Index: modules/search/search.admin.inc
===================================================================
RCS file: /cvs/drupal/drupal/modules/search/search.admin.inc,v
retrieving revision 1.8
diff -u -p -r1.8 search.admin.inc
--- modules/search/search.admin.inc	11 Jan 2009 21:19:18 -0000	1.8
+++ modules/search/search.admin.inc	11 Jun 2009 05:41:04 -0000
@@ -86,6 +86,20 @@ function search_admin_settings() {
     '#default_value' => TRUE,
     '#description' => t('Whether to apply a simple Chinese/Japanese/Korean tokenizer based on overlapping sequences. Turn this off if you want to use an external preprocessor for this instead. Does not affect other languages.')
   );
+  
+  // Create the options array
+  $n_gram_options[0] = t('Full Word Matches');
+  foreach (range(1, 6) as $size) {
+    $n_gram_options[$size] = t('@num Character size', array('@num' => $size));
+  }
+  
+  $form['indexing_settings']['search_gram_size'] = array(
+    '#type' => 'select',
+    '#title' => t('Character Matches'),
+    '#description' => t('This allows for partial word matching in searches. It breaks a word down in a several N sized character strings. Set it to Full Word Matches if you do not want this feature. The smaller the number of characters the more accurate the results but at a larger database cost.'),
+    '#options' => $n_gram_options,
+    '#default_value' => variable_get('search_gram_size', 0),
+  );
 
   $form['#validate'] = array('search_admin_settings_validate');
 
@@ -101,9 +115,14 @@ function search_admin_settings_validate(
   if ($form_state['values']['op'] == t('Re-index site')) {
     drupal_goto('admin/settings/search/wipe');
   }
+  // only allow gram sizes that are smaller or equal to the min word size
+  if ($form_state['values']['minimum_word_size'] < $form_state['values']['search_gram_size']) {
+    form_set_error('search_gram_size', t('N-Gram size must be less then or equal to the minimum word size'));
+  }
   // If these settings change, the index needs to be rebuilt.
-  if ((variable_get('minimum_word_size', 3) != $form_state['values']['minimum_word_size']) ||
-      (variable_get('overlap_cjk', TRUE) != $form_state['values']['overlap_cjk'])) {
+  else if ((variable_get('minimum_word_size', 3) != $form_state['values']['minimum_word_size']) ||
+      (variable_get('overlap_cjk', TRUE) != $form_state['values']['overlap_cjk']) || 
+      (variable_get('search_gram_size', 0) != $form_state['values']['search_gram_size'])) {
     drupal_set_message(t('The index will be rebuilt.'));
     search_wipe();
   }
Index: modules/search/search.module
===================================================================
RCS file: /cvs/drupal/drupal/modules/search/search.module,v
retrieving revision 1.298
diff -u -p -r1.298 search.module
--- modules/search/search.module	3 Jun 2009 06:52:29 -0000	1.298
+++ modules/search/search.module	11 Jun 2009 05:41:05 -0000
@@ -321,6 +321,11 @@ function search_simplify($text) {
 
   // Call an external processor for word handling.
   search_invoke_preprocess($text);
+  
+  // Check if N-Gram is enabled
+  if ($size = variable_get('search_gram_size', 0)) {
+    $text = search_gram_words($text, $size);
+  }
 
   // Simple CJK handling
   if (variable_get('overlap_cjk', TRUE)) {
@@ -347,6 +352,29 @@ function search_simplify($text) {
 }
 
 /**
+ * Provides N-Gramming functionality. 
+ * 
+ * @param string $text
+ *  single piece of plain-text that was extracted from between two HTML tags. Will not contain any HTML entities
+ * 
+ * @param int $gram_size
+ *  The size of the N-Gram
+ * 
+ * @return string 
+ *  processed string into N-Gram words
+ */
+function search_gram_words($text, $gram_size) {
+  // step through each of the text
+  // and add it modified text as space deliminated
+  $words = array();
+  for($start = 0; $start + $gram_size <= drupal_strlen($text); $start++) {
+    $words[] = drupal_substr($text, $start, $gram_size);
+  }
+  // implode the text so its 'words'
+  return implode(" ", $words);
+}
+
+/**
  * Basic CJK tokenizer. Simply splits a string into consecutive, overlapping
  * sequences of characters ('minimum_word_size' long).
  */
@@ -1246,7 +1274,7 @@ function search_excerpt($keys, $text) {
       }
       // Locate a keyword (position $p), then locate a space in front (position
       // $q) and behind it (position $s)
-      if (preg_match('/' . $boundary . $key . $boundary . '/iu', $text, $match, PREG_OFFSET_CAPTURE, $included[$key])) {
+      if (preg_match('/' . $boundary .'[^' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . ']*' . $key . '[^' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . ']*' . $boundary . '/iu', $text, $match, PREG_OFFSET_CAPTURE, $included[$key])) {
         $p = $match[0][1];
         if (($q = strpos($text, ' ', max(0, $p - 60))) !== FALSE) {
           $end = substr($text, $p, 80);
@@ -1304,7 +1333,7 @@ function search_excerpt($keys, $text) {
   $text = (isset($newranges[0]) ? '' : '... ') . implode(' ... ', $out) . ' ...';
 
   // Highlight keywords. Must be done at once to prevent conflicts ('strong' and '<strong>').
-  $text = preg_replace('/' . $boundary . '(' . implode('|', $keys) . ')' . $boundary . '/iu', '<strong>\0</strong>', $text);
+  $text = preg_replace('/' . $boundary . '[^' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . ']*' . '(' . implode('|', $keys) . ')' . '[^' . PREG_CLASS_SEARCH_EXCLUDE . PREG_CLASS_CJK . ']*' . $boundary . '/iu', '<strong>\0</strong>', $text);
   return $text;
 }