Multi-byte character safe excerpting from nbachiyski. fixes #6077

git-svn-id: http://svn.automattic.com/wordpress/trunk@7140 1a063a9b-81f0-0310-95a4-ce76da25c4cd

wp-includes/formatting.php

@@ -1370,4 +1370,26 @@ function wp_sprintf_l($pattern, $args) {
 	return $result . substr($pattern, 2);
 }
 
+/**
+ * Safely extracts not more than the first $count characters from html string
+ *
+ * UTF-8, tags and entities safe prefix extraction. Entities inside will be
+ * counted as one character. As a side effect, all entities will be converted to
+ * their decimal form.
+ *
+ * @param integer $str String to get the excerpt from
+ * @param integer $count Maximum number of visible characters to take
+ * @eaturn string the excerpt
+ */
+function wp_html_excerpt( $str, $count ) {
+	$str = strip_tags( $str );
+	$str = html_entity_decode( $str, ENT_QUOTES);
+	$str = mb_strcut( $str, 0, $count );
+	// remove part of an entity at the end
+	$str = preg_replace( '/&[^;\s]{0,6}$/', '', $str );
+	// we decoded some entities we should put back
+	$str = wp_specialchars( $str );
+	return $str;
+}
+
 ?>