Index: modules/search/search.module
===================================================================
RCS file: /cvs/drupal/drupal/modules/search/search.module,v
retrieving revision 1.256
diff -u -F^f -r1.256 search.module
--- modules/search/search.module	6 May 2008 12:18:50 -0000	1.256
+++ modules/search/search.module	10 May 2008 19:43:09 -0000
@@ -298,41 +298,80 @@ function search_update_totals() {
   }
 }
 
+function search_filter($op, $delta = 0, $format = -1, $text = '') {
+  switch ($op) {
+    case 'list':
+      return array(0 => t('Decode entities'),
+        1 => t('Drupal string-to-lower'),
+        2 => t('Simple CJK handling'),
+        3 => t('Numerical data'),
+        4 => t('Punctuation'),
+      );
+
+    case 'description':
+      switch ($delta) {
+        case 0:
+          return t('Decode all HTML entities (including numerical ones) to regular UTF-8 bytes.');
+        case 1;
+          return t('Lowercase strings in a unicode-safe way.');
+        case 2;
+          return t('Matches all Chinese, Japanese, and Korean characters that are candidates for auto-splitting.');
+        case 3:
+          return t('Remove the punctuation from numerical data.');
+        case 4:
+          return t('Remove punctuation and make variants of hyphenated and underscored words, so that low-budget will become "lowbudget", "low" and "budget".');
+        default;
+          return '';
+      }
+
+    case 'no cache':
+      return TRUE;
+
+    case 'process':
+      switch ($delta) {
+        case 0:
+          return decode_entities($text);
+        case 1:
+          return drupal_strtolower($text);
+        case 2:
+          return preg_replace_callback('/[' . PREG_CLASS_CJK . ']+/u', 'search_expand_cjk', $text);
+        case 3:
+          // To improve searching for numerical data such as dates, IP addresses
+          // or version numbers, we consider a group of numerical characters
+          // separated only by punctuation characters to be one piece.
+          // This also means that searching for e.g. '20/03/1984' also returns
+          // results with '20-03-1984' in them.
+          // Readable regexp: ([number]+)[punctuation]+(?=[number])
+          return preg_replace('/([' . PREG_CLASS_NUMBERS . ']+)[' . PREG_CLASS_PUNCTUATION . ']+(?=[' . PREG_CLASS_NUMBERS . '])/u', '\1', $text);
+        case 4:
+          // The dot, underscore and dash are simply removed. This allows meaningful
+          // search behavior with acronyms and URLs.
+          $matches = array();
+          
+          //something full-fledged something
+          preg_match_all('/(\s*)(\w+)([._-]+)(\w+)(\s*)/', $text, $matches);
+          foreach ($matches[0] as $key => $match) {
+            $text = str_replace($match, $matches[1][$key] . $matches[2][$key] . $matches[4][$key] . $matches[5][$key], $text);
+            $text .= ' ' . $matches[2][$key] . ' ' . $matches[4][$key];
+          }
+          
+          // With the exception of the rules above, we consider all punctuation,
+          // marks, spacers, etc, to be a word boundary.
+          return preg_replace('/[' . PREG_CLASS_SEARCH_EXCLUDE . ']+/u', ' ', $text);
+        default:
+          return $text;
+      }
+      
+    default:
+      return $text;
+  }
+}
+
 /**
  * Simplifies a string according to indexing rules.
  */
 function search_simplify($text) {
-  // Decode entities to UTF-8
-  $text = decode_entities($text);
-
-  // Lowercase
-  $text = drupal_strtolower($text);
-
-  // Call an external processor for word handling.
-  search_invoke_preprocess($text);
-
-  // Simple CJK handling
-  if (variable_get('overlap_cjk', TRUE)) {
-    $text = preg_replace_callback('/[' . PREG_CLASS_CJK . ']+/u', 'search_expand_cjk', $text);
-  }
-
-  // To improve searching for numerical data such as dates, IP addresses
-  // or version numbers, we consider a group of numerical characters
-  // separated only by punctuation characters to be one piece.
-  // This also means that searching for e.g. '20/03/1984' also returns
-  // results with '20-03-1984' in them.
-  // Readable regexp: ([number]+)[punctuation]+(?=[number])
-  $text = preg_replace('/([' . PREG_CLASS_NUMBERS . ']+)[' . PREG_CLASS_PUNCTUATION . ']+(?=[' . PREG_CLASS_NUMBERS . '])/u', '\1', $text);
-
-  // The dot, underscore and dash are simply removed. This allows meaningful
-  // search behavior with acronyms and URLs.
-  $text = preg_replace('/[._-]+/', '', $text);
-
-  // With the exception of the rules above, we consider all punctuation,
-  // marks, spacers, etc, to be a word boundary.
-  $text = preg_replace('/[' . PREG_CLASS_SEARCH_EXCLUDE . ']+/u', ' ', $text);
-
-  return $text;
+  return check_markup($text, 3, FALSE);
 }
 
 /**
@@ -396,9 +435,9 @@ function _search_index_truncate(&$text) 
 /**
  * Invokes hook_search_preprocess() in modules.
  */
-function search_invoke_preprocess(&$text) {
+function search_invoke_preprocess(&$text, $language = NULL) {
   foreach (module_implements('search_preprocess') as $module) {
-    $text = module_invoke($module, 'search_preprocess', $text);
+    $text = module_invoke($module, 'search_preprocess', $text, $language);
   }
 }