#!c:/perl/bin/perl

#This version allows the use of a filename specified on the command line
use strict;
use warnings;

package HTMLStrip;
use base "HTML::Parser";
#system("cls");
my $output = "c:/perl/bin/parseOutput.txt";
if (-e $output) {
    unlink $output;
}
open PARSETEXT,'>',$output or die $!;
my $p = new HTMLStrip;
# parse line-by-line, rather than the whole file at once
    while (<>) {
        $p->parse($_);
    }
# flush and parse remaining unparsed HTML
$p->eof;
close PARSETEXT;

sub text {
    my ($self, $text) = @_;
    chomp($text);
    $text =~ s/#.*//;            # comments
    $text =~ s/^\s+//;           # leading whitespace
    $text =~ s/\s+$//;           # trailing whitespace
    #Once the beginning comment if found, remove style
    if ($text =~ /^<\!--$/) {
        next unless ($text =~ /^-->$/);
    }
    #Print non-blank lines
    if (length($text) > 0) {
        print PARSETEXT $text . "\n";
    }
}

#Process OPENING/STARTING HTML tags
sub start {
    my ($self, $tag, $attr, $attrseq, $origtext) = @_;
    
    #We're only interested in dealing with table tags
    if ($tag =~ /^table$/) {
        print PARSETEXT "\n************* BEGIN TABLE ****************\n";
    }
    if ($tag =~ /^tr$/) {
        print PARSETEXT "\n";
    }
    if ($tag =~ /^td$/) {
        print PARSETEXT "\t";
        if (defined $attr->{'class'}) {
            if ($attr->{'class'} =~ /alarmClear/) {
                print PARSETEXT "OK";
            }
            if ($attr->{'class'} =~ /alarmSet/) {
                print PARSETEXT "ALARM";
            }
        }    
    }
}

#Process CLOSING/ENDING HTML tags
sub end {
    my($self, $tag, $origtext) = @_;
    if ($tag =~ /^table$/) {
        print PARSETEXT "\n************* END TABLE ****************\n";
    }
}