aboutsummaryrefslogtreecommitdiffstats
path: root/library/HTMLPurifier/URI.php
diff options
context:
space:
mode:
authorfriendica <info@friendica.com>2015-01-01 22:18:27 -0800
committerfriendica <info@friendica.com>2015-01-01 22:18:27 -0800
commita0052f0176bd079e6a94baec59fea2ec5a8d651e (patch)
treec323edd823681bc2e8ca757e7eaf8354d42c7b51 /library/HTMLPurifier/URI.php
parent545e47933a0816699c68d98a7742a03260d6a54f (diff)
downloadvolse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.tar.gz
volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.tar.bz2
volse-hubzilla-a0052f0176bd079e6a94baec59fea2ec5a8d651e.zip
htmlpurifier update - compatibility issue with language library autoloader
Diffstat (limited to 'library/HTMLPurifier/URI.php')
-rw-r--r--library/HTMLPurifier/URI.php257
1 files changed, 199 insertions, 58 deletions
diff --git a/library/HTMLPurifier/URI.php b/library/HTMLPurifier/URI.php
index 8b50d0d18..a5e7ae298 100644
--- a/library/HTMLPurifier/URI.php
+++ b/library/HTMLPurifier/URI.php
@@ -10,17 +10,57 @@
*/
class HTMLPurifier_URI
{
+ /**
+ * @type string
+ */
+ public $scheme;
- public $scheme, $userinfo, $host, $port, $path, $query, $fragment;
+ /**
+ * @type string
+ */
+ public $userinfo;
/**
+ * @type string
+ */
+ public $host;
+
+ /**
+ * @type int
+ */
+ public $port;
+
+ /**
+ * @type string
+ */
+ public $path;
+
+ /**
+ * @type string
+ */
+ public $query;
+
+ /**
+ * @type string
+ */
+ public $fragment;
+
+ /**
+ * @param string $scheme
+ * @param string $userinfo
+ * @param string $host
+ * @param int $port
+ * @param string $path
+ * @param string $query
+ * @param string $fragment
* @note Automatically normalizes scheme and port
*/
- public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) {
+ public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment)
+ {
$this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme);
$this->userinfo = $userinfo;
$this->host = $host;
- $this->port = is_null($port) ? $port : (int) $port;
+ $this->port = is_null($port) ? $port : (int)$port;
$this->path = $path;
$this->query = $query;
$this->fragment = $fragment;
@@ -28,19 +68,22 @@ class HTMLPurifier_URI
/**
* Retrieves a scheme object corresponding to the URI's scheme/default
- * @param $config Instance of HTMLPurifier_Config
- * @param $context Instance of HTMLPurifier_Context
- * @return Scheme object appropriate for validating this URI
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return HTMLPurifier_URIScheme Scheme object appropriate for validating this URI
*/
- public function getSchemeObj($config, $context) {
+ public function getSchemeObj($config, $context)
+ {
$registry = HTMLPurifier_URISchemeRegistry::instance();
if ($this->scheme !== null) {
$scheme_obj = $registry->getScheme($this->scheme, $config, $context);
- if (!$scheme_obj) return false; // invalid scheme, clean it out
+ if (!$scheme_obj) {
+ return false;
+ } // invalid scheme, clean it out
} else {
// no scheme: retrieve the default one
$def = $config->getDefinition('URI');
- $scheme_obj = $registry->getScheme($def->defaultScheme, $config, $context);
+ $scheme_obj = $def->getDefaultScheme($config, $context);
if (!$scheme_obj) {
// something funky happened to the default scheme object
trigger_error(
@@ -56,30 +99,39 @@ class HTMLPurifier_URI
/**
* Generic validation method applicable for all schemes. May modify
* this URI in order to get it into a compliant form.
