This is just a sample script that shows how you can use the
HTML::Parser to safely downcase the tag namess and attribute names in
an HTML file.  It will go into the eg/ directory of the next
HTML::Parser release.

Regards,
Gisle

--------------------------------------------------------------
#!/usr/bin/perl -w

use strict;
use HTML::Parser ();

HTML::Parser->new(start_h   => [ \&start_lc, "tokenpos, text" ],
                  end_h     => [ sub { print lc shift }, "text" ],
                  default_h => [ sub { print shift }, "text" ],
                 )
    ->parse_file(shift) || die "Can't open file: $!\n";

sub start_lc {
    my($tpos, $text) = @_;
    for (my $i = 0; $i < @$tpos; $i += 2) {
        next if $i && ($i/2) % 2 == 0;  # skip attribute values
        $_ = lc $_ for substr($text, $tpos->[$i], $tpos->[$i+1]);
    }
    print $text;
}

Reply via email to