library/HTMLPurifier/URI.php

   1 <?php
   2
   3 /**
   4  * HTML Purifier's internal representation of a URI.
   5  * @note
   6  *      Internal data-structures are completely escaped. If the data needs
   7  *      to be used in a non-URI context (which is very unlikely), be sure
   8  *      to decode it first. The URI may not necessarily be well-formed until
   9  *      validate() is called.
  10  */
  11 class HTMLPurifier_URI
  12 {
  13     /**
  14      * @type string
  15      */
  16     public $scheme;
  17
  18     /**
  19      * @type string
  20      */
  21     public $userinfo;
  22
  23     /**
  24      * @type string
  25      */
  26     public $host;
  27
  28     /**
  29      * @type int
  30      */
  31     public $port;
  32
  33     /**
  34      * @type string
  35      */
  36     public $path;
  37
  38     /**
  39      * @type string
  40      */
  41     public $query;
  42
  43     /**
  44      * @type string
  45      */
  46     public $fragment;
  47
  48     /**
  49      * @param string $scheme
  50      * @param string $userinfo
  51      * @param string $host
  52      * @param int $port
  53      * @param string $path
  54      * @param string $query
  55      * @param string $fragment
  56      * @note Automatically normalizes scheme and port
  57      */
  58     public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment)
  59     {
  60         $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme);
  61         $this->userinfo = $userinfo;
  62         $this->host = $host;
  63         $this->port = is_null($port) ? $port : (int)$port;
  64         $this->path = $path;
  65         $this->query = $query;
  66         $this->fragment = $fragment;
  67     }
  68
  69     /**
  70      * Retrieves a scheme object corresponding to the URI's scheme/default
  71      * @param HTMLPurifier_Config $config
  72      * @param HTMLPurifier_Context $context
  73      * @return HTMLPurifier_URIScheme Scheme object appropriate for validating this URI
  74      */
  75     public function getSchemeObj($config, $context)
  76     {
  77         $registry = HTMLPurifier_URISchemeRegistry::instance();
  78         if ($this->scheme !== null) {
  79             $scheme_obj = $registry->getScheme($this->scheme, $config, $context);
  80             if (!$scheme_obj) {
  81                 return false;
  82             } // invalid scheme, clean it out
  83         } else {
  84             // no scheme: retrieve the default one
  85             $def = $config->getDefinition('URI');
  86             $scheme_obj = $def->getDefaultScheme($config, $context);
  87             if (!$scheme_obj) {
  88                 // something funky happened to the default scheme object
  89                 trigger_error(
  90                     'Default scheme object "' . $def->defaultScheme . '" was not readable',
  91                     E_USER_WARNING
  92                 );
  93                 return false;
  94             }
  95         }
  96         return $scheme_obj;
  97     }
  98
  99     /**
 100      * Generic validation method applicable for all schemes. May modify
 101      * this URI in order to get it into a compliant form.
 102      * @param HTMLPurifier_Config $config
 103      * @param HTMLPurifier_Context $context
 104      * @return bool True if validation/filtering succeeds, false if failure
 105      */
 106     public function validate($config, $context)
 107     {
 108         // ABNF definitions from RFC 3986
 109         $chars_sub_delims = '!$&\'()*+,;=';
 110         $chars_gen_delims = ':/?#[]@';
 111         $chars_pchar = $chars_sub_delims . ':@';
 112
 113         // validate host
 114         if (!is_null($this->host)) {
 115             $host_def = new HTMLPurifier_AttrDef_URI_Host();
 116             $this->host = $host_def->validate($this->host, $config, $context);
 117             if ($this->host === false) {
 118                 $this->host = null;
 119             }
 120         }
 121
 122         // validate scheme
 123         // NOTE: It's not appropriate to check whether or not this
 124         // scheme is in our registry, since a URIFilter may convert a
 125         // URI that we don't allow into one we do.  So instead, we just
 126         // check if the scheme can be dropped because there is no host
 127         // and it is our default scheme.
