mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2024-12-23 17:01:51 +00:00
e76f4b45d0
Basically, browsers don't parse what should be valid URIs correctly, so
we have to go through some backbends to accomodate them. Specifically,
for browseable URIs, the following URIs have unintended behavior:
- ///example.com
- http:/example.com
- http:///example.com
Furthermore, if the path begins with //, modifying these URLs must
be done with care, as if you remove the host-name component, the
parse tree changes.
I've modified the engine to follow correct URI semantics as much
as possible while outputting browser compatible code, and invalidate
the URI in cases where we can't deal. There has been a refactoring
of URIScheme so that this important check is always performed,
introducing a new member variable allow_empty_host which is true
on data, file, mailto and news schemes.
This also fixes bypass bugs on URI.Munge.
Signed-off-by: Edward Z. Yang <ezyang@mit.edu>
43 lines
1.4 KiB
PHP
43 lines
1.4 KiB
PHP
<?php
|
|
|
|
/**
|
|
* Validates ftp (File Transfer Protocol) URIs as defined by generic RFC 1738.
|
|
*/
|
|
class HTMLPurifier_URIScheme_ftp extends HTMLPurifier_URIScheme {
|
|
|
|
public $default_port = 21;
|
|
public $browsable = true; // usually
|
|
public $hierarchical = true;
|
|
|
|
public function doValidate(&$uri, $config, $context) {
|
|
$uri->query = null;
|
|
|
|
// typecode check
|
|
$semicolon_pos = strrpos($uri->path, ';'); // reverse
|
|
if ($semicolon_pos !== false) {
|
|
$type = substr($uri->path, $semicolon_pos + 1); // no semicolon
|
|
$uri->path = substr($uri->path, 0, $semicolon_pos);
|
|
$type_ret = '';
|
|
if (strpos($type, '=') !== false) {
|
|
// figure out whether or not the declaration is correct
|
|
list($key, $typecode) = explode('=', $type, 2);
|
|
if ($key !== 'type') {
|
|
// invalid key, tack it back on encoded
|
|
$uri->path .= '%3B' . $type;
|
|
} elseif ($typecode === 'a' || $typecode === 'i' || $typecode === 'd') {
|
|
$type_ret = ";type=$typecode";
|
|
}
|
|
} else {
|
|
$uri->path .= '%3B' . $type;
|
|
}
|
|
$uri->path = str_replace(';', '%3B', $uri->path);
|
|
$uri->path .= $type_ret;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
}
|
|
|
|
// vim: et sw=4 sts=4
|