php5.class.kses.php

完美的在线教育系统

					return true;
				}
				elseif(is_string($protocol_data))
				{
					$this->allowed_protocols = array();
					$this->AddProtocol($protocol_data);
					return true;
				}
				else
				{
					trigger_error("kses5::SetProtocols() did not receive a string or an array.", E_USER_WARNING);
					return false;
				}
			}

			/**
			 *	Raw dump of allowed protocols
			 *
			 *	This returns an indexed array of allowed protocols for a particular KSES
			 *	instantiation.
			 *
			 *	@access public
			 *	@return array The list of allowed protocols.
			 *	@since PHP5 OOP 1.0.2
			 */
			public function DumpProtocols()
			{
				return $this->allowed_protocols;
			}

			/**
			 *	Raw dump of allowed (X)HTML elements
			 *
			 *	This returns an indexed array of allowed (X)HTML elements and attributes
			 *	for a particular KSES instantiation.
			 *
			 *	@access public
			 *	@return array The list of allowed elements.
			 *	@since PHP5 OOP 1.0.2
			 */
			public function DumpElements()
			{
				return $this->allowed_html;
			}


			/**
			 *	Adds valid (X)HTML with corresponding attributes that will be kept when stripping 'evil scripts'.
			 *
			 *	This method accepts one argument that can be either a string
			 *	or an array of strings.  Invalid data will be ignored.
			 *
			 *	@access public
			 *	@param string $tag (X)HTML tag that will be allowed after stripping text.
			 *	@param array $attribs Associative array of allowed attributes - key => attribute name - value => attribute parameter
			 *	@return bool Status of Adding (X)HTML and attributes.
			 *	@since PHP4 OOP 0.0.1
			 */
			public function AddHTML($tag = "", $attribs = array())
			{
				if(!is_string($tag))
				{
					trigger_error("kses5::AddHTML() requires the tag to be a string", E_USER_WARNING);
					return false;
				}

				$tag = strtolower(trim($tag));
				if($tag == "")
				{
					trigger_error("kses5::AddHTML() tried to add an empty/NULL tag", E_USER_WARNING);
					return false;
				}

				if(!is_array($attribs))
				{
					trigger_error("kses5::AddHTML() requires an array (even an empty one) of attributes for '$tag'", E_USER_WARNING);
					return false;
				}

				$new_attribs = array();
				if(is_array($attribs) && count($attribs) > 0)
				{
					foreach($attribs as $idx1 => $val1)
					{
						$new_idx1 = strtolower($idx1);
						$new_val1 = $attribs[$idx1];

						if(is_array($new_val1) && count($attribs) > 0)
						{
							$tmp_val = array();
							foreach($new_val1 as $idx2 => $val2)
							{
								$new_idx2 = strtolower($idx2);
								$tmp_val[$new_idx2] = $val2;
							}
							$new_val1 = $tmp_val;
						}

						$new_attribs[$new_idx1] = $new_val1;
					}
				}

				$this->allowed_html[$tag] = $new_attribs;
				return true;
			}

			/**
			 *	This method removes any NULL characters in $string.
			 *
			 *	@access private
			 *	@param string $string
			 *	@return string String without any NULL/chr(173)
			 *	@since PHP4 OOP 0.0.1
			 */
			private function removeNulls($string)
			{
				$string = preg_replace('/\0+/', '', $string);
				$string = preg_replace('/(\\\\0)+/', '', $string);
				return $string;
			}

			/**
			 *	Normalizes HTML entities
			 *
			 *	This function normalizes HTML entities. It will convert "AT&T" to the correct
			 *	"AT&T", ":" to ":", "&#XYZZY;" to "&#XYZZY;" and so on.
			 *
			 *	@access private
			 *	@param string $string
			 *	@return string String with normalized entities
			 *	@since PHP4 OOP 0.0.1
			 */
			private function normalizeEntities($string)
			{
				# Disarm all entities by converting & to &
				$string = str_replace('&', '&', $string);

				#	TODO: Change back (Keep?) the allowed entities in our entity white list

				#	Keeps entities that start with [A-Za-z]
				$string = preg_replace(
					'/&([A-Za-z][A-Za-z0-9]{0,19});/',
					'&\\1;',
					$string
				);

				#	Change numeric entities to valid 16 bit values

				$string = preg_replace(
					'/&#0*([0-9]{1,5});/e',
					'\$this->normalizeEntities16bit("\\1")',
					$string
				);

				#	Change &XHHHHHHH (Hex digits) to 16 bit hex values
				$string = preg_replace(
					'/&#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/',
					'&#\\1\\2;',
					$string
				);

				return $string;
			}

			/**
			 *	Helper method used by normalizeEntites()
			 *
			 *	This method helps normalizeEntities() to only accept 16 bit values
			 *	and nothing more for &#number; entities.
			 *
			 *	This method helps normalize_entities() during a preg_replace()
			 *	where a &#(0)*XXXXX; occurs.  The '(0)*XXXXXX' value is converted to
			 *	a number and the result is returned as a numeric entity if the number
			 *	is less than 65536.  Otherwise, the value is returned 'as is'.
			 *
			 *	@access private
			 *	@param string $i
			 *	@return string Normalized numeric entity
			 *	@see normalizeEntities()
			 *	@since PHP4 OOP 0.0.1
			 */
			private function normalizeEntities16bit($i)
			{
			  return (($i > 65535) ? "&#$i;" : "&#$i;");
			}

