xpressengine / xe-core

classes/security/htmlpurifier/library/HTMLPurifier/Lexer/DirectLex.php

Doc Comments +4 added lines, -1 removed lines

@@ -319,6 +319,9 @@ 
 
     /**
      * PHP 5.0.x compatible substr_count that implements offset and length
+     * @param string $needle
+     * @param integer $offset
+     * @param integer $length
      */
     protected function substrCount($haystack, $needle, $offset, $length) {
         static $oldVersion;
@@ -336,7 +339,7 @@ 
     /**
      * Takes the inside of an HTML tag and makes an assoc array of attributes.
      *
-     * @param $string Inside of tag excluding name.
+     * @param string $string Inside of tag excluding name.
      * @returns Assoc array of attributes.
      */
     public function parseAttributeString($string, $config, $context) {

Indentation +471 added lines, -471 removed lines

@@ -13,477 +13,477 @@
 class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
 {
 
-    public $tracksLineNumbers = true;
-
-    /**
-     * Whitespace characters for str(c)spn.
-     */
-    protected $_whitespace = "\x20\x09\x0D\x0A";
-
-    /**
-     * Callback function for script CDATA fudge
-     * @param $matches, in form of array(opening tag, contents, closing tag)
-     */
-    protected function scriptCallback($matches) {
-        return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8', false) . $matches[3];
-    }
-
-    public function tokenizeHTML($html, $config, $context) {
-
-        // special normalization for script tags without any armor
-        // our "armor" heurstic is a < sign any number of whitespaces after
-        // the first script tag
-        if ($config->get('HTML.Trusted')) {
-            $html = preg_replace_callback('#(<script[^>]*>)(\s*[^<].+?)(</script>)#si',
-                array($this, 'scriptCallback'), $html);
-        }
-
-        $html = $this->normalize($html, $config, $context);
-
-        $cursor = 0; // our location in the text
-        $inside_tag = false; // whether or not we're parsing the inside of a tag
-        $array = array(); // result array
-
-        // This is also treated to mean maintain *column* numbers too
-        $maintain_line_numbers = $config->get('Core.MaintainLineNumbers');
-
-        if ($maintain_line_numbers === null) {
-            // automatically determine line numbering by checking
-            // if error collection is on
-            $maintain_line_numbers = $config->get('Core.CollectErrors');
-        }
-
-        if ($maintain_line_numbers) {
-            $current_line = 1;
-            $current_col  = 0;
-            $length = strlen($html);
-        } else {
-            $current_line = false;
-            $current_col  = false;
-            $length = false;
-        }
-        $context->register('CurrentLine', $current_line);
-        $context->register('CurrentCol',  $current_col);
-        $nl = "\n";
-        // how often to manually recalculate. This will ALWAYS be right,
-        // but it's pretty wasteful. Set to 0 to turn off
-        $synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval');
-
-        $e = false;
-        if ($config->get('Core.CollectErrors')) {
-            $e =& $context->get('ErrorCollector');
-        }
-
-        // for testing synchronization
-        $loops = 0;
-
-        while(++$loops) {
-
-            // $cursor is either at the start of a token, or inside of
-            // a tag (i.e. there was a < immediately before it), as indicated
-            // by $inside_tag
-
-            if ($maintain_line_numbers) {
-
-                // $rcursor, however, is always at the start of a token.
-                $rcursor = $cursor - (int) $inside_tag;
-
-                // Column number is cheap, so we calculate it every round.
-                // We're interested at the *end* of the newline string, so
-                // we need to add strlen($nl) == 1 to $nl_pos before subtracting it
-                // from our "rcursor" position.
-                $nl_pos = strrpos($html, $nl, $rcursor - $length);
-                $current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1);
-
-                // recalculate lines
-                if (
-                    $synchronize_interval &&  // synchronization is on
-                    $cursor > 0 &&            // cursor is further than zero
-                    $loops % $synchronize_interval === 0 // time to synchronize!
-                ) {
-                    $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
-                }
-
-            }
-
-            $position_next_lt = strpos($html, '<', $cursor);
-            $position_next_gt = strpos($html, '>', $cursor);
-
-            // triggers on "<b>asdf</b>" but not "asdf <b></b>"
-            // special case to set up context
-            if ($position_next_lt === $cursor) {
-                $inside_tag = true;
-                $cursor++;
-            }
-
-            if (!$inside_tag && $position_next_lt !== false) {
-                // We are not inside tag and there still is another tag to parse
-                $token = new
-                    HTMLPurifier_Token_Text(
-                        $this->parseData(
-                            substr(
-                                $html, $cursor, $position_next_lt - $cursor
-                            )
-                        )
-                    );
-                if ($maintain_line_numbers) {
-                    $token->rawPosition($current_line, $current_col);
-                    $current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor);
-                }
-                $array[] = $token;
-                $cursor  = $position_next_lt + 1;
-                $inside_tag = true;
-                continue;
-            } elseif (!$inside_tag) {
-                // We are not inside tag but there are no more tags
-                // If we're already at the end, break
-                if ($cursor === strlen($html)) break;
-                // Create Text of rest of string
-                $token = new
-                    HTMLPurifier_Token_Text(
-                        $this->parseData(
-                            substr(
-                                $html, $cursor
-                            )
-                        )
-                    );
-                if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
-                $array[] = $token;
-                break;
-            } elseif ($inside_tag && $position_next_gt !== false) {
-                // We are in tag and it is well formed
-                // Grab the internals of the tag
-                $strlen_segment = $position_next_gt - $cursor;
-
-                if ($strlen_segment < 1) {
-                    // there's nothing to process!
-                    $token = new HTMLPurifier_Token_Text('<');
-                    $cursor++;
-                    continue;
-                }
-
-                $segment = substr($html, $cursor, $strlen_segment);
-
-                if ($segment === false) {
-                    // somehow, we attempted to access beyond the end of
-                    // the string, defense-in-depth, reported by Nate Abele
-                    break;
-                }
-
-                // Check if it's a comment
-                if (
-                    substr($segment, 0, 3) === '!--'
-                ) {
-                    // re-determine segment length, looking for -->
-                    $position_comment_end = strpos($html, '-->', $cursor);
-                    if ($position_comment_end === false) {
-                        // uh oh, we have a comment that extends to
-                        // infinity. Can't be helped: set comment
-                        // end position to end of string
-                        if ($e) $e->send(E_WARNING, 'Lexer: Unclosed comment');
-                        $position_comment_end = strlen($html);
-                        $end = true;
-                    } else {
-                        $end = false;
-                    }
-                    $strlen_segment = $position_comment_end - $cursor;
-                    $segment = substr($html, $cursor, $strlen_segment);
-                    $token = new
-                        HTMLPurifier_Token_Comment(
-                            substr(
-                                $segment, 3, $strlen_segment - 3
-                            )
-                        );
-                    if ($maintain_line_numbers) {
-                        $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
-                    }
-                    $array[] = $token;
-                    $cursor = $end ? $position_comment_end : $position_comment_end + 3;
-                    $inside_tag = false;
-                    continue;
-                }
-
-                // Check if it's an end tag
-                $is_end_tag = (strpos($segment,'/') === 0);
-                if ($is_end_tag) {
-                    $type = substr($segment, 1);
-                    $token = new HTMLPurifier_Token_End($type);
-                    if ($maintain_line_numbers) {
-                        $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
-                    }
-                    $array[] = $token;
-                    $inside_tag = false;
-                    $cursor = $position_next_gt + 1;
-                    continue;
-                }
-
-                // Check leading character is alnum, if not, we may
-                // have accidently grabbed an emoticon. Translate into
-                // text and go our merry way
-                if (!ctype_alpha($segment[0])) {
-                    // XML:  $segment[0] !== '_' && $segment[0] !== ':'
-                    if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt');
-                    $token = new HTMLPurifier_Token_Text('<');
-                    if ($maintain_line_numbers) {
-                        $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
-                    }
-                    $array[] = $token;
-                    $inside_tag = false;
-                    continue;
-                }
-
-                // Check if it is explicitly self closing, if so, remove
-                // trailing slash. Remember, we could have a tag like <br>, so
-                // any later token processing scripts must convert improperly
-                // classified EmptyTags from StartTags.
-                $is_self_closing = (strrpos($segment,'/') === $strlen_segment-1);
-                if ($is_self_closing) {
-                    $strlen_segment--;
-                    $segment = substr($segment, 0, $strlen_segment);
-                }
-
-                // Check if there are any attributes
-                $position_first_space = strcspn($segment, $this->_whitespace);
-
-                if ($position_first_space >= $strlen_segment) {
-                    if ($is_self_closing) {
-                        $token = new HTMLPurifier_Token_Empty($segment);
-                    } else {
-                        $token = new HTMLPurifier_Token_Start($segment);
-                    }
-                    if ($maintain_line_numbers) {
-                        $token->rawPosition($current_line, $current_col);
-                        $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
-                    }
-                    $array[] = $token;
-                    $inside_tag = false;
-                    $cursor = $position_next_gt + 1;
-                    continue;
-                }
-
-                // Grab out all the data
-                $type = substr($segment, 0, $position_first_space);
-                $attribute_string =
-                    trim(
-                        substr(
-                            $segment, $position_first_space
-                        )
-                    );
-                if ($attribute_string) {
-                    $attr = $this->parseAttributeString(
-                                    $attribute_string
-                                  , $config, $context
-                              );
-                } else {
-                    $attr = array();
-                }
-
-                if ($is_self_closing) {
-                    $token = new HTMLPurifier_Token_Empty($type, $attr);
-                } else {
-                    $token = new HTMLPurifier_Token_Start($type, $attr);
-                }
-                if ($maintain_line_numbers) {
-                    $token->rawPosition($current_line, $current_col);
-                    $current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
-                }
-                $array[] = $token;
-                $cursor = $position_next_gt + 1;
-                $inside_tag = false;
-                continue;
-            } else {
-                // inside tag, but there's no ending > sign
-                if ($e) $e->send(E_WARNING, 'Lexer: Missing gt');
-                $token = new
-                    HTMLPurifier_Token_Text(
-                        '<' .
-                        $this->parseData(
-                            substr($html, $cursor)
-                        )
-                    );
-                if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
-                // no cursor scroll? Hmm...
-                $array[] = $token;
-                break;
-            }
-            break;
-        }
-
-        $context->destroy('CurrentLine');
-        $context->destroy('CurrentCol');
-        return $array;
-    }
-
-    /**
-     * PHP 5.0.x compatible substr_count that implements offset and length
-     */
-    protected function substrCount($haystack, $needle, $offset, $length) {
-        static $oldVersion;
-        if ($oldVersion === null) {
-            $oldVersion = version_compare(PHP_VERSION, '5.1', '<');
-        }
-        if ($oldVersion) {
-            $haystack = substr($haystack, $offset, $length);
-            return substr_count($haystack, $needle);
-        } else {
-            return substr_count($haystack, $needle, $offset, $length);
-        }
-    }
-
-    /**
-     * Takes the inside of an HTML tag and makes an assoc array of attributes.
-     *
-     * @param $string Inside of tag excluding name.
-     * @returns Assoc array of attributes.
-     */
-    public function parseAttributeString($string, $config, $context) {
-        $string = (string) $string; // quick typecast
-
-        if ($string == '') return array(); // no attributes
-
-        $e = false;
-        if ($config->get('Core.CollectErrors')) {
-            $e =& $context->get('ErrorCollector');
-        }
-
-        // let's see if we can abort as quickly as possible
-        // one equal sign, no spaces => one attribute
-        $num_equal = substr_count($string, '=');
-        $has_space = strpos($string, ' ');
-        if ($num_equal === 0 && !$has_space) {
-            // bool attribute
-            return array($string => $string);
-        } elseif ($num_equal === 1 && !$has_space) {
-            // only one attribute
-            list($key, $quoted_value) = explode('=', $string);
-            $quoted_value = trim($quoted_value);
-            if (!$key) {
-                if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
-                return array();
-            }
-            if (!$quoted_value) return array($key => '');
-            $first_char = @$quoted_value[0];
-            $last_char  = @$quoted_value[strlen($quoted_value)-1];
-
-            $same_quote = ($first_char == $last_char);
-            $open_quote = ($first_char == '"' || $first_char == "'");
-
-            if ( $same_quote && $open_quote) {
-                // well behaved
-                $value = substr($quoted_value, 1, strlen($quoted_value) - 2);
-            } else {
-                // not well behaved
-                if ($open_quote) {
-                    if ($e) $e->send(E_ERROR, 'Lexer: Missing end quote');
-                    $value = substr($quoted_value, 1);
-                } else {
-                    $value = $quoted_value;
-                }
-            }
-            if ($value === false) $value = '';
-            return array($key => $this->parseData($value));
-        }
-
-        // setup loop environment
-        $array  = array(); // return assoc array of attributes
-        $cursor = 0; // current position in string (moves forward)
-        $size   = strlen($string); // size of the string (stays the same)
-
-        // if we have unquoted attributes, the parser expects a terminating
-        // space, so let's guarantee that there's always a terminating space.
-        $string .= ' ';
-
-        while(true) {
-
-            if ($cursor >= $size) {
-                break;
-            }
-
-            $cursor += ($value = strspn($string, $this->_whitespace, $cursor));
-            // grab the key
-
-            $key_begin = $cursor; //we're currently at the start of the key
-
-            // scroll past all characters that are the key (not whitespace or =)
-            $cursor += strcspn($string, $this->_whitespace . '=', $cursor);
-
-            $key_end = $cursor; // now at the end of the key
-
-            $key = substr($string, $key_begin, $key_end - $key_begin);
-
-            if (!$key) {
-                if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
-                $cursor += strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
-                continue; // empty key
-            }
-
-            // scroll past all whitespace
-            $cursor += strspn($string, $this->_whitespace, $cursor);
-
-            if ($cursor >= $size) {
-                $array[$key] = $key;
-                break;
-            }
-
-            // if the next character is an equal sign, we've got a regular
-            // pair, otherwise, it's a bool attribute
-            $first_char = @$string[$cursor];
-
-            if ($first_char == '=') {
-                // key="value"
-
-                $cursor++;
-                $cursor += strspn($string, $this->_whitespace, $cursor);
-
-                if ($cursor === false) {
-                    $array[$key] = '';
-                    break;
-                }
-
-                // we might be in front of a quote right now
-
-                $char = @$string[$cursor];
-
-                if ($char == '"' || $char == "'") {
-                    // it's quoted, end bound is $char
-                    $cursor++;
-                    $value_begin = $cursor;
-                    $cursor = strpos($string, $char, $cursor);
-                    $value_end = $cursor;
-                } else {
-                    // it's not quoted, end bound is whitespace
-                    $value_begin = $cursor;
-                    $cursor += strcspn($string, $this->_whitespace, $cursor);
-                    $value_end = $cursor;
-                }
-
-                // we reached a premature end
-                if ($cursor === false) {
-                    $cursor = $size;
-                    $value_end = $cursor;
-                }
-
-                $value = substr($string, $value_begin, $value_end - $value_begin);
-                if ($value === false) $value = '';
-                $array[$key] = $this->parseData($value);
-                $cursor++;
-
-            } else {
-                // boolattr
-                if ($key !== '') {
-                    $array[$key] = $key;
-                } else {
-                    // purely theoretical
-                    if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
-                }
-
-            }
-        }
-        return $array;
-    }
+	public $tracksLineNumbers = true;
+
+	/**
+	 * Whitespace characters for str(c)spn.
+	 */
+	protected $_whitespace = "\x20\x09\x0D\x0A";
+
+	/**
+	 * Callback function for script CDATA fudge
+	 * @param $matches, in form of array(opening tag, contents, closing tag)
+	 */
+	protected function scriptCallback($matches) {
+		return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8', false) . $matches[3];
+	}
+
+	public function tokenizeHTML($html, $config, $context) {
+
+		// special normalization for script tags without any armor
+		// our "armor" heurstic is a < sign any number of whitespaces after
+		// the first script tag
+		if ($config->get('HTML.Trusted')) {
+			$html = preg_replace_callback('#(<script[^>]*>)(\s*[^<].+?)(</script>)#si',
+				array($this, 'scriptCallback'), $html);
+		}
+
+		$html = $this->normalize($html, $config, $context);
+
+		$cursor = 0; // our location in the text
+		$inside_tag = false; // whether or not we're parsing the inside of a tag
+		$array = array(); // result array
+
+		// This is also treated to mean maintain *column* numbers too
+		$maintain_line_numbers = $config->get('Core.MaintainLineNumbers');
+
+		if ($maintain_line_numbers === null) {
+			// automatically determine line numbering by checking
+			// if error collection is on
+			$maintain_line_numbers = $config->get('Core.CollectErrors');
+		}
+
+		if ($maintain_line_numbers) {
+			$current_line = 1;
+			$current_col  = 0;
+			$length = strlen($html);
+		} else {
+			$current_line = false;
+			$current_col  = false;
+			$length = false;
+		}
+		$context->register('CurrentLine', $current_line);
+		$context->register('CurrentCol',  $current_col);
+		$nl = "\n";
+		// how often to manually recalculate. This will ALWAYS be right,
+		// but it's pretty wasteful. Set to 0 to turn off
+		$synchronize_interval = $config->get('Core.DirectLexLineNumberSyncInterval');
+
+		$e = false;
+		if ($config->get('Core.CollectErrors')) {
+			$e =& $context->get('ErrorCollector');
+		}
+
+		// for testing synchronization
+		$loops = 0;
+
+		while(++$loops) {
+
+			// $cursor is either at the start of a token, or inside of
+			// a tag (i.e. there was a < immediately before it), as indicated
+			// by $inside_tag
+
+			if ($maintain_line_numbers) {
+
+				// $rcursor, however, is always at the start of a token.
+				$rcursor = $cursor - (int) $inside_tag;
+
+				// Column number is cheap, so we calculate it every round.
+				// We're interested at the *end* of the newline string, so
+				// we need to add strlen($nl) == 1 to $nl_pos before subtracting it
+				// from our "rcursor" position.
+				$nl_pos = strrpos($html, $nl, $rcursor - $length);
+				$current_col = $rcursor - (is_bool($nl_pos) ? 0 : $nl_pos + 1);
+
+				// recalculate lines
+				if (
+					$synchronize_interval &&  // synchronization is on
+					$cursor > 0 &&            // cursor is further than zero
+					$loops % $synchronize_interval === 0 // time to synchronize!
+				) {
+					$current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
+				}
+
+			}
+
+			$position_next_lt = strpos($html, '<', $cursor);
+			$position_next_gt = strpos($html, '>', $cursor);
+
+			// triggers on "<b>asdf</b>" but not "asdf <b></b>"
+			// special case to set up context
+			if ($position_next_lt === $cursor) {
+				$inside_tag = true;
+				$cursor++;
+			}
+
+			if (!$inside_tag && $position_next_lt !== false) {
+				// We are not inside tag and there still is another tag to parse
+				$token = new
+					HTMLPurifier_Token_Text(
+						$this->parseData(
+							substr(
+								$html, $cursor, $position_next_lt - $cursor
+							)
+						)
+					);
+				if ($maintain_line_numbers) {
+					$token->rawPosition($current_line, $current_col);
+					$current_line += $this->substrCount($html, $nl, $cursor, $position_next_lt - $cursor);
+				}
+				$array[] = $token;
+				$cursor  = $position_next_lt + 1;
+				$inside_tag = true;
+				continue;
+			} elseif (!$inside_tag) {
+				// We are not inside tag but there are no more tags
+				// If we're already at the end, break
+				if ($cursor === strlen($html)) break;
+				// Create Text of rest of string
+				$token = new
+					HTMLPurifier_Token_Text(
+						$this->parseData(
+							substr(
+								$html, $cursor
+							)
+						)
+					);
+				if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+				$array[] = $token;
+				break;
+			} elseif ($inside_tag && $position_next_gt !== false) {
+				// We are in tag and it is well formed
+				// Grab the internals of the tag
+				$strlen_segment = $position_next_gt - $cursor;
+
+				if ($strlen_segment < 1) {
+					// there's nothing to process!
+					$token = new HTMLPurifier_Token_Text('<');
+					$cursor++;
+					continue;
+				}
+
+				$segment = substr($html, $cursor, $strlen_segment);
+
+				if ($segment === false) {
+					// somehow, we attempted to access beyond the end of
+					// the string, defense-in-depth, reported by Nate Abele
+					break;
+				}
+
+				// Check if it's a comment
+				if (
+					substr($segment, 0, 3) === '!--'
+				) {
+					// re-determine segment length, looking for -->
+					$position_comment_end = strpos($html, '-->', $cursor);
+					if ($position_comment_end === false) {
+						// uh oh, we have a comment that extends to
+						// infinity. Can't be helped: set comment
+						// end position to end of string
+						if ($e) $e->send(E_WARNING, 'Lexer: Unclosed comment');
+						$position_comment_end = strlen($html);
+						$end = true;
+					} else {
+						$end = false;
+					}
+					$strlen_segment = $position_comment_end - $cursor;
+					$segment = substr($html, $cursor, $strlen_segment);
+					$token = new
+						HTMLPurifier_Token_Comment(
+							substr(
+								$segment, 3, $strlen_segment - 3
+							)
+						);
+					if ($maintain_line_numbers) {
+						$token->rawPosition($current_line, $current_col);
+						$current_line += $this->substrCount($html, $nl, $cursor, $strlen_segment);
+					}
+					$array[] = $token;
+					$cursor = $end ? $position_comment_end : $position_comment_end + 3;
+					$inside_tag = false;
+					continue;
+				}
+
+				// Check if it's an end tag
+				$is_end_tag = (strpos($segment,'/') === 0);
+				if ($is_end_tag) {
+					$type = substr($segment, 1);
+					$token = new HTMLPurifier_Token_End($type);
+					if ($maintain_line_numbers) {
+						$token->rawPosition($current_line, $current_col);
+						$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+					}
+					$array[] = $token;
+					$inside_tag = false;
+					$cursor = $position_next_gt + 1;
+					continue;
+				}
+
+				// Check leading character is alnum, if not, we may
+				// have accidently grabbed an emoticon. Translate into
+				// text and go our merry way
+				if (!ctype_alpha($segment[0])) {
+					// XML:  $segment[0] !== '_' && $segment[0] !== ':'
+					if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt');
+					$token = new HTMLPurifier_Token_Text('<');
+					if ($maintain_line_numbers) {
+						$token->rawPosition($current_line, $current_col);
+						$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+					}
+					$array[] = $token;
+					$inside_tag = false;
+					continue;
+				}
+
+				// Check if it is explicitly self closing, if so, remove
+				// trailing slash. Remember, we could have a tag like <br>, so
+				// any later token processing scripts must convert improperly
+				// classified EmptyTags from StartTags.
+				$is_self_closing = (strrpos($segment,'/') === $strlen_segment-1);
+				if ($is_self_closing) {
+					$strlen_segment--;
+					$segment = substr($segment, 0, $strlen_segment);
+				}
+
+				// Check if there are any attributes
+				$position_first_space = strcspn($segment, $this->_whitespace);
+
+				if ($position_first_space >= $strlen_segment) {
+					if ($is_self_closing) {
+						$token = new HTMLPurifier_Token_Empty($segment);
+					} else {
+						$token = new HTMLPurifier_Token_Start($segment);
+					}
+					if ($maintain_line_numbers) {
+						$token->rawPosition($current_line, $current_col);
+						$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+					}
+					$array[] = $token;
+					$inside_tag = false;
+					$cursor = $position_next_gt + 1;
+					continue;
+				}
+
+				// Grab out all the data
+				$type = substr($segment, 0, $position_first_space);
+				$attribute_string =
+					trim(
+						substr(
+							$segment, $position_first_space
+						)
+					);
+				if ($attribute_string) {
+					$attr = $this->parseAttributeString(
+									$attribute_string
+								  , $config, $context
+							  );
+				} else {
+					$attr = array();
+				}
+
+				if ($is_self_closing) {
+					$token = new HTMLPurifier_Token_Empty($type, $attr);
+				} else {
+					$token = new HTMLPurifier_Token_Start($type, $attr);
+				}
+				if ($maintain_line_numbers) {
+					$token->rawPosition($current_line, $current_col);
+					$current_line += $this->substrCount($html, $nl, $cursor, $position_next_gt - $cursor);
+				}
+				$array[] = $token;
+				$cursor = $position_next_gt + 1;
+				$inside_tag = false;
+				continue;
+			} else {
+				// inside tag, but there's no ending > sign
+				if ($e) $e->send(E_WARNING, 'Lexer: Missing gt');
+				$token = new
+					HTMLPurifier_Token_Text(
+						'<' .
+						$this->parseData(
+							substr($html, $cursor)
+						)
+					);
+				if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+				// no cursor scroll? Hmm...
+				$array[] = $token;
+				break;
+			}
+			break;
+		}
+
+		$context->destroy('CurrentLine');
+		$context->destroy('CurrentCol');
+		return $array;
+	}
+
+	/**
+	 * PHP 5.0.x compatible substr_count that implements offset and length
+	 */
+	protected function substrCount($haystack, $needle, $offset, $length) {
+		static $oldVersion;
+		if ($oldVersion === null) {
+			$oldVersion = version_compare(PHP_VERSION, '5.1', '<');
+		}
+		if ($oldVersion) {
+			$haystack = substr($haystack, $offset, $length);
+			return substr_count($haystack, $needle);
+		} else {
+			return substr_count($haystack, $needle, $offset, $length);
+		}
+	}
+
+	/**
+	 * Takes the inside of an HTML tag and makes an assoc array of attributes.
+	 *
+	 * @param $string Inside of tag excluding name.
+	 * @returns Assoc array of attributes.
+	 */
+	public function parseAttributeString($string, $config, $context) {
+		$string = (string) $string; // quick typecast
+
+		if ($string == '') return array(); // no attributes
+
+		$e = false;
+		if ($config->get('Core.CollectErrors')) {
+			$e =& $context->get('ErrorCollector');
+		}
+
+		// let's see if we can abort as quickly as possible
+		// one equal sign, no spaces => one attribute
+		$num_equal = substr_count($string, '=');
+		$has_space = strpos($string, ' ');
+		if ($num_equal === 0 && !$has_space) {
+			// bool attribute
+			return array($string => $string);
+		} elseif ($num_equal === 1 && !$has_space) {
+			// only one attribute
+			list($key, $quoted_value) = explode('=', $string);
+			$quoted_value = trim($quoted_value);
+			if (!$key) {
+				if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+				return array();
+			}
+			if (!$quoted_value) return array($key => '');
+			$first_char = @$quoted_value[0];
+			$last_char  = @$quoted_value[strlen($quoted_value)-1];
+
+			$same_quote = ($first_char == $last_char);
+			$open_quote = ($first_char == '"' || $first_char == "'");
+
+			if ( $same_quote && $open_quote) {
+				// well behaved
+				$value = substr($quoted_value, 1, strlen($quoted_value) - 2);
+			} else {
+				// not well behaved
+				if ($open_quote) {
+					if ($e) $e->send(E_ERROR, 'Lexer: Missing end quote');
+					$value = substr($quoted_value, 1);
+				} else {
+					$value = $quoted_value;
+				}
+			}
+			if ($value === false) $value = '';
+			return array($key => $this->parseData($value));
+		}
+
+		// setup loop environment
+		$array  = array(); // return assoc array of attributes
+		$cursor = 0; // current position in string (moves forward)
+		$size   = strlen($string); // size of the string (stays the same)
+
+		// if we have unquoted attributes, the parser expects a terminating
+		// space, so let's guarantee that there's always a terminating space.
+		$string .= ' ';
+
+		while(true) {
+
+			if ($cursor >= $size) {
+				break;
+			}
+
+			$cursor += ($value = strspn($string, $this->_whitespace, $cursor));
+			// grab the key
+
+			$key_begin = $cursor; //we're currently at the start of the key
+
+			// scroll past all characters that are the key (not whitespace or =)
+			$cursor += strcspn($string, $this->_whitespace . '=', $cursor);
+
+			$key_end = $cursor; // now at the end of the key
+
+			$key = substr($string, $key_begin, $key_end - $key_begin);
+
+			if (!$key) {
+				if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+				$cursor += strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
+				continue; // empty key
+			}
+
+			// scroll past all whitespace
+			$cursor += strspn($string, $this->_whitespace, $cursor);
+
+			if ($cursor >= $size) {
+				$array[$key] = $key;
+				break;
+			}
+
+			// if the next character is an equal sign, we've got a regular
+			// pair, otherwise, it's a bool attribute
+			$first_char = @$string[$cursor];
+
+			if ($first_char == '=') {
+				// key="value"
+
+				$cursor++;
+				$cursor += strspn($string, $this->_whitespace, $cursor);
+
+				if ($cursor === false) {
+					$array[$key] = '';
+					break;
+				}
+
+				// we might be in front of a quote right now
+
+				$char = @$string[$cursor];
+
+				if ($char == '"' || $char == "'") {
+					// it's quoted, end bound is $char
+					$cursor++;
+					$value_begin = $cursor;
+					$cursor = strpos($string, $char, $cursor);
+					$value_end = $cursor;
+				} else {
+					// it's not quoted, end bound is whitespace
+					$value_begin = $cursor;
+					$cursor += strcspn($string, $this->_whitespace, $cursor);
+					$value_end = $cursor;
+				}
+
+				// we reached a premature end
+				if ($cursor === false) {
+					$cursor = $size;
+					$value_end = $cursor;
+				}
+
+				$value = substr($string, $value_begin, $value_end - $value_begin);
+				if ($value === false) $value = '';
+				$array[$key] = $this->parseData($value);
+				$cursor++;
+
+			} else {
+				// boolattr
+				if ($key !== '') {
+					$array[$key] = $key;
+				} else {
+					// purely theoretical
+					if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+				}
+
+			}
+		}
+		return $array;
+	}
 
