#!/usr/local/bin/perl

# Convert UTF-8 encoded files to use numerical character references
# i.e. 係

if ($#ARGV == -1) {
    print "Please supply the name of the file to convert.\n";
}

open(FD, $ARGV[0]) or die "Can't open $!\n";
while ($inline = <FD>) {
    chomp($inline);
    @chars = ();
    $outline = "";
    (@chars) = 
	($inline =~ m/([\x01-\x7f]|
		       [\xc0-\xdf][\x80-\xbf]|
		       [\xe0-\xef][\x80-\xbf][\x80-\xbf])/xg);
    foreach $char (@chars) {
	if (length($char) == 1) {
	    $outline .= $char;
	} elsif (length($char) == 2) {
	    $unival = (vec($char, 0, 8) & 0x1f) * 0x40 + 
		(vec($char, 1, 8) & 0x3f);
	    $outline .= "\&#$unival;";
	} elsif (length($char) == 3) {
	    $unival = (vec($char, 0, 8) & 0x0f) * 0x1000 + 
		(vec($char, 1, 8) & 0x3f) * 0x40 +
		(vec($char, 2, 8) & 0x3f);
	    $outline .= "\&#$unival;";
	}
    }
    print $outline . "\n";
}
close(FD);