# $Id: UTF8Hack.pl,v 1.2 2003/02/26 16:23:31 akosut Exp $
# by Alexei Kosut <akosut@cs.stanford.edu>
#
# Adding utf8_hack="1" to a template tag will check its output for
# UTF-8 text.  If the output is not valid UTF-8, it is assumed to be
# ISO-8859-1, and is translated to UTF-8 appropriately.

use MT;
use MT::Template::Context;
use Text::Iconv;

use strict;
use warnings;

use bytes;

# "Borrowed" from the LiveJournal source code
sub is_utf8 ($) {
    return $_[0] =~ m/^([\x00-\x7f]|[\xc2-\xdf][\x80-\xbf]|\xe0[\xa0-\xbf][\x80-\xbf]|[\xe1-\xef][\x80-\xbf][\x80-\xbf]|\xf0[\x90-\xbf][\x80-\xbf][\x80-\xbf]|[\xf1-\xf7][\x80-\xbf][\x80-\xbf][\x80-\xbf])*$/;
}

MT::Template::Context->add_global_filter(utf8_hack => sub {
    my $s = shift;

    if (!is_utf8($s)) {
	$s = Text::Iconv->new("iso-8859-1", "utf-8")->convert($s);
    }

    return $s;
});