use Benchmark qw(cmpthese timethese);
$rex1=qr!
(<[^/]([^>]*[^/>])?>)|(</[^>]*>)|(<[^>]*/>)|
(
    [\p{Lu}\p{Ll}\p{Lt}\p{Nd}\p{Nl}\p{No}\x{4e00}-\x{9fa5}\x{3007}\x{3021}-\x{3029}]
    (?:
        [-\p{Lu}\p{Ll}\p{Lt}\p{Nd}\p{Nl}\p{No}._:''\x{4e00}-\x{9fa5}\x{3007}\x{3021}-\x{3029}]*
        [\p{Lu}\p{Ll}\p{Lt}\p{Nd}\p{Nl}\p{No}\x{4e00}-\x{9fa5}\x{3007}\x{3021}-\x{3029}]
    )?
)!x;

$rex2=qr!(<[^/]([^>]*[^/>])?>)|(</[^>]*>)|(<[^>]*/>)|
((\p{Lu}|\p{Ll}|\p{Lt}|\p{Nd}|\p{Nl}|\p{No}|[\x{4e00}-\x{9fa5}]|\x{3007}
|[\x{3021}-\x{3029}])((\p{Lu}|\p{Ll}|\p{Lt}|\p{Nd}|\p{Nl}|\p{No}|[-._:'']
|[\x{4e00}-\x{9fa5}]|\x{3007}|[\x{3021}-\x{3029}])*(\p{Lu}|\p{Ll}|\p{Lt}
|\p{Nd}|\p{Nl}|\p{No}|[\x{4e00}-\x{9fa5}]|\x{3007}|[\x{3021}-\x{3029}]))?)!x;

$html=get_text(); # fix this!

my $test={'rex1'=>'$count1=0; $count1++ while $html=~/$rex1/g;',
          'rex2'=>'$count2=0; $count2++ while $html=~/$rex2/g;',};
timethese(-1,$test);
cmpthese(-1,$test);


print "$count1\n$count2\n";

sub get_text {
    return <<'EOFTEXT';
*** PUT SOME HTML/XML HERE ***
EOFTEXT
}