HTML Validation script using only CPAN modules. Originally http://www.w3.org/mid/[email protected]

validate.pl

#!perl -w

BEGIN
{
    $ENV{SP_CHARSET_FIXED} = 1;      
    $ENV{SP_ENCODING}      = "UTF-8";
    $ENV{SP_BCTF}          = "UTF-8";
}

sub ErrorHandler::new {bless {p=>$_[1]}, shift}
sub ErrorHandler::error
{
  push @{$_[0]->{errors}}, $_[0]->{p}->split_message($_[1])
}

use strict;
use warnings;
use SGML::Parser::OpenSP 0.99 qw();
use HTML::Encoding            qw();
use HTML::Doctype             qw();
use LWP::UserAgent            qw();
use Encode                    qw();
use I18N::Charset             qw();

our $HTML_CATALOG = "sgml.soc";
our $XML_CATALOG  = "xml.soc";
our @SP_OPTS =
qw/
  non-sgml-char-ref
  valid
  no-duplicate
/;

my $u = LWP::UserAgent->new;
my $p = SGML::Parser::OpenSP->new;
my $h = HTML::Doctype::Detector->new($p);
my $e = ErrorHandler->new($p);

my $r = $u->get("http://www.sun.com");

my $name1 = HTML::Encoding::encoding_from_http_message($r);
my $name2 = I18N::Charset::enco_charset_name($name1);
my $text = Encode::decode($name2 => $r->content);

# XHTML detection
$p->handler($h);
$p->catalogs($HTML_CATALOG);
$p->parse_string($text);

my $is_xhtml = $h->is_xhtml;

# Validation
$p->handler($e);
$p->catalogs($is_xhtml ? $XML_CATALOG : $HTML_CATALOG);
$p->warnings(@SP_OPTS, $is_xhtml ? 'xml' : ());
$p->parse_string($text);

foreach my $error (@{$e->{errors}})
{
    my $prim = $error->{primary_message};
    printf "[%4d %4d %s]: %s\n",
      $prim->{LineNumber},
      $prim->{ColumnNumber},
      $prim->{Severity},
      $prim->{Text}
}