French space armoring: Use unicode regex instead of octal escapes

Follow up to Id8cdb887182f346acab2d108836ce201626848af

Change-Id: I35f7b35746e63a98a115a0dbc9d5869b691c3a9c

diff --git a/includes/parser/Sanitizer.php b/includes/parser/Sanitizer.php
index 89a7c96..21498f8 100644 (file)
--- a/includes/parser/Sanitizer.php
+++ b/includes/parser/Sanitizer.php
@@ -1155,9 +1155,9 @@ class Sanitizer {
                $fixtags = [
                        # French spaces, last one Guillemet-left
                        # only if there is something before the space
-                       '/(.) (?=\\?|:|;|!|%|\\302\\273)/' => "\\1$space",
+                       '/(.) (?=[?:;!%»])/u' => "\\1$space",
                        # French spaces, Guillemet-right
-                       '/(\\302\\253) /' => "\\1$space",
+                       '/(«) /u' => "\\1$space",
                ];
                return preg_replace( array_keys( $fixtags ), array_values( $fixtags ), $text );
        }