1: 2: 3: 4: 5: 6: 7: 8: 9: 10: 11: 12: 13: 14: 15: 16: 17: 18: 19: 20: 21: 22: 23: 24: 25: 26: 27: 28: 29: 30: 31: 32: 33: 34: 35: 36: 37: 38: 39: 40: 41: 42: 43: 44: 45: 46: 47: 48: 49: 50: 51: 52: 53: 54: 55: 56: 57: 58: 59: 60: 61: 62: 63: 64: 65: 66: 67: 68: 69: 70: 71: 72: 73: 74: 75: 76: 77: 78: 79: 80: 81: 82: 83: 84: 85: 86: 87: 88: 89: 90: 91: 92: 93: 94: 95: 96: 97: 98: 99: 100: 101: 102: 103: 104: 105: 106: 107: 108: 109: 110: 111: 112: 113: 114: 115: 116: 117: 118: 119: 120: 121: 122: 123: 124: 125: 126: 127: 128: 129: 130: 131: 132: 133: 134: 135: 136: 137: 138: 139: 140: 141: 142: 143: 144: 145: 146: 147: 148: 149: 150: 151: 152: 153: 154: 155: 156: 157: 158: 159: 160: 161: 162: 163: 164: 165: 166: 167: 168: 169: 170: 171: 172: 173: 174: 175: 176: 177: 178: 179: 180: 181: 182: 183: 184: 185: 186: 187: 188: 189: 190: 191: 192: 193: 194: 195: 196: 197: 198: 199: 200: 201: 202: 203: 204: 205: 206: 207: 208: 209: 210: 211: 212: 213: 214: 215: 216: 217: 218: 219: 220: 221: 222: 223: 224: 225: 226: 227: 228: 229: 230: 231: 232: 233: 234: 235: 236: 237: 238: 239: 240: 241: 242: 243: 244: 245: 246: 247: 248: 249: 250: 251: 252: 253: 254: 255: 256: 257: 258: 259: 260: 261: 262: 263: 264: 265: 266: 267: 268: 269: 270: 271: 272: 273: 274: 275: 276: 277: 278: 279: 280: 281: 282: 283: 284: 285: 286: 287: 288: 289: 290: 291: 292: 293: 294: 295: 296: 297: 298: 299: 300: 301: 302: 303: 304: 305: 306: 307: 308: 309: 310: 311: 312: 313: 314: 315: 316: 317: 318: 319: 320: 321: 322: 323: 324: 325: 326: 327: 328: 329: 330: 331: 332: 333: 334: 335: 336: 337: 338: 339: 340: 341: 342: 343: 344: 345: 346: 347: 348: 349: 350: 351: 352: 353: 354: 355: 356: 357: 358: 359: 360: 361: 362: 363: 364: 365: 366: 367: 368: 369: 370: 371: 372: 373: 374: 375: 376: 377: 378: 379: 380: 381: 382: 383: 384: 385: 386: 387: 388: 389: 390: 391: 392: 393: 394: 395: 396: 397: 398: 399: 400: 401: 402: 403: 404: 405: 406: 407: 408: 409: 410: 411: 412: 413: 414: 415: 416: 417: 418: 419: 420: 421: 422: 423: 424: 425: 426: 427: 428: 429: 430: 431: 432: 433: 434: 435: 436: 437: 438: 439: 440: 441: 442: 443: 444: 445: 446: 447: 448: 449: 450: 451: 452: 453: 454: 455: 456: 457: 458: 459: 460: 461: 462: 463: 464: 465: 466: 467: 468: 469: 470: 471: 472: 473: 474: 475: 476: 477: 478: 479: 480: 481: 482: 483: 484: 485: 486: 487: 488: 489: 490: 491: 492: 493: 494: 495: 496: 497: 498: 499: 500: 501: 502: 503: 504: 505: 506: 507: 508: 509: 510: 511: 512: 513: 514: 515: 516: 517: 518: 519: 520: 521: 522: 523: 524: 525: 526: 527: 528: 529: 530: 531: 532: 533: 534: 535: 536: 537: 538: 539: 540: 541: 542: 543: 544: 545: 546: 547: 548: 549: 550: 551: 552: 553: 554: 555: 556: 557: 558: 559: 560: 561: 562: 563: 564: 565: 566: 567: 568: 569: 570: 571: 572: 573: 574: 575: 576: 577: 578: 579: 580: 581: 582: 583: 584: 585: 586: 587: 588: 589: 590: <?php
/**
* Note: Zenphoto does not want html entities encoded. This script has been modified
* to prevent the encodings.
