sub comparator {
my $str1 = shift @_;
my $str2 = shift @_;
my $original = '';
my $revised  = '';

my @from = split(/((?:<[^>]+>)+|(?:\s)+|(?:\w[A-Za-z'-]*\w*)+|(?:\W|\P{IsWord})|(?:\p{IsDigit}))/, $str1);
my @to   = split(/((?:<[^>]+>)+|(?:\s)+|(?:\w[A-Za-z'-]*\w*)+|(?:\W|\P{IsWord})|(?:\p{IsDigit}))/, $str2);

my $OS = qq|<span class="m">|;
my $OE = qq|</span> |;
my $RS = qq|<span class="hl">|;
my $RE = qq|</span> |;

  traverse_sequences( \@from, \@to,
    {
    MATCH     => sub { my $oldtext = $from[shift()]; $original .= $oldtext; $revised .= $oldtext },
    DISCARD_A => sub { my $oldtext = $from[shift()]; if ($oldtext =~ m/(?:\p{IsPunct})|(?:\s)/) {$original .= $oldtext } else { $original .= $OS.$oldtext.$OE } },
    DISCARD_B => sub { my $newtext = $to[pop()];     if ($newtext =~ m/(?:\p{IsPunct})|(?:\s)/) {$revised  .= $newtext } else { $revised  .= $RS.$newtext.$RE } },
    } );
    
	return ($original, $revised);
	
} #END SUB comparator