#!/usr/bin/perl

# Xavatoria Indexed Search, Index Building Module
#	Copyright 1997 by Fluid Dynamics <xav.com>
#
# For latest version and help files, visit:
#	http://www.xav.com/scripts/xavatoria/
# __________________________________________________________________


# Enter the location on your system of the new index file:

$Index_File = "/home/martialartsresource/www/filipino/index.txt";

# $baseurl is the web page that corresponds with files in your base 
# directory, which is called $basedir.  Use absolute paths like shown, 
# not relative paths.  Do NOT include trailing slashes.

$baseurl = "http://64.33.44.189/anonftp/pub/eskrima/digests";
$basedir = "/home/martialartsresource/anonftp/pub/eskrima/digests";

# $extensions holds the file extensions that will be included in 
# searches. It's best to leave out ones like ".log" or ".cgi".  Note 
# the special "\." delimiters, and their occurrence at both the 
# beginning and end of the set:

$extensions = "\.txt\.html\.htm\.shtml\.stm\.ztml\.shtml\.";
*$extensions = "\.n*\.";

# Below are the files or directories that you do NOT want to be 
# searched.  Note that they all have one blank space after the 
# file or directory, and that directories do not include trailing 
# slashes.  Also note that we use the ".=" instead of the "=".

$DMZ .= "/null ";
#$DMZ .= "/usr/www/users/xav/cgi-bin ";
#$DMZ .= "/usr/www/users/xav/counters ";

# Below you list the files that your visitors really should see (why 
# not show off your best work, eh?).  While the search results remain 
# honest as to whether or not terms were found, these files will have 
# their numerical ranking multiplied by the CRANK FACTOR, which should 
# be an integer between two and twenty.  Only files can go here, not 
# directories.  The same rules from above apply...

$CRANK_FACTOR = 18;

#$CRANK .= "/usr/www/users/xav/links.ztml ";
#$CRANK .= "/usr/www/users/xav/scripts/index.html ";
#$CRANK .= "/usr/www/users/xav/clients.html ";

# Options for Weighted Search:
#
# All occurrences of a search term count as one point.  The occurrence 
# of a term in the URL, Title, Meta keywords, or Meta description 
# can have added weight (equivalent to a multiplier per hit).  Enter 
# the multipliers in the array below - the defaults are (4, 10, 10, 4). 
# If this makes no sense to you, just ignore it and leave the defaults 
# as they are - they work pretty well.  Note that this will give extra 
# weight to those pages that have a properly formatted Title and Meta  
# tags, even if they contain the same basic information (kinda like the 
# real search engines).

$Filename_Rank = 4;
$Title_Rank = 10;
$Keyword_Rank = 10;
$Description_Rank = 4;

# No further editing is necessary, but feel free to play around...
# 
# __________________________________________________________________

print "Content-type: text/plain\n\n";
if ($ENV{'SERVER_SOFTWARE'} =~ /IIS/)
	{
	$slash = '\\';
	}
else
	{
	$slash = '/';
	}
unless (-e $basedir)
	{
	print "Fatal Error!\n";
	print "Searched for a directory at specified location:\n";
	print "    $basedir\n";
	print "No directory found. Check settings.\n";
	exit;
	}
@directories = ($basedir);
$maxvar = 1;
for ($i=0;$i<$maxvar;$i++)
	{
	$directory = @directories[$i];
	opendir(DIR,$directory);
	@entries = readdir(DIR);
	closedir(DIR);
	foreach $entry (@entries)
		{
		next if (($entry eq ".") || ($entry eq ".."));
		$full = $directory . $slash . $entry;
		next if ($DMZ =~ /$full /i);
		if (-d $full)
			{
			push(@directories,$full);
			$maxvar++;
			}
		elsif ((-T $full) && ($full =~ /(.*)\.(.*)/))
			{
			push(@FILES,$full);
#			push(@FILES,$full) if ($extensions =~ /\.$2\./);
			}
		}
	}
$Number_Files = @FILES;
print "  $Number_Files\n";
$delimiter = '%%==%%';
open(ALLFILES,">$Index_File") || &Fatal;
foreach $FILE (@FILES)
	{
	open(FL,"$FILE");
	$string = join(' ',<FL>);
	close(FL);

