C:\Documents and Settings\Administrator>\SFU\Perl\bin\Perl html2doc-server.pl
Server startup in 9 seconds on tcp/7422
New connection
3 1024-byte input buffers processed
Open temporary c:\SFU\tmp\s8o.0.html
Write temporary c:\SFU\tmp\s8o.0.html.doc
24 1024-byte output buffers processed
Done with connection
New connection
3 1024-byte input buffers processed
Open temporary c:\SFU\tmp\s8o.10.html
Write temporary c:\SFU\tmp\s8o.10.html.doc
24 1024-byte output buffers processed
Done with connection

$ cat input.html | socat STDIO TCP4:windows:7422 > output.doc
$ file output.doc
output.doc: Microsoft Office Document
$ cat input.html | socat STDIO TCP4:windows:7422 > output.doc
$ file output.doc
output.doc: empty

use IO::Socket;
use Win32::OLE qw(in with);
use Win32::OLE::Const 'Microsoft Word';
use Win32::OLE::Variant;
use IO::Handle;
use POSIX;

## This is a server that accepts HTML documents on port
## 7422, returning a Word document. As far as I know, it
## can only be run with ActiveState ActivePerl on Windows
## with Microsoft Word installed. Also, if using SFU,
## must run from C:\SFU\Perl\bin\Perl.exe, not the
## POSIX version at C:\SFU\usr\local\bin\perl. The POSIX
## version has no support for Win32::OLE. If anyone hacks
## OLE support into the POSIX version, let me know at:
## <inittab@unixdev.net>.

my $server_port = 7422;

my $current_time = time();

my $word;
eval {$word = Win32::OLE->GetActiveObject('Word.Application')};
die "Word not installed" if $@;
unless (defined $word) {
    $word = Win32::OLE->new('Word.Application', sub { $_[0]->Quit; })
        or die "Cannot start Word";
}

Win32::OLE->Option(Warn => 3);

$server = IO::Socket::INET->new(LocalPort => $server_port,
                                Proto     => 'tcp',
                                Type      => SOCK_STREAM,
                                Reuse     => 1,
                                Listen    => 5)
                    or die "Could not open server on tcp/$server_port 
+: $@\n";

print STDERR "Server startup in ", time() - $current_time, " seconds o
+n tcp/$server_port\n";

while ($client = $server->accept()) {
    print STDERR "New connection\n";

    ###TODO: GET REAL TEMPORARY FILENAME (this is hit-and-miss)
    my $file = "c:\\SFU\\tmp" . POSIX::tmpnam() . "0.html";

    ###RECEIVE HTML FROM CLIENT
    open(IFILE, ">$file") or next; #TODO: log error
    my $i = 0;
    my $buf = "";
    while (read($client, $buf, 1024, 0) > 0) {
        print IFILE $buf;
        $i++;
    }
    print STDERR "$i 1024-byte input buffers processed\n";
    undef $i;
    undef $buf;
    close(IFILE);

    print STDERR "Open temporary $file\n"; #TODO: if verbose
    my $doc = $word->{'Documents'}->Open("$file") or next; #TODO: log 
+error

    print STDERR "Write temporary $file.doc\n"; #TODO: if verbose
    $doc->SaveAs("$file.doc", {
                                 'FileFormat' => wdFormatDocument
                                 });
    $doc->Close();
    undef $doc;

    ###SEND DOC BACK TO CLIENT
    open(OFILE, "<$file.doc") or die "Could not open Office Document";
+ #TODO: log error
    binmode(OFILE);
    my $buf = "";
    my $i = 0;
    while (read(OFILE, $buf, 1024, 0) > 0) {
            print $client $buf;
            $i++;
    }
    print STDERR "$i 1024-byte output buffers processed\n";
    undef $i;
    undef $buf;
    close(OFILE);

    ###REMOVE TEMPORARY HTML & DOC
    unlink("$file") or print STDERR "ERROR: could not delete $file\n";
    unlink("$file.doc") or print STDERR "ERROR: could not delete $file
+.doc\n";

    $client->close;

    print STDERR "Done with connection\n";
}

undef $word;
close($server);
[download]