			/**
			 *	Allows for additional user defined modifications to text.
			 *
			 *	This method allows for additional modifications to be performed on
			 *	a string that's being run through Parse().  Currently, it returns the
			 *	input string 'as is'.
			 *
			 *	This method is provided for users to extend the kses class for their own
			 *	requirements.
			 *
			 *	@access public
			 *	@param string $string String to perfrom additional modifications on.
			 *	@return string User modified string.
			 *	@see Parse()
			 *	@since PHP5 OOP 1.0.0
			 */
			private function filterKsesTextHook($string)
			{
			  return $string;
			}

			/**
			 *	Allows for additional user defined modifications to text.
			 *
			 *	@deprecated use filterKsesTextHook()
			 *	@param string $string
			 *	@return string
			 *	@see filterKsesTextHook()
			 *	@since PHP4 OOP 0.0.1
			 */
			private function _hook($string)
			{
				return $this->filterKsesTextHook($string);
			}

			/**
			 *	This method goes through an array, and changes the keys to all lower case.
			 *
			 *	@access private
			 *	@param array $in_array Associative array
			 *	@return array Modified array
			 *	@since PHP4 OOP 0.0.1
			 */
			private function makeArrayKeysLowerCase($in_array)
			{
				$out_array = array();

				if(is_array($in_array) && count($in_array) > 0)
				{
					foreach ($in_array as $in_key => $in_val)
					{
						$out_key = strtolower($in_key);
						$out_array[$out_key] = array();

						if(is_array($in_val) && count($in_val) > 0)
						{
							foreach ($in_val as $in_key2 => $in_val2)
							{
								$out_key2 = strtolower($in_key2);
								$out_array[$out_key][$out_key2] = $in_val2;
							}
						}
					}
				}

				return $out_array;
			}

			/**
			 *	This method strips out disallowed and/or mangled (X)HTML tags along with assigned attributes.
			 *
			 *	This method 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
			 *	allowed attribute list.
			 *
			 *	@access private
			 *	@param string $string
			 *	@return string Modified string minus disallowed/mangled (X)HTML and attributes
			 *	@since PHP4 OOP 0.0.1
			 */
			private function stripTags($string)
			{
				$string = preg_replace('%\\\\"%', '"', $string);

				if (substr($string, 0, 1) != '<')
				{
					# It matched a ">" character
					return '&gt;';
				}

				if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches))
				{
					# It's seriously malformed
					return '';
				}

				$slash    = trim($matches[1]);
				$elem     = $matches[2];
				$attrlist = $matches[3];

				if (
					!isset($this->allowed_html[strtolower($elem)]) ||
					!is_array($this->allowed_html[strtolower($elem)]))
				{
					#	Found an HTML element not in the white list
					return '';
				}

				if ($slash != '')
				{
					return "<$slash$elem>";
				}
				# No attributes are allowed for closing elements

				return $this->stripAttributes("$slash$elem", $attrlist);
			}

			/**
			 *	This method strips out disallowed attributes for (X)HTML tags.
			 *
			 *	This method removes all attributes if none are allowed for this element.
			 *	If some are allowed it calls combAttributes() to split them further, and then it
			 *	builds up new HTML code from the data that combAttributes() 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.
			 *
			 *	@access private
			 *	@param string $element (X)HTML tag to check
			 *	@param string $attr Text containing attributes to check for validity.
			 *	@return string Resulting valid (X)HTML or ''
			 *	@see combAttributes()
			 *	@since PHP4 OOP 0.0.1
			 */
			private function stripAttributes($element, $attr)
			{
				# 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 (
					!isset($this->allowed_html[strtolower($element)]) ||
					count($this->allowed_html[strtolower($element)]) == 0
				)
				{
					return "<$element$xhtml_slash>";
				}

				# Split it
				$attrarr = $this->combAttributes($attr);

				# Go through $attrarr, and save the allowed attributes for this element
				# in $attr2
				$attr2 = '';
				if(is_array($attrarr) && count($attrarr) > 0)
				{
					foreach ($attrarr as $arreach)
					{
						if(!isset($this->allowed_html[strtolower($element)][strtolower($arreach['name'])]))
						{
							continue;
						}

						$current = $this->allowed_html[strtolower($element)][strtolower($arreach['name'])];

						if (!is_array($current))
						{
							# there are no checks
							$attr2 .= ' '.$arreach['whole'];
						}
						else
						{
							# there are some checks
							$ok = true;
							if(is_array($current) && count($current) > 0)
							{
								foreach ($current as $currkey => $currval)
								{
									if (!$this->checkAttributeValue($arreach['value'], $arreach['vless'], $currkey, $currval))
									{
										$ok = false;
										break;
									}
								}
							}

							if ($ok)
							{
								# it passed them
								$attr2 .= ' '.$arreach['whole'];
							}
						}
					}
				}

				# Remove any "<" or ">" characters
				$attr2 = preg_replace('/[<>]/', '', $attr2);
				return "<$element$attr2$xhtml_slash>";