Update composer dependencies

This commit is contained in:
Kijin Sung 2017-06-29 23:39:23 +09:00
parent 49cc39e507
commit cbd324c35b
428 changed files with 17862 additions and 5885 deletions

View file

@ -101,6 +101,14 @@ class HTMLPurifier_Encoder
* It will parse according to UTF-8 and return a valid UTF8 string, with
* non-SGML codepoints excluded.
*
* Specifically, it will permit:
* \x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}
* Source: https://www.w3.org/TR/REC-xml/#NT-Char
* Arguably this function should be modernized to the HTML5 set
* of allowed characters:
* https://www.w3.org/TR/html5/syntax.html#preprocessing-the-input-stream
* which simultaneously expand and restrict the set of allowed characters.
*
* @param string $str The string to clean
* @param bool $force_php
* @return string
@ -122,15 +130,12 @@ class HTMLPurifier_Encoder
* function that needs to be able to understand UTF-8 characters.
* As of right now, only smart lossless character encoding converters
* would need that, and I'm probably not going to implement them.
* Once again, PHP 6 should solve all our problems.
*/
public static function cleanUTF8($str, $force_php = false)
{
// UTF-8 validity is checked since PHP 4.3.5
// This is an optimization: if the string is already valid UTF-8, no
// need to do PHP stuff. 99% of the time, this will be the case.
// The regexp matches the XML char production, as well as well as excluding
// non-SGML codepoints U+007F to U+009F
if (preg_match(
'/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du',
$str
@ -255,6 +260,7 @@ class HTMLPurifier_Encoder
// 7F-9F is not strictly prohibited by XML,
// but it is non-SGML, and thus we don't allow it
(0xA0 <= $mUcs4 && 0xD7FF >= $mUcs4) ||
(0xE000 <= $mUcs4 && 0xFFFD >= $mUcs4) ||
(0x10000 <= $mUcs4 && 0x10FFFF >= $mUcs4)
)
) {