From 758e671652bad925ac40a88d100ca821aed132a8 Mon Sep 17 00:00:00 2001
From: "C. Scott Ananian" <cscott@cscott.net>
Date: Thu, 21 Jun 2018 14:53:04 -0400
Subject: [PATCH] French space armoring: Use unicode regex instead of octal
 escapes

Follow up to Id8cdb887182f346acab2d108836ce201626848af

Change-Id: I35f7b35746e63a98a115a0dbc9d5869b691c3a9c
---
 includes/parser/Sanitizer.php | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/includes/parser/Sanitizer.php b/includes/parser/Sanitizer.php
index 89a7c96124..21498f89eb 100644
--- 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 );
 	}
-- 
2.20.1