- * @param $config Instance of HTMLPurifier_Config
- * @param $context Instance of HTMLPurifier_Context
- * @return True if validation/filtering succeeds, false if failure
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return bool True if validation/filtering succeeds, false if failure
*/
- public function validate($config, $context) {
-
+ public function validate($config, $context)
+ {
// ABNF definitions from RFC 3986
$chars_sub_delims = '!$&\'()*+,;=';
$chars_gen_delims = ':/?#[]@';
$chars_pchar = $chars_sub_delims . ':@';
- // validate scheme (MUST BE FIRST!)
- if (!is_null($this->scheme) && is_null($this->host)) {
- $def = $config->getDefinition('URI');
- if ($def->defaultScheme === $this->scheme) {
- $this->scheme = null;
- }
- }
-
// validate host
if (!is_null($this->host)) {
$host_def = new HTMLPurifier_AttrDef_URI_Host();
$this->host = $host_def->validate($this->host, $config, $context);
- if ($this->host === false) $this->host = null;
+ if ($this->host === false) {
+ $this->host = null;
+ }
+ }
+
+ // validate scheme
+ // NOTE: It's not appropriate to check whether or not this
+ // scheme is in our registry, since a URIFilter may convert a
+ // URI that we don't allow into one we do. So instead, we just
+ // check if the scheme can be dropped because there is no host
+ // and it is our default scheme.
+ if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') {
+ // support for relative paths is pretty abysmal when the
+ // scheme is present, so axe it when possible
+ $def = $config->getDefinition('URI');
+ if ($def->defaultScheme === $this->scheme) {
+ $this->scheme = null;
+ }
}
// validate username
@@ -90,38 +142,55 @@ class HTMLPurifier_URI
// validate port
if (!is_null($this->port)) {
- if ($this->port < 1 || $this->port > 65535) $this->port = null;
+ if ($this->port < 1 || $this->port > 65535) {
+ $this->port = null;
+ }
}
// validate path
- $path_parts = array();
$segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/');
- if (!is_null($this->host)) {
+ if (!is_null($this->host)) { // this catches $this->host === ''
// path-abempty (hier and relative)
+ // http://www.example.com/my/path
+ // //www.example.com/my/path (looks odd, but works, and
+ // recognized by most browsers)
+ // (this set is valid or invalid on a scheme by scheme
+ // basis, so we'll deal with it later)
+ // file:///my/path
+ // ///my/path
$this->path = $segments_encoder->encode($this->path);
- } elseif ($this->path !== '' && $this->path[0] === '/') {
- // path-absolute (hier and relative)
- if (strlen($this->path) >= 2 && $this->path[1] === '/') {
- // This shouldn't ever happen!
- $this->path = '';
- } else {
+ } elseif ($this->path !== '') {
+ if ($this->path[0] === '/') {
+ // path-absolute (hier and relative)
+ // http:/my/path
+ // /my/path
+ if (strlen($this->path) >= 2 && $this->path[1] === '/') {
+ // This could happen if both the host gets stripped
+ // out
+ // http://my/path
+ // //my/path
+ $this->path = '';
+ } else {
+ $this->path = $segments_encoder->encode($this->path);
+ }
+ } elseif (!is_null($this->scheme)) {
+ // path-rootless (hier)
+ // http:my/path
+ // Short circuit evaluation means we don't need to check nz
$this->path = $segments_encoder->encode($this->path);
- }
- } elseif (!is_null($this->scheme) && $this->path !== '') {
- // path-rootless (hier)
- // Short circuit evaluation means we don't need to check nz
- $this->path = $segments_encoder->encode($this->path);
- } elseif (is_null($this->scheme) && $this->path !== '') {
- // path-noscheme (relative)
- // (once again, not checking nz)
- $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@');
- $c = strpos($this->path, '/');
- if ($c !== false) {
- $this->path =
- $segment_nc_encoder->encode(substr($this->path, 0, $c)) .