*
* Additionally it has been modified so css properties within style attributes are not mistaken
* as "bad protocols" and cleared.
*
* Also some re-formatting has been done and function documentation has been changed to follow standard phpdoc blocks
*
* Search for Zenphoto for changes.
*
* -------------------------------------------------
*
* kses 0.2.2 - HTML/XHTML filter that only allows some elements and attributes
* Copyright (C) 2002, 2003, 2005 Ulf Harnhammar
*
* This program is free software and open source software; you can redistribute
* it and/or modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation; either version 2 of the License,
* or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA or visit
* http://www.gnu.org/licenses/gpl.html
*
* *** CONTACT INFORMATION ***
*
* E-mail: metaur at users dot sourceforge dot net
* Web page: http://sourceforge.net/projects/kses
* Paper mail: Ulf Harnhammar
* Ymergatan 17 C
* 753 25 Uppsala
* SWEDEN
*
* [kses strips evil scripts!]
*
* @package core
* @subpackage libraries\lib-kses
*/
/**
* This function makes sure that only the allowed HTML element names, attribute
* names and attribute values plus only sane HTML entities will occur in
* $string. You have to remove any slashes from PHP's magic quotes before you
* call this function.
*
* @param type $string
* @param type $allowed_html
* @param type $allowed_protocols
* @return type
*/
function kses($string, $allowed_html, $allowed_protocols = array('http', 'https', 'ftp', 'news', 'nntp', 'telnet',
'gopher', 'mailto')) {
$string = kses_no_null($string);
$string = kses_js_entities($string);
// $string = kses_normalize_entities($string); Zenphoto does not want & encoded
$string = kses_hook($string);
// $allowed_html = kses_array_lc($allowed_html); Zenphoto insures that these are already lowercase
return kses_split($string, $allowed_html, $allowed_protocols);
}
/**
* You add any kses hooks here.
*/
function kses_hook($string) {
return $string;
}
/**
* This function returns kses' version number.
*/
function kses_version() {
return '0.2.2';
}
/**
* This function searches for HTML tags, no matter how malformed. It also
* matches stray ">" characters.
*/
function kses_split($string, $allowed_html, $allowed_protocols) {
global $_allowed_html, $_allowed_protocols;
//Zenphoto:preg_replace with the "e" modifier is deprecated, use callback
$_allowed_html = $allowed_html;
$_allowed_protocols = $allowed_protocols;
return preg_replace_callback('%(<' . //EITHER: <
'[^>]*' . //things that aren't >
'(>|$)' . //> or end of string
'|>)%', //OR: just a >
"kses_split2", $string);
}
/**
* This function does a lot of work. It rejects some very malformed things
* like <:::>. It returns an empty string, if the element isn't allowed (look
* ma, no strip_tags()!). Otherwise it splits the tag into an element and an
* attribute list.
*
* @global type $_allowed_html
* @global type $_allowed_protocols
* @param type $matches
* @return string
*/
function kses_split2($matches) {
//Zenphoto:preg_replace with the "e" modifier is deprecated, this is the callback
global $_allowed_html, $_allowed_protocols;
$allowed_html = $_allowed_html;
$allowed_protocols = $_allowed_protocols;
$string = kses_stripslashes($matches[1]);
if (substr($string, 0, 1) != '<') {
return '>';
//It matched a ">" character
}
if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>$%', $string, $matches)) {
return $string;
//It's seriously malformed
}
$slash = trim($matches[1]);
$elem = $matches[2];
$attrlist = $matches[3];
if (!@isset($allowed_html[strtolower($elem)]))
return '';
//They are using a not allowed HTML element
if ($slash != '')
return "<$slash$elem>";
//No attributes are allowed for closing elements
return kses_attr("$slash$elem", $attrlist, $allowed_html, $allowed_protocols);
}
/**
* This function removes all attributes, if none are allowed for this element.