 }
 

Braces +43 added lines, -14 removed lines

@@ -137,7 +137,9 @@ 
             } elseif (!$inside_tag) {
                 // We are not inside tag but there are no more tags
                 // If we're already at the end, break
-                if ($cursor === strlen($html)) break;
+                if ($cursor === strlen($html)) {
+                	break;
+                }
                 // Create Text of rest of string
                 $token = new
                     HTMLPurifier_Token_Text(
@@ -147,7 +149,9 @@ 
                             )
                         )
                     );
-                if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+                if ($maintain_line_numbers) {
+                	$token->rawPosition($current_line, $current_col);
+                }
                 $array[] = $token;
                 break;
             } elseif ($inside_tag && $position_next_gt !== false) {
@@ -180,7 +184,9 @@ 
                         // uh oh, we have a comment that extends to
                         // infinity. Can't be helped: set comment
                         // end position to end of string
-                        if ($e) $e->send(E_WARNING, 'Lexer: Unclosed comment');
+                        if ($e) {
+                        	$e->send(E_WARNING, 'Lexer: Unclosed comment');
+                        }
                         $position_comment_end = strlen($html);
                         $end = true;
                     } else {
@@ -224,7 +230,9 @@ 
                 // text and go our merry way
                 if (!ctype_alpha($segment[0])) {
                     // XML:  $segment[0] !== '_' && $segment[0] !== ':'
-                    if ($e) $e->send(E_NOTICE, 'Lexer: Unescaped lt');
+                    if ($e) {
+                    	$e->send(E_NOTICE, 'Lexer: Unescaped lt');
+                    }
                     $token = new HTMLPurifier_Token_Text('<');
                     if ($maintain_line_numbers) {
                         $token->rawPosition($current_line, $current_col);
@@ -296,7 +304,9 @@ 
                 continue;
             } else {
                 // inside tag, but there's no ending > sign
-                if ($e) $e->send(E_WARNING, 'Lexer: Missing gt');
+                if ($e) {
+                	$e->send(E_WARNING, 'Lexer: Missing gt');
+                }
                 $token = new
                     HTMLPurifier_Token_Text(
                         '<' .
@@ -304,7 +314,9 @@ 
                             substr($html, $cursor)
                         )
                     );
-                if ($maintain_line_numbers) $token->rawPosition($current_line, $current_col);
+                if ($maintain_line_numbers) {
+                	$token->rawPosition($current_line, $current_col);
+                }
                 // no cursor scroll? Hmm...
                 $array[] = $token;
                 break;
@@ -342,7 +354,10 @@ 
     public function parseAttributeString($string, $config, $context) {
         $string = (string) $string; // quick typecast
 
-        if ($string == '') return array(); // no attributes
+        if ($string == '') {
+        	return array();
+        }
+        // no attributes
 
         $e = false;
         if ($config->get('Core.CollectErrors')) {
@@ -361,10 +376,14 @@ 
             list($key, $quoted_value) = explode('=', $string);
             $quoted_value = trim($quoted_value);
             if (!$key) {
-                if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+                if ($e) {
+                	$e->send(E_ERROR, 'Lexer: Missing attribute key');
+                }
                 return array();
             }
-            if (!$quoted_value) return array($key => '');
+            if (!$quoted_value) {
+            	return array($key => '');
+            }
             $first_char = @$quoted_value[0];
             $last_char  = @$quoted_value[strlen($quoted_value)-1];
 
@@ -377,13 +396,17 @@ 
             } else {
                 // not well behaved
                 if ($open_quote) {
-                    if ($e) $e->send(E_ERROR, 'Lexer: Missing end quote');
+                    if ($e) {
+                    	$e->send(E_ERROR, 'Lexer: Missing end quote');
+                    }
                     $value = substr($quoted_value, 1);
                 } else {
                     $value = $quoted_value;
                 }
             }
-            if ($value === false) $value = '';
+            if ($value === false) {
+            	$value = '';
+            }
             return array($key => $this->parseData($value));
         }
 
@@ -415,7 +438,9 @@ 
             $key = substr($string, $key_begin, $key_end - $key_begin);
 
             if (!$key) {
-                if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+                if ($e) {
+                	$e->send(E_ERROR, 'Lexer: Missing attribute key');
+                }
                 $cursor += strcspn($string, $this->_whitespace, $cursor + 1); // prevent infinite loop
                 continue; // empty key
             }
@@ -467,7 +492,9 @@ 
                 }
 
                 $value = substr($string, $value_begin, $value_end - $value_begin);
-                if ($value === false) $value = '';
+                if ($value === false) {
+                	$value = '';
+                }
                 $array[$key] = $this->parseData($value);
                 $cursor++;
 
@@ -477,7 +504,9 @@ 
                     $array[$key] = $key;
                 } else {
                     // purely theoretical
-                    if ($e) $e->send(E_ERROR, 'Lexer: Missing attribute key');
+                    if ($e) {
+                    	$e->send(E_ERROR, 'Lexer: Missing attribute key');
+                    }
                 }
 
             }

Spacing +14 added lines, -14 removed lines

@@ -25,7 +25,7 @@ 
      * @param $matches, in form of array(opening tag, contents, closing tag)
      */
     protected function scriptCallback($matches) {
-        return $matches[1] . htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8', false) . $matches[3];
+        return $matches[1].htmlspecialchars($matches[2], ENT_COMPAT, 'UTF-8', false).$matches[3];
     }
 
     public function tokenizeHTML($html, $config, $context) {
@@ -63,7 +63,7 @@ 
             $length = false;
         }
         $context->register('CurrentLine', $current_line);
-        $context->register('CurrentCol',  $current_col);
+        $context->register('CurrentCol', $current_col);
         $nl = "\n";
         // how often to manually recalculate. This will ALWAYS be right,
         // but it's pretty wasteful. Set to 0 to turn off
@@ -71,13 +71,13 @@ 
 
         $e = false;
         if ($config->get('Core.CollectErrors')) {
-            $e =& $context->get('ErrorCollector');
+            $e = & $context->get('ErrorCollector');
         }
 
         // for testing synchronization
         $loops = 0;
 
-        while(++$loops) {
+        while (++$loops) {
 
             // $cursor is either at the start of a token, or inside of
             // a tag (i.e. there was a < immediately before it), as indicated
@@ -97,8 +97,8 @@ 
 
                 // recalculate lines
                 if (
-                    $synchronize_interval &&  // synchronization is on
-                    $cursor > 0 &&            // cursor is further than zero
+                    $synchronize_interval && // synchronization is on
+                    $cursor > 0 && // cursor is further than zero
                     $loops % $synchronize_interval === 0 // time to synchronize!
                 ) {
                     $current_line = 1 + $this->substrCount($html, $nl, 0, $cursor);
@@ -205,7 +205,7 @@ 
                 }
 
                 // Check if it's an end tag
-                $is_end_tag = (strpos($segment,'/') === 0);
+                $is_end_tag = (strpos($segment, '/') === 0);
                 if ($is_end_tag) {
                     $type = substr($segment, 1);
                     $token = new HTMLPurifier_Token_End($type);
@@ -239,7 +239,7 @@ 
                 // trailing slash. Remember, we could have a tag like <br>, so
                 // any later token processing scripts must convert improperly
                 // classified EmptyTags from StartTags.
-                $is_self_closing = (strrpos($segment,'/') === $strlen_segment-1);
+                $is_self_closing = (strrpos($segment, '/') === $strlen_segment - 1);
                 if ($is_self_closing) {
                     $strlen_segment--;
                     $segment = substr($segment, 0, $strlen_segment);
@@ -299,7 +299,7 @@ 
                 if ($e) $e->send(E_WARNING, 'Lexer: Missing gt');
                 $token = new
                     HTMLPurifier_Token_Text(
-                        '<' .
+                        '<'.
                         $this->parseData(
                             substr($html, $cursor)
                         )
@@ -346,7 +346,7 @@ 
 
         $e = false;
         if ($config->get('Core.CollectErrors')) {
-            $e =& $context->get('ErrorCollector');
+            $e = & $context->get('ErrorCollector');
         }
 
         // let's see if we can abort as quickly as possible
@@ -366,12 +366,12 @@ 
             }
             if (!$quoted_value) return array($key => '');
             $first_char = @$quoted_value[0];
-            $last_char  = @$quoted_value[strlen($quoted_value)-1];
+            $last_char  = @$quoted_value[strlen($quoted_value) - 1];
 
             $same_quote = ($first_char == $last_char);
             $open_quote = ($first_char == '"' || $first_char == "'");
 
-            if ( $same_quote && $open_quote) {
+            if ($same_quote && $open_quote) {
                 // well behaved
                 $value = substr($quoted_value, 1, strlen($quoted_value) - 2);
             } else {
@@ -396,7 +396,7 @@ 
         // space, so let's guarantee that there's always a terminating space.
         $string .= ' ';
 
-        while(true) {
+        while (true) {
 
             if ($cursor >= $size) {
                 break;
@@ -408,7 +408,7 @@ 
             $key_begin = $cursor; //we're currently at the start of the key
 
             // scroll past all characters that are the key (not whitespace or =)
-            $cursor += strcspn($string, $this->_whitespace . '=', $cursor);
+            $cursor += strcspn($string, $this->_whitespace.'=', $cursor);
 
             $key_end = $cursor; // now at the end of the key
 

classes/security/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php

Doc Comments +1 added lines, -1 removed lines

@@ -111,7 +111,7 @@
     /**
      * @param $node  DOMNode to be tokenized.
      * @param $tokens   Array-list of already tokenized tokens.
-     * @param $collect  Says whether or start and close are collected, set to
+     * @param boolean $collect  Says whether or start and close are collected, set to
      *                    false at first recursion because it's the implicit DIV
      *                    tag you're dealing with.
      * @returns bool if the token needs an endtoken

Indentation +210 added lines, -210 removed lines

@@ -27,216 +27,216 @@
 class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer
 {
 
-    private $factory;
-
-    public function __construct() {
-        // setup the factory
-        parent::__construct();
-        $this->factory = new HTMLPurifier_TokenFactory();
-    }
-
-    public function tokenizeHTML($html, $config, $context) {
-
-        $html = $this->normalize($html, $config, $context);
-
-        // attempt to armor stray angled brackets that cannot possibly
-        // form tags and thus are probably being used as emoticons
-        if ($config->get('Core.AggressivelyFixLt')) {
-            $char = '[^a-z!\/]';
-            $comment = "/<!--(.*?)(-->|\z)/is";
-            $html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html);
-            do {
-                $old = $html;
-                $html = preg_replace("/<($char)/i", '&lt;\\1', $html);
-            } while ($html !== $old);
-            $html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments
-        }
-
-        // preprocess html, essential for UTF-8
-        $html = $this->wrapHTML($html, $config, $context);
-
-        $doc = new DOMDocument();
-        $doc->encoding = 'UTF-8'; // theoretically, the above has this covered
-
-        set_error_handler(array($this, 'muteErrorHandler'));
-        $doc->loadHTML($html);
-        restore_error_handler();
-
-        $tokens = array();
-        $this->tokenizeDOM(
-            $doc->getElementsByTagName('html')->item(0)-> // <html>
-                  getElementsByTagName('body')->item(0)-> //   <body>
-                  getElementsByTagName('div')->item(0)    //     <div>
-            , $tokens);
-        return $tokens;
-    }
-
-    /**
-     * Iterative function that tokenizes a node, putting it into an accumulator.
-     * To iterate is human, to recurse divine - L. Peter Deutsch
-     * @param $node     DOMNode to be tokenized.
-     * @param $tokens   Array-list of already tokenized tokens.
-     * @returns Tokens of node appended to previously passed tokens.
-     */
-    protected function tokenizeDOM($node, &$tokens) {
-
-        $level = 0;
-        $nodes = array($level => array($node));
-        $closingNodes = array();
-        do {
-            while (!empty($nodes[$level])) {
-                $node = array_shift($nodes[$level]); // FIFO
-                $collect = $level > 0 ? true : false;
-                $needEndingTag = $this->createStartNode($node, $tokens, $collect);
-                if ($needEndingTag) {
-                    $closingNodes[$level][] = $node;
-                }
-                if ($node->childNodes && $node->childNodes->length) {
-                    $level++;
-                    $nodes[$level] = array();
-                    foreach ($node->childNodes as $childNode) {
-                        array_push($nodes[$level], $childNode);
-                    }
-                }
-            }
-            $level--;
-            if ($level && isset($closingNodes[$level])) {
-                while($node = array_pop($closingNodes[$level])) {
-                    $this->createEndNode($node, $tokens);
-                }
-            }
-        } while ($level > 0);
-    }
-
-    /**
-     * @param $node  DOMNode to be tokenized.
-     * @param $tokens   Array-list of already tokenized tokens.
-     * @param $collect  Says whether or start and close are collected, set to
-     *                    false at first recursion because it's the implicit DIV
-     *                    tag you're dealing with.
-     * @returns bool if the token needs an endtoken
-     */
-    protected function createStartNode($node, &$tokens, $collect) {
-        // intercept non element nodes. WE MUST catch all of them,
-        // but we're not getting the character reference nodes because
-        // those should have been preprocessed
-        if ($node->nodeType === XML_TEXT_NODE) {
-            $tokens[] = $this->factory->createText($node->data);
-            return false;
-        } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) {
-            // undo libxml's special treatment of <script> and <style> tags
-            $last = end($tokens);
-            $data = $node->data;
-            // (note $node->tagname is already normalized)
-            if ($last instanceof HTMLPurifier_Token_Start && ($last->name == 'script' || $last->name == 'style')) {
-                $new_data = trim($data);
-                if (substr($new_data, 0, 4) === '<!--') {
-                    $data = substr($new_data, 4);
-                    if (substr($data, -3) === '-->') {
-                        $data = substr($data, 0, -3);
-                    } else {
-                        // Highly suspicious! Not sure what to do...
-                    }
-                }
-            }
-            $tokens[] = $this->factory->createText($this->parseData($data));
-            return false;
-        } elseif ($node->nodeType === XML_COMMENT_NODE) {
-            // this is code is only invoked for comments in script/style in versions
-            // of libxml pre-2.6.28 (regular comments, of course, are still
-            // handled regularly)
-            $tokens[] = $this->factory->createComment($node->data);
-            return false;
-        } elseif (
-            // not-well tested: there may be other nodes we have to grab
-            $node->nodeType !== XML_ELEMENT_NODE
-        ) {
-            return false;
-        }
-
-        $attr = $node->hasAttributes() ? $this->transformAttrToAssoc($node->attributes) : array();
-
-        // We still have to make sure that the element actually IS empty
-        if (!$node->childNodes->length) {
-            if ($collect) {
-                $tokens[] = $this->factory->createEmpty($node->tagName, $attr);
-            }
-            return false;
-        } else {
-            if ($collect) {
-                $tokens[] = $this->factory->createStart(
-                    $tag_name = $node->tagName, // somehow, it get's dropped
-                    $attr
-                );
-            }
-            return true;
-        }
-    }
-
-    protected function createEndNode($node, &$tokens) {
-        $tokens[] = $this->factory->createEnd($node->tagName);
-    }
-
-
-    /**
-     * Converts a DOMNamedNodeMap of DOMAttr objects into an assoc array.
-     *
-     * @param $attribute_list DOMNamedNodeMap of DOMAttr objects.
-     * @returns Associative array of attributes.
-     */
-    protected function transformAttrToAssoc($node_map) {
-        // NamedNodeMap is documented very well, so we're using undocumented
-        // features, namely, the fact that it implements Iterator and
-        // has a ->length attribute
-        if ($node_map->length === 0) return array();
-        $array = array();
-        foreach ($node_map as $attr) {
-            $array[$attr->name] = $attr->value;
-        }
-        return $array;
-    }
-
-    /**
-     * An error handler that mutes all errors
-     */
-    public function muteErrorHandler($errno, $errstr) {}
-
-    /**
-     * Callback function for undoing escaping of stray angled brackets
-     * in comments
-     */
-    public function callbackUndoCommentSubst($matches) {
-        return '<!--' . strtr($matches[1], array('&amp;'=>'&','&lt;'=>'<')) . $matches[2];
-    }
-
-    /**
-     * Callback function that entity-izes ampersands in comments so that
-     * callbackUndoCommentSubst doesn't clobber them
-     */
-    public function callbackArmorCommentEntities($matches) {
-        return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
-    }
-
-    /**
-     * Wraps an HTML fragment in the necessary HTML
-     */
-    protected function wrapHTML($html, $config, $context) {
-        $def = $config->getDefinition('HTML');
-        $ret = '';
-
-        if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
-            $ret .= '<!DOCTYPE html ';
-            if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
-            if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
-            $ret .= '>';
-        }
-
-        $ret .= '<html><head>';
-        $ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />';
-        // No protection if $html contains a stray </div>!
-        $ret .= '</head><body><div>'.$html.'</div></body></html>';
-        return $ret;
-    }
+	private $factory;
+
+	public function __construct() {
+		// setup the factory
+		parent::__construct();
+		$this->factory = new HTMLPurifier_TokenFactory();
+	}
+
+	public function tokenizeHTML($html, $config, $context) {
+
+		$html = $this->normalize($html, $config, $context);
+
+		// attempt to armor stray angled brackets that cannot possibly
+		// form tags and thus are probably being used as emoticons
+		if ($config->get('Core.AggressivelyFixLt')) {
+			$char = '[^a-z!\/]';
+			$comment = "/<!--(.*?)(-->|\z)/is";
+			$html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html);
+			do {
+				$old = $html;
+				$html = preg_replace("/<($char)/i", '&lt;\\1', $html);
+			} while ($html !== $old);
+			$html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments
+		}
+
+		// preprocess html, essential for UTF-8
+		$html = $this->wrapHTML($html, $config, $context);
+
+		$doc = new DOMDocument();
+		$doc->encoding = 'UTF-8'; // theoretically, the above has this covered
+
+		set_error_handler(array($this, 'muteErrorHandler'));
+		$doc->loadHTML($html);
+		restore_error_handler();
+
+		$tokens = array();
+		$this->tokenizeDOM(
+			$doc->getElementsByTagName('html')->item(0)-> // <html>
+				  getElementsByTagName('body')->item(0)-> //   <body>
+				  getElementsByTagName('div')->item(0)    //     <div>
+			, $tokens);
+		return $tokens;
+	}
+
+	/**
+	 * Iterative function that tokenizes a node, putting it into an accumulator.
+	 * To iterate is human, to recurse divine - L. Peter Deutsch
+	 * @param $node     DOMNode to be tokenized.
+	 * @param $tokens   Array-list of already tokenized tokens.
+	 * @returns Tokens of node appended to previously passed tokens.
+	 */
+	protected function tokenizeDOM($node, &$tokens) {
+
+		$level = 0;
+		$nodes = array($level => array($node));
+		$closingNodes = array();
+		do {
+			while (!empty($nodes[$level])) {
+				$node = array_shift($nodes[$level]); // FIFO
+				$collect = $level > 0 ? true : false;
+				$needEndingTag = $this->createStartNode($node, $tokens, $collect);
+				if ($needEndingTag) {
+					$closingNodes[$level][] = $node;
+				}
+				if ($node->childNodes && $node->childNodes->length) {
+					$level++;
+					$nodes[$level] = array();
+					foreach ($node->childNodes as $childNode) {
+						array_push($nodes[$level], $childNode);
+					}
+				}
+			}
+			$level--;
+			if ($level && isset($closingNodes[$level])) {
+				while($node = array_pop($closingNodes[$level])) {
+					$this->createEndNode($node, $tokens);
+				}
+			}
+		} while ($level > 0);
+	}
+
+	/**
+	 * @param $node  DOMNode to be tokenized.
+	 * @param $tokens   Array-list of already tokenized tokens.
+	 * @param $collect  Says whether or start and close are collected, set to
+	 *                    false at first recursion because it's the implicit DIV
+	 *                    tag you're dealing with.
+	 * @returns bool if the token needs an endtoken
+	 */
+	protected function createStartNode($node, &$tokens, $collect) {
+		// intercept non element nodes. WE MUST catch all of them,
+		// but we're not getting the character reference nodes because
+		// those should have been preprocessed
+		if ($node->nodeType === XML_TEXT_NODE) {
+			$tokens[] = $this->factory->createText($node->data);
+			return false;
+		} elseif ($node->nodeType === XML_CDATA_SECTION_NODE) {
+			// undo libxml's special treatment of <script> and <style> tags
+			$last = end($tokens);
+			$data = $node->data;
+			// (note $node->tagname is already normalized)
+			if ($last instanceof HTMLPurifier_Token_Start && ($last->name == 'script' || $last->name == 'style')) {
+				$new_data = trim($data);
+				if (substr($new_data, 0, 4) === '<!--') {
+					$data = substr($new_data, 4);
+					if (substr($data, -3) === '-->') {
+						$data = substr($data, 0, -3);
+					} else {
+						// Highly suspicious! Not sure what to do...
+					}
+				}
+			}
+			$tokens[] = $this->factory->createText($this->parseData($data));
+			return false;
+		} elseif ($node->nodeType === XML_COMMENT_NODE) {
+			// this is code is only invoked for comments in script/style in versions
+			// of libxml pre-2.6.28 (regular comments, of course, are still
+			// handled regularly)
+			$tokens[] = $this->factory->createComment($node->data);
+			return false;
+		} elseif (
+			// not-well tested: there may be other nodes we have to grab
+			$node->nodeType !== XML_ELEMENT_NODE
+		) {
+			return false;
+		}
+
+		$attr = $node->hasAttributes() ? $this->transformAttrToAssoc($node->attributes) : array();
+
+		// We still have to make sure that the element actually IS empty
+		if (!$node->childNodes->length) {
+			if ($collect) {
+				$tokens[] = $this->factory->createEmpty($node->tagName, $attr);
+			}
+			return false;
+		} else {
+			if ($collect) {
+				$tokens[] = $this->factory->createStart(
+					$tag_name = $node->tagName, // somehow, it get's dropped
+					$attr
+				);
+			}
+			return true;
+		}
+	}
+
+	protected function createEndNode($node, &$tokens) {
+		$tokens[] = $this->factory->createEnd($node->tagName);
+	}
+
+
+	/**
+	 * Converts a DOMNamedNodeMap of DOMAttr objects into an assoc array.
+	 *
+	 * @param $attribute_list DOMNamedNodeMap of DOMAttr objects.
+	 * @returns Associative array of attributes.
+	 */
+	protected function transformAttrToAssoc($node_map) {
+		// NamedNodeMap is documented very well, so we're using undocumented
+		// features, namely, the fact that it implements Iterator and
+		// has a ->length attribute
+		if ($node_map->length === 0) return array();
+		$array = array();
+		foreach ($node_map as $attr) {
+			$array[$attr->name] = $attr->value;
+		}
+		return $array;
+	}
+
+	/**
+	 * An error handler that mutes all errors
+	 */
+	public function muteErrorHandler($errno, $errstr) {}
+
+	/**
+	 * Callback function for undoing escaping of stray angled brackets
+	 * in comments
+	 */
+	public function callbackUndoCommentSubst($matches) {
+		return '<!--' . strtr($matches[1], array('&amp;'=>'&','&lt;'=>'<')) . $matches[2];
+	}
+
+	/**
+	 * Callback function that entity-izes ampersands in comments so that
+	 * callbackUndoCommentSubst doesn't clobber them
+	 */
+	public function callbackArmorCommentEntities($matches) {
+		return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
+	}
+
+	/**
+	 * Wraps an HTML fragment in the necessary HTML
+	 */
+	protected function wrapHTML($html, $config, $context) {
+		$def = $config->getDefinition('HTML');
+		$ret = '';
+
+		if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
+			$ret .= '<!DOCTYPE html ';
+			if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
+			if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
+			$ret .= '>';
+		}
+
+		$ret .= '<html><head>';
+		$ret .= '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />';
+		// No protection if $html contains a stray </div>!
+		$ret .= '</head><body><div>'.$html.'</div></body></html>';
+		return $ret;
+	}
 
