| Total Complexity | 115 |
| Total Lines | 1056 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like kses5 often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use kses5, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 107 | class kses5 |
||
| 108 | { |
||
| 109 | /**#@+ |
||
| 110 | * @access private |
||
| 111 | * @var array |
||
| 112 | */ |
||
| 113 | private $allowed_protocols; |
||
| 114 | private $allowed_html; |
||
| 115 | /**#@-*/ |
||
| 116 | |||
| 117 | /** |
||
| 118 | * Constructor for kses. |
||
| 119 | * |
||
| 120 | * This sets a default collection of protocols allowed in links, and creates an |
||
| 121 | * empty set of allowed HTML tags. |
||
| 122 | * @since PHP5 OOP 1.0.0 |
||
| 123 | */ |
||
| 124 | public function __construct() |
||
| 125 | { |
||
| 126 | /** |
||
| 127 | * You could add protocols such as ftp, new, gopher, mailto, irc, etc. |
||
| 128 | * |
||
| 129 | * The base values the original kses provided were: |
||
| 130 | * 'http', 'https', 'ftp', 'news', 'nntp', 'telnet', 'gopher', 'mailto' |
||
| 131 | */ |
||
| 132 | $this->allowed_protocols = array('http', 'ftp', 'mailto'); |
||
| 133 | $this->allowed_html = array(); |
||
| 134 | } |
||
| 135 | |||
| 136 | /** |
||
| 137 | * Basic task of kses - parses $string and strips it as required. |
||
| 138 | * |
||
| 139 | * This method strips all the disallowed (X)HTML tags, attributes |
||
| 140 | * and protocols from the input $string. |
||
| 141 | * |
||
| 142 | * @access public |
||
| 143 | * @param string $string String to be stripped of 'evil scripts' |
||
| 144 | * @return string The stripped string |
||
| 145 | * @since PHP4 OOP 0.0.1 |
||
| 146 | */ |
||
| 147 | public function Parse($string = "") |
||
| 148 | { |
||
| 149 | if (get_magic_quotes_gpc()) |
||
| 150 | { |
||
| 151 | $string = stripslashes($string); |
||
| 152 | } |
||
| 153 | $string = $this->removeNulls($string); |
||
| 154 | // Remove JavaScript entities from early Netscape 4 versions |
||
| 155 | $string = preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string); |
||
| 156 | $string = $this->normalizeEntities($string); |
||
| 157 | $string = $this->filterKsesTextHook($string); |
||
| 158 | $string = preg_replace('%(<' . '[^>]*' . '(>|$)' . '|>)%e', "\$this->stripTags('\\1')", $string); |
||
| 159 | return $string; |
||
| 160 | } |
||
| 161 | |||
| 162 | /** |
||
| 163 | * Allows for single/batch addition of protocols |
||
| 164 | * |
||
| 165 | * This method accepts one argument that can be either a string |
||
| 166 | * or an array of strings. Invalid data will be ignored. |
||
| 167 | * |
||
| 168 | * The argument will be processed, and each string will be added |
||
| 169 | * via AddProtocol(). |
||
| 170 | * |
||
| 171 | * @access public |
||
| 172 | * @param mixed , A string or array of protocols that will be added to the internal list of allowed protocols. |
||
| 173 | * @return bool Status of adding valid protocols. |
||
| 174 | * @see AddProtocol() |
||
| 175 | * @since PHP5 OOP 1.0.0 |
||
| 176 | */ |
||
| 177 | public function AddProtocols() |
||
| 178 | { |
||
| 179 | $c_args = func_num_args(); |
||
| 180 | if($c_args != 1) |
||
| 181 | { |
||
| 182 | trigger_error("kses5::AddProtocols() did not receive an argument.", E_USER_WARNING); |
||
| 183 | return false; |
||
| 184 | } |
||
| 185 | |||
| 186 | $protocol_data = func_get_arg(0); |
||
| 187 | |||
| 188 | if(is_array($protocol_data) && count($protocol_data) > 0) |
||
| 189 | { |
||
| 190 | foreach($protocol_data as $protocol) |
||
| 191 | { |
||
| 192 | $this->AddProtocol($protocol); |
||
| 193 | } |
||
| 194 | return true; |
||
| 195 | } |
||
| 196 | elseif(is_string($protocol_data)) |
||
| 197 | { |
||
| 198 | $this->AddProtocol($protocol_data); |
||
| 199 | return true; |
||
| 200 | } |
||
| 201 | else |
||
| 202 | { |
||
| 203 | trigger_error("kses5::AddProtocols() did not receive a string or an array.", E_USER_WARNING); |
||
| 204 | return false; |
||
| 205 | } |
||
| 206 | } |
||
| 207 | |||
| 208 | /** |
||
| 209 | * Allows for single/batch addition of protocols |
||
| 210 | * |
||
| 211 | * @deprecated Use AddProtocols() |
||
| 212 | * @see AddProtocols() |
||
| 213 | * @return bool |
||
| 214 | * @since PHP4 OOP 0.0.1 |
||
| 215 | */ |
||
| 216 | public function Protocols() |
||
| 217 | { |
||
| 218 | $c_args = func_num_args(); |
||
| 219 | if($c_args != 1) |
||
| 220 | { |
||
| 221 | trigger_error("kses5::Protocols() did not receive an argument.", E_USER_WARNING); |
||
| 222 | return false; |
||
| 223 | } |
||
| 224 | |||
| 225 | return $this->AddProtocols(func_get_arg(0)); |
||
| 226 | } |
||
| 227 | |||
| 228 | /** |
||
| 229 | * Adds a single protocol to $this->allowed_protocols. |
||
| 230 | * |
||
| 231 | * This method accepts a string argument and adds it to |
||
| 232 | * the list of allowed protocols to keep when performing |
||
| 233 | * Parse(). |
||
| 234 | * |
||
| 235 | * @access public |
||
| 236 | * @param string $protocol The name of the protocol to be added. |
||
