#!/usr/bin/perl

use CGI::Carp qw(fatalsToBrowser);
use strict;
use warnings;
use CGI;
use File::Find;
use HTML::Parser;

my $cgi     = CGI->new();
print $cgi->header(type => 'text/plain');
my %params  = $cgi->Vars();
my $string  = '';
my $basedir = '/home/netzgrafik/www.lottermoser.at/test/';

my @files = ();
find(\&find_files,$basedir);
my %includes = search($params{terms},\@files);
print_found($params{terms},\%includes);

sub find_files{
    push(@files,$File::Find::name) if(-f $File::Find::name && $_ =~ /\.htm$/);
}

sub print_found{
    my ($terms,$hashref) = @_;
    print $terms," found in:\n";
    foreach my $key(keys(%$hashref)){
        print $key."\n" if($hashref->{$key} eq 'yes');
    }
}

sub search{
    my ($termsstring,$files) = @_;
    my @terms = split(/\s+/,$termsstring);
    
    my $parser = HTML::Parser->new(
                             api_version => 3,
                             start_h     => [\&start,"self,tagname,attr"],
                             text_h      => [\&text,"self,dtext"],
                             end_h       => [\&end,"self,tagname"]);

    my %include;
    for my $html_file(@$files){
        $string = '';
        $parser->parse_file($html_file);

        foreach my $term (@terms) {
            $term = umlauts($term);
            if ($string =~ /$term/) {
                $include{$html_file} = 'yes';
                last;
            }
            else {
                $include{$html_file} = 'no';
            }
        }
    }
    return %include;
}

sub start{
    my ($self,$tag,$attr) = @_;
    if($tag eq 'div' && $attr->{class} eq 'scroll'){
        $self->{search} = 1;
    }
}

sub text{
    my ($self,$dtext) = @_;
    $string .= $dtext if($self->{search});
}

sub end{
    my ($self,$tag) = @_;
    if($tag eq 'div'){
        $self->{search} = 0;
    }
}  
      
sub umlauts{
    my ($term) = @_;
    $term=~ s/&”/ä\;/g;
    $term=~ s/¾/Ä\;/g;
    $term=~ s/&–/ö\;/g;
    $term=~ s/÷/Ö\;/g;
    $term=~ s/&¸/ü\;/g;
    $term=~ s/Ð/Ü\;/g;
    $term=~ s/þ/ß\;/g;
    return $term;
}

       foreach $term (@terms) {
           $term = umlauts($term);

       foreach my $term (@terms) {
           $term = umlauts($term);

print $cgi->header(type => 'text/plain');

print $cgi->header(-type => 'text/plain');

#!/usr/bin/perl

use CGI::Carp qw(fatalsToBrowser);
use strict;
use warnings;
use CGI;
use File::Find;
use HTML::Parser;

my $cgi     = CGI->new();
print $cgi->header(-type => 'text/plain');
my %params  = $cgi->Vars();
my $string  = '';
my $title      = '';
my $basedir = '/home/netzgrafik/www.lottermoser.at/test/';
my $base_url = 'http://www.lottermoser.at/';
my $hp_title = 'Alu - Lottermoser';

# hier noch den Pfad zur Vorlage eintragen
my $template = '';

my @files = ();
find(\&find_files,$basedir);
my ($includes) = search($params{terms},\@files);
print_html($base_url,$template,$hp_title,$params{terms},$includes);

sub find_files{
    push(@files,$File::Find::name) if(-f $File::Find::name && $_ =~ /\.htm$/);
}

sub print_found{
    my ($base,$template,$title,$terms,$hashref) = @_;

     my $content = '';
     {
         local $/;
         open(my $fh,'<',$template) or die $!;
         $content = <$fh>;
         close $fh;
     }

     my $html = '<ul>';
     for my $key(keys(%$hashref)){
         $html .= '<li><a href="'.$base.$key.'">'.$hashref->{$key}."</li>\n";
     }
     $html .= qq~</ul><hr align="left" width="100%" size="2" noshade color="#00007F">\n
              <font color="#00007F">Such Information:</font><p>
              <ul>\n<li><b><FONT COLOR=#00007F>Suchbegriff:</FONT></b>~;

    $html.= join(", ",split(/\s+/,$terms));

    $html .= qq~<li><a href="$base">$title</a>\n</ul>
                   <hr align="left" width="100%" size="2" noshade color="#00007F">
                   <a href="http://www.netzgrafik.com/">netzgrafik.com</a>.\n~;

     $content =~ s/\$Titel/$title/;
     $content =~ s/\$Message/$html/;

     print $content;
}

sub search{
    my ($termsstring,$files) = @_;
    my @terms = split(/\s+/,$termsstring);
   
    my $parser = HTML::Parser->new(
                            api_version => 3,
                            start_h     => [\&start,"self,tagname,attr"],
                            text_h      => [\&text,"self,dtext"],
                            end_h       => [\&end,"self,tagname"]);

    $parser->{divs} = 0;

    my %include;
    for my $html_file(@$files){
        $string = '';
        $title = '';
        $parser->parse_file($html_file);

        foreach my $term (@terms) {
            $term = umlauts($term);

            # hier wurde noch das "i" angefügt für "ignore case" also
            # matching ohne Berücksichtigung von Groß- und Kleinschreibung

            if ($string =~ /$term/i) {
                $include{$html_file} = $title;
                last;
            }
        }
    }
    return \%include;
}

sub start{
    my ($self,$tag,$attr) = @_;
    if($tag eq 'div' && $attr->{class} eq 'scroll'){
        $self->{search} = 1;
    }
    if($tag eq 'div' and $self->{search}){
        $self->{divs}++;
    }
    if($tag eq 'title'){
        $self->{title} = 1;
    }
}

sub text{
    my ($self,$dtext) = @_;
    $string .= $dtext if($self->{search});
    $title = $dtext if($self->{title});
}

sub end{
    my ($self,$tag) = @_;
    if($tag eq 'div' and $self->{search}){
        $self->{divs}--;
    }
    if($self->{divs} == 0){
        $self->{search} = 0;
    }
    if($tag eq 'title'){
        $self->{title} = 0;
    }
}  
     
sub umlauts{
    my ($term) = @_;
    $term=~ s/&”/ä\;/g;
    $term=~ s/¾/Ä\;/g;
    $term=~ s/&–/ö\;/g;
    $term=~ s/÷/Ö\;/g;
    $term=~ s/&¸/ü\;/g;
    $term=~ s/Ð/Ü\;/g;
    $term=~ s/þ/ß\;/g;
    return $term;
}