#!/usr/bin/perl
#
# Converting MSWord to HTML for use with MHonArc.
# Written by Frank Ronny Larsen June 2000
#
# Uses wvHtml from the wv package.
# Supports: Converting MSWord to HTML
# Downloading of original MSWORD
#
# TODO?: Images in Word-doc. Currently the version of wvHtml that I use
# do not convert the images, due to lack of libraries. Therefore
# this is not implemented here either.
#
package m2h_application_msword;
require 'mhmimetypes.pl';
$wvHtml = "/usr/local/bin/wvHtml -c iso-8859-15";
sub filter {
local($header, *fields, *data, $decoded, $args) = @_;
my $txt = "";
# Require MHonArc to decode the data.
if(!$decoded) {
return ("MHonArc did not manage to decode the MSWord data.
Probably weird encoding of the e-mail transmission.");
};
## Get content-type
my ($ctype) = split ';', $fields{'content-type'};
$ctype =~ tr/A-Z/a-z/;
# Write file so users can download the Worddoc itself.
my $filename = mhonarc::write_attachment( $ctype, \$data );
# Run wvHtml on the .doc file.
open C, "$wvHtml $mhonarc::OUTDIR/$filename |";
@Html = ;
close C;
# Strip HTML header. (Maybe use MHonArcs mh_text_html code for this?)
$txt = join ' ', @Html;
$txt =~ s|\n| |g;
$txt =~ s|^.*(.*)