| 237 | * @return bool Status of adding valid protocol. |
||
| 238 | * @since PHP4 OOP 0.0.1 |
||
| 239 | */ |
||
| 240 | public function AddProtocol($protocol = "") |
||
| 241 | { |
||
| 242 | if(!is_string($protocol)) |
||
| 243 | { |
||
| 244 | trigger_error("kses5::AddProtocol() requires a string.", E_USER_WARNING); |
||
| 245 | return false; |
||
| 246 | } |
||
| 247 | |||
| 248 | // Remove any inadvertent ':' at the end of the protocol. |
||
| 249 | if(substr($protocol, strlen($protocol) - 1, 1) == ":") |
||
| 250 | { |
||
| 251 | $protocol = substr($protocol, 0, strlen($protocol) - 1); |
||
| 252 | } |
||
| 253 | |||
| 254 | $protocol = strtolower(trim($protocol)); |
||
| 255 | if($protocol == "") |
||
| 256 | { |
||
| 257 | trigger_error("kses5::AddProtocol() tried to add an empty/NULL protocol.", E_USER_WARNING); |
||
| 258 | return false; |
||
| 259 | } |
||
| 260 | |||
| 261 | // prevent duplicate protocols from being added. |
||
| 262 | if(!in_array($protocol, $this->allowed_protocols)) |
||
| 263 | { |
||
| 264 | array_push($this->allowed_protocols, $protocol); |
||
| 265 | sort($this->allowed_protocols); |
||
| 266 | } |
||
| 267 | return true; |
||
| 268 | } |
||
| 269 | |||
| 270 | /** |
||
| 271 | * Removes a single protocol from $this->allowed_protocols. |
||
| 272 | * |
||
| 273 | * This method accepts a string argument and removes it from |
||
| 274 | * the list of allowed protocols to keep when performing |
||
| 275 | * Parse(). |
||
| 276 | * |
||
| 277 | * @access public |
||
| 278 | * @param string $protocol The name of the protocol to be removed. |
||
| 279 | * @return bool Status of removing valid protocol. |
||
| 280 | * @since PHP5 OOP 1.0.0 |
||
| 281 | */ |
||
| 282 | public function RemoveProtocol($protocol = "") |
||
| 283 | { |
||
| 284 | if(!is_string($protocol)) |
||
| 285 | { |
||
| 286 | trigger_error("kses5::RemoveProtocol() requires a string.", E_USER_WARNING); |
||
| 287 | return false; |
||
| 288 | } |
||
| 289 | |||
| 290 | // Remove any inadvertent ':' at the end of the protocol. |
||
| 291 | if(substr($protocol, strlen($protocol) - 1, 1) == ":") |
||
| 292 | { |
||
| 293 | $protocol = substr($protocol, 0, strlen($protocol) - 1); |
||
| 294 | } |
||
| 295 | |||
| 296 | $protocol = strtolower(trim($protocol)); |
||
| 297 | if($protocol == "") |
||
| 298 | { |
||
| 299 | trigger_error("kses5::RemoveProtocol() tried to remove an empty/NULL protocol.", E_USER_WARNING); |
||
| 300 | return false; |
||
| 301 | } |
||
| 302 | |||
| 303 | // Ensures that the protocol exists before removing it. |
||
| 304 | if(in_array($protocol, $this->allowed_protocols)) |
||
| 305 | { |
||
| 306 | $this->allowed_protocols = array_diff($this->allowed_protocols, array($protocol)); |
||
| 307 | sort($this->allowed_protocols); |
||
| 308 | } |
||
| 309 | |||
| 310 | return true; |
||
| 311 | } |
||
| 312 | |||
| 313 | /** |
||
| 314 | * Allows for single/batch removal of protocols |
||
| 315 | * |
||
| 316 | * This method accepts one argument that can be either a string |
||
| 317 | * or an array of strings. Invalid data will be ignored. |
||
| 318 | * |
||
| 319 | * The argument will be processed, and each string will be removed |
||
| 320 | * via RemoveProtocol(). |
||
| 321 | * |
||
| 322 | * @access public |
||
| 323 | * @param mixed , A string or array of protocols that will be removed from the internal list of allowed protocols. |
||
| 324 | * @return bool Status of removing valid protocols. |
||
| 325 | * @see RemoveProtocol() |
||
| 326 | * @since PHP5 OOP 1.0.0 |
||
| 327 | */ |
||
| 328 | public function RemoveProtocols() |
||
| 329 | { |
||
| 330 | $c_args = func_num_args(); |
||
| 331 | if($c_args != 1) |
||
| 332 | { |
||
| 333 | return false; |
||
| 334 | } |
||
| 335 | |||
| 336 | $protocol_data = func_get_arg(0); |
||
| 337 | |||
| 338 | if(is_array($protocol_data) && count($protocol_data) > 0) |
||
| 339 | { |
||
| 340 | foreach($protocol_data as $protocol) |
||
| 341 | { |
||
| 342 | $this->RemoveProtocol($protocol); |
||
| 343 | } |
||
| 344 | } |
||
| 345 | elseif(is_string($protocol_data)) |
||
| 346 | { |
||
| 347 | $this->RemoveProtocol($protocol_data); |
||
| 348 | return true; |
||
| 349 | } |
||
| 350 | else |
||
| 351 | { |
||
| 352 | trigger_error("kses5::RemoveProtocols() did not receive a string or an array.", E_USER_WARNING); |
||
| 353 | return false; |
||
| 354 | } |
||
| 355 | } |
||
| 356 | |||
| 357 | /** |
||
| 358 | * Allows for single/batch replacement of protocols |
||
| 359 | * |
||
| 360 | * This method accepts one argument that can be either a string |
||
| 361 | * or an array of strings. Invalid data will be ignored. |
||
| 362 | * |
||
| 363 | * Existing protocols will be removed, then the argument will be |
||
| 364 | * processed, and each string will be added via AddProtocol(). |
||
| 365 | * |
||
| 366 | * @access public |
||
| 367 | * @param mixed , A string or array of protocols that will be the new internal list of allowed protocols. |
||
| 368 | * @return bool Status of replacing valid protocols. |
||
