iterate over all C<GetFileList> items (i.e. result files).
464
465	=item 5. C<CleanUp> to delete files and free items.
466
467	=back
468
469	What follows is the file C<example-decoder> from the distribution that
470	illustrates the above worklfow in a non-trivial example.
471
472	#!/usr/bin/perl
473
474	# decode all the files in the directory uusrc/ and copy
475	# the resulting files to uudst/
476
477	use Convert::UUlib ':all';
478
479	sub namefilter {
480	my ($path) = @_;
481
482	$path=~s/^.*[\/\\]//;
483
484	$path
485	}
486
487	sub busycb {
488	my ($action, $curfile, $partno, $numparts, $percent, $fsize) = @_;
489	$_[0]=straction($action);
490	print "busy_callback(", (join ",",@_), ")\n";
491	0
492	}
493
494	SetOption OPT_RBUF, 128*1024;
495	SetOption OPT_WBUF, 1024*1024;
496	SetOption OPT_IGNMODE, 1;
497	SetOption OPT_IGNMODE, 1;
498	SetOption OPT_VERBOSE, 1;
499	SetOption OPT_AUTOCHK, 0;
500
501	# show the three ways you can set callback functions. I normally
502	# prefer the one with the sub inplace.
503	SetFNameFilter \&namefilter;
504
505	SetBusyCallback "busycb", 333;
506
507	SetMsgCallback sub {
508	my ($msg, $level) = @_;
509	print uc strmsglevel $_[1], ": $msg\n";
510	};
511
512	# the following non-trivial FileNameCallback takes care
513	# of some subject lines not detected properly by uulib:
514	SetFileNameCallback sub {
515	return unless $_[1]; # skip "Re:"-plies et al.
516	local $_ = $_[0];
517
518	# the following rules are rather effective on some newsgroups,
519	# like alt.binaries.games.anime, where non-mime, uuencoded data
520	# is very common
521
522	# if we find some *.rar, take it as the filename
523	return $1 if /(\S{3,}\.(?:[rstuvwxyz]\d\d\|rar))\s/i;
524
525	# one common subject format
526	return $1 if /- "(.{2,}?\..+?)" (?:yenc )?\(\d+\/\d+\)/i;
527
528	# - filename.par (04/55)
529	return $1 if /- "?(\S{3,}\.\S+?)"? (?:yenc )?\(\d+\/\d+\)/i;
530
531	# - (xxx) No. 1 sayuri81.jpg 756565 bytes
532	# - (20 files) No.17 Roseanne.jpg [2/2]
533	return $1 if /No\.[ 0-9]+ (\S+\....) (?:\d+ bytes )?\[/;
534
535	# try to detect some common forms of filenames
536	return $1 if /([a-z0-9_\-+.]{3,}\.[a-z]{3,4}(?:.\d+))/i;
537
538	# otherwise just pass what we have
539	()
540	};
541
542	# now read all files in the directory uusrc/*
543	for (<uusrc/*>) {
544	my ($retval, $count) = LoadFile ($_, $_, 1);
545	print "file($_), status(", strerror $retval, ") parts($count)\n";
546	}
547
548	Smerge -1;
549
550	SetOption OPT_SAVEPATH, "uudst/";
551
552	# now wade through all files and their source parts
553	for my $uu (GetFileList) {
554	print "file ", $uu->filename, "\n";
555	print " state ", $uu->state, "\n";
556	print " mode ", $uu->mode, "\n";
557	print " uudet ", strencoding $uu->uudet, "\n";
558	print " size ", $uu->size, "\n";
559	print " subfname ", $uu->subfname, "\n";
560	print " mimeid ", $uu->mimeid, "\n";
561	print " mimetype ", $uu->mimetype, "\n";
562
563	# print additional info about all parts
564	print " parts";
565	for ($uu->parts) {
566	for my $k (sort keys %$_) {
567	print " $k=$_->{$k}";
568	}
569	print "\n";
570	}
571
572	$uu->remove_temp;
573
574	if (my $err = $uu->decode) {
575	print " ERROR ", strerror $err, "\n";
576	} else {
577	print " successfully saved as uudst/", $uu->filename, "\n";
578	}
579	}
580
581	print "cleanup...\n";
582
583	CleanUp;
584
585	=head1 PERLMULTICORE SUPPORT
586
587	This module supports the perlmulticore standard (see
588	L<http://perlmulticore.schmorp.de/> for more info) for the following
589	functions - generally these are functions accessing the disk and/or using
590	considerable CPU time:
591
592	LoadFile
593	$item->decode
594	$item->decode_temp
595	$item->remove_temp
596	$item->info
597
598	The perl interpreter will be reacquired/released on every callback
599	invocation, so for performance reasons, callbacks should be avoided if
600	that is costly.
601
602	Future versions might enable multicore support for more functions.
603
604	=head1 BUGS AND LIMITATIONS
605
606	The original uulib library this module uses was written at a time where
607	main memory was measured in megabytes and buffer overflows as a security
608	thing didn't exist. While a lot of security fixes have been applied over
609	the years (including some defense in depth mechanism that can shield
610	against a lot of as-of-yet undetected bugs), using this library for
611	security purposes requires care.
612
613	Likewise, file sizes when the uulib library was written were tiny compared
614	to today, so do not expect this library to handle files larger than 2GB,
615	certainly not on a 32 bit host.
616
617	Lastly, this module uses a very "C-like" interface, which means it doesn't
618	protect you from invalid pointers as you might expect from "more perlish"
619	modules - for example, accessing a file item object after calling
620	C<CleanUp> will likely result in crashes, memory corruption, or worse.
621
622	=head1 AUTHOR
623
624	Marc Lehmann <schmorp@schmorp.de>, the original uulib library was written
625	by Frank Pilhofer <fp@informatik.uni-frankfurt.de>, and later heavily
626	bugfixed by Marc Lehmann.
627
628	=head1 SEE ALSO
629
630	perl(1), uudeview homepage at L<http://www.fpx.de/fp/Software/UUDeview/>.
631
632	=cut
633