sub safe_encode { my $str = shift; $str =~ s{ ([\xC0-\xDF].|[\xE0-\xEF]..|[\xF0-\xFF]...) }{ XmlUtf8Decode($1) }xegs; $str } sub XmlUtf8Decode { my( $str, $hex ) = @_; my $len = length $str; my $n; if ( $len == 4 ) { my @n = unpack "C4", $str; $n = (($n[0] & 0x0f) << 18) + (($n[1] & 0x3f) << 12) + (($n[2] & 0x3f) << 6) + ($n[3] & 0x3f); } elsif ( $len == 3 ) { my @n = unpack "C3", $str; $n = (($n[0] & 0x1f) << 12) + (($n[1] & 0x3f) << 6) + ($n[2] & 0x3f); } elsif ( $len == 2 ) { my @n = unpack "C2", $str; $n = (($n[0] & 0x3f) << 6) + ($n[1] & 0x3f); } elsif ( $len == 1 ) { $n = ord $str; } else { die "bad value '$str' for XmlUtf8Decode"; } $hex ? sprintf( "&#x%x;", $n ) : "&#$n;" }