| 369 | * @since PHP5 OOP 1.0.1 |
||
| 370 | * @see AddProtocol() |
||
| 371 | */ |
||
| 372 | public function SetProtocols() |
||
| 373 | { |
||
| 374 | $c_args = func_num_args(); |
||
| 375 | if($c_args != 1) |
||
| 376 | { |
||
| 377 | trigger_error("kses5::SetProtocols() did not receive an argument.", E_USER_WARNING); |
||
| 378 | return false; |
||
| 379 | } |
||
| 380 | |||
| 381 | $protocol_data = func_get_arg(0); |
||
| 382 | |||
| 383 | if(is_array($protocol_data) && count($protocol_data) > 0) |
||
| 384 | { |
||
| 385 | $this->allowed_protocols = array(); |
||
| 386 | foreach($protocol_data as $protocol) |
||
| 387 | { |
||
| 388 | $this->AddProtocol($protocol); |
||
| 389 | } |
||
| 390 | return true; |
||
| 391 | } |
||
| 392 | elseif(is_string($protocol_data)) |
||
| 393 | { |
||
| 394 | $this->allowed_protocols = array(); |
||
| 395 | $this->AddProtocol($protocol_data); |
||
| 396 | return true; |
||
| 397 | } |
||
| 398 | else |
||
| 399 | { |
||
| 400 | trigger_error("kses5::SetProtocols() did not receive a string or an array.", E_USER_WARNING); |
||
| 401 | return false; |
||
| 402 | } |
||
| 403 | } |
||
| 404 | |||
| 405 | /** |
||
| 406 | * Raw dump of allowed protocols |
||
| 407 | * |
||
| 408 | * This returns an indexed array of allowed protocols for a particular KSES |
||
| 409 | * instantiation. |
||
| 410 | * |
||
| 411 | * @access public |
||
| 412 | * @return array The list of allowed protocols. |
||
| 413 | * @since PHP5 OOP 1.0.2 |
||
| 414 | */ |
||
| 415 | public function DumpProtocols() |
||
| 416 | { |
||
| 417 | return $this->allowed_protocols; |
||
| 418 | } |
||
| 419 | |||
| 420 | /** |
||
| 421 | * Raw dump of allowed (X)HTML elements |
||
| 422 | * |
||
| 423 | * This returns an indexed array of allowed (X)HTML elements and attributes |
||
| 424 | * for a particular KSES instantiation. |
||
| 425 | * |
||
| 426 | * @access public |
||
| 427 | * @return array The list of allowed elements. |
||
| 428 | * @since PHP5 OOP 1.0.2 |
||
| 429 | */ |
||
| 430 | public function DumpElements() |
||
| 431 | { |
||
| 432 | return $this->allowed_html; |
||
| 433 | } |
||
| 434 | |||
| 435 | |||
| 436 | /** |
||
| 437 | * Adds valid (X)HTML with corresponding attributes that will be kept when stripping 'evil scripts'. |
||
| 438 | * |
||
| 439 | * This method accepts one argument that can be either a string |
||
| 440 | * or an array of strings. Invalid data will be ignored. |
||
| 441 | * |
||
| 442 | * @access public |
||
| 443 | * @param string $tag (X)HTML tag that will be allowed after stripping text. |
||
| 444 | * @param array $attribs Associative array of allowed attributes - key => attribute name - value => attribute parameter |
||
| 445 | * @return bool Status of Adding (X)HTML and attributes. |
||
| 446 | * @since PHP4 OOP 0.0.1 |
||
| 447 | */ |
||
| 448 | public function AddHTML($tag = "", $attribs = array()) |
||
| 449 | { |
||
| 450 | if(!is_string($tag)) |
||
| 451 | { |
||
| 452 | trigger_error("kses5::AddHTML() requires the tag to be a string", E_USER_WARNING); |
||
| 453 | return false; |
||
| 454 | } |
||
| 455 | |||
| 456 | $tag = strtolower(trim($tag)); |
||
| 457 | if($tag == "") |
||
| 458 | { |
||
| 459 | trigger_error("kses5::AddHTML() tried to add an empty/NULL tag", E_USER_WARNING); |
||
| 460 | return false; |
||
| 461 | } |
||
| 462 | |||
| 463 | if(!is_array($attribs)) |
||
| 464 | { |
||
| 465 | trigger_error("kses5::AddHTML() requires an array (even an empty one) of attributes for '$tag'", E_USER_WARNING); |
||
| 466 | return false; |
||
| 467 | } |
||
| 468 | |||
| 469 | $new_attribs = array(); |
||
| 470 | if(is_array($attribs) && count($attribs) > 0) |
||
| 471 | { |
||
| 472 | foreach($attribs as $idx1 => $val1) |
||
| 473 | { |
||
| 474 | $new_idx1 = strtolower($idx1); |
||
| 475 | $new_val1 = $attribs[$idx1]; |
||
| 476 | |||
| 477 | if(is_array($new_val1) && count($attribs) > 0) |
||
| 478 | { |
||
| 479 | $tmp_val = array(); |
||
| 480 | foreach($new_val1 as $idx2 => $val2) |
||
| 481 | { |
||
| 482 | $new_idx2 = strtolower($idx2); |
||
| 483 | $tmp_val[$new_idx2] = $val2; |
||
| 484 | } |
||
| 485 | $new_val1 = $tmp_val; |
||
| 486 | } |
||
| 487 | |||
| 488 | $new_attribs[$new_idx1] = $new_val1; |
||
| 489 | } |
||
| 490 | } |
||
| 491 | |||
| 492 | $this->allowed_html[$tag] = $new_attribs; |
||
| 493 | return true; |
||
| 494 | } |
||
| 495 | |||
| 496 | /** |
||
| 497 | * This method removes any NULL characters in $string. |
||
| 498 | * |
||
| 499 | * @access private |
||
| 500 | * @param string $string |
||
| 501 | * @return string String without any NULL/chr(173) |
||
| 502 | * @since PHP4 OOP 0.0.1 |
||
| 503 | */ |
||
| 504 | private function removeNulls($string) |
||
| 505 | { |
||
| 506 | $string = preg_replace('/\0+/', '', $string); |
||
| 507 | $string = preg_replace('/(\\\\0)+/', '', $string); |
||
| 508 | return $string; |
||
| 509 | } |
||
| 510 | |||
| 511 | /** |
||
| 512 | * Normalizes HTML entities |
||
| 513 | * |
||
| 514 | * This function normalizes HTML entities. It will convert "AT&T" to the correct |
