mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-30 19:00:10 +02:00
Code Issues Releases Wiki Activity

Rewrite CSS url() and font-family output logic.

Browse Source 
The new logic is as follows:

* Given a URL to insert into url(), check that it is properly URL
  encoded (in particular, a doublequote and backslash never occurs
  within it) and then place it as url("http://example.com").

* Given a font name, if it is strictly alphanumeric, it is safe to omit
  quotes. Otherwise, wrap in double quotes and replace '"' with '\22 '
  (note trailing space) and '\' with '\5C ' (ditto).

We introduce expandCSSEscape() which is a hack for common parsing
idioms in CSS; this means that CSS escapes are now recognized inside
URLs as well as unquoted font names.

Signed-off-by: Edward Z. Yang <ezyang@mit.edu>
This commit is contained in:
Edward Z. Yang
2010-05-21 11:53:52 -04:00
parent df3100b1b3
commit d3abcb90e3
15 changed files with 99 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
library/HTMLPurifier/AttrDef.php
View File

@@ -82,6 +82,42 @@ abstract class HTMLPurifier_AttrDef
return preg_replace('/rgb\((\d+)\s*,\s*(\d+)\s*,\s*(\d+)\)/', 'rgb(\1,\2,\3)', $string);
}
/**
* Parses a possibly escaped CSS string and returns the "pure"
* version of it.
*/
protected function expandCSSEscape($string) {
// flexibly parse it
$ret = '';
for ($i = 0, $c = strlen($string); $i < $c; $i++) {
if ($string[$i] === '\\') {
$i++;
if ($i >= $c) {
$ret .= '\\';
break;
}
if (ctype_xdigit($string[$i])) {
$code = $string[$i];
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
if (!ctype_xdigit($string[$i])) break;
$code .= $string[$i];
}
// We have to be extremely careful when adding
// new characters, to make sure we're not breaking
// the encoding.
$char = HTMLPurifier_Encoder::unichr(hexdec($code));
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
$ret .= $char;
if ($i < $c && trim($string[$i]) !== '') $i--;
continue;
}
if ($string[$i] === "\n") continue;
}
$ret .= $string[$i];
}
return $ret;
}
}
// vim: et sw=4 sts=4

52
library/HTMLPurifier/AttrDef/CSS/FontFamily.php
View File

@@ -34,37 +34,10 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
$quote = $font[0];
if ($font[$length - 1] !== $quote) continue;
$font = substr($font, 1, $length - 2);
$new_font = '';
for ($i = 0, $c = strlen($font); $i < $c; $i++) {
if ($font[$i] === '\\') {
$i++;
if ($i >= $c) {
$new_font .= '\\';
break;
}
if (ctype_xdigit($font[$i])) {
$code = $font[$i];
for ($a = 1, $i++; $i < $c && $a < 6; $i++, $a++) {
if (!ctype_xdigit($font[$i])) break;
$code .= $font[$i];
}
// We have to be extremely careful when adding
// new characters, to make sure we're not breaking
// the encoding.
$char = HTMLPurifier_Encoder::unichr(hexdec($code));
if (HTMLPurifier_Encoder::cleanUTF8($char) === '') continue;
$new_font .= $char;
if ($i < $c && trim($font[$i]) !== '') $i--;
continue;
}
if ($font[$i] === "\n") continue;
}
$new_font .= $font[$i];
}
$font = $new_font;
}
$font = $this->expandCSSEscape($font);
// $font is a pure representation of the font name
if (ctype_alnum($font) && $font !== '') {
@@ -73,12 +46,21 @@ class HTMLPurifier_AttrDef_CSS_FontFamily extends HTMLPurifier_AttrDef
continue;
}
// complicated font, requires quoting
// bugger out on whitespace. form feed (0C) really
// shouldn't show up regardless
$font = str_replace(array("\n", "\t", "\r", "\x0C"), ' ', $font);
// armor single quotes and new lines
$font = str_replace("\\", "\\\\", $font);
$font = str_replace("'", "\\'", $font);
$final .= "'$font', ";
// These ugly transforms don't pose a security
// risk (as \\ and \" might). We could try to be clever and
// use single-quote wrapping when there is a double quote
// present, but I have choosen not to implement that.
// (warning: this code relies on the selection of quotation
// mark below)
$font = str_replace('\\', '\\5C ', $font);
$font = str_replace('"', '\\22 ', $font);
// complicated font, requires quoting
$final .= "\"$font\", "; // note that this will later get turned into &quot;
}
$final = rtrim($final, ', ');
if ($final === '') return false;

12
library/HTMLPurifier/AttrDef/CSS/URI.php
View File

@@ -34,20 +34,16 @@ class HTMLPurifier_AttrDef_CSS_URI extends HTMLPurifier_AttrDef_URI
$uri = substr($uri, 1, $new_length - 1);
}
$keys = array( '(', ')', ',', ' ', '"', "'");
$values = array('\\(', '\\)', '\\,', '\\ ', '\\"', "\\'");
$uri = str_replace($values, $keys, $uri);
$uri = $this->expandCSSEscape($uri);
$result = parent::validate($uri, $config, $context);
if ($result === false) return false;
// escape necessary characters according to CSS spec
// except for the comma, none of these should appear in the
// URI at all
$result = str_replace($keys, $values, $result);
// extra sanity check; should have been done by URI
$result = str_replace(array('"', "\\", "\n", "\x0c", "\r"), "", $result);
return "url('$result')";
return "url(\"$result\")";
}