#850950 by jhodgdon, gpk: Fix problems in excerpt matching function.

[project/porterstemmer.git] / porterstemmer.module

diff --git a/porterstemmer.module b/porterstemmer.module
index 8b600a1..9a16805 100644 (file)
--- a/porterstemmer.module
+++ b/porterstemmer.module
@@ -65,25 +65,23 @@ function porterstemmer_help($path, $arg) {
  * Allows Porter Stemmer to display better search excerpts with the
  * Search by page module.
  */
-function porterstemmer_sbp_excerpt_match( $key, $text, $offset, $boundary ) {
+function porterstemmer_sbp_excerpt_match($key, $text, $offset, $boundary) {
   // Stem the keyword down to its root form.
-  $key = porterstemmer_stem( $key );
+  $key = porterstemmer_stem($key);
 
   // In many cases, the root word is a substring of the full word, but not
   // all. The cases where it is not, the root ends in e, i, or y, and if this
   // last letter is removed, the root is a substring of the full word.
   // So remove these letters at the end of the root.
-
   $didit = FALSE;
-  porterstemmer_suffix( $key, 'i', '', $didit, NULL, 2 ) OR
-    porterstemmer_suffix( $key, 'e', '', $didit, NULL, 2 ) OR
-    porterstemmer_suffix( $key, 'y', '', $didit, NULL, 2 );
+  porterstemmer_suffix($key, 'i', '', $didit, NULL, 2) OR
+    porterstemmer_suffix($key, 'e', '', $didit, NULL, 2) OR
+    porterstemmer_suffix($key, 'y', '', $didit, NULL, 2);
 
   // Look for this modified key at the start of a word.
-
   $match = array();
-  if (!preg_match('/' . $boundary . $key . '/iu', $text, $match, PREG_OFFSET_CAPTURE, $offset )) {
-    // didn't match our modified key.
+  if (!preg_match('/'. $boundary . '(' . $key . ')/iu', $text, $match, PREG_OFFSET_CAPTURE, $offset)) {
+    // Didn't match our modified key.
     return FALSE;
   }
 
@@ -91,26 +89,31 @@ function porterstemmer_sbp_excerpt_match( $key, $text, $offset, $boundary ) {
   // actually matched, so it can be highlighted (making sure it's a real match
   // for our key).
   $newmatch = array();
-  foreach ( $match as $item ) {
-    $pos = $match[0][1];
-    // Note: Do not use drupal_strlen/drupal_substr here! Need the real PHP
-    // string lengths/pos.
-    if (preg_match('/' . $boundary . '/iu', $text, $newmatch,
-        PREG_OFFSET_CAPTURE, $pos + strlen($key))) {
-      $keyfound = substr($text, $pos, $newmatch[0][1] - $pos);
-      $foundstem = porterstemmer_stem( $keyfound );
-      porterstemmer_suffix( $foundstem, 'i', '', $didit, NULL, 2 ) OR
-        porterstemmer_suffix( $foundstem, 'e', '', $didit, NULL, 2 ) OR
-        porterstemmer_suffix( $foundstem, 'y', '', $didit, NULL, 2 );
-
-      if ($foundstem == $key) {
-        return array('where' => $pos, 'keyword' => $keyfound);
-      }
-    }
+  $pos = $match[1][1];
+  // Note: Do not use drupal_strlen/drupal_substr here! Need the real PHP
+  // string lengths/pos.
+  if (preg_match('/' . $boundary . '/iu', $text, $newmatch,
+      PREG_OFFSET_CAPTURE, $pos + strlen($key))) {
+    $keyfound = substr($text, $pos, $newmatch[0][1] - $pos);
+  }
+  else {
+    // Assume we're going to the end of the string.
+    $keyfound = substr($text, $pos);
   }
 
-  // If we get here, none of the potential matches worked out.
-  return FALSE;
+  $foundstem = porterstemmer_stem($keyfound);
+  porterstemmer_suffix($foundstem, 'i', '', $didit, NULL, 2) OR
+    porterstemmer_suffix($foundstem, 'e', '', $didit, NULL, 2) OR
+    porterstemmer_suffix($foundstem, 'y', '', $didit, NULL, 2);
+
+  // Both $foundstem and $key may contain upper case.
+  if (drupal_strtolower($foundstem) == drupal_strtolower($key)) {
+    return array('where' => $pos, 'keyword' => $keyfound);
+  }
+
+  // If we get here, then it was a false match, and we should probably
+  // search again later in the string.
+  return porterstemmer_sbp_excerpt_match($key, $text, $pos + strlen($keyfound), $boundary);
 }
 
 /**