||
| 515 | * "AT&T", ":" to ":", "&#XYZZY;" to "&#XYZZY;" and so on. |
||
| 516 | * |
||
| 517 | * @access private |
||
| 518 | * @param string $string |
||
| 519 | * @return string String with normalized entities |
||
| 520 | * @since PHP4 OOP 0.0.1 |
||
| 521 | */ |
||
| 522 | private function normalizeEntities($string) |
||
| 523 | { |
||
| 524 | # Disarm all entities by converting & to & |
||
| 525 | $string = str_replace('&', '&', $string); |
||
| 526 | |||
| 527 | # TODO: Change back (Keep?) the allowed entities in our entity white list |
||
| 528 | |||
| 529 | # Keeps entities that start with [A-Za-z] |
||
| 530 | $string = preg_replace( |
||
| 531 | '/&([A-Za-z][A-Za-z0-9]{0,19});/', |
||
| 532 | '&\\1;', |
||
| 533 | $string |
||
| 534 | ); |
||
| 535 | |||
| 536 | # Change numeric entities to valid 16 bit values |
||
| 537 | |||
| 538 | $string = preg_replace( |
||
| 539 | '/&#0*([0-9]{1,5});/e', |
||
| 540 | '\$this->normalizeEntities16bit("\\1")', |
||
| 541 | $string |
||
| 542 | ); |
||
| 543 | |||
| 544 | # Change &XHHHHHHH (Hex digits) to 16 bit hex values |
||
| 545 | $string = preg_replace( |
||
| 546 | '/&#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/', |
||
| 547 | '&#\\1\\2;', |
||
| 548 | $string |
||
| 549 | ); |
||
| 550 | |||
| 551 | return $string; |
||
| 552 | } |
||
| 553 | |||
| 554 | /** |
||
| 555 | * Helper method used by normalizeEntites() |
||
| 556 | * |
||
| 557 | * This method helps normalizeEntities() to only accept 16 bit values |
||
| 558 | * and nothing more for &#number; entities. |
||
| 559 | * |
||
| 560 | * This method helps normalize_entities() during a preg_replace() |
||
| 561 | * where a &#(0)*XXXXX; occurs. The '(0)*XXXXXX' value is converted to |
||
| 562 | * a number and the result is returned as a numeric entity if the number |
||
| 563 | * is less than 65536. Otherwise, the value is returned 'as is'. |
||
| 564 | * |
||
| 565 | * @access private |
||
| 566 | * @param string $i |
||
| 567 | * @return string Normalized numeric entity |
||
| 568 | * @see normalizeEntities() |
||
| 569 | * @since PHP4 OOP 0.0.1 |
||
| 570 | */ |
||
| 571 | private function normalizeEntities16bit($i) |
||
| 572 | { |
||
| 573 | return (($i > 65535) ? "&#$i;" : "&#$i;"); |
||
| 574 | } |
||
| 575 | |||
| 576 | /** |
||
| 577 | * Allows for additional user defined modifications to text. |
||
| 578 | * |
||
| 579 | * This method allows for additional modifications to be performed on |
||
| 580 | * a string that's being run through Parse(). Currently, it returns the |
||
| 581 | * input string 'as is'. |
||
| 582 | * |
||
| 583 | * This method is provided for users to extend the kses class for their own |
||
| 584 | * requirements. |
||
| 585 | * |
||
| 586 | * @access public |
||
| 587 | * @param string $string String to perfrom additional modifications on. |
||
| 588 | * @return string User modified string. |
||
| 589 | * @see Parse() |
||
| 590 | * @since PHP5 OOP 1.0.0 |
||
| 591 | */ |
||
| 592 | private function filterKsesTextHook($string) |
||
| 593 | { |
||
| 594 | return $string; |
||
| 595 | } |
||
| 596 | |||
| 597 | /** |
||
| 598 | * Allows for additional user defined modifications to text. |
||
| 599 | * |
||
| 600 | * @deprecated use filterKsesTextHook() |
||
| 601 | * @param string $string |
||
| 602 | * @return string |
||
| 603 | * @see filterKsesTextHook() |
||
| 604 | * @since PHP4 OOP 0.0.1 |
||
| 605 | */ |
||
| 606 | private function _hook($string) |
||
| 607 | { |
||
| 608 | return $this->filterKsesTextHook($string); |
||
| 609 | } |
||
| 610 | |||
| 611 | /** |
||
| 612 | * This method goes through an array, and changes the keys to all lower case. |
||
| 613 | * |
||
| 614 | * @access private |
||
| 615 | * @param array $in_array Associative array |
||
| 616 | * @return array Modified array |
||
| 617 | * @since PHP4 OOP 0.0.1 |
||
| 618 | */ |
||
| 619 | private function makeArrayKeysLowerCase($in_array) |
||
| 620 | { |
||
| 621 | $out_array = array(); |
||
| 622 | |||
| 623 | if(is_array($in_array) && count($in_array) > 0) |
||
| 624 | { |
||
| 625 | foreach ($in_array as $in_key => $in_val) |
||
| 626 | { |
||
| 627 | $out_key = strtolower($in_key); |
||
| 628 | $out_array[$out_key] = array(); |
||
| 629 | |||
| 630 | if(is_array($in_val) && count($in_val) > 0) |
||
| 631 | { |
||
| 632 | foreach ($in_val as $in_key2 => $in_val2) |
||
| 633 | { |
||
| 634 | $out_key2 = strtolower($in_key2); |
||
| 635 | $out_array[$out_key][$out_key2] = $in_val2; |
||
| 636 | } |
||
| 637 | } |
||
| 638 | } |
||
| 639 | } |
||
| 640 | |||
| 641 | return $out_array; |
||
| 642 | } |
||
| 643 | |||
| 644 | /** |
||
| 645 | * This method strips out disallowed and/or mangled (X)HTML tags along with assigned attributes. |
||
| 646 | * |
||
| 647 | * This method does a lot of work. It rejects some very malformed things |
||
| 648 | * like <:::>. It returns an empty string if the element isn't allowed (look |
||
| 649 | * ma, no strip_tags()!). Otherwise it splits the tag into an element and an |