 }
 

Braces +9 added lines, -3 removed lines

@@ -188,7 +188,9 @@ 
         // NamedNodeMap is documented very well, so we're using undocumented
         // features, namely, the fact that it implements Iterator and
         // has a ->length attribute
-        if ($node_map->length === 0) return array();
+        if ($node_map->length === 0) {
+        	return array();
+        }
         $array = array();
         foreach ($node_map as $attr) {
             $array[$attr->name] = $attr->value;
@@ -226,8 +228,12 @@ 
 
         if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
             $ret .= '<!DOCTYPE html ';
-            if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
-            if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
+            if (!empty($def->doctype->dtdPublic)) {
+            	$ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
+            }
+            if (!empty($def->doctype->dtdSystem)) {
+            	$ret .= '"' . $def->doctype->dtdSystem . '" ';
+            }
             $ret .= '>';
         }
 

Spacing +5 added lines, -5 removed lines

@@ -101,7 +101,7 @@ 
             }
             $level--;
             if ($level && isset($closingNodes[$level])) {
-                while($node = array_pop($closingNodes[$level])) {
+                while ($node = array_pop($closingNodes[$level])) {
                     $this->createEndNode($node, $tokens);
                 }
             }
@@ -206,7 +206,7 @@ 
      * in comments
      */
     public function callbackUndoCommentSubst($matches) {
-        return '<!--' . strtr($matches[1], array('&amp;'=>'&','&lt;'=>'<')) . $matches[2];
+        return '<!--'.strtr($matches[1], array('&amp;'=>'&', '&lt;'=>'<')).$matches[2];
     }
 
     /**
@@ -214,7 +214,7 @@ 
      * callbackUndoCommentSubst doesn't clobber them
      */
     public function callbackArmorCommentEntities($matches) {
-        return '<!--' . str_replace('&', '&amp;', $matches[1]) . $matches[2];
+        return '<!--'.str_replace('&', '&amp;', $matches[1]).$matches[2];
     }
 
     /**
@@ -226,8 +226,8 @@ 
 
         if (!empty($def->doctype->dtdPublic) || !empty($def->doctype->dtdSystem)) {
             $ret .= '<!DOCTYPE html ';
-            if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "' . $def->doctype->dtdPublic . '" ';
-            if (!empty($def->doctype->dtdSystem)) $ret .= '"' . $def->doctype->dtdSystem . '" ';
+            if (!empty($def->doctype->dtdPublic)) $ret .= 'PUBLIC "'.$def->doctype->dtdPublic.'" ';
+            if (!empty($def->doctype->dtdSystem)) $ret .= '"'.$def->doctype->dtdSystem.'" ';
             $ret .= '>';
         }
 

classes/security/htmlpurifier/library/HTMLPurifier/Lexer/PH5P.php

Doc Comments +18 added lines

@@ -124,6 +124,9 @@ 
     const CHARACTR = 4;
     const EOF      = 5;
 
+    /**
+     * @param string $data
+     */
     public function __construct($data) {
 
         $this->data = $data;
@@ -143,12 +146,20 @@ 
         return $this->tree->save();
     }
 
+    /**
+     * @return string
+     */
     private function char() {
         return ($this->char < $this->EOF)
             ? $this->data[$this->char]
             : false;
     }
 
+    /**
+     * @param integer $s
+     *
+     * @return string
+     */
     private function character($s, $l = 0) {
         if($s + $l < $this->EOF) {
             if($l === 0) {
@@ -159,6 +170,10 @@ 
         }
     }
 
+    /**
+     * @param string $char_class
+     * @param integer $start
+     */
     private function characters($char_class, $start) {
         return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
     }
@@ -3767,6 +3782,9 @@ 
             return self::PHRASING;
     }
 
+    /**
+     * @param string[] $elements
+     */
     private function clearStackToTableContext($elements) {
         /* When the steps above require the UA to clear the stack back to a
         table context, it means that the UA must, while the current node is not

Indentation +2868 added lines, -2868 removed lines

@@ -12,26 +12,26 @@ 
 
 class HTMLPurifier_Lexer_PH5P extends HTMLPurifier_Lexer_DOMLex {
     
-    public function tokenizeHTML($html, $config, $context) {
-        $new_html = $this->normalize($html, $config, $context);
-        $new_html = $this->wrapHTML($new_html, $config, $context);
-        try {
-            $parser = new HTML5($new_html);
-            $doc = $parser->save();
-        } catch (DOMException $e) {
-            // Uh oh, it failed. Punt to DirectLex.
-            $lexer = new HTMLPurifier_Lexer_DirectLex();
-            $context->register('PH5PError', $e); // save the error, so we can detect it
-            return $lexer->tokenizeHTML($html, $config, $context); // use original HTML
-        }
-        $tokens = array();
-        $this->tokenizeDOM(
-            $doc->getElementsByTagName('html')->item(0)-> // <html>
-                  getElementsByTagName('body')->item(0)-> //   <body>
-                  getElementsByTagName('div')->item(0)    //     <div>
-            , $tokens);
-        return $tokens;
-    }
+	public function tokenizeHTML($html, $config, $context) {
+		$new_html = $this->normalize($html, $config, $context);
+		$new_html = $this->wrapHTML($new_html, $config, $context);
+		try {
+			$parser = new HTML5($new_html);
+			$doc = $parser->save();
+		} catch (DOMException $e) {
+			// Uh oh, it failed. Punt to DirectLex.
+			$lexer = new HTMLPurifier_Lexer_DirectLex();
+			$context->register('PH5PError', $e); // save the error, so we can detect it
+			return $lexer->tokenizeHTML($html, $config, $context); // use original HTML
+		}
+		$tokens = array();
+		$this->tokenizeDOM(
+			$doc->getElementsByTagName('html')->item(0)-> // <html>
+				  getElementsByTagName('body')->item(0)-> //   <body>
+				  getElementsByTagName('div')->item(0)    //     <div>
+			, $tokens);
+		return $tokens;
+	}
     
 }
 
@@ -61,145 +61,145 @@ 
 */
 
 class HTML5 {
-    private $data;
-    private $char;
-    private $EOF;
-    private $state;
-    private $tree;
-    private $token;
-    private $content_model;
-    private $escape = false;
-    private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
-    'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
-    'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
-    'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
-    'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
-    'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
-    'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
-    'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
-    'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
-    'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
-    'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
-    'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
-    'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
-    'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
-    'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
-    'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
-    'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
-    'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
-    'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
-    'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
-    'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
-    'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
-    'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
-    'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
-    'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
-    'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
-    'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
-    'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
-    'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
-    'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
-    'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
-    'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
-    'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
-    'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
-    'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
-    'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
-    'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
-    'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
-    'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
-    'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
-    'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
-    'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
-
-    const PCDATA    = 0;
-    const RCDATA    = 1;
-    const CDATA     = 2;
-    const PLAINTEXT = 3;
-
-    const DOCTYPE  = 0;
-    const STARTTAG = 1;
-    const ENDTAG   = 2;
-    const COMMENT  = 3;
-    const CHARACTR = 4;
-    const EOF      = 5;
-
-    public function __construct($data) {
-
-        $this->data = $data;
-        $this->char = -1;
-        $this->EOF  = strlen($data);
-        $this->tree = new HTML5TreeConstructer;
-        $this->content_model = self::PCDATA;
-
-        $this->state = 'data';
-
-        while($this->state !== null) {
-            $this->{$this->state.'State'}();
-        }
-    }
-
-    public function save() {
-        return $this->tree->save();
-    }
-
-    private function char() {
-        return ($this->char < $this->EOF)
-            ? $this->data[$this->char]
-            : false;
-    }
-
-    private function character($s, $l = 0) {
-        if($s + $l < $this->EOF) {
-            if($l === 0) {
-                return $this->data[$s];
-            } else {
-                return substr($this->data, $s, $l);
-            }
-        }
-    }
-
-    private function characters($char_class, $start) {
-        return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
-    }
-
-    private function dataState() {
-        // Consume the next input character
-        $this->char++;
-        $char = $this->char();
-
-        if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
-            /* U+0026 AMPERSAND (&)
+	private $data;
+	private $char;
+	private $EOF;
+	private $state;
+	private $tree;
+	private $token;
+	private $content_model;
+	private $escape = false;
+	private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
+	'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
+	'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
+	'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
+	'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
+	'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
+	'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
+	'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
+	'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
+	'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
+	'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
+	'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
+	'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
+	'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
+	'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
+	'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
+	'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
+	'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
+	'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
+	'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
+	'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
+	'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
+	'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
+	'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
+	'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
+	'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
+	'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
+	'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
+	'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
+	'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
+	'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
+	'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
+	'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
+	'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
+	'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
+	'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
+	'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
+	'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
+	'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
+	'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
+	'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
+	'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
+
+	const PCDATA    = 0;
+	const RCDATA    = 1;
+	const CDATA     = 2;
+	const PLAINTEXT = 3;
+
+	const DOCTYPE  = 0;
+	const STARTTAG = 1;
+	const ENDTAG   = 2;
+	const COMMENT  = 3;
+	const CHARACTR = 4;
+	const EOF      = 5;
+
+	public function __construct($data) {
+
+		$this->data = $data;
+		$this->char = -1;
+		$this->EOF  = strlen($data);
+		$this->tree = new HTML5TreeConstructer;
+		$this->content_model = self::PCDATA;
+
+		$this->state = 'data';
+
+		while($this->state !== null) {
+			$this->{$this->state.'State'}();
+		}
+	}
+
+	public function save() {
+		return $this->tree->save();
+	}
+
+	private function char() {
+		return ($this->char < $this->EOF)
+			? $this->data[$this->char]
+			: false;
+	}
+
+	private function character($s, $l = 0) {
+		if($s + $l < $this->EOF) {
+			if($l === 0) {
+				return $this->data[$s];
+			} else {
+				return substr($this->data, $s, $l);
+			}
+		}
+	}
+
+	private function characters($char_class, $start) {
+		return preg_replace('#^(['.$char_class.']+).*#s', '\\1', substr($this->data, $start));
+	}
+
+	private function dataState() {
+		// Consume the next input character
+		$this->char++;
+		$char = $this->char();
+
+		if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
+			/* U+0026 AMPERSAND (&)
             When the content model flag is set to one of the PCDATA or RCDATA
             states: switch to the entity data state. Otherwise: treat it as per
             the "anything else"    entry below. */
-            $this->state = 'entityData';
+			$this->state = 'entityData';
 
-        } elseif($char === '-') {
-            /* If the content model flag is set to either the RCDATA state or
+		} elseif($char === '-') {
+			/* If the content model flag is set to either the RCDATA state or
             the CDATA state, and the escape flag is false, and there are at
             least three characters before this one in the input stream, and the
             last four characters in the input stream, including this one, are
             U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
             and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */
-            if(($this->content_model === self::RCDATA || $this->content_model ===
-            self::CDATA) && $this->escape === false &&
-            $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') {
-                $this->escape = true;
-            }
+			if(($this->content_model === self::RCDATA || $this->content_model ===
+			self::CDATA) && $this->escape === false &&
+			$this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') {
+				$this->escape = true;
+			}
 
-            /* In any case, emit the input character as a character token. Stay
+			/* In any case, emit the input character as a character token. Stay
             in the data state. */
-            $this->emitToken(array(
-                'type' => self::CHARACTR,
-                'data' => $char
-            ));
-
-        /* U+003C LESS-THAN SIGN (<) */
-        } elseif($char === '<' && ($this->content_model === self::PCDATA ||
-        (($this->content_model === self::RCDATA ||
-        $this->content_model === self::CDATA) && $this->escape === false))) {
-            /* When the content model flag is set to the PCDATA state: switch
+			$this->emitToken(array(
+				'type' => self::CHARACTR,
+				'data' => $char
+			));
+
+		/* U+003C LESS-THAN SIGN (<) */
+		} elseif($char === '<' && ($this->content_model === self::PCDATA ||
+		(($this->content_model === self::RCDATA ||
+		$this->content_model === self::CDATA) && $this->escape === false))) {
+			/* When the content model flag is set to the PCDATA state: switch
             to the tag open state.
 
             When the content model flag is set to either the RCDATA state or
@@ -207,171 +207,171 @@ 
             open state.
 
             Otherwise: treat it as per the "anything else" entry below. */
-            $this->state = 'tagOpen';
+			$this->state = 'tagOpen';
 
-        /* U+003E GREATER-THAN SIGN (>) */
-        } elseif($char === '>') {
-            /* If the content model flag is set to either the RCDATA state or
+		/* U+003E GREATER-THAN SIGN (>) */
+		} elseif($char === '>') {
+			/* If the content model flag is set to either the RCDATA state or
             the CDATA state, and the escape flag is true, and the last three
             characters in the input stream including this one are U+002D
             HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"),
             set the escape flag to false. */
-            if(($this->content_model === self::RCDATA ||
-            $this->content_model === self::CDATA) && $this->escape === true &&
-            $this->character($this->char, 3) === '-->') {
-                $this->escape = false;
-            }
+			if(($this->content_model === self::RCDATA ||
+			$this->content_model === self::CDATA) && $this->escape === true &&
+			$this->character($this->char, 3) === '-->') {
+				$this->escape = false;
+			}
 
-            /* In any case, emit the input character as a character token.
+			/* In any case, emit the input character as a character token.
             Stay in the data state. */
-            $this->emitToken(array(
-                'type' => self::CHARACTR,
-                'data' => $char
-            ));
+			$this->emitToken(array(
+				'type' => self::CHARACTR,
+				'data' => $char
+			));
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Emit an end-of-file token. */
-            $this->EOF();
+			$this->EOF();
 
-        } elseif($this->content_model === self::PLAINTEXT) {
-            /* When the content model flag is set to the PLAINTEXT state
+		} elseif($this->content_model === self::PLAINTEXT) {
+			/* When the content model flag is set to the PLAINTEXT state
             THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
             the text and emit it as a character token. */
-            $this->emitToken(array(
-                'type' => self::CHARACTR,
-                'data' => substr($this->data, $this->char)
-            ));
+			$this->emitToken(array(
+				'type' => self::CHARACTR,
+				'data' => substr($this->data, $this->char)
+			));
 
-            $this->EOF();
+			$this->EOF();
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             THIS DIFFERS GREATLY FROM THE SPEC: Get as many character that
             otherwise would also be treated as a character token and emit it
             as a single character token. Stay in the data state. */
-            $len  = strcspn($this->data, '<&', $this->char);
-            $char = substr($this->data, $this->char, $len);
-            $this->char += $len - 1;
-
-            $this->emitToken(array(
-                'type' => self::CHARACTR,
-                'data' => $char
-            ));
-
-            $this->state = 'data';
-        }
-    }
-
-    private function entityDataState() {
-        // Attempt to consume an entity.
-        $entity = $this->entity();
-
-        // If nothing is returned, emit a U+0026 AMPERSAND character token.
-        // Otherwise, emit the character token that was returned.
-        $char = (!$entity) ? '&' : $entity;
-        $this->emitToken(array(
-            'type' => self::CHARACTR,
-            'data' => $char
-        ));
-
-        // Finally, switch to the data state.
-        $this->state = 'data';
-    }
-
-    private function tagOpenState() {
-        switch($this->content_model) {
-            case self::RCDATA:
-            case self::CDATA:
-                /* If the next input character is a U+002F SOLIDUS (/) character,
+			$len  = strcspn($this->data, '<&', $this->char);
+			$char = substr($this->data, $this->char, $len);
+			$this->char += $len - 1;
+
+			$this->emitToken(array(
+				'type' => self::CHARACTR,
+				'data' => $char
+			));
+
+			$this->state = 'data';
+		}
+	}
+
+	private function entityDataState() {
+		// Attempt to consume an entity.
+		$entity = $this->entity();
+
+		// If nothing is returned, emit a U+0026 AMPERSAND character token.
+		// Otherwise, emit the character token that was returned.
+		$char = (!$entity) ? '&' : $entity;
+		$this->emitToken(array(
+			'type' => self::CHARACTR,
+			'data' => $char
+		));
+
+		// Finally, switch to the data state.
+		$this->state = 'data';
+	}
+
+	private function tagOpenState() {
+		switch($this->content_model) {
+			case self::RCDATA:
+			case self::CDATA:
+				/* If the next input character is a U+002F SOLIDUS (/) character,
                 consume it and switch to the close tag open state. If the next
                 input character is not a U+002F SOLIDUS (/) character, emit a
                 U+003C LESS-THAN SIGN character token and switch to the data
                 state to process the next input character. */
-                if($this->character($this->char + 1) === '/') {
-                    $this->char++;
-                    $this->state = 'closeTagOpen';
-
-                } else {
-                    $this->emitToken(array(
-                        'type' => self::CHARACTR,
-                        'data' => '<'
-                    ));
-
-                    $this->state = 'data';
-                }
-            break;
-
-            case self::PCDATA:
-                // If the content model flag is set to the PCDATA state
-                // Consume the next input character:
-                $this->char++;
-                $char = $this->char();
-
-                if($char === '!') {
-                    /* U+0021 EXCLAMATION MARK (!)
+				if($this->character($this->char + 1) === '/') {
+					$this->char++;
+					$this->state = 'closeTagOpen';
+
+				} else {
+					$this->emitToken(array(
+						'type' => self::CHARACTR,
+						'data' => '<'
+					));
+
+					$this->state = 'data';
+				}
+			break;
+
+			case self::PCDATA:
+				// If the content model flag is set to the PCDATA state
+				// Consume the next input character:
+				$this->char++;
+				$char = $this->char();
+
+				if($char === '!') {
+					/* U+0021 EXCLAMATION MARK (!)
                     Switch to the markup declaration open state. */
-                    $this->state = 'markupDeclarationOpen';
+					$this->state = 'markupDeclarationOpen';
 
-                } elseif($char === '/') {
-                    /* U+002F SOLIDUS (/)
+				} elseif($char === '/') {
+					/* U+002F SOLIDUS (/)
                     Switch to the close tag open state. */
-                    $this->state = 'closeTagOpen';
+					$this->state = 'closeTagOpen';
 
-                } elseif(preg_match('/^[A-Za-z]$/', $char)) {
-                    /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
+				} elseif(preg_match('/^[A-Za-z]$/', $char)) {
+					/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
                     Create a new start tag token, set its tag name to the lowercase
                     version of the input character (add 0x0020 to the character's code
                     point), then switch to the tag name state. (Don't emit the token
                     yet; further details will be filled in before it is emitted.) */
-                    $this->token = array(
-                        'name'  => strtolower($char),
-                        'type'  => self::STARTTAG,
-                        'attr'  => array()
-                    );
+					$this->token = array(
+						'name'  => strtolower($char),
+						'type'  => self::STARTTAG,
+						'attr'  => array()
+					);
 
-                    $this->state = 'tagName';
+					$this->state = 'tagName';
 
-                } elseif($char === '>') {
-                    /* U+003E GREATER-THAN SIGN (>)
+				} elseif($char === '>') {
+					/* U+003E GREATER-THAN SIGN (>)
                     Parse error. Emit a U+003C LESS-THAN SIGN character token and a
                     U+003E GREATER-THAN SIGN character token. Switch to the data state. */
-                    $this->emitToken(array(
-                        'type' => self::CHARACTR,
-                        'data' => '<>'
-                    ));
+					$this->emitToken(array(
+						'type' => self::CHARACTR,
+						'data' => '<>'
+					));
 
-                    $this->state = 'data';
+					$this->state = 'data';
 
-                } elseif($char === '?') {
-                    /* U+003F QUESTION MARK (?)
+				} elseif($char === '?') {
+					/* U+003F QUESTION MARK (?)
                     Parse error. Switch to the bogus comment state. */
-                    $this->state = 'bogusComment';
+					$this->state = 'bogusComment';
 
-                } else {
-                    /* Anything else
+				} else {
+					/* Anything else
                     Parse error. Emit a U+003C LESS-THAN SIGN character token and
                     reconsume the current input character in the data state. */
-                    $this->emitToken(array(
-                        'type' => self::CHARACTR,
-                        'data' => '<'
-                    ));
-
-                    $this->char--;
-                    $this->state = 'data';
-                }
-            break;
-        }
-    }
-
-    private function closeTagOpenState() {
-        $next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
-        $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
-
-        if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
-        (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
-        $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
-            /* If the content model flag is set to the RCDATA or CDATA states then
+					$this->emitToken(array(
+						'type' => self::CHARACTR,
+						'data' => '<'
+					));
+
+					$this->char--;
+					$this->state = 'data';
+				}
+			break;
+		}
+	}
+
+	private function closeTagOpenState() {
+		$next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
+		$the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
+
+		if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
+		(!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
+		$this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
+			/* If the content model flag is set to the RCDATA or CDATA states then
             examine the next few characters. If they do not match the tag name of
             the last start tag token emitted (case insensitively), or if they do but
             they are not immediately followed by one of the following characters:
@@ -386,426 +386,426 @@ 
             ...then there is a parse error. Emit a U+003C LESS-THAN SIGN character
             token, a U+002F SOLIDUS character token, and switch to the data state
             to process the next input character. */
-            $this->emitToken(array(
-                'type' => self::CHARACTR,
-                'data' => '</'
-            ));
+			$this->emitToken(array(
+				'type' => self::CHARACTR,
+				'data' => '</'
+			));
 
-            $this->state = 'data';
+			$this->state = 'data';
 
-        } else {
-            /* Otherwise, if the content model flag is set to the PCDATA state,
+		} else {
+			/* Otherwise, if the content model flag is set to the PCDATA state,
             or if the next few characters do match that tag name, consume the
             next input character: */
-            $this->char++;
-            $char = $this->char();
+			$this->char++;
+			$char = $this->char();
 
-            if(preg_match('/^[A-Za-z]$/', $char)) {
-                /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
+			if(preg_match('/^[A-Za-z]$/', $char)) {
+				/* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
                 Create a new end tag token, set its tag name to the lowercase version
                 of the input character (add 0x0020 to the character's code point), then
                 switch to the tag name state. (Don't emit the token yet; further details
                 will be filled in before it is emitted.) */
-                $this->token = array(
-                    'name'  => strtolower($char),
-                    'type'  => self::ENDTAG
-                );
+				$this->token = array(
+					'name'  => strtolower($char),
+					'type'  => self::ENDTAG
+				);
 
-                $this->state = 'tagName';
+				$this->state = 'tagName';
 
-            } elseif($char === '>') {
-                /* U+003E GREATER-THAN SIGN (>)
+			} elseif($char === '>') {
+				/* U+003E GREATER-THAN SIGN (>)
                 Parse error. Switch to the data state. */
-                $this->state = 'data';
+				$this->state = 'data';
 
-            } elseif($this->char === $this->EOF) {
-                /* EOF
+			} elseif($this->char === $this->EOF) {
+				/* EOF
                 Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
                 SOLIDUS character token. Reconsume the EOF character in the data state. */
-                $this->emitToken(array(
-                    'type' => self::CHARACTR,
-                    'data' => '</'
-                ));
-
-                $this->char--;
-                $this->state = 'data';
-
-            } else {
-                /* Parse error. Switch to the bogus comment state. */
-                $this->state = 'bogusComment';
-            }
-        }
-    }
-
-    private function tagNameState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            /* U+0009 CHARACTER TABULATION
+				$this->emitToken(array(
+					'type' => self::CHARACTR,
+					'data' => '</'
+				));
+
+				$this->char--;
+				$this->state = 'data';
+
+			} else {
+				/* Parse error. Switch to the bogus comment state. */
+				$this->state = 'bogusComment';
+			}
+		}
+	}
+
+	private function tagNameState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			/* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
             U+000C FORM FEED (FF)
             U+0020 SPACE
             Switch to the before attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($char === '>') {
-            /* U+003E GREATER-THAN SIGN (>)
+		} elseif($char === '>') {
+			/* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
-            $this->emitToken($this->token);
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->state = 'data';
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
-            $this->emitToken($this->token);
+			$this->emitToken($this->token);
 
-            $this->char--;
-            $this->state = 'data';
+			$this->char--;
+			$this->state = 'data';
 
-        } elseif($char === '/') {
-            /* U+002F SOLIDUS (/)
+		} elseif($char === '/') {
+			/* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Switch to the before
             attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Append the current input character to the current tag token's tag name.
             Stay in the tag name state. */
-            $this->token['name'] .= strtolower($char);
-            $this->state = 'tagName';
-        }
-    }
-
-    private function beforeAttributeNameState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            /* U+0009 CHARACTER TABULATION
+			$this->token['name'] .= strtolower($char);
+			$this->state = 'tagName';
+		}
+	}
+
+	private function beforeAttributeNameState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			/* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
             U+000C FORM FEED (FF)
             U+0020 SPACE
             Stay in the before attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($char === '>') {
-            /* U+003E GREATER-THAN SIGN (>)
+		} elseif($char === '>') {
+			/* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
-            $this->emitToken($this->token);
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->state = 'data';
 
-        } elseif($char === '/') {
-            /* U+002F SOLIDUS (/)
+		} elseif($char === '/') {
+			/* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Stay in the before
             attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
-            $this->emitToken($this->token);
+			$this->emitToken($this->token);
 