	$string =~ s/\n/ /g;

	($Title,$Description) = &Extract_Meta;

	$Size = -s $FILE;

	$last = &Last_Modified($FILE);

	$webname = $FILE;
	$webname =~ s/\\/\//g;
	if ($webname =~ /^$basedir(.*)/)
		{
		$webname = $1;
		}
	$URL = $baseurl . $webname;

	print ALLFILES $CRANK_FACTOR if ($CRANK =~ /$FILE/);
	print ALLFILES $delimiter . $URL . $delimiter;

#	print ALLFILES $Title . $delimiter;
	print ALLFILES $URL . $delimiter;
	print ALLFILES $Description . $delimiter;
	print ALLFILES $Size . $delimiter . $last . $delimiter;

	for ($i=0; $i<$Filename_Rank; $i++)
		{
		$string .= " $URL";
		}
	$string = " " . $string . " ";
	$string =~ s/\W/ /g;
	$string =~ s/_/ /g;
	$string =~ s/\s+/ /g;
	print ALLFILES $string . "\n";
	}
close(ALLFILES);
print "Done - Captured $Number_Files files total.\n";
$Index_Size = -s $Index_File;
print "Index file is $Index_Size bytes.\n\n";
sub Last_Modified
# This procedure was written by Jeff Carnahan of Terminal Productions
# (http://www.terminalp.com)
{
$filename = shift;
($sec,$min,$hour,$mday,$mon,$year) = localtime((stat($filename))[9]);
@months = (Jan,Feb,Mar,Apr,May,Jun,Jul,Aug,Sep,Oct,Nov,Dec);
return "$mday $months[$mon] $year";
}
sub Extract_Meta
{
$string .= " || ";
($Title,$Description) = ("","");
if ($string =~ /<title>([^<]*)<\/title>/i)
	{
	$Title = $1;
	$string =~ s/<title>([^<]*)<\/title>/ /oi;
	for ($i=0; $i<$Title_Rank; $i++)
		{
		$string .= " " . $Title;
		}
	}
else
	{
 	$Title = $FILE;
	}
if ($string =~ /<meta\s+name="keywords"\s+content="([^\"]*)">/i)
	{
	for ($i=0; $i<$Keyword_Rank; $i++)
		{
		$string .= " " . $1;
		}
	}
if ($string =~ /<meta\s+name="description"\s+content="([^\"]*)">/i)
	{
	$Description = $1;
	for ($i=0; $i<$Description_Rank; $i++)
		{
		$string .= $Description;
		}
	}
$string =~ s/<[^>]*\s+ALT\s*=\s*"(([^>"])*)"[^>]*>/ $1 /ig;
$string =~ s/<([^>]|\n)*>/ /g;
if ($Description eq "")
	{
	@words = split(/\s+/,$string);
 	for ($i=23; $i<80; $i++)
#	for ($i=0; $i<25; $i++)
		{
		last if ($words[$i] eq "||");
		$Description .= "$words[$i] ";
		}
	$Description .= "...";
	}
$string =~ s/\W/ /g;
$string =~ s/_/ /g;
$Title =~ s/\s+/ /g;
if ($Title =~ /^ (.*)/)
	{
	$Title = $1;
	}
$Description =~ s/\s+/ /g;
if ($Description =~ /^ (.*)/)
	{
	$Description = $1;
	}
return($Title,$Description);
}
sub Fatal
{
print "Fatal Error! Cannot write to index file.\n";
print "This script does not have permission to modify the file:\n";
print "          $Index_File.\n";
print "Build Module aborted.\n\n";
print "Hint: Try:\n\n";
print "chmod 777 $Index_File\n\n";
exit;
}