||
| 650 | * allowed attribute list. |
||
| 651 | * |
||
| 652 | * @access private |
||
| 653 | * @param string $string |
||
| 654 | * @return string Modified string minus disallowed/mangled (X)HTML and attributes |
||
| 655 | * @since PHP4 OOP 0.0.1 |
||
| 656 | */ |
||
| 657 | private function stripTags($string) |
||
| 658 | { |
||
| 659 | $string = preg_replace('%\\\\"%', '"', $string); |
||
| 660 | |||
| 661 | if (substr($string, 0, 1) != '<') |
||
| 662 | { |
||
| 663 | # It matched a ">" character |
||
| 664 | return '>'; |
||
| 665 | } |
||
| 666 | |||
| 667 | if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches)) |
||
| 668 | { |
||
| 669 | # It's seriously malformed |
||
| 670 | return ''; |
||
| 671 | } |
||
| 672 | |||
| 673 | $slash = trim($matches[1]); |
||
| 674 | $elem = $matches[2]; |
||
| 675 | $attrlist = $matches[3]; |
||
| 676 | |||
| 677 | if ( |
||
| 678 | !isset($this->allowed_html[strtolower($elem)]) || |
||
| 679 | !is_array($this->allowed_html[strtolower($elem)])) |
||
| 680 | { |
||
| 681 | # Found an HTML element not in the white list |
||
| 682 | return ''; |
||
| 683 | } |
||
| 684 | |||
| 685 | if ($slash != '') |
||
| 686 | { |
||
| 687 | return "<$slash$elem>"; |
||
| 688 | } |
||
| 689 | # No attributes are allowed for closing elements |
||
| 690 | |||
| 691 | return $this->stripAttributes("$slash$elem", $attrlist); |
||
| 692 | } |
||
| 693 | |||
| 694 | /** |
||
| 695 | * This method strips out disallowed attributes for (X)HTML tags. |
||
| 696 | * |
||
| 697 | * This method removes all attributes if none are allowed for this element. |
||
| 698 | * If some are allowed it calls combAttributes() to split them further, and then it |
||
| 699 | * builds up new HTML code from the data that combAttributes() returns. It also |
||
| 700 | * removes "<" and ">" characters, if there are any left. One more thing it |
||
| 701 | * does is to check if the tag has a closing XHTML slash, and if it does, |
||
| 702 | * it puts one in the returned code as well. |
||
| 703 | * |
||
| 704 | * @access private |
||
| 705 | * @param string $element (X)HTML tag to check |
||
| 706 | * @param string $attr Text containing attributes to check for validity. |
||
| 707 | * @return string Resulting valid (X)HTML or '' |
||
| 708 | * @see combAttributes() |
||
| 709 | * @since PHP4 OOP 0.0.1 |
||
| 710 | */ |
||
| 711 | private function stripAttributes($element, $attr) |
||
| 712 | { |
||
| 713 | # Is there a closing XHTML slash at the end of the attributes? |
||
| 714 | $xhtml_slash = ''; |
||
| 715 | if (preg_match('%\s/\s*$%', $attr)) |
||
| 716 | { |
||
| 717 | $xhtml_slash = ' /'; |
||
| 718 | } |
||
| 719 | |||
| 720 | # Are any attributes allowed at all for this element? |
||
| 721 | if ( |
||
| 722 | !isset($this->allowed_html[strtolower($element)]) || |
||
| 723 | count($this->allowed_html[strtolower($element)]) == 0 |
||
| 724 | ) |
||
| 725 | { |
||
| 726 | return "<$element$xhtml_slash>"; |
||
| 727 | } |
||
| 728 | |||
| 729 | # Split it |
||
| 730 | $attrarr = $this->combAttributes($attr); |
||
| 731 | |||
| 732 | # Go through $attrarr, and save the allowed attributes for this element |
||
| 733 | # in $attr2 |
||
| 734 | $attr2 = ''; |
||
| 735 | if(is_array($attrarr) && count($attrarr) > 0) |
||
| 736 | { |
||
| 737 | foreach ($attrarr as $arreach) |
||
| 738 | { |
||
| 739 | if(!isset($this->allowed_html[strtolower($element)][strtolower($arreach['name'])])) |
||
| 740 | { |
||
| 741 | continue; |
||
| 742 | } |
||
| 743 | |||
| 744 | $current = $this->allowed_html[strtolower($element)][strtolower($arreach['name'])]; |
||
| 745 | |||
| 746 | if (!is_array($current)) |
||
| 747 | { |
||
| 748 | # there are no checks |
||
| 749 | $attr2 .= ' '.$arreach['whole']; |
||
| 750 | } |
||
| 751 | else |
||
| 752 | { |
||
| 753 | # there are some checks |
||
| 754 | $ok = true; |
||
| 755 | if(is_array($current) && count($current) > 0) |
||
| 756 | { |
||
| 757 | foreach ($current as $currkey => $currval) |
||
| 758 | { |
||
| 759 | if (!$this->checkAttributeValue($arreach['value'], $arreach['vless'], $currkey, $currval)) |
||
| 760 | { |
||
| 761 | $ok = false; |
||
| 762 | break; |
||
| 763 | } |
||
| 764 | } |
||
| 765 | } |
||
| 766 | |||
| 767 | if ($ok) |
||
| 768 | { |
||
| 769 | # it passed them |
||
| 770 | $attr2 .= ' '.$arreach['whole']; |
||
| 771 | } |
||
| 772 | } |
||
| 773 | } |
||
| 774 | } |
||
| 775 | |||
| 776 | # Remove any "<" or ">" characters |
||
| 777 | $attr2 = preg_replace('/[<>]/', '', $attr2); |
||
| 778 | return "<$element$attr2$xhtml_slash>"; |
||
| 779 | } |
||
| 780 | |||
| 781 | /** |
||
| 782 | * This method combs through an attribute list string and returns an associative array of attributes and values. |
||
| 783 | * |
||
| 784 | * This method does a lot of work. It parses an attribute list into an array |
||
| 785 | * with attribute data, and tries to do the right thing even if it gets weird |
||
| 786 | * input. It will add quotes around attribute values that don't have any quotes |