* If some are allowed it calls kses_hair() to split them further, and then it
* builds up new HTML code from the data that kses_hair() returns. It also
* removes "<" and ">" characters, if there are any left. One more thing it
* does is to check if the tag has a closing XHTML slash, and if it does,
* it puts one in the returned code as well.
*
* @param type $element
* @param type $attr
* @param type $allowed_html
* @param type $allowed_protocols
* @return type
*/
function kses_attr($element, $attr, $allowed_html, $allowed_protocols) {
//Is there a closing XHTML slash at the end of the attributes?
$xhtml_slash = '';
if (preg_match('%\s/\s*$%', $attr))
$xhtml_slash = ' /';
//Are any attributes allowed at all for this element?
if (@count($allowed_html[strtolower($element)]) == 0)
return "<$element$xhtml_slash>";
//Split it
$attrarr = kses_hair($attr, $allowed_protocols);
//Go through $attrarr, and save the allowed attributes for this element
//in $attr2
$attr2 = '';
foreach ($attrarr as $arreach) {
if (!@isset($allowed_html[strtolower($element)]
[strtolower($arreach['name'])]))
continue; //the attribute is not allowed
$current = $allowed_html[strtolower($element)]
[strtolower($arreach['name'])];
if (!is_array($current))
$attr2 .= ' ' . $arreach['whole'];
//there are no checks
else {
//there are some checks
$ok = true;
foreach ($current as $currkey => $currval)
if (!kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval)) {
$ok = false;
break;
}
if ($ok)
$attr2 .= ' ' . $arreach['whole']; //it passed them
}
}
//Remove any "<" or ">" characters
$attr2 = preg_replace('/[<>]/', '', $attr2);
return "<$element$attr2$xhtml_slash>";
}
/**
* This function does a lot of work. It parses an attribute list into an array
* with attribute data, and tries to do the right thing even if it gets weird
* input. It will add quotes around attribute values that don't have any quotes
* or apostrophes around them, to make it easier to produce HTML code that will
* conform to W3C's HTML specification. It will also remove bad URL protocols
* from attribute values.
*
* @param type $attr
* @param type $allowed_protocols
* @return type
*/
function kses_hair($attr, $allowed_protocols) {
$attrarr = array();
$mode = 0;
$attrname = '';
//Loop through the whole attribute list
while (strlen($attr) != 0) {
$working = 0; //Was the last operation successful?
switch ($mode) {
case 0: //attribute name, href for instance
if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) {
$attrname = $match[1];
$working = $mode = 1;
$attr = preg_replace('/^[-a-zA-Z]+/', '', $attr);
}
break;
case 1: //equals sign or valueless ("selected")
if (preg_match('/^\s*=\s*/', $attr)) { //equals sign
$working = 1;
$mode = 2;
$attr = preg_replace('/^\s*=\s*/', '', $attr);
break;
}
if (preg_match('/^\s+/', $attr)) { //valueless
$working = 1;
$mode = 0;
$attrarr[] = array
('name' => $attrname,
'value' => '',
'whole' => $attrname,
'vless' => 'y');
$attr = preg_replace('/^\s+/', '', $attr);
}
break;
case 2: //attribute value, a URL after href= for instance
if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) {
//"value"
//Zenhoto: Avoid first css property of style attribute being mistaked for bad protocol and clear partly
$thisval = $match[1];
if ($attrname != 'style') {
$thisval = kses_bad_protocol($match[1], $allowed_protocols);
}
$attrarr[] = array
('name' => $attrname,
'value' => $thisval,
'whole' => "$attrname=\"$thisval\"",
'vless' => 'n');
$working = 1;
$mode = 0;
$attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr);
break;
}
if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) {
//'value'
//Zenhoto: Avoid first css property of style attribute being mistaked for bad protocol and clear partly
$thisval = $match[1];
if ($attrname != 'style') {
$thisval = kses_bad_protocol($match[1], $allowed_protocols);
}
$attrarr[] = array
('name' => $attrname,
'value' => $thisval,
'whole' => "$attrname='$thisval'",
'vless' => 'n');
$working = 1;
$mode = 0;
$attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr);
break;
}
if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) {
//value
//Zenhoto: Avoid first css property of style attribute being mistaked for bad protocol and clear partly
$thisval = $match[1];
if ($attrname != 'style') {
$thisval = kses_bad_protocol($match[1], $allowed_protocols);
}
$attrarr[] = array
('name' => $attrname,
'value' => $thisval,
'whole' => "$attrname=\"$thisval\"",
'vless' => 'n');
//We add quotes to conform to W3C's HTML spec.