 128         if (!is_null($this->scheme) && is_null($this->host) || $this->host === '') {
 129             // support for relative paths is pretty abysmal when the
 130             // scheme is present, so axe it when possible
 131             $def = $config->getDefinition('URI');
 132             if ($def->defaultScheme === $this->scheme) {
 133                 $this->scheme = null;
 134             }
 135         }
 136
 137         // validate username
 138         if (!is_null($this->userinfo)) {
 139             $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':');
 140             $this->userinfo = $encoder->encode($this->userinfo);
 141         }
 142
 143         // validate port
 144         if (!is_null($this->port)) {
 145             if ($this->port < 1 || $this->port > 65535) {
 146                 $this->port = null;
 147             }
 148         }
 149
 150         // validate path
 151         $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/');
 152         if (!is_null($this->host)) { // this catches $this->host === ''
 153             // path-abempty (hier and relative)
 154             // http://www.example.com/my/path
 155             // //www.example.com/my/path (looks odd, but works, and
 156             //                            recognized by most browsers)
 157             // (this set is valid or invalid on a scheme by scheme
 158             // basis, so we'll deal with it later)
 159             // file:///my/path
 160             // ///my/path
 161             $this->path = $segments_encoder->encode($this->path);
 162         } elseif ($this->path !== '') {
 163             if ($this->path[0] === '/') {
 164                 // path-absolute (hier and relative)
 165                 // http:/my/path
 166                 // /my/path
 167                 if (strlen($this->path) >= 2 && $this->path[1] === '/') {
 168                     // This could happen if both the host gets stripped
 169                     // out
 170                     // http://my/path
 171                     // //my/path
 172                     $this->path = '';
 173                 } else {
 174                     $this->path = $segments_encoder->encode($this->path);
 175                 }
 176             } elseif (!is_null($this->scheme)) {
 177                 // path-rootless (hier)
 178                 // http:my/path
 179                 // Short circuit evaluation means we don't need to check nz
 180                 $this->path = $segments_encoder->encode($this->path);
 181             } else {
 182                 // path-noscheme (relative)
 183                 // my/path
 184                 // (once again, not checking nz)
 185                 $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@');
 186                 $c = strpos($this->path, '/');
 187                 if ($c !== false) {
 188                     $this->path =
 189                         $segment_nc_encoder->encode(substr($this->path, 0, $c)) .
 190                         $segments_encoder->encode(substr($this->path, $c));
 191                 } else {
 192                     $this->path = $segment_nc_encoder->encode($this->path);
 193                 }
 194             }
 195         } else {
 196             // path-empty (hier and relative)
 197             $this->path = ''; // just to be safe
 198         }
 199
 200         // qf = query and fragment
 201         $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?');
 202
 203         if (!is_null($this->query)) {
 204             $this->query = $qf_encoder->encode($this->query);
 205         }
 206
 207         if (!is_null($this->fragment)) {
 208             $this->fragment = $qf_encoder->encode($this->fragment);
 209         }
 210         return true;
 211     }
 212
 213     /**
 214      * Convert URI back to string
 215      * @return string URI appropriate for output
 216      */
 217     public function toString()
 218     {
 219         // reconstruct authority
 220         $authority = null;
 221         // there is a rendering difference between a null authority
 222         // (http:foo-bar) and an empty string authority
 223         // (http:///foo-bar).
 224         if (!is_null($this->host)) {
 225             $authority = '';
 226             if (!is_null($this->userinfo)) {
 227                 $authority .= $this->userinfo . '@';
 228             }
 229             $authority .= $this->host;
 230             if (!is_null($this->port)) {
 231                 $authority .= ':' . $this->port;
 232             }
 233         }
 234
 235         // Reconstruct the result
 236         // One might wonder about parsing quirks from browsers after
 237         // this reconstruction.  Unfortunately, parsing behavior depends
 238         // on what *scheme* was employed (file:///foo is handled *very*
 239         // differently than http:///foo), so unfortunately we have to
 240         // defer to the schemes to do the right thing.
 241         $result = '';
 242         if (!is_null($this->scheme)) {
 243             $result .= $this->scheme . ':';
 244         }
 245         if (!is_null($authority)) {
 246             $result .= '//' . $authority;
 247         }
 248         $result .= $this->path;
 249         if (!is_null($this->query)) {
 250             $result .= '?' . $this->query;
 251         }
 252         if (!is_null($this->fragment)) {
 253             $result .= '#' . $this->fragment;
 254         }
 255
 256         return $result;
 257     }
 258
 259     /**
 260      * Returns true if this URL might be considered a 'local' URL given
 261      * the current context.  This is true when the host is null, or
 262      * when it matches the host supplied to the configuration.
 263      *
 264      * Note that this does not do any scheme checking, so it is mostly
 265      * only appropriate for metadata that doesn't care about protocol
 266      * security.  isBenign is probably what you actually want.
 267      * @param HTMLPurifier_Config $config
 268      * @param HTMLPurifier_Context $context
 269      * @return bool
 270      */
 271     public function isLocal($config, $context)
 272     {
 273         if ($this->host === null) {
 274             return true;
 275         }
 276         $uri_def = $config->getDefinition('URI');
 277         if ($uri_def->host === $this->host) {
 278             return true;
 279         }
 280         return false;
 281     }
 282
 283     /**
 284      * Returns true if this URL should be considered a 'benign' URL,
 285      * that is:
 286      *
 287      *      - It is a local URL (isLocal), and
 288      *      - It has a equal or better level of security
 289      * @param HTMLPurifier_Config $config
 290      * @param HTMLPurifier_Context $context
 291      * @return bool
 292      */
 293     public function isBenign($config, $context)
 294     {
 295         if (!$this->isLocal($config, $context)) {
 296             return false;
 297         }
 298
 299         $scheme_obj = $this->getSchemeObj($config, $context);
 300         if (!$scheme_obj) {
 301             return false;
 302         } // conservative approach
 303
 304         $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context);
 305         if ($current_scheme_obj->secure) {
 306             if (!$scheme_obj->secure) {
 307                 return false;
 308             }
 309         }
 310         return true;
 311     }
 312 }
 313
 314 // vim: et sw=4 sts=4