||
| 787 | * or apostrophes around them, to make it easier to produce HTML code that will |
||
| 788 | * conform to W3C's HTML specification. It will also remove bad URL protocols |
||
| 789 | * from attribute values. |
||
| 790 | * |
||
| 791 | * @access private |
||
| 792 | * @param string $attr Text containing tag attributes for parsing |
||
| 793 | * @return array Associative array containing data on attribute and value |
||
| 794 | * @since PHP4 OOP 0.0.1 |
||
| 795 | */ |
||
| 796 | private function combAttributes($attr) |
||
| 797 | { |
||
| 798 | $attrarr = array(); |
||
| 799 | $mode = 0; |
||
| 800 | $attrname = ''; |
||
| 801 | |||
| 802 | # Loop through the whole attribute list |
||
| 803 | |||
| 804 | while (strlen($attr) != 0) |
||
| 805 | { |
||
| 806 | # Was the last operation successful? |
||
| 807 | $working = 0; |
||
| 808 | |||
| 809 | switch ($mode) |
||
| 810 | { |
||
| 811 | case 0: # attribute name, href for instance |
||
| 812 | if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) |
||
| 813 | { |
||
| 814 | $attrname = $match[1]; |
||
| 815 | $working = $mode = 1; |
||
| 816 | $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr); |
||
| 817 | } |
||
| 818 | break; |
||
| 819 | case 1: # equals sign or valueless ("selected") |
||
| 820 | if (preg_match('/^\s*=\s*/', $attr)) # equals sign |
||
| 821 | { |
||
| 822 | $working = 1; |
||
| 823 | $mode = 2; |
||
| 824 | $attr = preg_replace('/^\s*=\s*/', '', $attr); |
||
| 825 | break; |
||
| 826 | } |
||
| 827 | if (preg_match('/^\s+/', $attr)) # valueless |
||
| 828 | { |
||
| 829 | $working = 1; |
||
| 830 | $mode = 0; |
||
| 831 | $attrarr[] = array( |
||
| 832 | 'name' => $attrname, |
||
| 833 | 'value' => '', |
||
| 834 | 'whole' => $attrname, |
||
| 835 | 'vless' => 'y' |
||
| 836 | ); |
||
| 837 | $attr = preg_replace('/^\s+/', '', $attr); |
||
| 838 | } |
||
| 839 | break; |
||
| 840 | case 2: # attribute value, a URL after href= for instance |
||
| 841 | if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) # "value" |
||
| 842 | { |
||
| 843 | $thisval = $this->removeBadProtocols($match[1]); |
||
| 844 | $attrarr[] = array( |
||
| 845 | 'name' => $attrname, |
||
| 846 | 'value' => $thisval, |
||
| 847 | 'whole' => $attrname . '="' . $thisval . '"', |
||
| 848 | 'vless' => 'n' |
||
| 849 | ); |
||
| 850 | $working = 1; |
||
| 851 | $mode = 0; |
||
| 852 | $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr); |
||
| 853 | break; |
||
| 854 | } |
||
| 855 | if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) # 'value' |
||
| 856 | { |
||
| 857 | $thisval = $this->removeBadProtocols($match[1]); |
||
| 858 | $attrarr[] = array( |
||
| 859 | 'name' => $attrname, |
||
| 860 | 'value' => $thisval, |
||
| 861 | 'whole' => "$attrname='$thisval'", |
||
| 862 | 'vless' => 'n' |
||
| 863 | ); |
||
| 864 | $working = 1; |
||
| 865 | $mode = 0; |
||
| 866 | $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr); |
||
| 867 | break; |
||
| 868 | } |
||
| 869 | if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) # value |
||
| 870 | { |
||
| 871 | $thisval = $this->removeBadProtocols($match[1]); |
||
| 872 | $attrarr[] = array( |
||
| 873 | 'name' => $attrname, |
||
| 874 | 'value' => $thisval, |
||
| 875 | 'whole' => $attrname . '="' . $thisval . '"', |
||
| 876 | 'vless' => 'n' |
||
| 877 | ); |
||
| 878 | # We add quotes to conform to W3C's HTML spec. |
||
| 879 | $working = 1; |
||
| 880 | $mode = 0; |
||
| 881 | $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr); |
||
| 882 | } |
||
| 883 | break; |
||
| 884 | } |
||
| 885 | |||
| 886 | if ($working == 0) # not well formed, remove and try again |
||
| 887 | { |
||
| 888 | $attr = preg_replace('/^("[^"]*("|$)|\'[^\']*(\'|$)|\S)*\s*/', '', $attr); |
||
| 889 | $mode = 0; |
||
| 890 | } |
||
| 891 | } |
||
| 892 | |||
| 893 | # special case, for when the attribute list ends with a valueless |
||
| 894 | # attribute like "selected" |
||
| 895 | if ($mode == 1) |
||
| 896 | { |
||
| 897 | $attrarr[] = array( |
||
| 898 | 'name' => $attrname, |
||
| 899 | 'value' => '', |
||
| 900 | 'whole' => $attrname, |
||
| 901 | 'vless' => 'y' |
||
| 902 | ); |
||
| 903 | } |
||
| 904 | |||
| 905 | return $attrarr; |
||
| 906 | } |
||
| 907 | |||
| 908 | /** |
||
| 909 | * This method removes disallowed protocols. |
||
| 910 | * |
||
| 911 | * This method removes all non-allowed protocols from the beginning of |
||
| 912 | * $string. It ignores whitespace and the case of the letters, and it does |
||
| 913 | * understand HTML entities. It does its work in a while loop, so it won't be |
||
| 914 | * fooled by a string like "javascript:javascript:alert(57)". |
||
| 915 | * |
||
| 916 | * @access private |
||
| 917 | * @param string $string String to check for protocols |
||
| 918 | * @return string String with removed protocols |
||
| 919 | * @since PHP4 OOP 0.0.1 |
||
| 920 | */ |
||
| 921 | private function removeBadProtocols($string) |
||
| 922 | { |
||
| 923 | $string = $this->RemoveNulls($string); |
