From f58a27c8b2bc8256f3e0b95374e32a19e0167647 Mon Sep 17 00:00:00 2001
From: Jigal van Hemert <jigal.van.hemert@typo3.org>
Date: Mon, 14 Oct 2013 10:34:52 +0200
Subject: [PATCH] [BUGFIX] Use callback in preg_replace in RemoveXSS
Since PHP 5.5.0 the use of the /e modifier is deprecated in preg_replace.
Use callback function instead.
Also change comments to CGL format.
Change-Id: I44f12e8bfa1c976e494dae847cc6c53d15ed7c2d
Fixes: #52771
Releases: 6.0, 6.1, 6.2
Reviewed-on: https://review.typo3.org/24723
Reviewed-by: Stefan Neufeind
Tested-by: Stefan Neufeind
Reviewed-by: Markus Klein
Tested-by: Markus Klein
---
typo3/contrib/RemoveXSS/RemoveXSS.php | 64 ++++++++++++++++-----------
1 file changed, 38 insertions(+), 26 deletions(-)
diff --git a/typo3/contrib/RemoveXSS/RemoveXSS.php b/typo3/contrib/RemoveXSS/RemoveXSS.php
index 4bee4340994b..b1598d0c7558 100644
--- a/typo3/contrib/RemoveXSS/RemoveXSS.php
+++ b/typo3/contrib/RemoveXSS/RemoveXSS.php
@@ -32,25 +32,37 @@ class RemoveXSS {
* @return string Input string with potential XSS code removed
*/
public static function process($val, $replaceString = '<x>') {
- // don't use empty $replaceString because then no XSS-remove will be done
+ // Don't use empty $replaceString because then no XSS-remove will be done
if ($replaceString == '') {
$replaceString = '<x>';
}
- // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
- // this prevents some character re-spacing such as <java\0script>
- // note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
+ // Remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed.
+ // This prevents some character re-spacing such as <java\0script>
+ // Note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
$val = preg_replace('/([\x00-\x08]|[\x0b-\x0c]|[\x0e-\x19])/', '', $val);
- // straight replacements, the user should never need these since they're normal characters
- // this prevents like <IMG SRC=@avascript:alert('XSS')>
- $searchHexEncodings = '/&#[xX]0{0,8}(21|22|23|24|25|26|27|28|29|2a|2b|2d|2f|30|31|32|33|34|35|36|37|38|39|3a|3b|3d|3f|40|41|42|43|44|45|46|47|48|49|4a|4b|4c|4d|4e|4f|50|51|52|53|54|55|56|57|58|59|5a|5b|5c|5d|5e|5f|60|61|62|63|64|65|66|67|68|69|6a|6b|6c|6d|6e|6f|70|71|72|73|74|75|76|77|78|79|7a|7b|7c|7d|7e);?/ie';
- $searchUnicodeEncodings = '/�{0,8}(33|34|35|36|37|38|39|40|41|42|43|45|47|48|49|50|51|52|53|54|55|56|57|58|59|61|63|64|65|66|67|68|69|70|71|72|73|74|75|76|77|78|79|80|81|82|83|84|85|86|87|88|89|90|91|92|93|94|95|96|97|98|99|100|101|102|103|104|105|106|107|108|109|110|111|112|113|114|115|116|117|118|119|120|121|122|123|124|125|126);?/ie';
+ // Straight replacements, the user should never need these since they're normal characters.