-            $this->char--;
-            $this->state = 'data';
+			$this->char--;
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Start a new attribute in the current tag token. Set that attribute's
             name to the current input character, and its value to the empty string.
             Switch to the attribute name state. */
-            $this->token['attr'][] = array(
-                'name'  => strtolower($char),
-                'value' => null
-            );
-
-            $this->state = 'attributeName';
-        }
-    }
-
-    private function attributeNameState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            /* U+0009 CHARACTER TABULATION
+			$this->token['attr'][] = array(
+				'name'  => strtolower($char),
+				'value' => null
+			);
+
+			$this->state = 'attributeName';
+		}
+	}
+
+	private function attributeNameState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			/* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
             U+000C FORM FEED (FF)
             U+0020 SPACE
             Stay in the before attribute name state. */
-            $this->state = 'afterAttributeName';
+			$this->state = 'afterAttributeName';
 
-        } elseif($char === '=') {
-            /* U+003D EQUALS SIGN (=)
+		} elseif($char === '=') {
+			/* U+003D EQUALS SIGN (=)
             Switch to the before attribute value state. */
-            $this->state = 'beforeAttributeValue';
+			$this->state = 'beforeAttributeValue';
 
-        } elseif($char === '>') {
-            /* U+003E GREATER-THAN SIGN (>)
+		} elseif($char === '>') {
+			/* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
-            $this->emitToken($this->token);
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->state = 'data';
 
-        } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
-            /* U+002F SOLIDUS (/)
+		} elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+			/* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Switch to the before
             attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
-            $this->emitToken($this->token);
+			$this->emitToken($this->token);
 
-            $this->char--;
-            $this->state = 'data';
+			$this->char--;
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Append the current input character to the current attribute's name.
             Stay in the attribute name state. */
-            $last = count($this->token['attr']) - 1;
-            $this->token['attr'][$last]['name'] .= strtolower($char);
+			$last = count($this->token['attr']) - 1;
+			$this->token['attr'][$last]['name'] .= strtolower($char);
 
-            $this->state = 'attributeName';
-        }
-    }
+			$this->state = 'attributeName';
+		}
+	}
 
-    private function afterAttributeNameState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
+	private function afterAttributeNameState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            /* U+0009 CHARACTER TABULATION
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			/* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
             U+000C FORM FEED (FF)
             U+0020 SPACE
             Stay in the after attribute name state. */
-            $this->state = 'afterAttributeName';
+			$this->state = 'afterAttributeName';
 
-        } elseif($char === '=') {
-            /* U+003D EQUALS SIGN (=)
+		} elseif($char === '=') {
+			/* U+003D EQUALS SIGN (=)
             Switch to the before attribute value state. */
-            $this->state = 'beforeAttributeValue';
+			$this->state = 'beforeAttributeValue';
 
-        } elseif($char === '>') {
-            /* U+003E GREATER-THAN SIGN (>)
+		} elseif($char === '>') {
+			/* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
-            $this->emitToken($this->token);
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->state = 'data';
 
-        } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
-            /* U+002F SOLIDUS (/)
+		} elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+			/* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Switch to the
             before attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
-            $this->emitToken($this->token);
+			$this->emitToken($this->token);
 
-            $this->char--;
-            $this->state = 'data';
+			$this->char--;
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Start a new attribute in the current tag token. Set that attribute's
             name to the current input character, and its value to the empty string.
             Switch to the attribute name state. */
-            $this->token['attr'][] = array(
-                'name'  => strtolower($char),
-                'value' => null
-            );
-
-            $this->state = 'attributeName';
-        }
-    }
-
-    private function beforeAttributeValueState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            /* U+0009 CHARACTER TABULATION
+			$this->token['attr'][] = array(
+				'name'  => strtolower($char),
+				'value' => null
+			);
+
+			$this->state = 'attributeName';
+		}
+	}
+
+	private function beforeAttributeValueState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			/* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
             U+000C FORM FEED (FF)
             U+0020 SPACE
             Stay in the before attribute value state. */
-            $this->state = 'beforeAttributeValue';
+			$this->state = 'beforeAttributeValue';
 
-        } elseif($char === '"') {
-            /* U+0022 QUOTATION MARK (")
+		} elseif($char === '"') {
+			/* U+0022 QUOTATION MARK (")
             Switch to the attribute value (double-quoted) state. */
-            $this->state = 'attributeValueDoubleQuoted';
+			$this->state = 'attributeValueDoubleQuoted';
 
-        } elseif($char === '&') {
-            /* U+0026 AMPERSAND (&)
+		} elseif($char === '&') {
+			/* U+0026 AMPERSAND (&)
             Switch to the attribute value (unquoted) state and reconsume
             this input character. */
-            $this->char--;
-            $this->state = 'attributeValueUnquoted';
+			$this->char--;
+			$this->state = 'attributeValueUnquoted';
 
-        } elseif($char === '\'') {
-            /* U+0027 APOSTROPHE (')
+		} elseif($char === '\'') {
+			/* U+0027 APOSTROPHE (')
             Switch to the attribute value (single-quoted) state. */
-            $this->state = 'attributeValueSingleQuoted';
+			$this->state = 'attributeValueSingleQuoted';
 
-        } elseif($char === '>') {
-            /* U+003E GREATER-THAN SIGN (>)
+		} elseif($char === '>') {
+			/* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
-            $this->emitToken($this->token);
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Append the current input character to the current attribute's value.
             Switch to the attribute value (unquoted) state. */
-            $last = count($this->token['attr']) - 1;
-            $this->token['attr'][$last]['value'] .= $char;
+			$last = count($this->token['attr']) - 1;
+			$this->token['attr'][$last]['value'] .= $char;
 
-            $this->state = 'attributeValueUnquoted';
-        }
-    }
+			$this->state = 'attributeValueUnquoted';
+		}
+	}
 
-    private function attributeValueDoubleQuotedState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
+	private function attributeValueDoubleQuotedState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
 
-        if($char === '"') {
-            /* U+0022 QUOTATION MARK (")
+		if($char === '"') {
+			/* U+0022 QUOTATION MARK (")
             Switch to the before attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($char === '&') {
-            /* U+0026 AMPERSAND (&)
+		} elseif($char === '&') {
+			/* U+0026 AMPERSAND (&)
             Switch to the entity in attribute value state. */
-            $this->entityInAttributeValueState('double');
+			$this->entityInAttributeValueState('double');
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Parse error. Emit the current tag token. Reconsume the character
             in the data state. */
-            $this->emitToken($this->token);
+			$this->emitToken($this->token);
 
-            $this->char--;
-            $this->state = 'data';
+			$this->char--;
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Append the current input character to the current attribute's value.
             Stay in the attribute value (double-quoted) state. */
-            $last = count($this->token['attr']) - 1;
-            $this->token['attr'][$last]['value'] .= $char;
+			$last = count($this->token['attr']) - 1;
+			$this->token['attr'][$last]['value'] .= $char;
 
-            $this->state = 'attributeValueDoubleQuoted';
-        }
-    }
+			$this->state = 'attributeValueDoubleQuoted';
+		}
+	}
 
-    private function attributeValueSingleQuotedState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
+	private function attributeValueSingleQuotedState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
 
-        if($char === '\'') {
-            /* U+0022 QUOTATION MARK (')
+		if($char === '\'') {
+			/* U+0022 QUOTATION MARK (')
             Switch to the before attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($char === '&') {
-            /* U+0026 AMPERSAND (&)
+		} elseif($char === '&') {
+			/* U+0026 AMPERSAND (&)
             Switch to the entity in attribute value state. */
-            $this->entityInAttributeValueState('single');
+			$this->entityInAttributeValueState('single');
 
-        } elseif($this->char === $this->EOF) {
-            /* EOF
+		} elseif($this->char === $this->EOF) {
+			/* EOF
             Parse error. Emit the current tag token. Reconsume the character
             in the data state. */
-            $this->emitToken($this->token);
+			$this->emitToken($this->token);
 
-            $this->char--;
-            $this->state = 'data';
+			$this->char--;
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Append the current input character to the current attribute's value.
             Stay in the attribute value (single-quoted) state. */
-            $last = count($this->token['attr']) - 1;
-            $this->token['attr'][$last]['value'] .= $char;
+			$last = count($this->token['attr']) - 1;
+			$this->token['attr'][$last]['value'] .= $char;
 
-            $this->state = 'attributeValueSingleQuoted';
-        }
-    }
+			$this->state = 'attributeValueSingleQuoted';
+		}
+	}
 
-    private function attributeValueUnquotedState() {
-        // Consume the next input character:
-        $this->char++;
-        $char = $this->character($this->char);
+	private function attributeValueUnquotedState() {
+		// Consume the next input character:
+		$this->char++;
+		$char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            /* U+0009 CHARACTER TABULATION
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			/* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
             U+000C FORM FEED (FF)
             U+0020 SPACE
             Switch to the before attribute name state. */
-            $this->state = 'beforeAttributeName';
+			$this->state = 'beforeAttributeName';
 
-        } elseif($char === '&') {
-            /* U+0026 AMPERSAND (&)
+		} elseif($char === '&') {
+			/* U+0026 AMPERSAND (&)
             Switch to the entity in attribute value state. */
-            $this->entityInAttributeValueState();
+			$this->entityInAttributeValueState();
 
-        } elseif($char === '>') {
-            /* U+003E GREATER-THAN SIGN (>)
+		} elseif($char === '>') {
+			/* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
-            $this->emitToken($this->token);
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->state = 'data';
 
-        } else {
-            /* Anything else
+		} else {
+			/* Anything else
             Append the current input character to the current attribute's value.
             Stay in the attribute value (unquoted) state. */
-            $last = count($this->token['attr']) - 1;
-            $this->token['attr'][$last]['value'] .= $char;
-
-            $this->state = 'attributeValueUnquoted';
-        }
-    }
-
-    private function entityInAttributeValueState() {
-        // Attempt to consume an entity.
-        $entity = $this->entity();
-
-        // If nothing is returned, append a U+0026 AMPERSAND character to the
-        // current attribute's value. Otherwise, emit the character token that
-        // was returned.
-        $char = (!$entity)
-            ? '&'
-            : $entity;
-
-        $last = count($this->token['attr']) - 1;
-        $this->token['attr'][$last]['value'] .= $char;
-    }
-
-    private function bogusCommentState() {
-        /* Consume every character up to the first U+003E GREATER-THAN SIGN
+			$last = count($this->token['attr']) - 1;
+			$this->token['attr'][$last]['value'] .= $char;
+
+			$this->state = 'attributeValueUnquoted';
+		}
+	}
+
+	private function entityInAttributeValueState() {
+		// Attempt to consume an entity.
+		$entity = $this->entity();
+
+		// If nothing is returned, append a U+0026 AMPERSAND character to the
+		// current attribute's value. Otherwise, emit the character token that
+		// was returned.
+		$char = (!$entity)
+			? '&'
+			: $entity;
+
+		$last = count($this->token['attr']) - 1;
+		$this->token['attr'][$last]['value'] .= $char;
+	}
+
+	private function bogusCommentState() {
+		/* Consume every character up to the first U+003E GREATER-THAN SIGN
         character (>) or the end of the file (EOF), whichever comes first. Emit
         a comment token whose data is the concatenation of all the characters
         starting from and including the character that caused the state machine
@@ -813,446 +813,446 @@ 
         consumed character before the U+003E character, if any, or up to the
         end of the file otherwise. (If the comment was started by the end of
         the file (EOF), the token is empty.) */
-        $data = $this->characters('^>', $this->char);
-        $this->emitToken(array(
-            'data' => $data,
-            'type' => self::COMMENT
-        ));
+		$data = $this->characters('^>', $this->char);
+		$this->emitToken(array(
+			'data' => $data,
+			'type' => self::COMMENT
+		));
 
-        $this->char += strlen($data);
+		$this->char += strlen($data);
 
-        /* Switch to the data state. */
-        $this->state = 'data';
+		/* Switch to the data state. */
+		$this->state = 'data';
 
-        /* If the end of the file was reached, reconsume the EOF character. */
-        if($this->char === $this->EOF) {
-            $this->char = $this->EOF - 1;
-        }
-    }
+		/* If the end of the file was reached, reconsume the EOF character. */
+		if($this->char === $this->EOF) {
+			$this->char = $this->EOF - 1;
+		}
+	}
 
-    private function markupDeclarationOpenState() {
-        /* If the next two characters are both U+002D HYPHEN-MINUS (-)
+	private function markupDeclarationOpenState() {
+		/* If the next two characters are both U+002D HYPHEN-MINUS (-)
         characters, consume those two characters, create a comment token whose
         data is the empty string, and switch to the comment state. */
-        if($this->character($this->char + 1, 2) === '--') {
-            $this->char += 2;
-            $this->state = 'comment';
-            $this->token = array(
-                'data' => null,
-                'type' => self::COMMENT
-            );
-
-        /* Otherwise if the next seven chacacters are a case-insensitive match
+		if($this->character($this->char + 1, 2) === '--') {
+			$this->char += 2;
+			$this->state = 'comment';
+			$this->token = array(
+				'data' => null,
+				'type' => self::COMMENT
+			);
+
+		/* Otherwise if the next seven chacacters are a case-insensitive match
         for the word "DOCTYPE", then consume those characters and switch to the
         DOCTYPE state. */
-        } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
-            $this->char += 7;
-            $this->state = 'doctype';
+		} elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
+			$this->char += 7;
+			$this->state = 'doctype';
 
-        /* Otherwise, is is a parse error. Switch to the bogus comment state.
+		/* Otherwise, is is a parse error. Switch to the bogus comment state.
         The next character that is consumed, if any, is the first character
         that will be in the comment. */
-        } else {
-            $this->char++;
-            $this->state = 'bogusComment';
-        }
-    }
-
-    private function commentState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        /* U+002D HYPHEN-MINUS (-) */
-        if($char === '-') {
-            /* Switch to the comment dash state  */
-            $this->state = 'commentDash';
-
-        /* EOF */
-        } elseif($this->char === $this->EOF) {
-            /* Parse error. Emit the comment token. Reconsume the EOF character
+		} else {
+			$this->char++;
+			$this->state = 'bogusComment';
+		}
+	}
+
+	private function commentState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		/* U+002D HYPHEN-MINUS (-) */
+		if($char === '-') {
+			/* Switch to the comment dash state  */
+			$this->state = 'commentDash';
+
+		/* EOF */
+		} elseif($this->char === $this->EOF) {
+			/* Parse error. Emit the comment token. Reconsume the EOF character
             in the data state. */
-            $this->emitToken($this->token);
-            $this->char--;
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->char--;
+			$this->state = 'data';
 
-        /* Anything else */
-        } else {
-            /* Append the input character to the comment token's data. Stay in
+		/* Anything else */
+		} else {
+			/* Append the input character to the comment token's data. Stay in
             the comment state. */
-            $this->token['data'] .= $char;
-        }
-    }
-
-    private function commentDashState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        /* U+002D HYPHEN-MINUS (-) */
-        if($char === '-') {
-            /* Switch to the comment end state  */
-            $this->state = 'commentEnd';
-
-        /* EOF */
-        } elseif($this->char === $this->EOF) {
-            /* Parse error. Emit the comment token. Reconsume the EOF character
+			$this->token['data'] .= $char;
+		}
+	}
+
+	private function commentDashState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		/* U+002D HYPHEN-MINUS (-) */
+		if($char === '-') {
+			/* Switch to the comment end state  */
+			$this->state = 'commentEnd';
+
+		/* EOF */
+		} elseif($this->char === $this->EOF) {
+			/* Parse error. Emit the comment token. Reconsume the EOF character
             in the data state. */
-            $this->emitToken($this->token);
-            $this->char--;
-            $this->state = 'data';
+			$this->emitToken($this->token);
+			$this->char--;
+			$this->state = 'data';
 
-        /* Anything else */
-        } else {
-            /* Append a U+002D HYPHEN-MINUS (-) character and the input
+		/* Anything else */
+		} else {
+			/* Append a U+002D HYPHEN-MINUS (-) character and the input
             character to the comment token's data. Switch to the comment state. */
-            $this->token['data'] .= '-'.$char;
-            $this->state = 'comment';
-        }
-    }
-
-    private function commentEndState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        if($char === '>') {
-            $this->emitToken($this->token);
-            $this->state = 'data';
-
-        } elseif($char === '-') {
-            $this->token['data'] .= '-';
-
-        } elseif($this->char === $this->EOF) {
-            $this->emitToken($this->token);
-            $this->char--;
-            $this->state = 'data';
-
-        } else {
-            $this->token['data'] .= '--'.$char;
-            $this->state = 'comment';
-        }
-    }
-
-    private function doctypeState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            $this->state = 'beforeDoctypeName';
-
-        } else {
-            $this->char--;
-            $this->state = 'beforeDoctypeName';
-        }
-    }
-
-    private function beforeDoctypeNameState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            // Stay in the before DOCTYPE name state.
-
-        } elseif(preg_match('/^[a-z]$/', $char)) {
-            $this->token = array(
-                'name' => strtoupper($char),
-                'type' => self::DOCTYPE,
-                'error' => true
-            );
-
-            $this->state = 'doctypeName';
-
-        } elseif($char === '>') {
-            $this->emitToken(array(
-                'name' => null,
-                'type' => self::DOCTYPE,
-                'error' => true
-            ));
-
-            $this->state = 'data';
-
-        } elseif($this->char === $this->EOF) {
-            $this->emitToken(array(
-                'name' => null,
-                'type' => self::DOCTYPE,
-                'error' => true
-            ));
-
-            $this->char--;
-            $this->state = 'data';
-
-        } else {
-            $this->token = array(
-                'name' => $char,
-                'type' => self::DOCTYPE,
-                'error' => true
-            );
-
-            $this->state = 'doctypeName';
-        }
-    }
-
-    private function doctypeNameState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            $this->state = 'AfterDoctypeName';
-
-        } elseif($char === '>') {
-            $this->emitToken($this->token);
-            $this->state = 'data';
-
-        } elseif(preg_match('/^[a-z]$/', $char)) {
-            $this->token['name'] .= strtoupper($char);
-
-        } elseif($this->char === $this->EOF) {
-            $this->emitToken($this->token);
-            $this->char--;
-            $this->state = 'data';
-
-        } else {
-            $this->token['name'] .= $char;
-        }
-
-        $this->token['error'] = ($this->token['name'] === 'HTML')
-            ? false
-            : true;
-    }
-
-    private function afterDoctypeNameState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
-            // Stay in the DOCTYPE name state.
-
-        } elseif($char === '>') {
-            $this->emitToken($this->token);
-            $this->state = 'data';
-
-        } elseif($this->char === $this->EOF) {
-            $this->emitToken($this->token);
-            $this->char--;
-            $this->state = 'data';
-
-        } else {
-            $this->token['error'] = true;
-            $this->state = 'bogusDoctype';
-        }
-    }
-
-    private function bogusDoctypeState() {
-        /* Consume the next input character: */
-        $this->char++;
-        $char = $this->char();
-
-        if($char === '>') {
-            $this->emitToken($this->token);
-            $this->state = 'data';
-
-        } elseif($this->char === $this->EOF) {
-            $this->emitToken($this->token);
-            $this->char--;
-            $this->state = 'data';
-
-        } else {
-            // Stay in the bogus DOCTYPE state.
-        }
-    }
-
-    private function entity() {
-        $start = $this->char;
-
-        // This section defines how to consume an entity. This definition is
-        // used when parsing entities in text and in attributes.
-
-        // The behaviour depends on the identity of the next character (the
-        // one immediately after the U+0026 AMPERSAND character): 
-
-        switch($this->character($this->char + 1)) {
-            // U+0023 NUMBER SIGN (#)
-            case '#':
-
-                // The behaviour further depends on the character after the
-                // U+0023 NUMBER SIGN:
-                switch($this->character($this->char + 1)) {
-                    // U+0078 LATIN SMALL LETTER X
-                    // U+0058 LATIN CAPITAL LETTER X
-                    case 'x':
-                    case 'X':
-                        // Follow the steps below, but using the range of
-                        // characters U+0030 DIGIT ZERO through to U+0039 DIGIT
-                        // NINE, U+0061 LATIN SMALL LETTER A through to U+0066
-                        // LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
-                        // A, through to U+0046 LATIN CAPITAL LETTER F (in other
-                        // words, 0-9, A-F, a-f).
-                        $char = 1;
-                        $char_class = '0-9A-Fa-f';
-                    break;
-
-                    // Anything else
-                    default:
-                        // Follow the steps below, but using the range of
-                        // characters U+0030 DIGIT ZERO through to U+0039 DIGIT
-                        // NINE (i.e. just 0-9).
-                        $char = 0;
-                        $char_class = '0-9';
-                    break;
-                }
-
-                // Consume as many characters as match the range of characters
-                // given above.
-                $this->char++;
-                $e_name = $this->characters($char_class, $this->char + $char + 1);
-                $entity = $this->character($start, $this->char);
-                $cond = strlen($e_name) > 0;
-
-                // The rest of the parsing happens bellow.
-            break;
-
-            // Anything else
-            default:
-                // Consume the maximum number of characters possible, with the
-                // consumed characters case-sensitively matching one of the
-                // identifiers in the first column of the entities table.
-                $e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
-                $len = strlen($e_name);
-
-                for($c = 1; $c <= $len; $c++) {
-                    $id = substr($e_name, 0, $c);
-                    $this->char++;
-
-                    if(in_array($id, $this->entities)) {
-                        if ($e_name[$c-1] !== ';') {
-                            if ($c < $len && $e_name[$c] == ';') {
-                                $this->char++; // consume extra semicolon
-                            }
-                        }
-                        $entity = $id;
-                        break;
-                    }
-                }
-
-                $cond = isset($entity);
-                // The rest of the parsing happens bellow.
-            break;
-        }
-
-        if(!$cond) {
-            // If no match can be made, then this is a parse error. No
-            // characters are consumed, and nothing is returned.
-            $this->char = $start;
-            return false;
-        }
-
-        // Return a character token for the character corresponding to the
-        // entity name (as given by the second column of the entities table).
-        return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8');
-    }
-
-    private function emitToken($token) {
-        $emit = $this->tree->emitToken($token);
-
-        if(is_int($emit)) {
-            $this->content_model = $emit;
-
-        } elseif($token['type'] === self::ENDTAG) {
-            $this->content_model = self::PCDATA;
-        }
-    }
-
-    private function EOF() {
-        $this->state = null;
-        $this->tree->emitToken(array(
-            'type' => self::EOF
-        ));
-    }
+			$this->token['data'] .= '-'.$char;
+			$this->state = 'comment';
+		}
+	}
+
+	private function commentEndState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		if($char === '>') {
+			$this->emitToken($this->token);
+			$this->state = 'data';
+
+		} elseif($char === '-') {
+			$this->token['data'] .= '-';
+
+		} elseif($this->char === $this->EOF) {
+			$this->emitToken($this->token);
+			$this->char--;
+			$this->state = 'data';
+
+		} else {
+			$this->token['data'] .= '--'.$char;
+			$this->state = 'comment';
+		}
+	}
+
+	private function doctypeState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			$this->state = 'beforeDoctypeName';
+
+		} else {
+			$this->char--;
+			$this->state = 'beforeDoctypeName';
+		}
+	}
+
+	private function beforeDoctypeNameState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			// Stay in the before DOCTYPE name state.
+
+		} elseif(preg_match('/^[a-z]$/', $char)) {
+			$this->token = array(
+				'name' => strtoupper($char),
+				'type' => self::DOCTYPE,
+				'error' => true
+			);
+
+			$this->state = 'doctypeName';
+
+		} elseif($char === '>') {
+			$this->emitToken(array(
+				'name' => null,
+				'type' => self::DOCTYPE,
+				'error' => true
+			));
+
+			$this->state = 'data';
+
+		} elseif($this->char === $this->EOF) {
+			$this->emitToken(array(
+				'name' => null,
+				'type' => self::DOCTYPE,
+				'error' => true
+			));
+
+			$this->char--;
+			$this->state = 'data';
+
+		} else {
+			$this->token = array(
+				'name' => $char,
+				'type' => self::DOCTYPE,
+				'error' => true
+			);
+
+			$this->state = 'doctypeName';
+		}
+	}
+
+	private function doctypeNameState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			$this->state = 'AfterDoctypeName';
+
+		} elseif($char === '>') {
+			$this->emitToken($this->token);
+			$this->state = 'data';
+
+		} elseif(preg_match('/^[a-z]$/', $char)) {
+			$this->token['name'] .= strtoupper($char);
+
+		} elseif($this->char === $this->EOF) {
+			$this->emitToken($this->token);
+			$this->char--;
+			$this->state = 'data';
+
+		} else {
+			$this->token['name'] .= $char;
+		}
+
+		$this->token['error'] = ($this->token['name'] === 'HTML')
+			? false
+			: true;
+	}
+
+	private function afterDoctypeNameState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+			// Stay in the DOCTYPE name state.
+
+		} elseif($char === '>') {
+			$this->emitToken($this->token);
+			$this->state = 'data';
+
+		} elseif($this->char === $this->EOF) {
+			$this->emitToken($this->token);
+			$this->char--;
+			$this->state = 'data';
+
+		} else {
+			$this->token['error'] = true;
+			$this->state = 'bogusDoctype';
+		}
+	}
+
+	private function bogusDoctypeState() {
+		/* Consume the next input character: */
+		$this->char++;
+		$char = $this->char();
+
+		if($char === '>') {
+			$this->emitToken($this->token);
+			$this->state = 'data';
+
+		} elseif($this->char === $this->EOF) {
+			$this->emitToken($this->token);
+			$this->char--;
+			$this->state = 'data';
+
+		} else {
+			// Stay in the bogus DOCTYPE state.
+		}
+	}
+
+	private function entity() {
+		$start = $this->char;
+
+		// This section defines how to consume an entity. This definition is
+		// used when parsing entities in text and in attributes.
+
+		// The behaviour depends on the identity of the next character (the
+		// one immediately after the U+0026 AMPERSAND character): 
+
+		switch($this->character($this->char + 1)) {
+			// U+0023 NUMBER SIGN (#)
+			case '#':
+
+				// The behaviour further depends on the character after the
+				// U+0023 NUMBER SIGN:
+				switch($this->character($this->char + 1)) {
+					// U+0078 LATIN SMALL LETTER X
+					// U+0058 LATIN CAPITAL LETTER X
+					case 'x':
+					case 'X':
+						// Follow the steps below, but using the range of
+						// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
+						// NINE, U+0061 LATIN SMALL LETTER A through to U+0066
+						// LATIN SMALL LETTER F, and U+0041 LATIN CAPITAL LETTER
+						// A, through to U+0046 LATIN CAPITAL LETTER F (in other
+						// words, 0-9, A-F, a-f).
+						$char = 1;
+						$char_class = '0-9A-Fa-f';
+					break;
+
+					// Anything else
+					default:
+						// Follow the steps below, but using the range of
+						// characters U+0030 DIGIT ZERO through to U+0039 DIGIT
+						// NINE (i.e. just 0-9).
+						$char = 0;
+						$char_class = '0-9';
+					break;
+				}
+
+				// Consume as many characters as match the range of characters
+				// given above.
+				$this->char++;
+				$e_name = $this->characters($char_class, $this->char + $char + 1);
+				$entity = $this->character($start, $this->char);
+				$cond = strlen($e_name) > 0;
+
+				// The rest of the parsing happens bellow.
+			break;
+
+			// Anything else
+			default:
+				// Consume the maximum number of characters possible, with the
+				// consumed characters case-sensitively matching one of the
+				// identifiers in the first column of the entities table.
+				$e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
+				$len = strlen($e_name);
+
+				for($c = 1; $c <= $len; $c++) {
+					$id = substr($e_name, 0, $c);
+					$this->char++;
+
+					if(in_array($id, $this->entities)) {
+						if ($e_name[$c-1] !== ';') {
+							if ($c < $len && $e_name[$c] == ';') {
+								$this->char++; // consume extra semicolon
+							}
+						}
+						$entity = $id;
+						break;
+					}
+				}
+
+				$cond = isset($entity);
+				// The rest of the parsing happens bellow.
+			break;
+		}
+
+		if(!$cond) {
+			// If no match can be made, then this is a parse error. No
+			// characters are consumed, and nothing is returned.
+			$this->char = $start;
+			return false;
+		}
+
+		// Return a character token for the character corresponding to the
+		// entity name (as given by the second column of the entities table).
+		return html_entity_decode('&'.$entity.';', ENT_QUOTES, 'UTF-8');
+	}
+
+	private function emitToken($token) {
+		$emit = $this->tree->emitToken($token);
+
+		if(is_int($emit)) {
+			$this->content_model = $emit;
+
+		} elseif($token['type'] === self::ENDTAG) {
+			$this->content_model = self::PCDATA;
+		}
+	}
+
+	private function EOF() {
+		$this->state = null;
+		$this->tree->emitToken(array(
+			'type' => self::EOF
+		));
+	}
 }
 
