Fix regex to remove UTF-8 chars invalid in XML 1.0

dregad · dregad · commit ff2e6506406a · 2012-11-15T23:32:26.000+01:00
The regex introduced in string_html_specialchars() function with commit 2b5d662 caused problems with multibyte UTF-8 chars, as PCRE require that they are specified like '\x{NNNN}'; the syntax without braces '\xNN' only supports up to 2 hex digits [1]. Fixes #14744 [1] http://php.net/regexp.reference.escape
diff --git a/core/string_api.php b/core/string_api.php
@@ -912,7 +912,7 @@ function string_html_entities( $p_string ) {
 function string_html_specialchars( $p_string ) {
 	# Remove any invalid character from the string per XML 1.0 specification
 	# http://www.w3.org/TR/2008/REC-xml-20081126/#NT-Char
-	$p_string = preg_replace( '/[^\x9\xA\xD\x20-\xD7FF\xE000-\xFFFD\x{10000}-\x{10FFFF}]/u', '', $p_string );
+	$p_string = preg_replace( '/[^\x9\xA\xD\x20-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]+/u', '', $p_string );
 
 	# achumakov: @ added to avoid warning output in unsupported codepages
 	# e.g. 8859-2, windows-1257, Korean, which are treated as 8859-1.
