package Apache2::Highlights;

# highlights.cgi - create lists from a MyLibrary database

# Eric Lease Morgan <eric_morgan@infomotions.com>
# September 8, 2009  - first investigations; based on MyLibary, obviously
# September 12, 2009 - added search; tweaked wording
# September 13, 2009 - tweaked keywords; made it a package
# September 15, 2009 - tweaked about

# configure
use constant INSTANCE       => 'highlights';
use constant LOCATION_LOCAL => 2;
use constant SOLR           => 'http://localhost:210/solr/highlights';
use constant CMDTERM        => 'term';

# require/use
use Apache2::Const -compile => qw( OK );
use CGI;
use MyLibrary::Core;
use strict;
use WebService::Solr;

sub handler {

	# initialize
	my $r    = shift;
	my $html = '';
	my $cgi = CGI->new;
	my $cmd  = $cgi->param( 'cmd' );
	MyLibrary::Config->instance( INSTANCE );
	
	# branch accordingly
	if ( ! $cmd ) {
	
		# display the home page
		$html = &template;
		$html =~ s/##CONTENT##/&home/e;
		$html =~ s/##QUERY##//e;
		$html =~ s/##NUMBER_OF_RESOURCES##/&number_of_items/e;
		$html =~ s/##FACETS##/&facet_term_combinations( $cgi )/e;
			
	}
	
	elsif ($cmd eq 'about') {
	
		# display the home page
		$html = &template;
		$html =~ s/##CONTENT##/&about/e;
		$html =~ s/##QUERY##//e;
			
	}
	
	elsif ( $cmd eq 'search' ) {
	
		my $solr     = WebService::Solr->new( SOLR );
		my $query    = $cgi->param( 'query' );
		my $response = $solr->search( $query );
		my @hits     = $response->docs;
		my $hits     = $#hits + 1;
	
		# build the hit list
		my $list = '';
		foreach my $doc ( @hits ) {
		
			# slurp
			my $id             = 'h-' . $doc->value_for( 'id' );
			my $name           = $doc->value_for( 'name' );
			my $note           = $doc->value_for( 'note' );
			my $creator        = $doc->value_for( 'creator' );
			my $date_published = $doc->value_for( 'date_published' );
			my $date_read      = $doc->value_for( 'date_read' );
			my $source         = $doc->value_for( 'source' );
			my $rights         = $doc->value_for( 'rights' );
			my $local_url      = $doc->value_for( 'local_url' );
			my $remote_url     = $doc->value_for( 'remote_url' );
			my @formats        = $doc->values_for( 'Formats' );
			my @keywords       = $doc->values_for( 'facet_subject' );
			my @themes         = $doc->values_for( 'Themes' );
	
			# details
			my $sublist = '';
			if ( $creator )        { $sublist .= $cgi->li( "<b>Creator(s)</b> - $creator" ) }
			if ( $date_published ) { $sublist .= $cgi->li( "<b>Date published</b> - $date_published" ) }
			if ( $date_read )      { $sublist .= $cgi->li( "<b>Date read</b> - $date_read" ) }
			if ( $source )         { $sublist .= $cgi->li( "<b>Source</b> - $source" ) }
			if ( $rights )         { $sublist .= $cgi->li( "<b>Rights</b> - $rights" ) }
			if ( $remote_url )     { $sublist .= $cgi->li( "<b>Remote URL</b> - " . $cgi->a({ href => $remote_url }, $remote_url )) }
			
			my $keywords = '';
			foreach ( @keywords ) { $keywords .= "$_; " }
			if ( $keywords ) { $sublist .= $cgi->li( "<b>Keywords</b> - $keywords" ) }
			
			my $formats = '';
			foreach ( @formats ) { $formats .= "$_; " }
			$sublist .= $cgi->li( "<b>Formats</b> - $formats" );
			
			my $themes = '';
			foreach ( @themes ) { $themes .= "$_; " }
			$sublist .= $cgi->li( "<b>Themes</b> - $themes" );
	