- $segments_encoder->encode(substr($this->path, $c));
} else {
- $this->path = $segment_nc_encoder->encode($this->path);
+ // path-noscheme (relative)
+ // my/path
+ // (once again, not checking nz)
+ $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@');
+ $c = strpos($this->path, '/');
+ if ($c !== false) {
+ $this->path =
+ $segment_nc_encoder->encode(substr($this->path, 0, $c)) .
+ $segments_encoder->encode(substr($this->path, $c));
+ } else {
+ $this->path = $segment_nc_encoder->encode($this->path);
+ }
}
} else {
// path-empty (hier and relative)
@@ -138,36 +207,108 @@ class HTMLPurifier_URI
if (!is_null($this->fragment)) {
$this->fragment = $qf_encoder->encode($this->fragment);
}
-
return true;
-
}
/**
* Convert URI back to string
- * @return String URI appropriate for output
+ * @return string URI appropriate for output
*/
- public function toString() {
+ public function toString()
+ {
// reconstruct authority
$authority = null;
+ // there is a rendering difference between a null authority
+ // (http:foo-bar) and an empty string authority
+ // (http:///foo-bar).
if (!is_null($this->host)) {
$authority = '';
- if(!is_null($this->userinfo)) $authority .= $this->userinfo . '@';
+ if (!is_null($this->userinfo)) {
+ $authority .= $this->userinfo . '@';
+ }
$authority .= $this->host;
- if(!is_null($this->port)) $authority .= ':' . $this->port;
+ if (!is_null($this->port)) {
+ $authority .= ':' . $this->port;
+ }
}
- // reconstruct the result
+ // Reconstruct the result
+ // One might wonder about parsing quirks from browsers after
+ // this reconstruction. Unfortunately, parsing behavior depends
+ // on what *scheme* was employed (file:///foo is handled *very*
+ // differently than http:///foo), so unfortunately we have to
+ // defer to the schemes to do the right thing.
$result = '';
- if (!is_null($this->scheme)) $result .= $this->scheme . ':';
- if (!is_null($authority)) $result .= '//' . $authority;
+ if (!is_null($this->scheme)) {
+ $result .= $this->scheme . ':';
+ }
+ if (!is_null($authority)) {
+ $result .= '//' . $authority;
+ }
$result .= $this->path;
- if (!is_null($this->query)) $result .= '?' . $this->query;
- if (!is_null($this->fragment)) $result .= '#' . $this->fragment;
+ if (!is_null($this->query)) {
+ $result .= '?' . $this->query;
+ }
+ if (!is_null($this->fragment)) {
+ $result .= '#' . $this->fragment;
+ }
return $result;
}
+ /**
+ * Returns true if this URL might be considered a 'local' URL given
+ * the current context. This is true when the host is null, or
+ * when it matches the host supplied to the configuration.
+ *
+ * Note that this does not do any scheme checking, so it is mostly
+ * only appropriate for metadata that doesn't care about protocol
+ * security. isBenign is probably what you actually want.
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return bool
+ */
+ public function isLocal($config, $context)
+ {
+ if ($this->host === null) {
+ return true;
+ }
+ $uri_def = $config->getDefinition('URI');
+ if ($uri_def->host === $this->host) {
+ return true;
+ }
+ return false;
+ }
+
+ /**
+ * Returns true if this URL should be considered a 'benign' URL,
+ * that is:
+ *
+ * - It is a local URL (isLocal), and
+ * - It has a equal or better level of security
+ * @param HTMLPurifier_Config $config
+ * @param HTMLPurifier_Context $context
+ * @return bool
+ */
+ public function isBenign($config, $context)
+ {
+ if (!$this->isLocal($config, $context)) {
+ return false;
+ }
+
+ $scheme_obj = $this->getSchemeObj($config, $context);
+ if (!$scheme_obj) {
+ return false;
+ } // conservative approach
+
+ $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context);
+ if ($current_scheme_obj->secure) {
+ if (!$scheme_obj->secure) {
+ return false;
+ }
+ }
+ return true;
+ }
}
// vim: et sw=4 sts=4