 class HTML5TreeConstructer {
-    public $stack = array();
-
-    private $phase;
-    private $mode;
-    private $dom;
-    private $foster_parent = null;
-    private $a_formatting  = array();
-
-    private $head_pointer = null;
-    private $form_pointer = null;
-
-    private $scoping = array('button','caption','html','marquee','object','table','td','th');
-    private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
-    private $special = array('address','area','base','basefont','bgsound',
-    'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
-    'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
-    'h6','head','hr','iframe','image','img','input','isindex','li','link',
-    'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
-    'option','p','param','plaintext','pre','script','select','spacer','style',
-    'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
-
-    // The different phases.
-    const INIT_PHASE = 0;
-    const ROOT_PHASE = 1;
-    const MAIN_PHASE = 2;
-    const END_PHASE  = 3;
-
-    // The different insertion modes for the main phase.
-    const BEFOR_HEAD = 0;
-    const IN_HEAD    = 1;
-    const AFTER_HEAD = 2;
-    const IN_BODY    = 3;
-    const IN_TABLE   = 4;
-    const IN_CAPTION = 5;
-    const IN_CGROUP  = 6;
-    const IN_TBODY   = 7;
-    const IN_ROW     = 8;
-    const IN_CELL    = 9;
-    const IN_SELECT  = 10;
-    const AFTER_BODY = 11;
-    const IN_FRAME   = 12;
-    const AFTR_FRAME = 13;
-
-    // The different types of elements.
-    const SPECIAL    = 0;
-    const SCOPING    = 1;
-    const FORMATTING = 2;
-    const PHRASING   = 3;
-
-    const MARKER     = 0;
-
-    public function __construct() {
-        $this->phase = self::INIT_PHASE;
-        $this->mode = self::BEFOR_HEAD;
-        $this->dom = new DOMDocument;
-
-        $this->dom->encoding = 'UTF-8';
-        $this->dom->preserveWhiteSpace = true;
-        $this->dom->substituteEntities = true;
-        $this->dom->strictErrorChecking = false;
-    }
-
-    // Process tag tokens
-    public function emitToken($token) {
-        switch($this->phase) {
-            case self::INIT_PHASE: return $this->initPhase($token); break;
-            case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
-            case self::MAIN_PHASE: return $this->mainPhase($token); break;
-            case self::END_PHASE : return $this->trailingEndPhase($token); break;
-        }
-    }
-
-    private function initPhase($token) {
-        /* Initially, the tree construction stage must handle each token
+	public $stack = array();
+
+	private $phase;
+	private $mode;
+	private $dom;
+	private $foster_parent = null;
+	private $a_formatting  = array();
+
+	private $head_pointer = null;
+	private $form_pointer = null;
+
+	private $scoping = array('button','caption','html','marquee','object','table','td','th');
+	private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
+	private $special = array('address','area','base','basefont','bgsound',
+	'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
+	'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
+	'h6','head','hr','iframe','image','img','input','isindex','li','link',
+	'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
+	'option','p','param','plaintext','pre','script','select','spacer','style',
+	'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
+
+	// The different phases.
+	const INIT_PHASE = 0;
+	const ROOT_PHASE = 1;
+	const MAIN_PHASE = 2;
+	const END_PHASE  = 3;
+
+	// The different insertion modes for the main phase.
+	const BEFOR_HEAD = 0;
+	const IN_HEAD    = 1;
+	const AFTER_HEAD = 2;
+	const IN_BODY    = 3;
+	const IN_TABLE   = 4;
+	const IN_CAPTION = 5;
+	const IN_CGROUP  = 6;
+	const IN_TBODY   = 7;
+	const IN_ROW     = 8;
+	const IN_CELL    = 9;
+	const IN_SELECT  = 10;
+	const AFTER_BODY = 11;
+	const IN_FRAME   = 12;
+	const AFTR_FRAME = 13;
+
+	// The different types of elements.
+	const SPECIAL    = 0;
+	const SCOPING    = 1;
+	const FORMATTING = 2;
+	const PHRASING   = 3;
+
+	const MARKER     = 0;
+
+	public function __construct() {
+		$this->phase = self::INIT_PHASE;
+		$this->mode = self::BEFOR_HEAD;
+		$this->dom = new DOMDocument;
+
+		$this->dom->encoding = 'UTF-8';
+		$this->dom->preserveWhiteSpace = true;
+		$this->dom->substituteEntities = true;
+		$this->dom->strictErrorChecking = false;
+	}
+
+	// Process tag tokens
+	public function emitToken($token) {
+		switch($this->phase) {
+			case self::INIT_PHASE: return $this->initPhase($token); break;
+			case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
+			case self::MAIN_PHASE: return $this->mainPhase($token); break;
+			case self::END_PHASE : return $this->trailingEndPhase($token); break;
+		}
+	}
+
+	private function initPhase($token) {
+		/* Initially, the tree construction stage must handle each token
         emitted from the tokenisation stage as follows: */
 
-        /* A DOCTYPE token that is marked as being in error
+		/* A DOCTYPE token that is marked as being in error
         A comment token
         A start tag token
         An end tag token
@@ -1260,575 +1260,575 @@ 
             U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
             or U+0020 SPACE
         An end-of-file token */
-        if((isset($token['error']) && $token['error']) ||
-        $token['type'] === HTML5::COMMENT ||
-        $token['type'] === HTML5::STARTTAG ||
-        $token['type'] === HTML5::ENDTAG ||
-        $token['type'] === HTML5::EOF ||
-        ($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
-        !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) {
-            /* This specification does not define how to handle this case. In
+		if((isset($token['error']) && $token['error']) ||
+		$token['type'] === HTML5::COMMENT ||
+		$token['type'] === HTML5::STARTTAG ||
+		$token['type'] === HTML5::ENDTAG ||
+		$token['type'] === HTML5::EOF ||
+		($token['type'] === HTML5::CHARACTR && isset($token['data']) &&
+		!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data']))) {
+			/* This specification does not define how to handle this case. In
             particular, user agents may ignore the entirety of this specification
             altogether for such documents, and instead invoke special parse modes
             with a greater emphasis on backwards compatibility. */
 
-            $this->phase = self::ROOT_PHASE;
-            return $this->rootElementPhase($token);
+			$this->phase = self::ROOT_PHASE;
+			return $this->rootElementPhase($token);
 
-        /* A DOCTYPE token marked as being correct */
-        } elseif(isset($token['error']) && !$token['error']) {
-            /* Append a DocumentType node to the Document  node, with the name
+		/* A DOCTYPE token marked as being correct */
+		} elseif(isset($token['error']) && !$token['error']) {
+			/* Append a DocumentType node to the Document  node, with the name
             attribute set to the name given in the DOCTYPE token (which will be
             "HTML"), and the other attributes specific to DocumentType objects
             set to null, empty lists, or the empty string as appropriate. */
-            $doctype = new DOMDocumentType(null, null, 'HTML');
+			$doctype = new DOMDocumentType(null, null, 'HTML');
 
-            /* Then, switch to the root element phase of the tree construction
+			/* Then, switch to the root element phase of the tree construction
             stage. */
-            $this->phase = self::ROOT_PHASE;
+			$this->phase = self::ROOT_PHASE;
 
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
-        $token['data'])) {
-            /* Append that character  to the Document node. */
-            $text = $this->dom->createTextNode($token['data']);
-            $this->dom->appendChild($text);
-        }
-    }
-
-    private function rootElementPhase($token) {
-        /* After the initial phase, as each token is emitted from the tokenisation
+		} elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
+		$token['data'])) {
+			/* Append that character  to the Document node. */
+			$text = $this->dom->createTextNode($token['data']);
+			$this->dom->appendChild($text);
+		}
+	}
+
+	private function rootElementPhase($token) {
+		/* After the initial phase, as each token is emitted from the tokenisation
         stage, it must be processed as described in this section. */
 
-        /* A DOCTYPE token */
-        if($token['type'] === HTML5::DOCTYPE) {
-            // Parse error. Ignore the token.
+		/* A DOCTYPE token */
+		if($token['type'] === HTML5::DOCTYPE) {
+			// Parse error. Ignore the token.
 
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the Document object with the data
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the Document object with the data
             attribute set to the data given in the comment token. */
-            $comment = $this->dom->createComment($token['data']);
-            $this->dom->appendChild($comment);
+			$comment = $this->dom->createComment($token['data']);
+			$this->dom->appendChild($comment);
 
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        } elseif($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append that character  to the Document node. */
-            $text = $this->dom->createTextNode($token['data']);
-            $this->dom->appendChild($text);
+		} elseif($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append that character  to the Document node. */
+			$text = $this->dom->createTextNode($token['data']);
+			$this->dom->appendChild($text);
 
-        /* A character token that is not one of U+0009 CHARACTER TABULATION,
+		/* A character token that is not one of U+0009 CHARACTER TABULATION,
             U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED
             (FF), or U+0020 SPACE
         A start tag token
         An end tag token
         An end-of-file token */
-        } elseif(($token['type'] === HTML5::CHARACTR &&
-        !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
-        $token['type'] === HTML5::STARTTAG ||
-        $token['type'] === HTML5::ENDTAG ||
-        $token['type'] === HTML5::EOF) {
-            /* Create an HTMLElement node with the tag name html, in the HTML
+		} elseif(($token['type'] === HTML5::CHARACTR &&
+		!preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
+		$token['type'] === HTML5::STARTTAG ||
+		$token['type'] === HTML5::ENDTAG ||
+		$token['type'] === HTML5::EOF) {
+			/* Create an HTMLElement node with the tag name html, in the HTML
             namespace. Append it to the Document object. Switch to the main
             phase and reprocess the current token. */
-            $html = $this->dom->createElement('html');
-            $this->dom->appendChild($html);
-            $this->stack[] = $html;
+			$html = $this->dom->createElement('html');
+			$this->dom->appendChild($html);
+			$this->stack[] = $html;
 
-            $this->phase = self::MAIN_PHASE;
-            return $this->mainPhase($token);
-        }
-    }
+			$this->phase = self::MAIN_PHASE;
+			return $this->mainPhase($token);
+		}
+	}
 
-    private function mainPhase($token) {
-        /* Tokens in the main phase must be handled as follows: */
+	private function mainPhase($token) {
+		/* Tokens in the main phase must be handled as follows: */
 
-        /* A DOCTYPE token */
-        if($token['type'] === HTML5::DOCTYPE) {
-            // Parse error. Ignore the token.
+		/* A DOCTYPE token */
+		if($token['type'] === HTML5::DOCTYPE) {
+			// Parse error. Ignore the token.
 
-        /* A start tag token with the tag name "html" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
-            /* If this start tag token was not the first start tag token, then
+		/* A start tag token with the tag name "html" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
+			/* If this start tag token was not the first start tag token, then
             it is a parse error. */
 
-            /* For each attribute on the token, check to see if the attribute
+			/* For each attribute on the token, check to see if the attribute
             is already present on the top element of the stack of open elements.
             If it is not, add the attribute and its corresponding value to that
             element. */
-            foreach($token['attr'] as $attr) {
-                if(!$this->stack[0]->hasAttribute($attr['name'])) {
-                    $this->stack[0]->setAttribute($attr['name'], $attr['value']);
-                }
-            }
-
-        /* An end-of-file token */
-        } elseif($token['type'] === HTML5::EOF) {
-            /* Generate implied end tags. */
-            $this->generateImpliedEndTags();
-
-        /* Anything else. */
-        } else {
-            /* Depends on the insertion mode: */
-            switch($this->mode) {
-                case self::BEFOR_HEAD: return $this->beforeHead($token); break;
-                case self::IN_HEAD:    return $this->inHead($token); break;
-                case self::AFTER_HEAD: return $this->afterHead($token); break;
-                case self::IN_BODY:    return $this->inBody($token); break;
-                case self::IN_TABLE:   return $this->inTable($token); break;
-                case self::IN_CAPTION: return $this->inCaption($token); break;
-                case self::IN_CGROUP:  return $this->inColumnGroup($token); break;
-                case self::IN_TBODY:   return $this->inTableBody($token); break;
-                case self::IN_ROW:     return $this->inRow($token); break;
-                case self::IN_CELL:    return $this->inCell($token); break;
-                case self::IN_SELECT:  return $this->inSelect($token); break;
-                case self::AFTER_BODY: return $this->afterBody($token); break;
-                case self::IN_FRAME:   return $this->inFrameset($token); break;
-                case self::AFTR_FRAME: return $this->afterFrameset($token); break;
-                case self::END_PHASE:  return $this->trailingEndPhase($token); break;
-            }
-        }
-    }
-
-    private function beforeHead($token) {
-        /* Handle the token as follows: */
-
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+			foreach($token['attr'] as $attr) {
+				if(!$this->stack[0]->hasAttribute($attr['name'])) {
+					$this->stack[0]->setAttribute($attr['name'], $attr['value']);
+				}
+			}
+
+		/* An end-of-file token */
+		} elseif($token['type'] === HTML5::EOF) {
+			/* Generate implied end tags. */
+			$this->generateImpliedEndTags();
+
+		/* Anything else. */
+		} else {
+			/* Depends on the insertion mode: */
+			switch($this->mode) {
+				case self::BEFOR_HEAD: return $this->beforeHead($token); break;
+				case self::IN_HEAD:    return $this->inHead($token); break;
+				case self::AFTER_HEAD: return $this->afterHead($token); break;
+				case self::IN_BODY:    return $this->inBody($token); break;
+				case self::IN_TABLE:   return $this->inTable($token); break;
+				case self::IN_CAPTION: return $this->inCaption($token); break;
+				case self::IN_CGROUP:  return $this->inColumnGroup($token); break;
+				case self::IN_TBODY:   return $this->inTableBody($token); break;
+				case self::IN_ROW:     return $this->inRow($token); break;
+				case self::IN_CELL:    return $this->inCell($token); break;
+				case self::IN_SELECT:  return $this->inSelect($token); break;
+				case self::AFTER_BODY: return $this->afterBody($token); break;
+				case self::IN_FRAME:   return $this->inFrameset($token); break;
+				case self::AFTR_FRAME: return $this->afterFrameset($token); break;
+				case self::END_PHASE:  return $this->trailingEndPhase($token); break;
+			}
+		}
+	}
+
+	private function beforeHead($token) {
+		/* Handle the token as follows: */
+
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append the character to the current node. */
-            $this->insertText($token['data']);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data attribute
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append the character to the current node. */
+			$this->insertText($token['data']);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data attribute
             set to the data given in the comment token. */
-            $this->insertComment($token['data']);
+			$this->insertComment($token['data']);
 
-        /* A start tag token with the tag name "head" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
-            /* Create an element for the token, append the new element to the
+		/* A start tag token with the tag name "head" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
+			/* Create an element for the token, append the new element to the
             current node and push it onto the stack of open elements. */
-            $element = $this->insertElement($token);
+			$element = $this->insertElement($token);
 
-            /* Set the head element pointer to this new element node. */
-            $this->head_pointer = $element;
+			/* Set the head element pointer to this new element node. */
+			$this->head_pointer = $element;
 
-            /* Change the insertion mode to "in head". */
-            $this->mode = self::IN_HEAD;
+			/* Change the insertion mode to "in head". */
+			$this->mode = self::IN_HEAD;
 
-        /* A start tag token whose tag name is one of: "base", "link", "meta",
+		/* A start tag token whose tag name is one of: "base", "link", "meta",
         "script", "style", "title". Or an end tag with the tag name "html".
         Or a character token that is not one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE. Or any other start tag token */
-        } elseif($token['type'] === HTML5::STARTTAG ||
-        ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
-        ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
-        $token['data']))) {
-            /* Act as if a start tag token with the tag name "head" and no
+		} elseif($token['type'] === HTML5::STARTTAG ||
+		($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
+		($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
+		$token['data']))) {
+			/* Act as if a start tag token with the tag name "head" and no
             attributes had been seen, then reprocess the current token. */
-            $this->beforeHead(array(
-                'name' => 'head',
-                'type' => HTML5::STARTTAG,
-                'attr' => array()
-            ));
+			$this->beforeHead(array(
+				'name' => 'head',
+				'type' => HTML5::STARTTAG,
+				'attr' => array()
+			));
 
-            return $this->inHead($token);
+			return $this->inHead($token);
 
-        /* Any other end tag */
-        } elseif($token['type'] === HTML5::ENDTAG) {
-            /* Parse error. Ignore the token. */
-        }
-    }
+		/* Any other end tag */
+		} elseif($token['type'] === HTML5::ENDTAG) {
+			/* Parse error. Ignore the token. */
+		}
+	}
 
-    private function inHead($token) {
-        /* Handle the token as follows: */
+	private function inHead($token) {
+		/* Handle the token as follows: */
 
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE.
 
         THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
         or script element, append the character to the current node regardless
         of its content. */
-        if(($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
-        $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
-        array('title', 'style', 'script')))) {
-            /* Append the character to the current node. */
-            $this->insertText($token['data']);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data attribute
+		if(($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
+		$token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
+		array('title', 'style', 'script')))) {
+			/* Append the character to the current node. */
+			$this->insertText($token['data']);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data attribute
             set to the data given in the comment token. */
-            $this->insertComment($token['data']);
+			$this->insertComment($token['data']);
 
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        in_array($token['name'], array('title', 'style', 'script'))) {
-            array_pop($this->stack);
-            return HTML5::PCDATA;
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		in_array($token['name'], array('title', 'style', 'script'))) {
+			array_pop($this->stack);
+			return HTML5::PCDATA;
 
-        /* A start tag with the tag name "title" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
-            /* Create an element for the token and append the new element to the
+		/* A start tag with the tag name "title" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
+			/* Create an element for the token and append the new element to the
             node pointed to by the head element pointer, or, if that is null
             (innerHTML case), to the current node. */
-            if($this->head_pointer !== null) {
-                $element = $this->insertElement($token, false);
-                $this->head_pointer->appendChild($element);
+			if($this->head_pointer !== null) {
+				$element = $this->insertElement($token, false);
+				$this->head_pointer->appendChild($element);
 
-            } else {
-                $element = $this->insertElement($token);
-            }
+			} else {
+				$element = $this->insertElement($token);
+			}
 
-            /* Switch the tokeniser's content model flag  to the RCDATA state. */
-            return HTML5::RCDATA;
+			/* Switch the tokeniser's content model flag  to the RCDATA state. */
+			return HTML5::RCDATA;
 
-        /* A start tag with the tag name "style" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
-            /* Create an element for the token and append the new element to the
+		/* A start tag with the tag name "style" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
+			/* Create an element for the token and append the new element to the
             node pointed to by the head element pointer, or, if that is null
             (innerHTML case), to the current node. */
-            if($this->head_pointer !== null) {
-                $element = $this->insertElement($token, false);
-                $this->head_pointer->appendChild($element);
-
-            } else {
-                $this->insertElement($token);
-            }
-
-            /* Switch the tokeniser's content model flag  to the CDATA state. */
-            return HTML5::CDATA;
-
-        /* A start tag with the tag name "script" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
-            /* Create an element for the token. */
-            $element = $this->insertElement($token, false);
-            $this->head_pointer->appendChild($element);
-
-            /* Switch the tokeniser's content model flag  to the CDATA state. */
-            return HTML5::CDATA;
-
-        /* A start tag with the tag name "base", "link", or "meta" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('base', 'link', 'meta'))) {
-            /* Create an element for the token and append the new element to the
+			if($this->head_pointer !== null) {
+				$element = $this->insertElement($token, false);
+				$this->head_pointer->appendChild($element);
+
+			} else {
+				$this->insertElement($token);
+			}
+
+			/* Switch the tokeniser's content model flag  to the CDATA state. */
+			return HTML5::CDATA;
+
+		/* A start tag with the tag name "script" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
+			/* Create an element for the token. */
+			$element = $this->insertElement($token, false);
+			$this->head_pointer->appendChild($element);
+
+			/* Switch the tokeniser's content model flag  to the CDATA state. */
+			return HTML5::CDATA;
+
+		/* A start tag with the tag name "base", "link", or "meta" */
+		} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('base', 'link', 'meta'))) {
+			/* Create an element for the token and append the new element to the
             node pointed to by the head element pointer, or, if that is null
             (innerHTML case), to the current node. */
-            if($this->head_pointer !== null) {
-                $element = $this->insertElement($token, false);
-                $this->head_pointer->appendChild($element);
-                array_pop($this->stack);
-
-            } else {
-                $this->insertElement($token);
-            }
-
-        /* An end tag with the tag name "head" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
-            /* If the current node is a head element, pop the current node off
+			if($this->head_pointer !== null) {
+				$element = $this->insertElement($token, false);
+				$this->head_pointer->appendChild($element);
+				array_pop($this->stack);
+
+			} else {
+				$this->insertElement($token);
+			}
+
+		/* An end tag with the tag name "head" */
+		} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
+			/* If the current node is a head element, pop the current node off
             the stack of open elements. */
-            if($this->head_pointer->isSameNode(end($this->stack))) {
-                array_pop($this->stack);
+			if($this->head_pointer->isSameNode(end($this->stack))) {
+				array_pop($this->stack);
 
-            /* Otherwise, this is a parse error. */
-            } else {
-                // k
-            }
+			/* Otherwise, this is a parse error. */
+			} else {
+				// k
+			}
 
-            /* Change the insertion mode to "after head". */
-            $this->mode = self::AFTER_HEAD;
+			/* Change the insertion mode to "after head". */
+			$this->mode = self::AFTER_HEAD;
 
-        /* A start tag with the tag name "head" or an end tag except "html". */
-        } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
-        ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
-            // Parse error. Ignore the token.
+		/* A start tag with the tag name "head" or an end tag except "html". */
+		} elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
+		($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
+			// Parse error. Ignore the token.
 