			$sublist = $cgi->ul( {style => 'margin-bottom: 1em'}, $sublist );
			$sublist = $cgi->div({ -id => $id, -style => 'display: none' }, $sublist );
	
			# create the hit list
			$list .= $cgi->li( $cgi->a({ href => $local_url }, $name ) . " - $note". ' &nbsp;' . $cgi->a({ -href => "javascript:expand('$id')", -style => 'color: grey; text-decoration: none' }, 'details...' ) . $sublist );
	
		}
		$list = $cgi->ol( $list );
	
		# display the page
		$html = &template;
		$html =~ s/##CONTENT##/&results/e;
		$html =~ s/##QUERY##/$query/ge;
		$html =~ s/##HITS##/$hits/e;
		$html =~ s/##RESULTS##/$list/e;
	
	}
	
	elsif ($cmd eq 'term') {
	
		# get the input and find the term
		my $term_id = $cgi->param('id');
		my $term = MyLibrary::Term->new( id => $term_id );
	
		# build an html list of resources for the input
		my @resource_ids = $term->related_resources( sort => 'name' );
		my $list;
		foreach my $id ( @resource_ids ) {
		
			# get this resouce
			my $resource = MyLibrary::Resource->new( id => $id );
			
			# urls
			my $local_url = '';
			foreach ( $resource->resource_locations ) {
		
				if ( $_->resource_location_type == LOCATION_LOCAL ) { $local_url  = $_->location }
				
			}
			
			# build a list
			$list .= $cgi->li($cgi->a({-href => $local_url}, $resource->name ) . ' - ' . $resource->note);
			
		}
		$list = $cgi->ol($list);
		
		# display the about page
		$html = &template;
		$html =~ s/##CONTENT##/&term/e;
		$html =~ s/##QUERY##//e;
		$html =~ s/##TERM##/$term->term_name/e;
		$html =~ s/##TERM_NOTE##/$term->term_note/e;
		$html =~ s/##RESOURCE_LIST##/$list/e;
		
	}
			
	# done
	$html =~ s/##VERSION##/MyLibrary->version/e;
	$r->content_type( 'text/html' );
	$r->print( $html );
	return Apache2::Const::OK;

}


sub number_of_items { return scalar(MyLibrary::Resource->get_resources(output => 'id')) }


sub facet_term_combinations {

	my $cgi = shift;
	
	# get all the facets, build a list, and display it
	my @facets = MyLibrary::Facet->get_facets (sort => 'name');
	my $items;
	foreach (@facets) {
	
		# create a list of terms associated with each facet
		my $terms = '<ol>';
		foreach my $id ($_->related_terms(sort => 'name')) {
		
			my $term = MyLibrary::Term->new(id => $id);
			$terms .= '<li><a href="?cmd=' . CMDTERM . '&id=' . $id .  '">' . $term->term_name . '</a> <span style="color: gray"> (' . scalar($term->related_resources) . ' items)</span></li>';
		}
		
		$terms .= '</ol>';
		
		# build the list
		$items .= $cgi->li('<span style="font-weight: bold">' . $_->facet_name, '</span> - ', $_->facet_note, $terms);
		
	}
	
	# done
	return $cgi->ol($items);
	
}


sub term {

	return <<EOF;
<h1>Highlights &amp; Annotations - ##TERM##</h1>
<p>##TERM_NOTE##</p>
##RESOURCE_LIST##