$working = 1;
$mode = 0;
$attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr);
}
break;
}
if ($working == 0) { //not well formed, remove and try again
$attr = kses_html_error($attr);
$mode = 0;
}
}
if ($mode == 1)
/*
* special case, for when the attribute list ends with a valueless
* attribute like "selected"
*/
$attrarr[] = array
('name' => $attrname,
'value' => '',
'whole' => $attrname,
'vless' => 'y');
return $attrarr;
}
/**
* This function performs different checks for attribute values. The currently
* implemented checks are "maxlen", "minlen", "maxval", "minval" and "valueless"
* with even more checks to come soon.
*
* @param type $value
* @param type $vless
* @param type $checkname
* @param type $checkvalue
* @return boolean
*/
function kses_check_attr_val($value, $vless, $checkname, $checkvalue) {
$ok = true;
switch (strtolower($checkname)) {
case 'maxlen':
/*
* The maxlen check makes sure that the attribute value has a length not
* greater than the given value. This can be used to avoid Buffer Overflows
* in WWW clients and various Internet servers.
*/
if (strlen($value) > $checkvalue)
$ok = false;
break;
case 'minlen':
/*
* The minlen check makes sure that the attribute value has a length not
* smaller than the given value.
*/
if (strlen($value) < $checkvalue)
$ok = false;
break;
case 'maxval':
/*
* The maxval check does two things: it checks that the attribute value is
* an integer from 0 and up, without an excessive amount of zeroes or
* whitespace (to avoid Buffer Overflows). It also checks that the attribute
* value is not greater than the given value.
* This check can be used to avoid Denial of Service attacks.
*/
if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value))
$ok = false;
if ($value > $checkvalue)
$ok = false;
break;
case 'minval':
/*
* The minval check checks that the attribute value is a positive integer,
* and that it is not smaller than the given value.
*/
if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value))
$ok = false;
if ($value < $checkvalue)
$ok = false;
break;
case 'valueless':
/*
* The valueless check checks if the attribute has a value
* (like <a href="blah">) or not (<option selected>). If the given value
* is a "y" or a "Y", the attribute must not have a value.
* If the given value is an "n" or an "N", the attribute must have one.
*/
if (strtolower($checkvalue) != $vless)
$ok = false;
break;
}
return $ok;
}
/**
* This function removes all non-allowed protocols from the beginning of
* $string. It ignores whitespace and the case of the letters, and it does
* understand HTML entities. It does its work in a while loop, so it won't be
* fooled by a string like "javascript:javascript:alert(57)".
*
* @param type $string
* @param type $allowed_protocols
* @return type
*/
function kses_bad_protocol($string, $allowed_protocols) {
$string = kses_no_null($string);
$string = preg_replace('/\xad+/', '', $string); //deals with Opera "feature"
$string2 = $string . 'a';
while ($string != $string2) {
$string2 = $string;
$string = kses_bad_protocol_once($string, $allowed_protocols);
}
return $string;
}
/**
* This function removes any NULL characters in $string.
*
* @param type $string
* @return type
*/
function kses_no_null($string) {
$string = preg_replace('/\0+/', '', $string);
$string = preg_replace('/(\\\\0)+/', '', $string);
return $string;
}
/**
* This function changes the character sequence \" to just "
* It leaves all other slashes alone. It's really weird, but the quoting from
* preg_replace(//e) seems to require this.