||
| 924 | $string = preg_replace('/\xad+/', '', $string); # deals with Opera "feature" |
||
| 925 | $string2 = $string . 'a'; |
||
| 926 | |||
| 927 | $string2 = preg_split('/:|:|:/i', $string, 2); |
||
| 928 | if(isset($string2[1]) && !preg_match('%/\?%',$string2[0])) |
||
| 929 | { |
||
| 930 | $string = $this->filterProtocols($string2[0]).trim($string2[1]); |
||
| 931 | } |
||
| 932 | return $string; |
||
| 933 | } |
||
| 934 | |||
| 935 | /** |
||
| 936 | * Helper method used by removeBadProtocols() |
||
| 937 | * |
||
| 938 | * This function processes URL protocols, checks to see if they're in the white- |
||
| 939 | * list or not, and returns different data depending on the answer. |
||
| 940 | * |
||
| 941 | * @access private |
||
| 942 | * @param string $string String to check for protocols |
||
| 943 | * @return string String with removed protocols |
||
| 944 | * @see removeBadProtocols() |
||
| 945 | * @since PHP4 OOP 0.0.1 |
||
| 946 | */ |
||
| 947 | private function filterProtocols($string) |
||
| 948 | { |
||
| 949 | $string = $this->decodeEntities($string); |
||
| 950 | $string = preg_replace('/\s/', '', $string); |
||
| 951 | $string = $this->removeNulls($string); |
||
| 952 | $string = preg_replace('/\xad+/', '', $string2); # deals with Opera "feature" |
||
| 953 | $string = strtolower($string); |
||
| 954 | |||
| 955 | if(is_array($this->allowed_protocols) && count($this->allowed_protocols) > 0) |
||
| 956 | { |
||
| 957 | foreach ($this->allowed_protocols as $one_protocol) |
||
| 958 | { |
||
| 959 | if (strtolower($one_protocol) == $string) |
||
| 960 | { |
||
| 961 | return "$string:"; |
||
| 962 | } |
||
| 963 | } |
||
| 964 | } |
||
| 965 | |||
| 966 | return ''; |
||
| 967 | } |
||
| 968 | |||
| 969 | /** |
||
| 970 | * Controller method for performing checks on attribute values. |
||
| 971 | * |
||
| 972 | * This method calls the appropriate method as specified by $checkname with |
||
| 973 | * the parameters $value, $vless, and $checkvalue, and returns the result |
||
| 974 | * of the call. |
||
| 975 | * |
||
| 976 | * This method's functionality can be expanded by creating new methods |
||
| 977 | * that would match checkAttributeValue[$checkname]. |
||
| 978 | * |
||
| 979 | * Current checks implemented are: "maxlen", "minlen", "maxval", "minval" and "valueless" |
||
| 980 | * |
||
| 981 | * @access private |
||
| 982 | * @param string $value The value of the attribute to be checked. |
||
| 983 | * @param string $vless Indicates whether the the value is supposed to be valueless |
||
| 984 | * @param string $checkname The check to be performed |
||
| 985 | * @param string $checkvalue The value that is to be checked against |
||
| 986 | * @return bool Indicates whether the check passed or not |
||
| 987 | * @since PHP5 OOP 1.0.0 |
||
| 988 | */ |
||
| 989 | private function checkAttributeValue($value, $vless, $checkname, $checkvalue) |
||
| 990 | { |
||
| 991 | $ok = true; |
||
| 992 | $check_attribute_method_name = 'checkAttributeValue' . ucfirst(strtolower($checkname)); |
||
| 993 | if(method_exists($this, $check_attribute_method_name)) |
||
| 994 | { |
||
| 995 | $ok = $this->$check_attribute_method_name($value, $checkvalue, $vless); |
||
| 996 | } |
||
| 997 | |||
| 998 | return $ok; |
||
| 999 | } |
||
| 1000 | |||
| 1001 | /** |
||
| 1002 | * Helper method invoked by checkAttributeValue(). |
||
| 1003 | * |
||
| 1004 | * The maxlen check makes sure that the attribute value has a length not |
||
| 1005 | * greater than the given value. This can be used to avoid Buffer Overflows |
||
| 1006 | * in WWW clients and various Internet servers. |
||
| 1007 | * |
||
| 1008 | * @access private |
||
| 1009 | * @param string $value The value of the attribute to be checked. |
||
| 1010 | * @param int $checkvalue The maximum value allowed |
||
| 1011 | * @return bool Indicates whether the check passed or not |
||
| 1012 | * @see checkAttributeValue() |
||
| 1013 | * @since PHP5 OOP 1.0.0 |
||
| 1014 | */ |
||
| 1015 | private function checkAttributeValueMaxlen($value, $checkvalue) |
||
| 1016 | { |
||
| 1017 | if (strlen($value) > intval($checkvalue)) |
||
| 1018 | { |
||
| 1019 | return false; |
||
| 1020 | } |
||
| 1021 | return true; |
||
| 1022 | } |
||
| 1023 | |||
| 1024 | /** |
||
| 1025 | * Helper method invoked by checkAttributeValue(). |
||
| 1026 | * |
||
| 1027 | * The minlen check makes sure that the attribute value has a length not |
||
| 1028 | * smaller than the given value. |
||
| 1029 | * |
||
| 1030 | * @access private |
||
| 1031 | * @param string $value The value of the attribute to be checked. |
||
| 1032 | * @param int $checkvalue The minimum value allowed |
||
| 1033 | * @return bool Indicates whether the check passed or not |
||
| 1034 | * @see checkAttributeValue() |
||
| 1035 | * @since PHP5 OOP 1.0.0 |
||
| 1036 | */ |
||
| 1037 | private function checkAttributeValueMinlen($value, $checkvalue) |
||
| 1038 | { |
||
| 1039 | if (strlen($value) < intval($checkvalue)) |
||
| 1040 | { |
||
