#!/usr/bin/perl 
# Change the above line to reflect the location of your installation of PERL
#
# -------------------------------------------------------------------
# Program: swish-cgi.pl
# Author : John Millard (millarj@muohio.edu)
#
# Purpose: A gateway interface (CGI) to the SWISH Searcher/indexer
#
# Instructions: 
#
# 1. Install and configure SWISH -- 
#    Available from Enterprise Integration Technologies at 
#    http://www.eit.com/goodies/software/swish/swish.html
#
# 2. Index your site so that SWISH returns the url for each file
#    ie.  Swish should return http://www.yoursite.edu/file_name.html
#    See the SWISH documentation about REPLACE_RULES to see how.
#
# 3. Customize the User-Defined variables below to reflect your site.
#
# 4. Install this file in your cgi directory.  This may vary 
#    from site to site, but is usually in a directory like cgi-bin
#   
# 5. Create a link from your pages to the cgi
#    ex.  http://www.yoursite.edu/cgi-bin/swish-cgi
#    Running the cgi as a URL will generate a blank query form on the fly.
#    
#
# Note: if you don't like the the initial form that comes up, you can modify
#       the print_form subroutine
# 
#       To change the format of the returned results, you may modify the 
#       print_results subroutine

# -------- User defined configuration variables -----------

# Absolute path and command to execute the SWISH searcher
   $swish = "/usr/bin/swish-e";     

# URL of where you put this cgi
   $swishcgi = "index.cgi";

# Optional parameters to pass to the SWISH searcher
   $params = " ";                            

# Absolute path and filename of your created swish index file 
   $index = "/home/xml4lib/search/index.swish-e";

# The Full name of your organization -- Printed with Search Results
   $organization = "XML4Lib Electronic Discussion";

# The full name of your department -- Printed with search Results
#  $department = "Electronic Information Services and Instruction Office";

# ------ End of Configuration Variables ------------


# Retrieve either GET or POST information
if ( $ENV{'REQUEST_METHOD'} eq 'POST' )
{
   read(STDIN,$buffer,$ENV{'CONTENT_LENGTH'});
   @pairs = split(/&/,$buffer);
}
else
{
   @pairs = split(/&/,$ENV{'QUERY_STRING'});
}

foreach $pair (@pairs)
{
    ($name, $value) = split(/=/, $pair);

    # Un-Webify plus signs and %-encoding
    $value =~ tr/+/ /;
    $value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex($1))/eg;
    push(@search_tags, $value), next if ($name eq 'search_tags');

    $FORM{$name} = $value
}

$_ = $FORM{'query'};
s/\'//g;
s/\%27//g;   
$query = $_;
$results = $FORM{'results'};

if (@search_tags) 
   {
     $tags = join("",@search_tags);
     $search_tags = "\-t $tags"; 
   } else
     {
       $search_tags = "";
     }

 if ($query) 
    {
     &search_parse;
    } else
      {
	&html_header("XML4Lib Search");
        &print_form;
	&print_footer;
      }


sub search_parse
# Run SWISH and parse output
{
#Initialize counter variable for number of results
$count = 0; 

$pid = open(SWISH, "$swish -w \"$query\" -f $index |");
if ($pid) {
while (<SWISH>) { 
  # First, check to see if search produced an error
   chop;
   if ($_ eq "err: no results") 
   {&search_error("There were no items that matched your search 
request.");}

   if ($_ eq "err: could not open index file") 
   {&search_error("Could not open the index file $index.");}
   
   if ($_ eq "err: no search words specified") 
   {&search_error("Please enter at least one search word.");}

   if ($_ eq "err: a word is too common") 
 {&search_error("One of your search terms is too common, please try 
again.");}
  
# Next Line ignores lines that begin with a non-digit
  next if /^\D/;
  $count++;
  push(@results, $_);
}
close(SWISH);
&html_header("XML4Lib Elecronic Discussio");
&print_form;
print "<p>There are $count items that match your search.</p>\n<ol>\n";
foreach (@results) {
 select(STDOUT);
 ($stringone, $title, $filesize) = split(/\"/, $_);
 ($rank, $url) = split(/ /, $stringone);
$_= $url;
s/\/home\/xml4lib//;
$url = $_;
 print "<li><a href=\"$url\">$title</a></li>\n";
}
print "</ol>\n";
&print_footer;
} else {
      ($EUID, $EGID) = ($UID, $GID); # suid only
      exec($program, @options, @args)
      || die "can't exec program: $!";
      # NOTREACHED
}
}

sub search_error
{
 &html_header("Online Medieval &amp; Classical Library");
 $error_message = $_[0];
    print "<P ALIGN=CENTER>\n";
    print "$error_message</P>\n";
 &print_form;
 &print_footer;
exit;
}

sub html_header
# This subroutine takes the document title as a command
# line parameter and adds header information to the top
# of the HTML document to be returned.

{
    $document_title = $_[0];
    print "Content-type: text/html\n\n";
print <<END;

<!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>
   
<meta http-equiv="content-type" content="text/html; charset=utf-8" />
   
<title>$document_title</title>

<link type="text/css" rel="stylesheet" href="/style.css" />

</head>
<body>

<h1 class="header">
<a href="/">XML4Lib Electronic Discussion</a>
</h1>

<div class="content">

END

}


sub print_footer {

print <<END;

</div>
<hr />
<div class="footer">
Copyright &copy; 2001-2011 by Roy Tennant<br />
<a rel="license" 
href="http://creativecommons.org/licenses/by-nc/2.0/"><img 
alt="Creative Commons License" border="0" 
src="http://creativecommons.org/images/public/somerights20.gif" 
/></a><br />
</div>
</body>
</html>

END

}

sub print_form {

print "<div class=\"searchform\" style=\"text-align: center;\">\n";
print <<END;
END
print "<p><form action=\"$swishcgi\" method=\"get\">\n";
print "<input type=\"submit\" value=\"Search:\" />\n";
print "<input name=\"query\" size=\"30\" value=\"$query\" />\n";
print "</form></p>\n</div>\n";

}