#!/usr/local/bin/perl
use strict;
use warnings;
# (Change configuration variables as needed.)
my $path_to_index = '/path/to/indexdir';
my $source  = '/path/to/datadir';
use File::Spec::Functions qw( catfile );
use Lucy::Plan::Schema;
use Lucy::Plan::FullTextType;
use Lucy::Analysis::EasyAnalyzer;
use Lucy::Index::Indexer;

# Create Schema.
my $schema = Lucy::Plan::Schema->new;
my $easyanalyzer = Lucy::Analysis::EasyAnalyzer->new(
    language => 'en',
);
my $title_type = Lucy::Plan::FullTextType->new( 
    analyzer => $easyanalyzer,
);
my $content_type = Lucy::Plan::FullTextType->new(
    analyzer      => $easyanalyzer,
    highlightable => 1,
	 boost         => 2.0,   
);
my $url_type = Lucy::Plan::StringType->new( indexed => 0, );
my $cat_type = Lucy::Plan::StringType->new( stored => 0, );
$schema->spec_field( name => 'title',    type => $title_type );
$schema->spec_field( name => 'content',  type => $content_type );
$schema->spec_field( name => 'url',      type => $url_type );
$schema->spec_field( name => 'category', type => $cat_type );

# Create an Indexer object.
my $indexer = Lucy::Index::Indexer->new(
    index    => $path_to_index,
    schema   => $schema,
    create   => 1,
    truncate => 1,
);

# Collect names of source files.
opendir( my $dh, $source )
    or die "Couldn't opendir '$source': $!";
my @filenames = grep { $_ =~ /\.txt/ } readdir $dh;

# Iterate over list of source files.
for my $filename (@filenames) {
    print "Indexing $filename\n";
    my $doc = parse_file($filename);
    $indexer->add_doc($doc);
}

# Finalize the index and print a confirmation message.
$indexer->commit;
print "Finished.\n";

# Parse a file from our US Constitution collection and return a hashref with
# the fields title, body, url, and category.
sub parse_file {
    my $filename = shift;
    my $filepath = catfile( $source, $filename );
    open( my $fh, '<', $filepath ) or die "Can't open '$filepath': $!";my $text='';
	while(<$fh>){$text .= "$_";}
#   my $text = do { local "$_\n"; <$fh> };    # slurp file content
    
    #my $title    = $1;
    my $bodytext = $text ;
    my $category
        = $filename =~ /sample/      ? 'Student'
            :   die "Can't derive category for $filename";
    return {
        title    => $category,
        content  => $bodytext,
        url      => "/home/kbs/datadir/$filename",
        category => $category,
	
    };
}


##</code><code>##

#!/usr/bin/perl
use strict;
use warnings;
my $path_to_index = '/path/to/indexdir';
use CGI;
use List::Util qw( max min );
use POSIX qw( ceil );
use Encode qw( decode );
use Lucy::Search::IndexSearcher;
use Lucy::Highlight::Highlighter;
use Lucy::Search::QueryParser;
use Lucy::Search::TermQuery;
use Lucy::Search::ANDQuery;
my $cgi       = CGI->new;
my $q         = decode( "UTF-8", $cgi->param('q') || '' );
my $offset    = decode( "UTF-8", $cgi->param('offset') || 0 );
my $category  = decode( "UTF-8", $cgi->param('category') || '' );
my $page_size = 10;
# Create an IndexSearcher and a QueryParser.
my $searcher = Lucy::Search::IndexSearcher->new( 
    index => $path_to_index,
);
my $qparser = Lucy::Search::QueryParser->new( 
    schema => $searcher->get_schema,
);

# Build up a Query.
my $query = $qparser->parse($q);
if ($category) {
    my $category_query = Lucy::Search::TermQuery->new(
        field => 'category', 
        term  => $category,
    );
    $query = Lucy::Search::ANDQuery->new(
        children => [ $query, $category_query ]
    );
}

# Execute the Query and get a Hits object.
my $hits = $searcher->hits(
    query      => $query,
    offset     => $offset,
    num_wanted => $page_size,
);
my $hit_count = $hits->total_hits;

# Arrange for highlighted excerpts to be created.
my $highlighter = Lucy::Highlight::Highlighter->new(
    searcher => $searcher,
    query    => $q,
    field    => 'content'
);

# Create result list.
my $report = '';
while ( my $hit = $hits->next ) {
    my $score   = sprintf( "%0.3f", $hit->get_score );
    my $excerpt = $highlighter->create_excerpt($hit);my @exi=split (/\n/,$excerpt);
	
    $report .= qq|
        <p>
          <strong>$hit->{title}</strong></a>
          <em>$score</em> ; 
foreach my $v(@exi){
	if ($v=~ /$q/){
		$report .= qq|
		          <br />
			          $v 
		          <br />|;
			}
	
		}
	$report .= qq|
          <span class="excerptURL">$hit->{url}</span>
        </p>
    |;
}
blast_out_content( $q, $report );
sub blast_out_content {
    my ( $query_string, $hit_list, $paging_info, $category_select ) = @_;
    my $escaped_q = CGI::escapeHTML($query_string);
    binmode( STDOUT, ":encoding(UTF-8)" );
    print qq|Content-type: text/html; charset=UTF-8\n\n|;
    print qq|
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
    "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
  <meta http-equiv="Content-type" 
    content="text/html;charset=UTF-8">
  <link rel="stylesheet" type="text/css" 
    href="/us_constitution/uscon.css">
  <title>Lucy: $escaped_q</title>
</head>

<body>

  <div id="navigation">
    <form id="usconSearch" action="">
      <strong>
        Search the Name:
      </strong>
      <input type="text" name="q" id="q" value="$escaped_q">
      
      <input type="submit" value="=&gt;">
    </form>
  </div><!--navigation-->

  <div id="bodytext">

  $hit_list

  $paging_info

  </div><!--bodytext-->
    <p style="font-size: smaller; color: #666">
      <em>
       
      </em>
    </p>
  </div><!--bodytext-->

</body>

</html>
|;
}


##</code><code>##

ID	Name	Dept	Addr
1	Chella	IT	cbe
2	Sara	CSE	cbe
3	aaaaa	EEE	CBE
4	chella	CSE	thi
5	sara	ECE	che
6	dddd	MECH	che