+ // This prevents like <IMG SRC=@avascript:alert('XSS')>
+ $searchHexEncodings = '/&#[xX]0{0,8}(21|22|23|24|25|26|27|28|29|2a|2b|2d|2f|30|31|32|33|34|35|36|37|38|39|3a|3b|3d|3f|40|41|42|43|44|45|46|47|48|49|4a|4b|4c|4d|4e|4f|50|51|52|53|54|55|56|57|58|59|5a|5b|5c|5d|5e|5f|60|61|62|63|64|65|66|67|68|69|6a|6b|6c|6d|6e|6f|70|71|72|73|74|75|76|77|78|79|7a|7b|7c|7d|7e);?/i';
+ $searchUnicodeEncodings = '/�{0,8}(33|34|35|36|37|38|39|40|41|42|43|45|47|48|49|50|51|52|53|54|55|56|57|58|59|61|63|64|65|66|67|68|69|70|71|72|73|74|75|76|77|78|79|80|81|82|83|84|85|86|87|88|89|90|91|92|93|94|95|96|97|98|99|100|101|102|103|104|105|106|107|108|109|110|111|112|113|114|115|116|117|118|119|120|121|122|123|124|125|126);?/i';
while (preg_match($searchHexEncodings, $val) || preg_match($searchUnicodeEncodings, $val)) {
- $val = preg_replace($searchHexEncodings, "chr(hexdec('\\1'))", $val);
- $val = preg_replace($searchUnicodeEncodings, "chr('\\1')", $val);
+ $val = preg_replace_callback(
+ $searchHexEncodings,
+ function ($matches) {
+ return chr(hexdec($matches[1]));
+ },
+ $val
+ );
+ $val = preg_replace_callback(
+ $searchUnicodeEncodings,
+ function ($matches) {
+ return chr($matches[1]);
+ },
+ $val
+ );
}
- // now the only remaining whitespace attacks are \t, \n, and \r
+ // Now the only remaining whitespace attacks are \t, \n, and \r
$ra1 = array('javascript', 'vbscript', 'expression', 'applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed',
'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base', 'video', 'audio', 'track',
'canvas', 'onabort', 'onactivate', 'onafterprint', 'onafterupdate', 'onbeforeactivate', 'onbeforecopy', 'onbeforecut',
@@ -86,13 +98,13 @@ class RemoveXSS {
'onsuspend', 'ontimeupdate', 'onundo', 'onunload', 'onvolumechange', 'onwaiting');
$ra_protocol = array('javascript', 'vbscript', 'expression');
- //remove the potential &#xxx; stuff for testing
+ // Remove the potential &#xxx; stuff for testing
$val2 = preg_replace('/(&#[xX]?0{0,8}(9|10|13|a|b);?)*\s*/i', '', $val);
$ra = array();
foreach ($ra1 as $ra1word) {
- // stripos is faster than the regular expressions used later and because the words we're looking for only have
- // chars < 0x80 we can use the non-multibyte safe version
+ // Stripos is faster than the regular expressions used later and because the words we're looking for only have
+ // chars < 0x80 we can use the non-multibyte safe version.
if (stripos($val2, $ra1word ) !== FALSE ) {
//keep list of potential words that were found
if (in_array($ra1word, $ra_protocol, TRUE)) {
@@ -104,13 +116,13 @@ class RemoveXSS {
if (in_array($ra1word, $ra_attribute, TRUE)) {
$ra[] = array($ra1word, 'ra_attribute');
}
- //some keywords appear in more than one array
- //these get multiple entries in $ra, each with the appropriate type
+ // Some keywords appear in more than one array.
+ // These get multiple entries in $ra, each with the appropriate type
}
}
- //only process potential words
+ // Only process potential words
if (count($ra) > 0) {
- // keep replacing as long as the previous round replaced something
+ // Keep replacing as long as the previous round replaced something
$found = TRUE;
while ($found == TRUE) {
$val_before = $val;
@@ -122,29 +134,29 @@ class RemoveXSS {
}
$pattern .= $ra[$i][0][$j];
}
- //handle each type a little different (extra conditions to prevent false positives a bit better)
+ // Handle each type a little different (extra conditions to prevent false positives a bit better)
switch ($ra[$i][1]) {
case 'ra_protocol':
- //these take the form of e.g. 'javascript:'
+ // These take the form of e.g. 'javascript:'
$pattern .= '((&#[xX]0{0,8}([9ab]);?)|(�{0,8}(9|10|13);?)|\s)*(?=:)';
break;
case 'ra_tag':
- //these take the form of e.g. '<SCRIPT[^\da-z] ....';
+ // These take the form of e.g. '<SCRIPT[^\da-z] ....';
$pattern = '(?<=<)' . $pattern . '((&#[xX]0{0,8}([9ab]);?)|(�{0,8}(9|10|13);?)|\s)*(?=[^\da-z])';
break;
case 'ra_attribute':
- //these take the form of e.g. 'onload=' Beware that a lot of characters are allowed
- //between the attribute and the equal sign!
+ // These take the form of e.g. 'onload=' Beware that a lot of characters are allowed
+ // between the attribute and the equal sign!
$pattern .= '[\s\!\#\$\%\&\(\)\*\~\+\-\_\.\,\:\;\?\@\[\/\|\\\\\]\^\`]*(?==)';
break;
}
$pattern = '/' . $pattern . '/i';
- // add in <x> to nerf the tag
+ // Add in <x> to nerf the tag
$replacement = substr_replace($ra[$i][0], $replaceString, 2, 0);
- // filter out the hex tags
+ // Filter out the hex tags
$val = preg_replace($pattern, $replacement, $val);
if ($val_before == $val) {
- // no replacements were made, so exit the loop
+ // No replacements were made, so exit the loop
$found = FALSE;
}
}
--
GitLab