| 1041 | return false; |
||
| 1042 | } |
||
| 1043 | return true; |
||
| 1044 | } |
||
| 1045 | |||
| 1046 | /** |
||
| 1047 | * Helper method invoked by checkAttributeValue(). |
||
| 1048 | * |
||
| 1049 | * The maxval check does two things: it checks that the attribute value is |
||
| 1050 | * an integer from 0 and up, without an excessive amount of zeroes or |
||
| 1051 | * whitespace (to avoid Buffer Overflows). It also checks that the attribute |
||
| 1052 | * value is not greater than the given value. |
||
| 1053 | * |
||
| 1054 | * This check can be used to avoid Denial of Service attacks. |
||
| 1055 | * |
||
| 1056 | * @access private |
||
| 1057 | * @param int $value The value of the attribute to be checked. |
||
| 1058 | * @param int $checkvalue The maximum numeric value allowed |
||
| 1059 | * @return bool Indicates whether the check passed or not |
||
| 1060 | * @see checkAttributeValue() |
||
| 1061 | * @since PHP5 OOP 1.0.0 |
||
| 1062 | */ |
||
| 1063 | private function checkAttributeValueMaxval($value, $checkvalue) |
||
| 1064 | { |
||
| 1065 | if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) |
||
| 1066 | { |
||
| 1067 | return false; |
||
| 1068 | } |
||
| 1069 | if (intval($value) > intval($checkvalue)) |
||
| 1070 | { |
||
| 1071 | return false; |
||
| 1072 | } |
||
| 1073 | return true; |
||
| 1074 | } |
||
| 1075 | |||
| 1076 | /** |
||
| 1077 | * Helper method invoked by checkAttributeValue(). |
||
| 1078 | * |
||
| 1079 | * The minval check checks that the attribute value is a positive integer, |
||
| 1080 | * and that it is not smaller than the given value. |
||
| 1081 | * |
||
| 1082 | * @access private |
||
| 1083 | * @param int $value The value of the attribute to be checked. |
||
| 1084 | * @param int $checkvalue The minimum numeric value allowed |
||
| 1085 | * @return bool Indicates whether the check passed or not |
||
| 1086 | * @see checkAttributeValue() |
||
| 1087 | * @since PHP5 OOP 1.0.0 |
||
| 1088 | */ |
||
| 1089 | private function checkAttributeValueMinval($value, $checkvalue) |
||
| 1090 | { |
||
| 1091 | if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) |
||
| 1092 | { |
||
| 1093 | return false; |
||
| 1094 | } |
||
| 1095 | if (intval($value) < ($checkvalue)) |
||
| 1096 | { |
||
| 1097 | return false; |
||
| 1098 | } |
||
| 1099 | return true; |
||
| 1100 | } |
||
| 1101 | |||
| 1102 | /** |
||
| 1103 | * Helper method invoked by checkAttributeValue(). |
||
| 1104 | * |
||
| 1105 | * The valueless check checks if the attribute has a value |
||
| 1106 | * (like <a href="blah">) or not (<option selected>). If the given value |
||
| 1107 | * is a "y" or a "Y", the attribute must not have a value. |
||
| 1108 | * |
||
| 1109 | * If the given value is an "n" or an "N", the attribute must have one. |
||
| 1110 | * |
||
| 1111 | * @access private |
||
| 1112 | * @param int $value The value of the attribute to be checked. |
||
| 1113 | * @param mixed $checkvalue This variable is ignored for this test |
||
| 1114 | * @param string $vless Flag indicating if this attribute is not supposed to have an attribute |
||
| 1115 | * @return bool Indicates whether the check passed or not |
||
| 1116 | * @see checkAttributeValue() |
||
| 1117 | * @since PHP5 OOP 1.0.0 |
||
| 1118 | */ |
||
| 1119 | private function checkAttributeValueValueless($value, $checkvalue, $vless) |
||
| 1120 | { |
||
| 1121 | if (strtolower($checkvalue) != $vless) |
||
| 1122 | { |
||
| 1123 | return false; |
||
| 1124 | } |
||
| 1125 | return true; |
||
| 1126 | } |
||
| 1127 | |||
| 1128 | /** |
||
| 1129 | * Decodes numeric HTML entities |
||
| 1130 | * |
||
| 1131 | * This method decodes numeric HTML entities (A and A). It doesn't |
||
| 1132 | * do anything with other entities like ä, but we don't need them in the |
||
| 1133 | * URL protocol white listing system anyway. |
||
| 1134 | * |
||
| 1135 | * @access private |
||
| 1136 | * @param string $value The entitiy to be decoded. |
||
| 1137 | * @return string Decoded entity |
||
| 1138 | * @since PHP4 OOP 0.0.1 |
||
| 1139 | */ |
||
| 1140 | private function decodeEntities($string) |
||
| 1141 | { |
||
| 1142 | $string = preg_replace('/&#([0-9]+);/e', 'chr("\\1")', $string); |
||
| 1143 | $string = preg_replace('/&#[Xx]([0-9A-Fa-f]+);/e', 'chr(hexdec("\\1"))', $string); |
||
| 1144 | return $string; |
||
| 1145 | } |
||
| 1146 | |||
| 1147 | /** |
||
| 1148 | * Returns PHP5 OOP version # of kses. |
||
| 1149 | * |
||
| 1150 | * Since this class has been refactored and documented and proven to work, |
||
| 1151 | * I'm fixing the version number at 1.0.0. |
||
| 1152 | * |
||
| 1153 | * This version is syntax compatible with the PHP4 OOP version 0.0.2. Future |
||
| 1154 | * versions may not be syntax compatible. |
||
| 1155 | * |
||
| 1156 | * @access public |
||
| 1157 | * @return string Version number |
||
| 1158 | * @since PHP4 OOP 0.0.1 |
||
| 1159 | */ |
||
| 1160 | public function Version() |
||
| 1161 | { |
||
| 1162 | return 'PHP5 OOP 1.0.2'; |
||
| 1163 | } |
||
| 1166 | ?> |