#!/usr/bin/perl
################################################################
# Simple Search Script     Version 1.0
# Written By Matt Wright     mattw@tahoenet.com
# Created on: 12/16/95     Last Modified on: 1/29/96
# Scripts found at:          http://www.worldwidemart.com/scripts/
################################################################
# Define Variables

# $basedir should be the system path to the files and directories
# you wish to search.

$basedir = '/path/to/files/you/wish/to/search/';

# $baseurl should be the same path as $basedir, except
# represented as a URL, so that the user can get to the web page
# when the filename is returned.

$baseurl = 'http://worldwidemart.com/scripts/';

# @files is an array that specifies which files you wish to
# search.  Wildcards, in the form of a (*) are accepted.  So to
# search all html files in the basedir and all text files, you
# would configure @files as:

@files = ('*.html','*.txt');

# The $title is the title of the page you are searching.  This
# will be returned on the results page as a way to get back to
# the main page.

$title = "My Web Server";

# $title_url is the URL that will be linked to the text in $title
# on the results page.

$title_url = 'http://www.server.xxx/';

# This is the URL to the search form; search.html

$search_url = 'http://www.server.xxx/search.html';

# Done
################################################################

# Parse Form Search Information
&parse_form;

# Get Files To Search Through
&get_files;

# Search the files
&search;

# Print Results of Search
&return_html;

sub parse_form {

   # Get the input
   read(STDIN, $buffer, $ENV{'CONTENT_LENGTH'});

   # Split the name-value pairs
   @pairs = split(/&/, $buffer);

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

      $value =~ tr/+/ /;
      $value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C",hex($1))/eg;

      $FORM{$name} = $value;
   }
}

sub get_files {

   # Change Directories to $basedir
   chdir($basedir);

   # Loop through the files in @files and with the ls command
   # determine all files that need to be searched.  This is
   # necessary so that the wildcards can be expanded into
   # filenames.
   foreach $file (@files) {
      $ls = `ls $file`;
      @ls = split(/\s+/,$ls);
      foreach $temp_file (@ls) {

         # If the file is a directory, then adjust the filename
         # accordingly.
         if (-d $file) {
            $filename = "$file$temp_file";
            if (-T $filename) {
               push(@FILES,$filename);
            }
         }

         # Otherwise, if the file is a text file, we can search
         # it.
         elsif (-T $temp_file) {
            push(@FILES,$temp_file);
         }
      }
   }
}

sub search {

   # Split the Search Terms that the user entered by spaces.
   @terms = split(/\s+/, $FORM{'terms'});

   foreach $FILE (@FILES) {

      # Open the File, Read it Into an Array.
      open(FILE,"$FILE");
      @LINES = <FILE>;
      close(FILE);

      # Join the LINES in the FILE with a space, and then take
      # out all new line characters.
      $string = join(' ',@LINES);
      $string =~ s/\n//g;

      # The loops below determine which syntax to use based on
      # user input such as case (in)sensitivity and the boolean
      # term (and/or)

      if ($FORM{'boolean'} eq 'AND') {
         foreach $term (@terms) {
            if ($FORM{'case'} eq 'Insensitive') {

               # If the string doesn't contain one of the terms,
               # don't include the file in report.
               if (!($string =~ /$term/i)) {
                  $include{$FILE} = 'no';
                  last;
               }
               else {
                  $include{$FILE} = 'yes';
               }
            }
            elsif ($FORM{'case'} eq 'Sensitive') {

               # If the string doesn't contain one of the terms
               # exactly, do not include it.
               if (!($string =~ /$term/)) {
                  $include{$FILE} = 'no';
                  last;
               }
               else {
                  $include{$FILE} = 'yes';
               }
            }
         }
      }
      elsif ($FORM{'boolean'} eq 'OR') {
         foreach $term (@terms) {
            if ($FORM{'case'} eq 'Insensitive') {

               # If string contains one of the terms, then
               # include the file in report.
               if ($string =~ /$term/i) {
                  $include{$FILE} = 'yes';
                  last;
               }
               else {
                  $include{$FILE} = 'no';
               }
            }
            elsif ($FORM{'case'} eq 'Sensitive') {

               # If the string includes one of the terms exactly
               # as entered, then include the file in report.
               if ($string =~ /$term/) {
                  $include{$FILE} = 'yes';
                  last;
               }
               else {
                  $include{$FILE} = 'no';
               }
            }
         }
      }

      # Attempt to locate the title of the page to display in
      # results.
      if ($string =~ /<title>(.*)<\/title>/i) {
         $titles{$FILE} = "$1";
      }
      else {
         $titles{$FILE} = "$FILE";
      }
   }
}

# Return the HTML and Results to User.
sub return_html {
   print "Content-type: text/html\n\n";
   print "<html>\n";
   print " <head>\n";
   print "  <title>Results of Search</title>\n";
   print " </head>\n";
   print " <body>\n";
   print "  <center>\n";
   print "   <h1>Results of Search in $title</h1>\n";
   print "  </center>\n\n";
   print "Below are the results of your Search in no ";
   print "particular order:<p><hr size=7 width=75%><p>\n";
   print "<ul>\n";
   foreach $key (keys %include) {
      if ($include{$key} eq 'yes') {
        print "<li><a href=\"$baseurl$key\">$titles{$key}</a>\n";
      }
   }
   print "</ul>\n";
   print "<hr size=7 width=75%>\n";
   print "Search Information:<p>\n";
   print "<ul>\n";
   print "<li><b>Terms:</b> ";
   $i = 0;
   foreach $term (@terms) {
      print "$term";
      $i++;
      if (!($i == @terms)) {
         print ", ";
      }
   }
   print "\n";
   print "<li><b>Boolean Used:</b> $FORM{'boolean'}\n";
   print "<li><b>Case $FORM{'case'}</b>\n";
   print "</ul><br><hr size=7 width=75%><P>\n";
   print "<ul>\n";
   print "<li><a href=\"$search_url\">Back to Search Page</a>\n";
   print "<li><a href=\"$title_url\">$title</a>\n";
   print "</ul>\n";
   print "<hr size=7 width=75%>\n";
   print "Search Script written by Matt Wright and can be found";
   print "at <a href=\"http://www.worldwidemart.com/scripts/\">";
   print "Matt's Script Archive</a>\n";
   print "</body>\n</html>\n";
}