*
* @param type $string
* @return type
*/
function kses_stripslashes($string) {
return preg_replace('%\\\\"%', '"', $string);
}
/**
* This function goes through an array, and changes the keys to all lower case.
*/
function kses_array_lc($inarray) {
$outarray = array();
foreach ($inarray as $inkey => $inval) {
$outkey = strtolower($inkey);
$outarray[$outkey] = array();
foreach ($inval as $inkey2 => $inval2) {
$outkey2 = strtolower($inkey2);
$outarray[$outkey][$outkey2] = $inval2;
}
}
return $outarray;
}
/**
* This function removes the HTML JavaScript entities found in early versions of
* Netscape 4.
*
* @param type $string
* @return type
*/
function kses_js_entities($string) {
return preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string);
}
/**
* This function deals with parsing errors in kses_hair(). The general plan is
* to remove everything to and including some whitespace, but it deals with
* quotes and apostrophes as well.
*
* @param type $string
* @return type
*/
function kses_html_error($string) {
return preg_replace('/^("[^"]*("|$)|\'[^\']*(\'|$)|\S)*\s*/', '', $string);
}
/**
* This function searches for URL protocols at the beginning of $string, while
* handling whitespace and HTML entities.
*
* @global type $_allowed_protocols
* @param type $string
* @param type $allowed_protocols
* @return type
*/
function kses_bad_protocol_once($string, $allowed_protocols) {
global $_allowed_protocols;
//Zenphoto:preg_replace with the "e" modifier is deprecated, use callback
$_allowed_protocols = $allowed_protocols;
return preg_replace_callback('/^((&[^;]*;|[\sA-Za-z0-9])*)' .
'(:|:|&#[Xx]3[Aa];)\s*/', 'kses_bad_protocol_once2', $string);
}
/**
* This function processes URL protocols, checks to see if they're in the white-
* list or not, and returns different data depending on the answer.
*
* @global type $_allowed_protocols
* @param type $matches
* @return string
*/
function kses_bad_protocol_once2($matches) {
//Zenphoto:preg_replace with the "e" modifier is deprecated, this is the callback
global $_allowed_protocols;
$allowed_protocols = $_allowed_protocols;
$string2 = kses_decode_entities($matches[1]);
$string2 = preg_replace('/\s/', '', $string2);
$string2 = kses_no_null($string2);
$string2 = preg_replace('/\xad+/', '', $string2);
//deals with Opera "feature"
$string2 = strtolower($string2);
$allowed = false;
foreach ($allowed_protocols as $one_protocol)
if (strtolower($one_protocol) == $string2) {
$allowed = true;
break;
}
if ($allowed)
return "$string2:";
else
return '';
}
/**
* This function normalizes HTML entities. It will convert "AT&T" to the correct
* "AT&T", ":" to ":", "&#XYZZY;" to "&#XYZZY;" and so on.
*
* @param type $string
* @return type
*/
function kses_normalize_entities($string) {
//Disarm all entities by converting & to &
$string = str_replace('&', '&', $string);
//Change back the allowed entities in our entity whitelist
$string = preg_replace('/&([A-Za-z][A-Za-z0-9]{0,19});/', '&\\1;', $string);
$string = preg_replace_callback('/&#0*([0-9]{1,5});/', 'kses_normalize_entities2', $string);
$string = preg_replace('/&#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/', '&#\\1\\2;', $string);
return $string;
}
/**
* This function helps kses_normalize_entities() to only accept 16 bit values
* and nothing more for &#number; entities.
*
* @param type $matches
* @return type
*/
function kses_normalize_entities2($matches) {
return (($matches[1] > 65535) ? "&#$i;" : "&#$i;");
}
/**
* This function decodes numeric HTML entities (A and A). It doesn't
* do anything with other entities like ä, but we don't need them in the
* URL protocol whitelisting system anyway.
*
* @param type $string
* @return type
*/
function kses_decode_entities($string) {
$string = preg_replace('/&#([0-9]+);/', 'chr("\\1")', $string);
$string = preg_replace('/&#[Xx]([0-9A-Fa-f]+);/', 'chr(hexdec("\\1"))', $string);
return $string;
}