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

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>

library/HTMLPurifier/AttrDef.php

@@ -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