Move UTF-8 cleanup into its own method

1 files changed, 19 insertions, 0 deletions

diff --git a/lib/class/ui.class.php b/lib/class/ui.class.php
index 36607e19..1a3efa15 100644
--- a/lib/class/ui.class.php
+++ b/lib/class/ui.class.php
@@ -89,6 +89,25 @@ class UI {
     }
 
     /**
+     * clean_utf8
+     *
+     * Removes characters that aren't valid in XML (which is a subset of valid
+     * UTF-8, but close enough for our purposes.)
+     * See http://www.w3.org/TR/2006/REC-xml-20060816/#charsets
+     */
+    public static function clean_utf8($string) {
+        if ($string) {
+            $clean = preg_replace('/[^\x{9}\x{a}\x{d}\x{20}-\x{d7ff}\x{e000}-\x{fffd}\x{10000}-\x{10ffff}]|[\x{7f}-\x{84}\x{86}-\x{9f}\x{fdd0}-\x{fddf}\x{1fffe}-\x{1ffff}\x{2fffe}-\x{2ffff}\x{3fffe}-\x{3ffff}\x{4fffe}-\x{4ffff}\x{5fffe}-\x{5ffff}\x{6fffe}-\x{6ffff}\x{7fffe}-\x{7ffff}\x{8fffe}-\x{8ffff}\x{9fffe}-\x{9ffff}\x{afffe}-\x{affff}\x{bfffe}-\x{bffff}\x{cfffe}-\x{cffff}\x{dfffe}-\x{dffff}\x{efffe}-\x{effff}\x{ffffe}-\x{fffff}\x{10fffe}-\x{10ffff}]/u', '', $string);
+            
+            if ($clean) {
+                return $clean;
+            }
+
+            debug_event('UI', 'Charset cleanup failed, something might break', 1);
+        }
+    }
+
+    /**
      * flip_class
      *
      * First initialised with an array of two class names. Subsequent calls