-        /* Anything else */
-        } else {
-            /* If the current node is a head element, act as if an end tag
+		/* Anything else */
+		} else {
+			/* If the current node is a head element, act as if an end tag
             token with the tag name "head" had been seen. */
-            if($this->head_pointer->isSameNode(end($this->stack))) {
-                $this->inHead(array(
-                    'name' => 'head',
-                    'type' => HTML5::ENDTAG
-                ));
-
-            /* Otherwise, change the insertion mode to "after head". */
-            } else {
-                $this->mode = self::AFTER_HEAD;
-            }
-
-            /* Then, reprocess the current token. */
-            return $this->afterHead($token);
-        }
-    }
-
-    private function afterHead($token) {
-        /* Handle the token as follows: */
-
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+			if($this->head_pointer->isSameNode(end($this->stack))) {
+				$this->inHead(array(
+					'name' => 'head',
+					'type' => HTML5::ENDTAG
+				));
+
+			/* Otherwise, change the insertion mode to "after head". */
+			} else {
+				$this->mode = self::AFTER_HEAD;
+			}
+
+			/* Then, reprocess the current token. */
+			return $this->afterHead($token);
+		}
+	}
+
+	private function afterHead($token) {
+		/* Handle the token as follows: */
+
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append the character to the current node. */
-            $this->insertText($token['data']);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data attribute
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append the character to the current node. */
+			$this->insertText($token['data']);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data attribute
             set to the data given in the comment token. */
-            $this->insertComment($token['data']);
+			$this->insertComment($token['data']);
 
-        /* A start tag token with the tag name "body" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
-            /* Insert a body element for the token. */
-            $this->insertElement($token);
+		/* A start tag token with the tag name "body" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
+			/* Insert a body element for the token. */
+			$this->insertElement($token);
 
-            /* Change the insertion mode to "in body". */
-            $this->mode = self::IN_BODY;
+			/* Change the insertion mode to "in body". */
+			$this->mode = self::IN_BODY;
 
-        /* A start tag token with the tag name "frameset" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
-            /* Insert a frameset element for the token. */
-            $this->insertElement($token);
+		/* A start tag token with the tag name "frameset" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
+			/* Insert a frameset element for the token. */
+			$this->insertElement($token);
 
-            /* Change the insertion mode to "in frameset". */
-            $this->mode = self::IN_FRAME;
+			/* Change the insertion mode to "in frameset". */
+			$this->mode = self::IN_FRAME;
 
-        /* A start tag token whose tag name is one of: "base", "link", "meta",
+		/* A start tag token whose tag name is one of: "base", "link", "meta",
         "script", "style", "title" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('base', 'link', 'meta', 'script', 'style', 'title'))) {
-            /* Parse error. Switch the insertion mode back to "in head" and
+		} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('base', 'link', 'meta', 'script', 'style', 'title'))) {
+			/* Parse error. Switch the insertion mode back to "in head" and
             reprocess the token. */
-            $this->mode = self::IN_HEAD;
-            return $this->inHead($token);
+			$this->mode = self::IN_HEAD;
+			return $this->inHead($token);
 
-        /* Anything else */
-        } else {
-            /* Act as if a start tag token with the tag name "body" and no
+		/* Anything else */
+		} else {
+			/* Act as if a start tag token with the tag name "body" and no
             attributes had been seen, and then reprocess the current token. */
-            $this->afterHead(array(
-                'name' => 'body',
-                'type' => HTML5::STARTTAG,
-                'attr' => array()
-            ));
-
-            return $this->inBody($token);
-        }
-    }
-
-    private function inBody($token) {
-        /* Handle the token as follows: */
-
-        switch($token['type']) {
-            /* A character token */
-            case HTML5::CHARACTR:
-                /* Reconstruct the active formatting elements, if any. */
-                $this->reconstructActiveFormattingElements();
-
-                /* Append the token's character to the current node. */
-                $this->insertText($token['data']);
-            break;
-
-            /* A comment token */
-            case HTML5::COMMENT:
-                /* Append a Comment node to the current node with the data
+			$this->afterHead(array(
+				'name' => 'body',
+				'type' => HTML5::STARTTAG,
+				'attr' => array()
+			));
+
+			return $this->inBody($token);
+		}
+	}
+
+	private function inBody($token) {
+		/* Handle the token as follows: */
+
+		switch($token['type']) {
+			/* A character token */
+			case HTML5::CHARACTR:
+				/* Reconstruct the active formatting elements, if any. */
+				$this->reconstructActiveFormattingElements();
+
+				/* Append the token's character to the current node. */
+				$this->insertText($token['data']);
+			break;
+
+			/* A comment token */
+			case HTML5::COMMENT:
+				/* Append a Comment node to the current node with the data
                 attribute set to the data given in the comment token. */
-                $this->insertComment($token['data']);
-            break;
+				$this->insertComment($token['data']);
+			break;
 
-            case HTML5::STARTTAG:
-            switch($token['name']) {
-                /* A start tag token whose tag name is one of: "script",
+			case HTML5::STARTTAG:
+			switch($token['name']) {
+				/* A start tag token whose tag name is one of: "script",
                 "style" */
-                case 'script': case 'style':
-                    /* Process the token as if the insertion mode had been "in
+				case 'script': case 'style':
+					/* Process the token as if the insertion mode had been "in
                     head". */
-                    return $this->inHead($token);
-                break;
+					return $this->inHead($token);
+				break;
 
-                /* A start tag token whose tag name is one of: "base", "link",
+				/* A start tag token whose tag name is one of: "base", "link",
                 "meta", "title" */
-                case 'base': case 'link': case 'meta': case 'title':
-                    /* Parse error. Process the token as if the insertion mode
+				case 'base': case 'link': case 'meta': case 'title':
+					/* Parse error. Process the token as if the insertion mode
                     had    been "in head". */
-                    return $this->inHead($token);
-                break;
+					return $this->inHead($token);
+				break;
 
-                /* A start tag token with the tag name "body" */
-                case 'body':
-                    /* Parse error. If the second element on the stack of open
+				/* A start tag token with the tag name "body" */
+				case 'body':
+					/* Parse error. If the second element on the stack of open
                     elements is not a body element, or, if the stack of open
                     elements has only one node on it, then ignore the token.
                     (innerHTML case) */
-                    if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
-                        // Ignore
+					if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
+						// Ignore
 
-                    /* Otherwise, for each attribute on the token, check to see
+					/* Otherwise, for each attribute on the token, check to see
                     if the attribute is already present on the body element (the
                     second element)    on the stack of open elements. If it is not,
                     add the attribute and its corresponding value to that
                     element. */
-                    } else {
-                        foreach($token['attr'] as $attr) {
-                            if(!$this->stack[1]->hasAttribute($attr['name'])) {
-                                $this->stack[1]->setAttribute($attr['name'], $attr['value']);
-                            }
-                        }
-                    }
-                break;
-
-                /* A start tag whose tag name is one of: "address",
+					} else {
+						foreach($token['attr'] as $attr) {
+							if(!$this->stack[1]->hasAttribute($attr['name'])) {
+								$this->stack[1]->setAttribute($attr['name'], $attr['value']);
+							}
+						}
+					}
+				break;
+
+				/* A start tag whose tag name is one of: "address",
                 "blockquote", "center", "dir", "div", "dl", "fieldset",
                 "listing", "menu", "ol", "p", "ul" */
-                case 'address': case 'blockquote': case 'center': case 'dir':
-                case 'div': case 'dl': case 'fieldset': case 'listing':
-                case 'menu': case 'ol': case 'p': case 'ul':
-                    /* If the stack of open elements has a p element in scope,
+				case 'address': case 'blockquote': case 'center': case 'dir':
+				case 'div': case 'dl': case 'fieldset': case 'listing':
+				case 'menu': case 'ol': case 'p': case 'ul':
+					/* If the stack of open elements has a p element in scope,
                     then act as if an end tag with the tag name p had been
                     seen. */
-                    if($this->elementInScope('p')) {
-                        $this->emitToken(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
-
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
-                break;
-
-                /* A start tag whose tag name is "form" */
-                case 'form':
-                    /* If the form element pointer is not null, ignore the
+					if($this->elementInScope('p')) {
+						$this->emitToken(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
+					}
+
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
+				break;
+
+				/* A start tag whose tag name is "form" */
+				case 'form':
+					/* If the form element pointer is not null, ignore the
                     token with a parse error. */
-                    if($this->form_pointer !== null) {
-                        // Ignore.
+					if($this->form_pointer !== null) {
+						// Ignore.
 
-                    /* Otherwise: */
-                    } else {
-                        /* If the stack of open elements has a p element in
+					/* Otherwise: */
+					} else {
+						/* If the stack of open elements has a p element in
                         scope, then act as if an end tag with the tag name p
                         had been seen. */
-                        if($this->elementInScope('p')) {
-                            $this->emitToken(array(
-                                'name' => 'p',
-                                'type' => HTML5::ENDTAG
-                            ));
-                        }
-
-                        /* Insert an HTML element for the token, and set the
+						if($this->elementInScope('p')) {
+							$this->emitToken(array(
+								'name' => 'p',
+								'type' => HTML5::ENDTAG
+							));
+						}
+
+						/* Insert an HTML element for the token, and set the
                         form element pointer to point to the element created. */
-                        $element = $this->insertElement($token);
-                        $this->form_pointer = $element;
-                    }
-                break;
-
-                /* A start tag whose tag name is "li", "dd" or "dt" */
-                case 'li': case 'dd': case 'dt':
-                    /* If the stack of open elements has a p  element in scope,
+						$element = $this->insertElement($token);
+						$this->form_pointer = $element;
+					}
+				break;
+
+				/* A start tag whose tag name is "li", "dd" or "dt" */
+				case 'li': case 'dd': case 'dt':
+					/* If the stack of open elements has a p  element in scope,
                     then act as if an end tag with the tag name p had been
                     seen. */
-                    if($this->elementInScope('p')) {
-                        $this->emitToken(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
+					if($this->elementInScope('p')) {
+						$this->emitToken(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
+					}
 
-                    $stack_length = count($this->stack) - 1;
+					$stack_length = count($this->stack) - 1;
 
-                    for($n = $stack_length; 0 <= $n; $n--) {
-                        /* 1. Initialise node to be the current node (the
+					for($n = $stack_length; 0 <= $n; $n--) {
+						/* 1. Initialise node to be the current node (the
                         bottommost node of the stack). */
-                        $stop = false;
-                        $node = $this->stack[$n];
-                        $cat  = $this->getElementCategory($node->tagName);
+						$stop = false;
+						$node = $this->stack[$n];
+						$cat  = $this->getElementCategory($node->tagName);
 
-                        /* 2. If node is an li, dd or dt element, then pop all
+						/* 2. If node is an li, dd or dt element, then pop all
                         the    nodes from the current node up to node, including
                         node, then stop this algorithm. */
-                        if($token['name'] === $node->tagName ||    ($token['name'] !== 'li'
-                        && ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
-                            for($x = $stack_length; $x >= $n ; $x--) {
-                                array_pop($this->stack);
-                            }
+						if($token['name'] === $node->tagName ||    ($token['name'] !== 'li'
+						&& ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
+							for($x = $stack_length; $x >= $n ; $x--) {
+								array_pop($this->stack);
+							}
 
-                            break;
-                        }
+							break;
+						}
 
-                        /* 3. If node is not in the formatting category, and is
+						/* 3. If node is not in the formatting category, and is
                         not    in the phrasing category, and is not an address or
                         div element, then stop this algorithm. */
-                        if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
-                        $node->tagName !== 'address' && $node->tagName !== 'div') {
-                            break;
-                        }
-                    }
+						if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
+						$node->tagName !== 'address' && $node->tagName !== 'div') {
+							break;
+						}
+					}
 
-                    /* Finally, insert an HTML element with the same tag
+					/* Finally, insert an HTML element with the same tag
                     name as the    token's. */
-                    $this->insertElement($token);
-                break;
+					$this->insertElement($token);
+				break;
 
-                /* A start tag token whose tag name is "plaintext" */
-                case 'plaintext':
-                    /* If the stack of open elements has a p  element in scope,
+				/* A start tag token whose tag name is "plaintext" */
+				case 'plaintext':
+					/* If the stack of open elements has a p  element in scope,
                     then act as if an end tag with the tag name p had been
                     seen. */
-                    if($this->elementInScope('p')) {
-                        $this->emitToken(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
+					if($this->elementInScope('p')) {
+						$this->emitToken(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
+					}
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
 
-                    return HTML5::PLAINTEXT;
-                break;
+					return HTML5::PLAINTEXT;
+				break;
 
-                /* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
+				/* A start tag whose tag name is one of: "h1", "h2", "h3", "h4",
                 "h5", "h6" */
-                case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
-                    /* If the stack of open elements has a p  element in scope,
+				case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
+					/* If the stack of open elements has a p  element in scope,
                     then act as if an end tag with the tag name p had been seen. */
-                    if($this->elementInScope('p')) {
-                        $this->emitToken(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
-
-                    /* If the stack of open elements has in scope an element whose
+					if($this->elementInScope('p')) {
+						$this->emitToken(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
+					}
+
+					/* If the stack of open elements has in scope an element whose
                     tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
                     this is a parse error; pop elements from the stack until an
                     element with one of those tag names has been popped from the
                     stack. */
-                    while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
-                        array_pop($this->stack);
-                    }
+					while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
+						array_pop($this->stack);
+					}
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
-                break;
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
+				break;
 
-                /* A start tag whose tag name is "a" */
-                case 'a':
-                    /* If the list of active formatting elements contains
+				/* A start tag whose tag name is "a" */
+				case 'a':
+					/* If the list of active formatting elements contains
                     an element whose tag name is "a" between the end of the
                     list and the last marker on the list (or the start of
                     the list if there is no marker on the list), then this
@@ -1837,940 +1837,940 @@ 
                     of active formatting elements and the stack of open
                     elements if the end tag didn't already remove it (it
                     might not have if the element is not in table scope). */
-                    $leng = count($this->a_formatting);
+					$leng = count($this->a_formatting);
 
-                    for($n = $leng - 1; $n >= 0; $n--) {
-                        if($this->a_formatting[$n] === self::MARKER) {
-                            break;
+					for($n = $leng - 1; $n >= 0; $n--) {
+						if($this->a_formatting[$n] === self::MARKER) {
+							break;
 
-                        } elseif($this->a_formatting[$n]->nodeName === 'a') {
-                            $this->emitToken(array(
-                                'name' => 'a',
-                                'type' => HTML5::ENDTAG
-                            ));
-                            break;
-                        }
-                    }
+						} elseif($this->a_formatting[$n]->nodeName === 'a') {
+							$this->emitToken(array(
+								'name' => 'a',
+								'type' => HTML5::ENDTAG
+							));
+							break;
+						}
+					}
 
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an HTML element for the token. */
-                    $el = $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$el = $this->insertElement($token);
 
-                    /* Add that element to the list of active formatting
+					/* Add that element to the list of active formatting
                     elements. */
-                    $this->a_formatting[] = $el;
-                break;
+					$this->a_formatting[] = $el;
+				break;
 
-                /* A start tag whose tag name is one of: "b", "big", "em", "font",
+				/* A start tag whose tag name is one of: "b", "big", "em", "font",
                 "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
-                case 'b': case 'big': case 'em': case 'font': case 'i':
-                case 'nobr': case 's': case 'small': case 'strike':
-                case 'strong': case 'tt': case 'u':
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+				case 'b': case 'big': case 'em': case 'font': case 'i':
+				case 'nobr': case 's': case 'small': case 'strike':
+				case 'strong': case 'tt': case 'u':
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an HTML element for the token. */
-                    $el = $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$el = $this->insertElement($token);
 
-                    /* Add that element to the list of active formatting
+					/* Add that element to the list of active formatting
                     elements. */
-                    $this->a_formatting[] = $el;
-                break;
+					$this->a_formatting[] = $el;
+				break;
 
-                /* A start tag token whose tag name is "button" */
-                case 'button':
-                    /* If the stack of open elements has a button element in scope,
+				/* A start tag token whose tag name is "button" */
+				case 'button':
+					/* If the stack of open elements has a button element in scope,
                     then this is a parse error; act as if an end tag with the tag
                     name "button" had been seen, then reprocess the token. (We don't
                     do that. Unnecessary.) */
-                    if($this->elementInScope('button')) {
-                        $this->inBody(array(
-                            'name' => 'button',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
+					if($this->elementInScope('button')) {
+						$this->inBody(array(
+							'name' => 'button',
+							'type' => HTML5::ENDTAG
+						));
+					}
 
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
 
-                    /* Insert a marker at the end of the list of active
+					/* Insert a marker at the end of the list of active
                     formatting elements. */
-                    $this->a_formatting[] = self::MARKER;
-                break;
+					$this->a_formatting[] = self::MARKER;
+				break;
 
-                /* A start tag token whose tag name is one of: "marquee", "object" */
-                case 'marquee': case 'object':
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+				/* A start tag token whose tag name is one of: "marquee", "object" */
+				case 'marquee': case 'object':
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
 
-                    /* Insert a marker at the end of the list of active
+					/* Insert a marker at the end of the list of active
                     formatting elements. */
-                    $this->a_formatting[] = self::MARKER;
-                break;
+					$this->a_formatting[] = self::MARKER;
+				break;
 
-                /* A start tag token whose tag name is "xmp" */
-                case 'xmp':
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+				/* A start tag token whose tag name is "xmp" */
+				case 'xmp':
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
 
-                    /* Switch the content model flag to the CDATA state. */
-                    return HTML5::CDATA;
-                break;
+					/* Switch the content model flag to the CDATA state. */
+					return HTML5::CDATA;
+				break;
 
-                /* A start tag whose tag name is "table" */
-                case 'table':
-                    /* If the stack of open elements has a p element in scope,
+				/* A start tag whose tag name is "table" */
+				case 'table':
+					/* If the stack of open elements has a p element in scope,
                     then act as if an end tag with the tag name p had been seen. */
-                    if($this->elementInScope('p')) {
-                        $this->emitToken(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
+					if($this->elementInScope('p')) {
+						$this->emitToken(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
+					}
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
 
-                    /* Change the insertion mode to "in table". */
-                    $this->mode = self::IN_TABLE;
-                break;
+					/* Change the insertion mode to "in table". */
+					$this->mode = self::IN_TABLE;
+				break;
 
-                /* A start tag whose tag name is one of: "area", "basefont",
+				/* A start tag whose tag name is one of: "area", "basefont",
                 "bgsound", "br", "embed", "img", "param", "spacer", "wbr" */
-                case 'area': case 'basefont': case 'bgsound': case 'br':
-                case 'embed': case 'img': case 'param': case 'spacer':
-                case 'wbr':
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
-
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
-
-                    /* Immediately pop the current node off the stack of open elements. */
-                    array_pop($this->stack);
-                break;
-
-                /* A start tag whose tag name is "hr" */
-                case 'hr':
-                    /* If the stack of open elements has a p element in scope,
+				case 'area': case 'basefont': case 'bgsound': case 'br':
+				case 'embed': case 'img': case 'param': case 'spacer':
+				case 'wbr':
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
+
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
+
+					/* Immediately pop the current node off the stack of open elements. */
+					array_pop($this->stack);
+				break;
+
+				/* A start tag whose tag name is "hr" */
+				case 'hr':
+					/* If the stack of open elements has a p element in scope,
                     then act as if an end tag with the tag name p had been seen. */
-                    if($this->elementInScope('p')) {
-                        $this->emitToken(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
-
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
-
-                    /* Immediately pop the current node off the stack of open elements. */
-                    array_pop($this->stack);
-                break;
-
-                /* A start tag whose tag name is "image" */
-                case 'image':
-                    /* Parse error. Change the token's tag name to "img" and
+					if($this->elementInScope('p')) {
+						$this->emitToken(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
+					}
+
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
+
+					/* Immediately pop the current node off the stack of open elements. */
+					array_pop($this->stack);
+				break;
+
+				/* A start tag whose tag name is "image" */
+				case 'image':
+					/* Parse error. Change the token's tag name to "img" and
                     reprocess it. (Don't ask.) */
-                    $token['name'] = 'img';
-                    return $this->inBody($token);
-                break;
+					$token['name'] = 'img';
+					return $this->inBody($token);
+				break;
 
-                /* A start tag whose tag name is "input" */
-                case 'input':
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+				/* A start tag whose tag name is "input" */
+				case 'input':
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an input element for the token. */
-                    $element = $this->insertElement($token, false);
+					/* Insert an input element for the token. */
+					$element = $this->insertElement($token, false);
 
-                    /* If the form element pointer is not null, then associate the
+					/* If the form element pointer is not null, then associate the
                     input element with the form element pointed to by the form
                     element pointer. */
-                    $this->form_pointer !== null
-                        ? $this->form_pointer->appendChild($element)
-                        : end($this->stack)->appendChild($element);
+					$this->form_pointer !== null
+						? $this->form_pointer->appendChild($element)
+						: end($this->stack)->appendChild($element);
 
-                    /* Pop that input element off the stack of open elements. */
-                    array_pop($this->stack);
-                break;
+					/* Pop that input element off the stack of open elements. */
+					array_pop($this->stack);
+				break;
 
-                /* A start tag whose tag name is "isindex" */
-                case 'isindex':
-                    /* Parse error. */
-                    // w/e
+				/* A start tag whose tag name is "isindex" */
+				case 'isindex':
+					/* Parse error. */
+					// w/e
 
-                    /* If the form element pointer is not null,
+					/* If the form element pointer is not null,
                     then ignore the token. */
-                    if($this->form_pointer === null) {
-                        /* Act as if a start tag token with the tag name "form" had
+					if($this->form_pointer === null) {
+						/* Act as if a start tag token with the tag name "form" had
                         been seen. */
-                        $this->inBody(array(
-                            'name' => 'body',
-                            'type' => HTML5::STARTTAG,
-                            'attr' => array()
-                        ));
+						$this->inBody(array(
+							'name' => 'body',
+							'type' => HTML5::STARTTAG,
+							'attr' => array()
+						));
 
-                        /* Act as if a start tag token with the tag name "hr" had
+						/* Act as if a start tag token with the tag name "hr" had
                         been seen. */
-                        $this->inBody(array(
-                            'name' => 'hr',
-                            'type' => HTML5::STARTTAG,
-                            'attr' => array()
-                        ));
+						$this->inBody(array(
+							'name' => 'hr',
+							'type' => HTML5::STARTTAG,
+							'attr' => array()
+						));
 
-                        /* Act as if a start tag token with the tag name "p" had
+						/* Act as if a start tag token with the tag name "p" had
                         been seen. */
-                        $this->inBody(array(
-                            'name' => 'p',
-                            'type' => HTML5::STARTTAG,
-                            'attr' => array()
-                        ));
+						$this->inBody(array(
+							'name' => 'p',
+							'type' => HTML5::STARTTAG,
+							'attr' => array()
+						));
 
-                        /* Act as if a start tag token with the tag name "label"
+						/* Act as if a start tag token with the tag name "label"
                         had been seen. */
-                        $this->inBody(array(
-                            'name' => 'label',
-                            'type' => HTML5::STARTTAG,
-                            'attr' => array()
-                        ));
+						$this->inBody(array(
+							'name' => 'label',
+							'type' => HTML5::STARTTAG,
+							'attr' => array()
+						));
 
-                        /* Act as if a stream of character tokens had been seen. */
-                        $this->insertText('This is a searchable index. '.
-                        'Insert your search keywords here: ');
+						/* Act as if a stream of character tokens had been seen. */
+						$this->insertText('This is a searchable index. '.
+						'Insert your search keywords here: ');
 
-                        /* Act as if a start tag token with the tag name "input"
+						/* Act as if a start tag token with the tag name "input"
                         had been seen, with all the attributes from the "isindex"
                         token, except with the "name" attribute set to the value
                         "isindex" (ignoring any explicit "name" attribute). */
-                        $attr = $token['attr'];
-                        $attr[] = array('name' => 'name', 'value' => 'isindex');
+						$attr = $token['attr'];
+						$attr[] = array('name' => 'name', 'value' => 'isindex');
 
-                        $this->inBody(array(
-                            'name' => 'input',
-                            'type' => HTML5::STARTTAG,
-                            'attr' => $attr
-                        ));
+						$this->inBody(array(
+							'name' => 'input',
+							'type' => HTML5::STARTTAG,
+							'attr' => $attr
+						));
 
-                        /* Act as if a stream of character tokens had been seen
+						/* Act as if a stream of character tokens had been seen
                         (see below for what they should say). */
-                        $this->insertText('This is a searchable index. '.
-                        'Insert your search keywords here: ');
+						$this->insertText('This is a searchable index. '.
+						'Insert your search keywords here: ');
 
-                        /* Act as if an end tag token with the tag name "label"
+						/* Act as if an end tag token with the tag name "label"
                         had been seen. */
-                        $this->inBody(array(
-                            'name' => 'label',
-                            'type' => HTML5::ENDTAG
-                        ));
+						$this->inBody(array(
+							'name' => 'label',
+							'type' => HTML5::ENDTAG
+						));
 
-                        /* Act as if an end tag token with the tag name "p" had
+						/* Act as if an end tag token with the tag name "p" had
                         been seen. */
-                        $this->inBody(array(
-                            'name' => 'p',
-                            'type' => HTML5::ENDTAG
-                        ));
+						$this->inBody(array(
+							'name' => 'p',
+							'type' => HTML5::ENDTAG
+						));
 
-                        /* Act as if a start tag token with the tag name "hr" had
+						/* Act as if a start tag token with the tag name "hr" had
                         been seen. */
-                        $this->inBody(array(
-                            'name' => 'hr',
-                            'type' => HTML5::ENDTAG
-                        ));
+						$this->inBody(array(
+							'name' => 'hr',
+							'type' => HTML5::ENDTAG
+						));
 
-                        /* Act as if an end tag token with the tag name "form" had
+						/* Act as if an end tag token with the tag name "form" had
                         been seen. */
-                        $this->inBody(array(
-                            'name' => 'form',
-                            'type' => HTML5::ENDTAG
-                        ));
-                    }
-                break;
-
-                /* A start tag whose tag name is "textarea" */
-                case 'textarea':
-                    $this->insertElement($token);
-
-                    /* Switch the tokeniser's content model flag to the
+						$this->inBody(array(
+							'name' => 'form',
+							'type' => HTML5::ENDTAG
+						));
+					}
+				break;
+
+				/* A start tag whose tag name is "textarea" */
+				case 'textarea':
+					$this->insertElement($token);
+
+					/* Switch the tokeniser's content model flag to the
                     RCDATA state. */
-                    return HTML5::RCDATA;
-                break;
+					return HTML5::RCDATA;
+				break;
 
-                /* A start tag whose tag name is one of: "iframe", "noembed",
+				/* A start tag whose tag name is one of: "iframe", "noembed",
                 "noframes" */
-                case 'iframe': case 'noembed': case 'noframes':
-                    $this->insertElement($token);
+				case 'iframe': case 'noembed': case 'noframes':
+					$this->insertElement($token);
 
-                    /* Switch the tokeniser's content model flag to the CDATA state. */
-                    return HTML5::CDATA;
-                break;
+					/* Switch the tokeniser's content model flag to the CDATA state. */
+					return HTML5::CDATA;
+				break;
 
-                /* A start tag whose tag name is "select" */
-                case 'select':
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
+				/* A start tag whose tag name is "select" */
+				case 'select':
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
 
-                    /* Insert an HTML element for the token. */
-                    $this->insertElement($token);
+					/* Insert an HTML element for the token. */
+					$this->insertElement($token);
 
-                    /* Change the insertion mode to "in select". */
-                    $this->mode = self::IN_SELECT;
-                break;
+					/* Change the insertion mode to "in select". */
+					$this->mode = self::IN_SELECT;
+				break;
 
-                /* A start or end tag whose tag name is one of: "caption", "col",
+				/* A start or end tag whose tag name is one of: "caption", "col",
                 "colgroup", "frame", "frameset", "head", "option", "optgroup",
                 "tbody", "td", "tfoot", "th", "thead", "tr". */
-                case 'caption': case 'col': case 'colgroup': case 'frame':
-                case 'frameset': case 'head': case 'option': case 'optgroup':
-                case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead':
-                case 'tr':
-                    // Parse error. Ignore the token.
-                break;
-
-                /* A start or end tag whose tag name is one of: "event-source",
+				case 'caption': case 'col': case 'colgroup': case 'frame':
+				case 'frameset': case 'head': case 'option': case 'optgroup':
+				case 'tbody': case 'td': case 'tfoot': case 'th': case 'thead':
+				case 'tr':
+					// Parse error. Ignore the token.
+				break;
+
+				/* A start or end tag whose tag name is one of: "event-source",
                 "section", "nav", "article", "aside", "header", "footer",
                 "datagrid", "command" */
-                case 'event-source': case 'section': case 'nav': case 'article':
-                case 'aside': case 'header': case 'footer': case 'datagrid':
-                case 'command':
-                    // Work in progress!
-                break;
-
-                /* A start tag token not covered by the previous entries */
-                default:
-                    /* Reconstruct the active formatting elements, if any. */
-                    $this->reconstructActiveFormattingElements();
-
-                    $this->insertElement($token, true, true);
-                break;
-            }
-            break;
-
-            case HTML5::ENDTAG:
-            switch($token['name']) {
-                /* An end tag with the tag name "body" */
-                case 'body':
-                    /* If the second element in the stack of open elements is
+				case 'event-source': case 'section': case 'nav': case 'article':
+				case 'aside': case 'header': case 'footer': case 'datagrid':
+				case 'command':
+					// Work in progress!
+				break;
+
+				/* A start tag token not covered by the previous entries */
+				default:
+					/* Reconstruct the active formatting elements, if any. */
+					$this->reconstructActiveFormattingElements();
+
+					$this->insertElement($token, true, true);
+				break;
+			}
+			break;
+
+			case HTML5::ENDTAG:
+			switch($token['name']) {
+				/* An end tag with the tag name "body" */
+				case 'body':
+					/* If the second element in the stack of open elements is
                     not a body element, this is a parse error. Ignore the token.
                     (innerHTML case) */
-                    if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
-                        // Ignore.
+					if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
+						// Ignore.
 