EOF

}

sub template {

	return <<EOF;
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
    <head>
        <title>Highlights &amp; Annotations</title>
		<script type="text/javascript">
			function expand( id ) {
				var details = document.getElementById( id );
				details.style.display = ( details.style.display == 'block' ) ? 'none' : 'block';
			}
		</script>
		<style>
			body {
				margin-left: 5%;
				margin-right: 5%;
				margin-top: 5%;
				font-family: Arial;
				font-size: medium;
			}
			.menu {
				float: left;
				padding-right: 10px;
				text-align: right;
				width: 18%;
			}
			.menu li {
				list-style: none;
				font-size: medium;
			}
			.content {
				margin-left: 23%;
				text-align: left;
			}
			.footer {
				border-top: 1px solid #778;
				margin-top: 1em;
				text-align: left;
				font-size: small;
			}
		</style>
    </head>
    <body>
        <div class='menu'>
			<ol><li><a href="./highlights.cgi">Home</a></li>
			<li><a href="./highlights.cgi?cmd=about">About</a></li>
			</ol>
			<form method='get' action='./highlights.cgi'>
			<input type='hidden' name='cmd' value='search' />
			<input type='text' name='query' value='##QUERY##' />
			<input type='submit' />
			</form>
        </div>
        <div class="content">
        
        ##CONTENT## 
        
        <div class='footer'>
<p style='float: right; font-size: small;'>Managed with <a href='http://search.cpan.org/dist/MyLibrary/'>MyLibrary</a> version ##VERSION##</p>
<p>Author: Eric Lease Morgan &lt;<a href="mailto:eric_morgan\@infomotions.com">eric_morgan\@infomotions.com</a>&gt;<br />
            Date created: 2009-09-12
            <br />Date updated: 2009-09-15
            <br />URL: 
            <a href="http://infomotions.com/highlights/">http://infomotions.com/highlights/</a></p>
        </div></div>
    </body>
</html>

EOF

}

sub results {

	return <<EOF;
<h1>Search results</h1>
<p>Your search -- <b>##QUERY##</b> -- found ##HITS## hit(s):</p>
##RESULTS##

EOF

}


sub home {

	return <<EOF;
<h1>Highlights &amp; Annotations: A value-added reading list</h1>
<p>This is a collection of things I've read with complete access to PDF versions. The collection presently includes <b>##NUMBER_OF_RESOURCES## items</b> divided into the following set of facets and terms:</p>
##FACETS##

EOF

}


sub about {

	return <<EOF;
<h1>About Highlights &amp; Annotations</h1>
<p> I have been having fun recently indexing PDF files. </p>

<p> For the pasts six months or so I have been keeping the articles I've read in a pile, and I was rather amazed at the size of the pile. It was about a foot tall. When I read these articles I "actively" read them -- meaning, I write, scribble, highlight, and annotate the text with my own special notation denoting names, keywords, definitions, citations, quotations, list items, examples, etc. This active reading process: 1) makes for better comprehension on my part, and 2) makes the articles easier to review and pick out the ideas I thought were salient. Being the librarian I am, I thought it might be cool ("kewl") to make the articles into a collection. Thus, the beginnings of Highlights &amp; Annotations: A Value-Added Reading List. </p>

<p> The techno-weenie process for creating and maintaining the content is something this community might find interesting: </p>

<ol>
	<li>Print article and read it actively.</li>

	<li>Convert the printed article into a PDF file -- complete with embedded OCR -- with my handy-dandy <a href="http://tinyurl.com/oafgwe">ScanSnap scanner</a>.</li>

	<li>Use <a href="http://infomotions.com/tmp/mylibrary.png">MyLibrary</a> to create metadata (author, title, date published, date read, note, keywords, facet/term combinations, local and remote URLs, etc.) describing the article.</li>

	<li>Save the PDF to my file system.</li>

	<li>Use <a href="http://www.foolabs.com/xpdf/">pdttotext</a> to extract the OCRed text from the PDF and index it along with the MyLibrary metadata using <a href="http://lucene.apache.org/solr/">Solr</a>.</li>

	<li>Provide a searchable/browsable <a href="http://infomotions.com/highlights/highlights.cgi">user interface</a> to the collection through a mod_perl <a href="http://infomotions.com/highlights/Highlights.pl">module</a>.</li>
</ol>

<p> Software is never done, and if it were then it would be called hardware. Accordingly, I know there are some things I need to do before I can truely deem the system version 1.0. At the same time my excitment is overflowing and I thought I'd share some geekdom with my fellow hackers.</p>

<p>Fun with PDF files and open source software. </p>



EOF

}


1; # return true or die