diff --git a/includes/processor_tokenizer.inc b/includes/processor_tokenizer.inc index bd445d6..5bf2700 100644 --- a/includes/processor_tokenizer.inc +++ b/includes/processor_tokenizer.inc @@ -21,9 +21,11 @@ class SearchApiTokenizer extends SearchApiAbstractProcessor { 'spaces' => array( '#type' => 'textfield', '#title' => t('Whitespace characters'), - '#description' => t('Specify the characters that should be regarded as whitespace and therefore used as word-delimiters. Specify the characters as a PCRE character class.', + '#description' => t('Specify the characters that should be regarded as whitespace and therefore used as word-delimiters. ' . + 'Specify the characters as a PCRE character class. ' . + 'Note: For non-English content, the default setting might not be suitable.', array('@link' => url('http://www.php.net/manual/en/regexp.reference.character-classes.php'))), - '#default_value' => '[^\p{L}\p{N}]', + '#default_value' => "[^\\p{L}\\p{N}^']", ), 'ignorable' => array( '#type' => 'textfield',