-                    /* If the current node is not the body element, then this
+					/* If the current node is not the body element, then this
                     is a parse error. */
-                    } elseif(end($this->stack)->nodeName !== 'body') {
-                        // Parse error.
-                    }
+					} elseif(end($this->stack)->nodeName !== 'body') {
+						// Parse error.
+					}
 
-                    /* Change the insertion mode to "after body". */
-                    $this->mode = self::AFTER_BODY;
-                break;
+					/* Change the insertion mode to "after body". */
+					$this->mode = self::AFTER_BODY;
+				break;
 
-                /* An end tag with the tag name "html" */
-                case 'html':
-                    /* Act as if an end tag with tag name "body" had been seen,
+				/* An end tag with the tag name "html" */
+				case 'html':
+					/* Act as if an end tag with tag name "body" had been seen,
                     then, if that token wasn't ignored, reprocess the current
                     token. */
-                    $this->inBody(array(
-                        'name' => 'body',
-                        'type' => HTML5::ENDTAG
-                    ));
+					$this->inBody(array(
+						'name' => 'body',
+						'type' => HTML5::ENDTAG
+					));
 
-                    return $this->afterBody($token);
-                break;
+					return $this->afterBody($token);
+				break;
 
-                /* An end tag whose tag name is one of: "address", "blockquote",
+				/* An end tag whose tag name is one of: "address", "blockquote",
                 "center", "dir", "div", "dl", "fieldset", "listing", "menu",
                 "ol", "pre", "ul" */
-                case 'address': case 'blockquote': case 'center': case 'dir':
-                case 'div': case 'dl': case 'fieldset': case 'listing':
-                case 'menu': case 'ol': case 'pre': case 'ul':
-                    /* If the stack of open elements has an element in scope
+				case 'address': case 'blockquote': case 'center': case 'dir':
+				case 'div': case 'dl': case 'fieldset': case 'listing':
+				case 'menu': case 'ol': case 'pre': case 'ul':
+					/* If the stack of open elements has an element in scope
                     with the same tag name as that of the token, then generate
                     implied end tags. */
-                    if($this->elementInScope($token['name'])) {
-                        $this->generateImpliedEndTags();
+					if($this->elementInScope($token['name'])) {
+						$this->generateImpliedEndTags();
 
-                        /* Now, if the current node is not an element with
+						/* Now, if the current node is not an element with
                         the same tag name as that of the token, then this
                         is a parse error. */
-                        // w/e
+						// w/e
 
-                        /* If the stack of open elements has an element in
+						/* If the stack of open elements has an element in
                         scope with the same tag name as that of the token,
                         then pop elements from this stack until an element
                         with that tag name has been popped from the stack. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->stack[$n]->nodeName === $token['name']) {
-                                $n = -1;
-                            }
-
-                            array_pop($this->stack);
-                        }
-                    }
-                break;
-
-                /* An end tag whose tag name is "form" */
-                case 'form':
-                    /* If the stack of open elements has an element in scope
+						for($n = count($this->stack) - 1; $n >= 0; $n--) {
+							if($this->stack[$n]->nodeName === $token['name']) {
+								$n = -1;
+							}
+
+							array_pop($this->stack);
+						}
+					}
+				break;
+
+				/* An end tag whose tag name is "form" */
+				case 'form':
+					/* If the stack of open elements has an element in scope
                     with the same tag name as that of the token, then generate
                     implied    end tags. */
-                    if($this->elementInScope($token['name'])) {
-                        $this->generateImpliedEndTags();
+					if($this->elementInScope($token['name'])) {
+						$this->generateImpliedEndTags();
 
-                    } 
+					} 
 
-                    if(end($this->stack)->nodeName !== $token['name']) {
-                        /* Now, if the current node is not an element with the
+					if(end($this->stack)->nodeName !== $token['name']) {
+						/* Now, if the current node is not an element with the
                         same tag name as that of the token, then this is a parse
                         error. */
-                        // w/e
+						// w/e
 
-                    } else {
-                        /* Otherwise, if the current node is an element with
+					} else {
+						/* Otherwise, if the current node is an element with
                         the same tag name as that of the token pop that element
                         from the stack. */
-                        array_pop($this->stack);
-                    }
+						array_pop($this->stack);
+					}
 
-                    /* In any case, set the form element pointer to null. */
-                    $this->form_pointer = null;
-                break;
+					/* In any case, set the form element pointer to null. */
+					$this->form_pointer = null;
+				break;
 
-                /* An end tag whose tag name is "p" */
-                case 'p':
-                    /* If the stack of open elements has a p element in scope,
+				/* An end tag whose tag name is "p" */
+				case 'p':
+					/* If the stack of open elements has a p element in scope,
                     then generate implied end tags, except for p elements. */
-                    if($this->elementInScope('p')) {
-                        $this->generateImpliedEndTags(array('p'));
+					if($this->elementInScope('p')) {
+						$this->generateImpliedEndTags(array('p'));
 
-                        /* If the current node is not a p element, then this is
+						/* If the current node is not a p element, then this is
                         a parse error. */
-                        // k
+						// k
 
-                        /* If the stack of open elements has a p element in
+						/* If the stack of open elements has a p element in
                         scope, then pop elements from this stack until the stack
                         no longer has a p element in scope. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->elementInScope('p')) {
-                                array_pop($this->stack);
-
-                            } else {
-                                break;
-                            }
-                        }
-                    }
-                break;
-
-                /* An end tag whose tag name is "dd", "dt", or "li" */
-                case 'dd': case 'dt': case 'li':
-                    /* If the stack of open elements has an element in scope
+						for($n = count($this->stack) - 1; $n >= 0; $n--) {
+							if($this->elementInScope('p')) {
+								array_pop($this->stack);
+
+							} else {
+								break;
+							}
+						}
+					}
+				break;
+
+				/* An end tag whose tag name is "dd", "dt", or "li" */
+				case 'dd': case 'dt': case 'li':
+					/* If the stack of open elements has an element in scope
                     whose tag name matches the tag name of the token, then
                     generate implied end tags, except for elements with the
                     same tag name as the token. */
-                    if($this->elementInScope($token['name'])) {
-                        $this->generateImpliedEndTags(array($token['name']));
+					if($this->elementInScope($token['name'])) {
+						$this->generateImpliedEndTags(array($token['name']));
 
-                        /* If the current node is not an element with the same
+						/* If the current node is not an element with the same
                         tag name as the token, then this is a parse error. */
-                        // w/e
+						// w/e
 
-                        /* If the stack of open elements has an element in scope
+						/* If the stack of open elements has an element in scope
                         whose tag name matches the tag name of the token, then
                         pop elements from this stack until an element with that
                         tag name has been popped from the stack. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->stack[$n]->nodeName === $token['name']) {
-                                $n = -1;
-                            }
+						for($n = count($this->stack) - 1; $n >= 0; $n--) {
+							if($this->stack[$n]->nodeName === $token['name']) {
+								$n = -1;
+							}
 
-                            array_pop($this->stack);
-                        }
-                    }
-                break;
+							array_pop($this->stack);
+						}
+					}
+				break;
 
-                /* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
+				/* An end tag whose tag name is one of: "h1", "h2", "h3", "h4",
                 "h5", "h6" */
-                case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
-                    $elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
+				case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
+					$elements = array('h1', 'h2', 'h3', 'h4', 'h5', 'h6');
 
-                    /* If the stack of open elements has in scope an element whose
+					/* If the stack of open elements has in scope an element whose
                     tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
                     generate implied end tags. */
-                    if($this->elementInScope($elements)) {
-                        $this->generateImpliedEndTags();
+					if($this->elementInScope($elements)) {
+						$this->generateImpliedEndTags();
 
-                        /* Now, if the current node is not an element with the same
+						/* Now, if the current node is not an element with the same
                         tag name as that of the token, then this is a parse error. */
-                        // w/e
+						// w/e
 
-                        /* If the stack of open elements has in scope an element
+						/* If the stack of open elements has in scope an element
                         whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
                         "h6", then pop elements from the stack until an element
                         with one of those tag names has been popped from the stack. */
-                        while($this->elementInScope($elements)) {
-                            array_pop($this->stack);
-                        }
-                    }
-                break;
+						while($this->elementInScope($elements)) {
+							array_pop($this->stack);
+						}
+					}
+				break;
 
-                /* An end tag whose tag name is one of: "a", "b", "big", "em",
+				/* An end tag whose tag name is one of: "a", "b", "big", "em",
                 "font", "i", "nobr", "s", "small", "strike", "strong", "tt", "u" */
-                case 'a': case 'b': case 'big': case 'em': case 'font':
-                case 'i': case 'nobr': case 's': case 'small': case 'strike':
-                case 'strong': case 'tt': case 'u':
-                    /* 1. Let the formatting element be the last element in
+				case 'a': case 'b': case 'big': case 'em': case 'font':
+				case 'i': case 'nobr': case 's': case 'small': case 'strike':
+				case 'strong': case 'tt': case 'u':
+					/* 1. Let the formatting element be the last element in
                     the list of active formatting elements that:
                         * is between the end of the list and the last scope
                         marker in the list, if any, or the start of the list
                         otherwise, and
                         * has the same tag name as the token.
                     */
-                    while(true) {
-                        for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
-                            if($this->a_formatting[$a] === self::MARKER) {
-                                break;
-
-                            } elseif($this->a_formatting[$a]->tagName === $token['name']) {
-                                $formatting_element = $this->a_formatting[$a];
-                                $in_stack = in_array($formatting_element, $this->stack, true);
-                                $fe_af_pos = $a;
-                                break;
-                            }
-                        }
-
-                        /* If there is no such node, or, if that node is
+					while(true) {
+						for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
+							if($this->a_formatting[$a] === self::MARKER) {
+								break;
+
+							} elseif($this->a_formatting[$a]->tagName === $token['name']) {
+								$formatting_element = $this->a_formatting[$a];
+								$in_stack = in_array($formatting_element, $this->stack, true);
+								$fe_af_pos = $a;
+								break;
+							}
+						}
+
+						/* If there is no such node, or, if that node is
                         also in the stack of open elements but the element
                         is not in scope, then this is a parse error. Abort
                         these steps. The token is ignored. */
-                        if(!isset($formatting_element) || ($in_stack &&
-                        !$this->elementInScope($token['name']))) {
-                            break;
+						if(!isset($formatting_element) || ($in_stack &&
+						!$this->elementInScope($token['name']))) {
+							break;
 
-                        /* Otherwise, if there is such a node, but that node
+						/* Otherwise, if there is such a node, but that node
                         is not in the stack of open elements, then this is a
                         parse error; remove the element from the list, and
                         abort these steps. */
-                        } elseif(isset($formatting_element) && !$in_stack) {
-                            unset($this->a_formatting[$fe_af_pos]);
-                            $this->a_formatting = array_merge($this->a_formatting);
-                            break;
-                        }
+						} elseif(isset($formatting_element) && !$in_stack) {
+							unset($this->a_formatting[$fe_af_pos]);
+							$this->a_formatting = array_merge($this->a_formatting);
+							break;
+						}
 
-                        /* 2. Let the furthest block be the topmost node in the
+						/* 2. Let the furthest block be the topmost node in the
                         stack of open elements that is lower in the stack
                         than the formatting element, and is not an element in
                         the phrasing or formatting categories. There might
                         not be one. */
-                        $fe_s_pos = array_search($formatting_element, $this->stack, true);
-                        $length = count($this->stack);
+						$fe_s_pos = array_search($formatting_element, $this->stack, true);
+						$length = count($this->stack);
 
-                        for($s = $fe_s_pos + 1; $s < $length; $s++) {
-                            $category = $this->getElementCategory($this->stack[$s]->nodeName);
+						for($s = $fe_s_pos + 1; $s < $length; $s++) {
+							$category = $this->getElementCategory($this->stack[$s]->nodeName);
 
-                            if($category !== self::PHRASING && $category !== self::FORMATTING) {
-                                $furthest_block = $this->stack[$s];
-                            }
-                        }
+							if($category !== self::PHRASING && $category !== self::FORMATTING) {
+								$furthest_block = $this->stack[$s];
+							}
+						}
 
-                        /* 3. If there is no furthest block, then the UA must
+						/* 3. If there is no furthest block, then the UA must
                         skip the subsequent steps and instead just pop all
                         the nodes from the bottom of the stack of open
                         elements, from the current node up to the formatting
                         element, and remove the formatting element from the
                         list of active formatting elements. */
-                        if(!isset($furthest_block)) {
-                            for($n = $length - 1; $n >= $fe_s_pos; $n--) {
-                                array_pop($this->stack);
-                            }
+						if(!isset($furthest_block)) {
+							for($n = $length - 1; $n >= $fe_s_pos; $n--) {
+								array_pop($this->stack);
+							}
 
-                            unset($this->a_formatting[$fe_af_pos]);
-                            $this->a_formatting = array_merge($this->a_formatting);
-                            break;
-                        }
+							unset($this->a_formatting[$fe_af_pos]);
+							$this->a_formatting = array_merge($this->a_formatting);
+							break;
+						}
 
-                        /* 4. Let the common ancestor be the element
+						/* 4. Let the common ancestor be the element
                         immediately above the formatting element in the stack
                         of open elements. */
-                        $common_ancestor = $this->stack[$fe_s_pos - 1];
+						$common_ancestor = $this->stack[$fe_s_pos - 1];
 
-                        /* 5. If the furthest block has a parent node, then
+						/* 5. If the furthest block has a parent node, then
                         remove the furthest block from its parent node. */
-                        if($furthest_block->parentNode !== null) {
-                            $furthest_block->parentNode->removeChild($furthest_block);
-                        }
+						if($furthest_block->parentNode !== null) {
+							$furthest_block->parentNode->removeChild($furthest_block);
+						}
 
-                        /* 6. Let a bookmark note the position of the
+						/* 6. Let a bookmark note the position of the
                         formatting element in the list of active formatting
                         elements relative to the elements on either side
                         of it in the list. */
-                        $bookmark = $fe_af_pos;
+						$bookmark = $fe_af_pos;
 
-                        /* 7. Let node and last node  be the furthest block.
+						/* 7. Let node and last node  be the furthest block.
                         Follow these steps: */
-                        $node = $furthest_block;
-                        $last_node = $furthest_block;
+						$node = $furthest_block;
+						$last_node = $furthest_block;
 
-                        while(true) {
-                            for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
-                                /* 7.1 Let node be the element immediately
+						while(true) {
+							for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
+								/* 7.1 Let node be the element immediately
                                 prior to node in the stack of open elements. */
-                                $node = $this->stack[$n];
+								$node = $this->stack[$n];
 
-                                /* 7.2 If node is not in the list of active
+								/* 7.2 If node is not in the list of active
                                 formatting elements, then remove node from
                                 the stack of open elements and then go back
                                 to step 1. */
-                                if(!in_array($node, $this->a_formatting, true)) {
-                                    unset($this->stack[$n]);
-                                    $this->stack = array_merge($this->stack);
+								if(!in_array($node, $this->a_formatting, true)) {
+									unset($this->stack[$n]);
+									$this->stack = array_merge($this->stack);
 
-                                } else {
-                                    break;
-                                }
-                            }
+								} else {
+									break;
+								}
+							}
 
-                            /* 7.3 Otherwise, if node is the formatting
+							/* 7.3 Otherwise, if node is the formatting
                             element, then go to the next step in the overall
                             algorithm. */
-                            if($node === $formatting_element) {
-                                break;
+							if($node === $formatting_element) {
+								break;
 
-                            /* 7.4 Otherwise, if last node is the furthest
+							/* 7.4 Otherwise, if last node is the furthest
                             block, then move the aforementioned bookmark to
                             be immediately after the node in the list of
                             active formatting elements. */
-                            } elseif($last_node === $furthest_block) {
-                                $bookmark = array_search($node, $this->a_formatting, true) + 1;
-                            }
+							} elseif($last_node === $furthest_block) {
+								$bookmark = array_search($node, $this->a_formatting, true) + 1;
+							}
 
-                            /* 7.5 If node has any children, perform a
+							/* 7.5 If node has any children, perform a
                             shallow clone of node, replace the entry for
                             node in the list of active formatting elements
                             with an entry for the clone, replace the entry
                             for node in the stack of open elements with an
                             entry for the clone, and let node be the clone. */
-                            if($node->hasChildNodes()) {
-                                $clone = $node->cloneNode();
-                                $s_pos = array_search($node, $this->stack, true);
-                                $a_pos = array_search($node, $this->a_formatting, true);
+							if($node->hasChildNodes()) {
+								$clone = $node->cloneNode();
+								$s_pos = array_search($node, $this->stack, true);
+								$a_pos = array_search($node, $this->a_formatting, true);
 
-                                $this->stack[$s_pos] = $clone;
-                                $this->a_formatting[$a_pos] = $clone;
-                                $node = $clone;
-                            }
+								$this->stack[$s_pos] = $clone;
+								$this->a_formatting[$a_pos] = $clone;
+								$node = $clone;
+							}
 
-                            /* 7.6 Insert last node into node, first removing
+							/* 7.6 Insert last node into node, first removing
                             it from its previous parent node if any. */
-                            if($last_node->parentNode !== null) {
-                                $last_node->parentNode->removeChild($last_node);
-                            }
+							if($last_node->parentNode !== null) {
+								$last_node->parentNode->removeChild($last_node);
+							}
 
-                            $node->appendChild($last_node);
+							$node->appendChild($last_node);
 
-                            /* 7.7 Let last node be node. */
-                            $last_node = $node;
-                        }
+							/* 7.7 Let last node be node. */
+							$last_node = $node;
+						}
 
-                        /* 8. Insert whatever last node ended up being in
+						/* 8. Insert whatever last node ended up being in
                         the previous step into the common ancestor node,
                         first removing it from its previous parent node if
                         any. */
-                        if($last_node->parentNode !== null) {
-                            $last_node->parentNode->removeChild($last_node);
-                        }
+						if($last_node->parentNode !== null) {
+							$last_node->parentNode->removeChild($last_node);
+						}
 
-                        $common_ancestor->appendChild($last_node);
+						$common_ancestor->appendChild($last_node);
 
-                        /* 9. Perform a shallow clone of the formatting
+						/* 9. Perform a shallow clone of the formatting
                         element. */
-                        $clone = $formatting_element->cloneNode();
+						$clone = $formatting_element->cloneNode();
 
-                        /* 10. Take all of the child nodes of the furthest
+						/* 10. Take all of the child nodes of the furthest
                         block and append them to the clone created in the
                         last step. */
-                        while($furthest_block->hasChildNodes()) {
-                            $child = $furthest_block->firstChild;
-                            $furthest_block->removeChild($child);
-                            $clone->appendChild($child);
-                        }
+						while($furthest_block->hasChildNodes()) {
+							$child = $furthest_block->firstChild;
+							$furthest_block->removeChild($child);
+							$clone->appendChild($child);
+						}
 
-                        /* 11. Append that clone to the furthest block. */
-                        $furthest_block->appendChild($clone);
+						/* 11. Append that clone to the furthest block. */
+						$furthest_block->appendChild($clone);
 
-                        /* 12. Remove the formatting element from the list
+						/* 12. Remove the formatting element from the list
                         of active formatting elements, and insert the clone
                         into the list of active formatting elements at the
                         position of the aforementioned bookmark. */
-                        $fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
-                        unset($this->a_formatting[$fe_af_pos]);
-                        $this->a_formatting = array_merge($this->a_formatting);
+						$fe_af_pos = array_search($formatting_element, $this->a_formatting, true);
+						unset($this->a_formatting[$fe_af_pos]);
+						$this->a_formatting = array_merge($this->a_formatting);
 
-                        $af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
-                        $af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
-                        $this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
+						$af_part1 = array_slice($this->a_formatting, 0, $bookmark - 1);
+						$af_part2 = array_slice($this->a_formatting, $bookmark, count($this->a_formatting));
+						$this->a_formatting = array_merge($af_part1, array($clone), $af_part2);
 
-                        /* 13. Remove the formatting element from the stack
+						/* 13. Remove the formatting element from the stack
                         of open elements, and insert the clone into the stack
                         of open elements immediately after (i.e. in a more
                         deeply nested position than) the position of the
                         furthest block in that stack. */
-                        $fe_s_pos = array_search($formatting_element, $this->stack, true);
-                        $fb_s_pos = array_search($furthest_block, $this->stack, true);
-                        unset($this->stack[$fe_s_pos]);
+						$fe_s_pos = array_search($formatting_element, $this->stack, true);
+						$fb_s_pos = array_search($furthest_block, $this->stack, true);
+						unset($this->stack[$fe_s_pos]);
 
-                        $s_part1 = array_slice($this->stack, 0, $fb_s_pos);
-                        $s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
-                        $this->stack = array_merge($s_part1, array($clone), $s_part2);
+						$s_part1 = array_slice($this->stack, 0, $fb_s_pos);
+						$s_part2 = array_slice($this->stack, $fb_s_pos + 1, count($this->stack));
+						$this->stack = array_merge($s_part1, array($clone), $s_part2);
 
-                        /* 14. Jump back to step 1 in this series of steps. */
-                        unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
-                    }
-                break;
+						/* 14. Jump back to step 1 in this series of steps. */
+						unset($formatting_element, $fe_af_pos, $fe_s_pos, $furthest_block);
+					}
+				break;
 
-                /* An end tag token whose tag name is one of: "button",
+				/* An end tag token whose tag name is one of: "button",
                 "marquee", "object" */
-                case 'button': case 'marquee': case 'object':
-                    /* If the stack of open elements has an element in scope whose
+				case 'button': case 'marquee': case 'object':
+					/* If the stack of open elements has an element in scope whose
                     tag name matches the tag name of the token, then generate implied
                     tags. */
-                    if($this->elementInScope($token['name'])) {
-                        $this->generateImpliedEndTags();
+					if($this->elementInScope($token['name'])) {
+						$this->generateImpliedEndTags();
 
-                        /* Now, if the current node is not an element with the same
+						/* Now, if the current node is not an element with the same
                         tag name as the token, then this is a parse error. */
-                        // k
+						// k
 
-                        /* Now, if the stack of open elements has an element in scope
+						/* Now, if the stack of open elements has an element in scope
                         whose tag name matches the tag name of the token, then pop
                         elements from the stack until that element has been popped from
                         the stack, and clear the list of active formatting elements up
                         to the last marker. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->stack[$n]->nodeName === $token['name']) {
-                                $n = -1;
-                            }
+						for($n = count($this->stack) - 1; $n >= 0; $n--) {
+							if($this->stack[$n]->nodeName === $token['name']) {
+								$n = -1;
+							}
 
-                            array_pop($this->stack);
-                        }
+							array_pop($this->stack);
+						}
 
-                        $marker = end(array_keys($this->a_formatting, self::MARKER, true));
+						$marker = end(array_keys($this->a_formatting, self::MARKER, true));
 
-                        for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
-                            array_pop($this->a_formatting);
-                        }
-                    }
-                break;
+						for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
+							array_pop($this->a_formatting);
+						}
+					}
+				break;
 
-                /* Or an end tag whose tag name is one of: "area", "basefont",
+				/* Or an end tag whose tag name is one of: "area", "basefont",
                 "bgsound", "br", "embed", "hr", "iframe", "image", "img",
                 "input", "isindex", "noembed", "noframes", "param", "select",
                 "spacer", "table", "textarea", "wbr" */
-                case 'area': case 'basefont': case 'bgsound': case 'br':
-                case 'embed': case 'hr': case 'iframe': case 'image':
-                case 'img': case 'input': case 'isindex': case 'noembed':
-                case 'noframes': case 'param': case 'select': case 'spacer':
-                case 'table': case 'textarea': case 'wbr':
-                    // Parse error. Ignore the token.
-                break;
-
-                /* An end tag token not covered by the previous entries */
-                default:
-                    for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                        /* Initialise node to be the current node (the bottommost
+				case 'area': case 'basefont': case 'bgsound': case 'br':
+				case 'embed': case 'hr': case 'iframe': case 'image':
+				case 'img': case 'input': case 'isindex': case 'noembed':
+				case 'noframes': case 'param': case 'select': case 'spacer':
+				case 'table': case 'textarea': case 'wbr':
+					// Parse error. Ignore the token.
+				break;
+
+				/* An end tag token not covered by the previous entries */
+				default:
+					for($n = count($this->stack) - 1; $n >= 0; $n--) {
+						/* Initialise node to be the current node (the bottommost
                         node of the stack). */
-                        $node = end($this->stack);
+						$node = end($this->stack);
 
-                        /* If node has the same tag name as the end tag token,
+						/* If node has the same tag name as the end tag token,
                         then: */
-                        if($token['name'] === $node->nodeName) {
-                            /* Generate implied end tags. */
-                            $this->generateImpliedEndTags();
+						if($token['name'] === $node->nodeName) {
+							/* Generate implied end tags. */
+							$this->generateImpliedEndTags();
 
-                            /* If the tag name of the end tag token does not
+							/* If the tag name of the end tag token does not
                             match the tag name of the current node, this is a
                             parse error. */
-                            // k
+							// k
 
-                            /* Pop all the nodes from the current node up to
+							/* Pop all the nodes from the current node up to
                             node, including node, then stop this algorithm. */
-                            for($x = count($this->stack) - $n; $x >= $n; $x--) {
-                                array_pop($this->stack);
-                            }
+							for($x = count($this->stack) - $n; $x >= $n; $x--) {
+								array_pop($this->stack);
+							}
                                     
