From d25849065374608676ffc1567d187d450f623680 Mon Sep 17 00:00:00 2001
From: Gary Pendergast <pento@git.wordpress.org>
Date: Sat, 28 Feb 2015 02:20:52 +0000
Subject: [PATCH] When sanitizing a URL to redirect to, UTF-8 characters can be
 URL encoded, instead of being removed.

While RFC 3986 does not specify which character sets are allowed in URIs, Section 2.5 states that octects matching UTF-8 character encoding should be percent-encoded, then unreserved octets outside of the UTF-8 range should be percent-encoded. As browsers tend to only implement support for UTF-8 in URLs, this change only implements the UTF-8 encoding part. We may revisit the second part if it becomes an issue.

Fixes #31486



git-svn-id: https://develop.svn.wordpress.org/trunk@31587 602fd350-edb4-49c9-b593-d223f7449a82
---
 src/wp-includes/pluggable.php               | 26 +++++++++++++++++++++
 tests/phpunit/tests/formatting/redirect.php |  1 +
 2 files changed, 27 insertions(+)

diff --git a/src/wp-includes/pluggable.php b/src/wp-includes/pluggable.php
index 4eae503d7e..71c0d3704b 100644
--- a/src/wp-includes/pluggable.php
+++ b/src/wp-includes/pluggable.php
@@ -1201,6 +1201,19 @@ if ( !function_exists('wp_sanitize_redirect') ) :
  * @return string redirect-sanitized URL
  **/
 function wp_sanitize_redirect($location) {
+	$regex = '/
+		(
+			(?: [\xC2-\xDF][\x80-\xBF]        # double-byte sequences   110xxxxx 10xxxxxx
+			|   \xE0[\xA0-\xBF][\x80-\xBF]    # triple-byte sequences   1110xxxx 10xxxxxx * 2
+			|   [\xE1-\xEC][\x80-\xBF]{2}
+			|   \xED[\x80-\x9F][\x80-\xBF]
+			|   [\xEE-\xEF][\x80-\xBF]{2}
+			|   \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
+			|   [\xF1-\xF3][\x80-\xBF]{3}
+			|   \xF4[\x80-\x8F][\x80-\xBF]{2}
+		){1,50}                              # ...one or more times
+		)/x';
+	$location = preg_replace_callback( $regex, '_wp_sanitize_utf8_in_redirect', $location );
 	$location = preg_replace('|[^a-z0-9-~+_.?#=&;,/:%!*\[\]()]|i', '', $location);
 	$location = wp_kses_no_null($location);
 
@@ -1209,6 +1222,19 @@ function wp_sanitize_redirect($location) {
 	$location = _deep_replace($strip, $location);
 	return $location;
 }
+
+/**
+ * URL encode UTF-8 characters in a URL.
+ *
+ * @ignore
+ * @since 4.2.0
+ * @access private
+ *
+ * @see wp_sanitize_redirect()
+ */
+function _wp_sanitize_utf8_in_redirect( $matches ) {
+	return urlencode( $matches[0] );
+}
 endif;
 
 if ( !function_exists('wp_safe_redirect') ) :
diff --git a/tests/phpunit/tests/formatting/redirect.php b/tests/phpunit/tests/formatting/redirect.php
index 90daf1a66f..54fb873e45 100644
--- a/tests/phpunit/tests/formatting/redirect.php
+++ b/tests/phpunit/tests/formatting/redirect.php
@@ -11,6 +11,7 @@ class Tests_Formatting_Redirect extends WP_UnitTestCase {
 		$this->assertEquals('http://example.com/watchthecarriagereturngo', wp_sanitize_redirect('http://example.com/watchthecarriagereturn%0Dgo'));
 		$this->assertEquals('http://example.com/watchthecarriagereturngo', wp_sanitize_redirect('http://example.com/watchthecarriagereturn%0dgo'));
 		$this->assertEquals('http://example.com/watchtheallowedcharacters-~+_.?#=&;,/:%!*stay', wp_sanitize_redirect('http://example.com/watchtheallowedcharacters-~+_.?#=&;,/:%!*stay'));
+		$this->assertEquals('http://example.com/watchtheutf8convert%F0%9D%8C%86', wp_sanitize_redirect("http://example.com/watchtheutf8convert\xf0\x9d\x8c\x86"));
 		//Nesting checks
 		$this->assertEquals('http://example.com/watchthecarriagereturngo', wp_sanitize_redirect('http://example.com/watchthecarriagereturn%0%0ddgo'));
 		$this->assertEquals('http://example.com/watchthecarriagereturngo', wp_sanitize_redirect('http://example.com/watchthecarriagereturn%0%0DDgo'));