-                        } else {
-                            $category = $this->getElementCategory($node);
+						} else {
+							$category = $this->getElementCategory($node);
 
-                            if($category !== self::SPECIAL && $category !== self::SCOPING) {
-                                /* Otherwise, if node is in neither the formatting
+							if($category !== self::SPECIAL && $category !== self::SCOPING) {
+								/* Otherwise, if node is in neither the formatting
                                 category nor the phrasing category, then this is a
                                 parse error. Stop this algorithm. The end tag token
                                 is ignored. */
-                                return false;
-                            }
-                        }
-                    }
-                break;
-            }
-            break;
-        }
-    }
-
-    private function inTable($token) {
-        $clear = array('html', 'table');
-
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+								return false;
+							}
+						}
+					}
+				break;
+			}
+			break;
+		}
+	}
+
+	private function inTable($token) {
+		$clear = array('html', 'table');
+
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append the character to the current node. */
-            $text = $this->dom->createTextNode($token['data']);
-            end($this->stack)->appendChild($text);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append the character to the current node. */
+			$text = $this->dom->createTextNode($token['data']);
+			end($this->stack)->appendChild($text);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
-            $comment = $this->dom->createComment($token['data']);
-            end($this->stack)->appendChild($comment);
+			$comment = $this->dom->createComment($token['data']);
+			end($this->stack)->appendChild($comment);
 
-        /* A start tag whose tag name is "caption" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        $token['name'] === 'caption') {
-            /* Clear the stack back to a table context. */
-            $this->clearStackToTableContext($clear);
+		/* A start tag whose tag name is "caption" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		$token['name'] === 'caption') {
+			/* Clear the stack back to a table context. */
+			$this->clearStackToTableContext($clear);
 
-            /* Insert a marker at the end of the list of active
+			/* Insert a marker at the end of the list of active
             formatting elements. */
-            $this->a_formatting[] = self::MARKER;
+			$this->a_formatting[] = self::MARKER;
 
-            /* Insert an HTML element for the token, then switch the
+			/* Insert an HTML element for the token, then switch the
             insertion mode to "in caption". */
-            $this->insertElement($token);
-            $this->mode = self::IN_CAPTION;
+			$this->insertElement($token);
+			$this->mode = self::IN_CAPTION;
 
-        /* A start tag whose tag name is "colgroup" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        $token['name'] === 'colgroup') {
-            /* Clear the stack back to a table context. */
-            $this->clearStackToTableContext($clear);
+		/* A start tag whose tag name is "colgroup" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		$token['name'] === 'colgroup') {
+			/* Clear the stack back to a table context. */
+			$this->clearStackToTableContext($clear);
 
-            /* Insert an HTML element for the token, then switch the
+			/* Insert an HTML element for the token, then switch the
             insertion mode to "in column group". */
-            $this->insertElement($token);
-            $this->mode = self::IN_CGROUP;
-
-        /* A start tag whose tag name is "col" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        $token['name'] === 'col') {
-            $this->inTable(array(
-                'name' => 'colgroup',
-                'type' => HTML5::STARTTAG,
-                'attr' => array()
-            ));
-
-            $this->inColumnGroup($token);
-
-        /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('tbody', 'tfoot', 'thead'))) {
-            /* Clear the stack back to a table context. */
-            $this->clearStackToTableContext($clear);
-
-            /* Insert an HTML element for the token, then switch the insertion
+			$this->insertElement($token);
+			$this->mode = self::IN_CGROUP;
+
+		/* A start tag whose tag name is "col" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		$token['name'] === 'col') {
+			$this->inTable(array(
+				'name' => 'colgroup',
+				'type' => HTML5::STARTTAG,
+				'attr' => array()
+			));
+
+			$this->inColumnGroup($token);
+
+		/* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
+		} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('tbody', 'tfoot', 'thead'))) {
+			/* Clear the stack back to a table context. */
+			$this->clearStackToTableContext($clear);
+
+			/* Insert an HTML element for the token, then switch the insertion
             mode to "in table body". */
-            $this->insertElement($token);
-            $this->mode = self::IN_TBODY;
+			$this->insertElement($token);
+			$this->mode = self::IN_TBODY;
 
-        /* A start tag whose tag name is one of: "td", "th", "tr" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        in_array($token['name'], array('td', 'th', 'tr'))) {
-            /* Act as if a start tag token with the tag name "tbody" had been
+		/* A start tag whose tag name is one of: "td", "th", "tr" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		in_array($token['name'], array('td', 'th', 'tr'))) {
+			/* Act as if a start tag token with the tag name "tbody" had been
             seen, then reprocess the current token. */
-            $this->inTable(array(
-                'name' => 'tbody',
-                'type' => HTML5::STARTTAG,
-                'attr' => array()
-            ));
-
-            return $this->inTableBody($token);
-
-        /* A start tag whose tag name is "table" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        $token['name'] === 'table') {
-            /* Parse error. Act as if an end tag token with the tag name "table"
+			$this->inTable(array(
+				'name' => 'tbody',
+				'type' => HTML5::STARTTAG,
+				'attr' => array()
+			));
+
+			return $this->inTableBody($token);
+
+		/* A start tag whose tag name is "table" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		$token['name'] === 'table') {
+			/* Parse error. Act as if an end tag token with the tag name "table"
             had been seen, then, if that token wasn't ignored, reprocess the
             current token. */
-            $this->inTable(array(
-                'name' => 'table',
-                'type' => HTML5::ENDTAG
-            ));
+			$this->inTable(array(
+				'name' => 'table',
+				'type' => HTML5::ENDTAG
+			));
 
-            return $this->mainPhase($token);
+			return $this->mainPhase($token);
 
-        /* An end tag whose tag name is "table" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        $token['name'] === 'table') {
-            /* If the stack of open elements does not have an element in table
+		/* An end tag whose tag name is "table" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		$token['name'] === 'table') {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
-                return false;
+			if(!$this->elementInScope($token['name'], true)) {
+				return false;
 
-            /* Otherwise: */
-            } else {
-                /* Generate implied end tags. */
-                $this->generateImpliedEndTags();
+			/* Otherwise: */
+			} else {
+				/* Generate implied end tags. */
+				$this->generateImpliedEndTags();
 
-                /* Now, if the current node is not a table element, then this
+				/* Now, if the current node is not a table element, then this
                 is a parse error. */
-                // w/e
+				// w/e
 
-                /* Pop elements from this stack until a table element has been
+				/* Pop elements from this stack until a table element has been
                 popped from the stack. */
-                while(true) {
-                    $current = end($this->stack)->nodeName;
-                    array_pop($this->stack);
+				while(true) {
+					$current = end($this->stack)->nodeName;
+					array_pop($this->stack);
 
-                    if($current === 'table') {
-                        break;
-                    }
-                }
+					if($current === 'table') {
+						break;
+					}
+				}
 
-                /* Reset the insertion mode appropriately. */
-                $this->resetInsertionMode();
-            }
+				/* Reset the insertion mode appropriately. */
+				$this->resetInsertionMode();
+			}
 
-        /* An end tag whose tag name is one of: "body", "caption", "col",
+		/* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
-        array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
-        'tfoot', 'th', 'thead', 'tr'))) {
-            // Parse error. Ignore the token.
-
-        /* Anything else */
-        } else {
-            /* Parse error. Process the token as if the insertion mode was "in
+		} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+		array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
+		'tfoot', 'th', 'thead', 'tr'))) {
+			// Parse error. Ignore the token.
+
+		/* Anything else */
+		} else {
+			/* Parse error. Process the token as if the insertion mode was "in
             body", with the following exception: */
 
-            /* If the current node is a table, tbody, tfoot, thead, or tr
+			/* If the current node is a table, tbody, tfoot, thead, or tr
             element, then, whenever a node would be inserted into the current
             node, it must instead be inserted into the foster parent element. */
-            if(in_array(end($this->stack)->nodeName,
-            array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
-                /* The foster parent element is the parent element of the last
+			if(in_array(end($this->stack)->nodeName,
+			array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
+				/* The foster parent element is the parent element of the last
                 table element in the stack of open elements, if there is a
                 table element and it has such a parent element. If there is no
                 table element in the stack of open elements (innerHTML case),
@@ -2781,1124 +2781,1124 @@ 
                 its parent node is not an element, then the foster parent
                 element is the element before the last table element in the
                 stack of open elements. */
-                for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                    if($this->stack[$n]->nodeName === 'table') {
-                        $table = $this->stack[$n];
-                        break;
-                    }
-                }
-
-                if(isset($table) && $table->parentNode !== null) {
-                    $this->foster_parent = $table->parentNode;
-
-                } elseif(!isset($table)) {
-                    $this->foster_parent = $this->stack[0];
-
-                } elseif(isset($table) && ($table->parentNode === null ||
-                $table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
-                    $this->foster_parent = $this->stack[$n - 1];
-                }
-            }
-
-            $this->inBody($token);
-        }
-    }
-
-    private function inCaption($token) {
-        /* An end tag whose tag name is "caption" */
-        if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
-            /* If the stack of open elements does not have an element in table
+				for($n = count($this->stack) - 1; $n >= 0; $n--) {
+					if($this->stack[$n]->nodeName === 'table') {
+						$table = $this->stack[$n];
+						break;
+					}
+				}
+
+				if(isset($table) && $table->parentNode !== null) {
+					$this->foster_parent = $table->parentNode;
+
+				} elseif(!isset($table)) {
+					$this->foster_parent = $this->stack[0];
+
+				} elseif(isset($table) && ($table->parentNode === null ||
+				$table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
+					$this->foster_parent = $this->stack[$n - 1];
+				}
+			}
+
+			$this->inBody($token);
+		}
+	}
+
+	private function inCaption($token) {
+		/* An end tag whose tag name is "caption" */
+		if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
-                // Ignore
+			if(!$this->elementInScope($token['name'], true)) {
+				// Ignore
 
-            /* Otherwise: */
-            } else {
-                /* Generate implied end tags. */
-                $this->generateImpliedEndTags();
+			/* Otherwise: */
+			} else {
+				/* Generate implied end tags. */
+				$this->generateImpliedEndTags();
 
-                /* Now, if the current node is not a caption element, then this
+				/* Now, if the current node is not a caption element, then this
                 is a parse error. */
-                // w/e
+				// w/e
 
-                /* Pop elements from this stack until a caption element has
+				/* Pop elements from this stack until a caption element has
                 been popped from the stack. */
-                while(true) {
-                    $node = end($this->stack)->nodeName;
-                    array_pop($this->stack);
+				while(true) {
+					$node = end($this->stack)->nodeName;
+					array_pop($this->stack);
 
-                    if($node === 'caption') {
-                        break;
-                    }
-                }
+					if($node === 'caption') {
+						break;
+					}
+				}
 
-                /* Clear the list of active formatting elements up to the last
+				/* Clear the list of active formatting elements up to the last
                 marker. */
-                $this->clearTheActiveFormattingElementsUpToTheLastMarker();
+				$this->clearTheActiveFormattingElementsUpToTheLastMarker();
 
-                /* Switch the insertion mode to "in table". */
-                $this->mode = self::IN_TABLE;
-            }
+				/* Switch the insertion mode to "in table". */
+				$this->mode = self::IN_TABLE;
+			}
 
-        /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+		/* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
         name is "table" */
-        } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
-        'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
-        $token['name'] === 'table')) {
-            /* Parse error. Act as if an end tag with the tag name "caption"
+		} elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
+		'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
+		$token['name'] === 'table')) {
+			/* Parse error. Act as if an end tag with the tag name "caption"
             had been seen, then, if that token wasn't ignored, reprocess the
             current token. */
-            $this->inCaption(array(
-                'name' => 'caption',
-                'type' => HTML5::ENDTAG
-            ));
+			$this->inCaption(array(
+				'name' => 'caption',
+				'type' => HTML5::ENDTAG
+			));
 
-            return $this->inTable($token);
+			return $this->inTable($token);
 
-        /* An end tag whose tag name is one of: "body", "col", "colgroup",
+		/* An end tag whose tag name is one of: "body", "col", "colgroup",
         "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
-        array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
-        'thead', 'tr'))) {
-            // Parse error. Ignore the token.
-
-        /* Anything else */
-        } else {
-            /* Process the token as if the insertion mode was "in body". */
-            $this->inBody($token);
-        }
-    }
-
-    private function inColumnGroup($token) {
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+		array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
+		'thead', 'tr'))) {
+			// Parse error. Ignore the token.
+
+		/* Anything else */
+		} else {
+			/* Process the token as if the insertion mode was "in body". */
+			$this->inBody($token);
+		}
+	}
+
+	private function inColumnGroup($token) {
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append the character to the current node. */
-            $text = $this->dom->createTextNode($token['data']);
-            end($this->stack)->appendChild($text);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append the character to the current node. */
+			$text = $this->dom->createTextNode($token['data']);
+			end($this->stack)->appendChild($text);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
-            $comment = $this->dom->createComment($token['data']);
-            end($this->stack)->appendChild($comment);
+			$comment = $this->dom->createComment($token['data']);
+			end($this->stack)->appendChild($comment);
 
-        /* A start tag whose tag name is "col" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
-            /* Insert a col element for the token. Immediately pop the current
+		/* A start tag whose tag name is "col" */
+		} elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
+			/* Insert a col element for the token. Immediately pop the current
             node off the stack of open elements. */
-            $this->insertElement($token);
-            array_pop($this->stack);
+			$this->insertElement($token);
+			array_pop($this->stack);
 
-        /* An end tag whose tag name is "colgroup" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        $token['name'] === 'colgroup') {
-            /* If the current node is the root html element, then this is a
+		/* An end tag whose tag name is "colgroup" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		$token['name'] === 'colgroup') {
+			/* If the current node is the root html element, then this is a
             parse error, ignore the token. (innerHTML case) */
-            if(end($this->stack)->nodeName === 'html') {
-                // Ignore
+			if(end($this->stack)->nodeName === 'html') {
+				// Ignore
 
-            /* Otherwise, pop the current node (which will be a colgroup
+			/* Otherwise, pop the current node (which will be a colgroup
             element) from the stack of open elements. Switch the insertion
             mode to "in table". */
-            } else {
-                array_pop($this->stack);
-                $this->mode = self::IN_TABLE;
-            }
-
-        /* An end tag whose tag name is "col" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
-            /* Parse error. Ignore the token. */
-
-        /* Anything else */
-        } else {
-            /* Act as if an end tag with the tag name "colgroup" had been seen,
+			} else {
+				array_pop($this->stack);
+				$this->mode = self::IN_TABLE;
+			}
+
+		/* An end tag whose tag name is "col" */
+		} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
+			/* Parse error. Ignore the token. */
+
+		/* Anything else */
+		} else {
+			/* Act as if an end tag with the tag name "colgroup" had been seen,
             and then, if that token wasn't ignored, reprocess the current token. */
-            $this->inColumnGroup(array(
-                'name' => 'colgroup',
-                'type' => HTML5::ENDTAG
-            ));
+			$this->inColumnGroup(array(
+				'name' => 'colgroup',
+				'type' => HTML5::ENDTAG
+			));
 
-            return $this->inTable($token);
-        }
-    }
+			return $this->inTable($token);
+		}
+	}
 
-    private function inTableBody($token) {
-        $clear = array('tbody', 'tfoot', 'thead', 'html');
+	private function inTableBody($token) {
+		$clear = array('tbody', 'tfoot', 'thead', 'html');
 
-        /* A start tag whose tag name is "tr" */
-        if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
-            /* Clear the stack back to a table body context. */
-            $this->clearStackToTableContext($clear);
+		/* A start tag whose tag name is "tr" */
+		if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
+			/* Clear the stack back to a table body context. */
+			$this->clearStackToTableContext($clear);
 
-            /* Insert a tr element for the token, then switch the insertion
+			/* Insert a tr element for the token, then switch the insertion
             mode to "in row". */
-            $this->insertElement($token);
-            $this->mode = self::IN_ROW;
+			$this->insertElement($token);
+			$this->mode = self::IN_ROW;
 
-        /* A start tag whose tag name is one of: "th", "td" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        ($token['name'] === 'th' ||    $token['name'] === 'td')) {
-            /* Parse error. Act as if a start tag with the tag name "tr" had
+		/* A start tag whose tag name is one of: "th", "td" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		($token['name'] === 'th' ||    $token['name'] === 'td')) {
+			/* Parse error. Act as if a start tag with the tag name "tr" had
             been seen, then reprocess the current token. */
-            $this->inTableBody(array(
-                'name' => 'tr',
-                'type' => HTML5::STARTTAG,
-                'attr' => array()
-            ));
-
-            return $this->inRow($token);
-
-        /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
-            /* If the stack of open elements does not have an element in table
+			$this->inTableBody(array(
+				'name' => 'tr',
+				'type' => HTML5::STARTTAG,
+				'attr' => array()
+			));
+
+			return $this->inRow($token);
+
+		/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. */
-            if(!$this->elementInScope($token['name'], true)) {
-                // Ignore
+			if(!$this->elementInScope($token['name'], true)) {
+				// Ignore
 
-            /* Otherwise: */
-            } else {
-                /* Clear the stack back to a table body context. */
-                $this->clearStackToTableContext($clear);
+			/* Otherwise: */
+			} else {
+				/* Clear the stack back to a table body context. */
+				$this->clearStackToTableContext($clear);
 
-                /* Pop the current node from the stack of open elements. Switch
+				/* Pop the current node from the stack of open elements. Switch
                 the insertion mode to "in table". */
-                array_pop($this->stack);
-                $this->mode = self::IN_TABLE;
-            }
+				array_pop($this->stack);
+				$this->mode = self::IN_TABLE;
+			}
 
-        /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+		/* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
-        } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
-        ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
-            /* If the stack of open elements does not have a tbody, thead, or
+		} elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
+		($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
+			/* If the stack of open elements does not have a tbody, thead, or
             tfoot element in table scope, this is a parse error. Ignore the
             token. (innerHTML case) */
-            if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
-                // Ignore.
+			if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
+				// Ignore.
 
-            /* Otherwise: */
-            } else {
-                /* Clear the stack back to a table body context. */
-                $this->clearStackToTableContext($clear);
+			/* Otherwise: */
+			} else {
+				/* Clear the stack back to a table body context. */
+				$this->clearStackToTableContext($clear);
 
-                /* Act as if an end tag with the same tag name as the current
+				/* Act as if an end tag with the same tag name as the current
                 node ("tbody", "tfoot", or "thead") had been seen, then
                 reprocess the current token. */
-                $this->inTableBody(array(
-                    'name' => end($this->stack)->nodeName,
-                    'type' => HTML5::ENDTAG
-                ));
+				$this->inTableBody(array(
+					'name' => end($this->stack)->nodeName,
+					'type' => HTML5::ENDTAG
+				));
 
-                return $this->mainPhase($token);
-            }
+				return $this->mainPhase($token);
+			}
 
-        /* An end tag whose tag name is one of: "body", "caption", "col",
+		/* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html", "td", "th", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
-        array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
-            /* Parse error. Ignore the token. */
-
-        /* Anything else */
-        } else {
-            /* Process the token as if the insertion mode was "in table". */
-            $this->inTable($token);
-        }
-    }
-
-    private function inRow($token) {
-        $clear = array('tr', 'html');
-
-        /* A start tag whose tag name is one of: "th", "td" */
-        if($token['type'] === HTML5::STARTTAG &&
-        ($token['name'] === 'th' || $token['name'] === 'td')) {
-            /* Clear the stack back to a table row context. */
-            $this->clearStackToTableContext($clear);
-
-            /* Insert an HTML element for the token, then switch the insertion
+		} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+		array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
+			/* Parse error. Ignore the token. */
+
+		/* Anything else */
+		} else {
+			/* Process the token as if the insertion mode was "in table". */
+			$this->inTable($token);
+		}
+	}
+
+	private function inRow($token) {
+		$clear = array('tr', 'html');
+
+		/* A start tag whose tag name is one of: "th", "td" */
+		if($token['type'] === HTML5::STARTTAG &&
+		($token['name'] === 'th' || $token['name'] === 'td')) {
+			/* Clear the stack back to a table row context. */
+			$this->clearStackToTableContext($clear);
+
+			/* Insert an HTML element for the token, then switch the insertion
             mode to "in cell". */
-            $this->insertElement($token);
-            $this->mode = self::IN_CELL;
+			$this->insertElement($token);
+			$this->mode = self::IN_CELL;
 
-            /* Insert a marker at the end of the list of active formatting
+			/* Insert a marker at the end of the list of active formatting
             elements. */
-            $this->a_formatting[] = self::MARKER;
+			$this->a_formatting[] = self::MARKER;
 
-        /* An end tag whose tag name is "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
-            /* If the stack of open elements does not have an element in table
+		/* An end tag whose tag name is "tr" */
+		} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
-                // Ignore.
+			if(!$this->elementInScope($token['name'], true)) {
+				// Ignore.
 
-            /* Otherwise: */
-            } else {
-                /* Clear the stack back to a table row context. */
-                $this->clearStackToTableContext($clear);
+			/* Otherwise: */
+			} else {
+				/* Clear the stack back to a table row context. */
+				$this->clearStackToTableContext($clear);
 
-                /* Pop the current node (which will be a tr element) from the
+				/* Pop the current node (which will be a tr element) from the
                 stack of open elements. Switch the insertion mode to "in table
                 body". */
-                array_pop($this->stack);
-                $this->mode = self::IN_TBODY;
-            }
+				array_pop($this->stack);
+				$this->mode = self::IN_TBODY;
+			}
 
-        /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+		/* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
-            /* Act as if an end tag with the tag name "tr" had been seen, then,
+		} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
+			/* Act as if an end tag with the tag name "tr" had been seen, then,
             if that token wasn't ignored, reprocess the current token. */
-            $this->inRow(array(
-                'name' => 'tr',
-                'type' => HTML5::ENDTAG
-            ));
+			$this->inRow(array(
+				'name' => 'tr',
+				'type' => HTML5::ENDTAG
+			));
 
-            return $this->inCell($token);
+			return $this->inCell($token);
 
-        /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
-            /* If the stack of open elements does not have an element in table
+		/* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. */
-            if(!$this->elementInScope($token['name'], true)) {
-                // Ignore.
+			if(!$this->elementInScope($token['name'], true)) {
+				// Ignore.
 
-            /* Otherwise: */
-            } else {
-                /* Otherwise, act as if an end tag with the tag name "tr" had
+			/* Otherwise: */
+			} else {
+				/* Otherwise, act as if an end tag with the tag name "tr" had
                 been seen, then reprocess the current token. */
-                $this->inRow(array(
-                    'name' => 'tr',
-                    'type' => HTML5::ENDTAG
-                ));
+				$this->inRow(array(
+					'name' => 'tr',
+					'type' => HTML5::ENDTAG
+				));
 
-                return $this->inCell($token);
-            }
+				return $this->inCell($token);
+			}
 
-        /* An end tag whose tag name is one of: "body", "caption", "col",
+		/* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html", "td", "th" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
-        array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
-            /* Parse error. Ignore the token. */
-
-        /* Anything else */
-        } else {
-            /* Process the token as if the insertion mode was "in table". */
-            $this->inTable($token);
-        }
-    }
-
-    private function inCell($token) {
-        /* An end tag whose tag name is one of: "td", "th" */
-        if($token['type'] === HTML5::ENDTAG &&
-        ($token['name'] === 'td' || $token['name'] === 'th')) {
-            /* If the stack of open elements does not have an element in table
+		} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+		array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
+			/* Parse error. Ignore the token. */
+
+		/* Anything else */
+		} else {
+			/* Process the token as if the insertion mode was "in table". */
+			$this->inTable($token);
+		}
+	}
+
+	private function inCell($token) {
+		/* An end tag whose tag name is one of: "td", "th" */
+		if($token['type'] === HTML5::ENDTAG &&
+		($token['name'] === 'td' || $token['name'] === 'th')) {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as that of the token, then this is a
             parse error and the token must be ignored. */
-            if(!$this->elementInScope($token['name'], true)) {
-                // Ignore.
+			if(!$this->elementInScope($token['name'], true)) {
+				// Ignore.
 
-            /* Otherwise: */
-            } else {
-                /* Generate implied end tags, except for elements with the same
+			/* Otherwise: */
+			} else {
+				/* Generate implied end tags, except for elements with the same
                 tag name as the token. */
-                $this->generateImpliedEndTags(array($token['name']));
+				$this->generateImpliedEndTags(array($token['name']));
 
-                /* Now, if the current node is not an element with the same tag
+				/* Now, if the current node is not an element with the same tag
                 name as the token, then this is a parse error. */
-                // k
+				// k
 
-                /* Pop elements from this stack until an element with the same
+				/* Pop elements from this stack until an element with the same
                 tag name as the token has been popped from the stack. */
-                while(true) {
-                    $node = end($this->stack)->nodeName;
-                    array_pop($this->stack);
+				while(true) {
+					$node = end($this->stack)->nodeName;
+					array_pop($this->stack);
 
-                    if($node === $token['name']) {
-                        break;
-                    }
-                }
+					if($node === $token['name']) {
+						break;
+					}
+				}
 
-                /* Clear the list of active formatting elements up to the last
+				/* Clear the list of active formatting elements up to the last
                 marker. */
-                $this->clearTheActiveFormattingElementsUpToTheLastMarker();
+				$this->clearTheActiveFormattingElementsUpToTheLastMarker();
 
-                /* Switch the insertion mode to "in row". (The current node
+				/* Switch the insertion mode to "in row". (The current node
                 will be a tr element at this point.) */
-                $this->mode = self::IN_ROW;
-            }
+				$this->mode = self::IN_ROW;
+			}
 
-        /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+		/* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
-        'thead', 'tr'))) {
-            /* If the stack of open elements does not have a td or th element
+		} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
+		'thead', 'tr'))) {
+			/* If the stack of open elements does not have a td or th element
             in table scope, then this is a parse error; ignore the token.
             (innerHTML case) */
-            if(!$this->elementInScope(array('td', 'th'), true)) {
-                // Ignore.
+			if(!$this->elementInScope(array('td', 'th'), true)) {
+				// Ignore.
 
-            /* Otherwise, close the cell (see below) and reprocess the current
+			/* Otherwise, close the cell (see below) and reprocess the current
             token. */
-            } else {
-                $this->closeCell();
-                return $this->inRow($token);
-            }
+			} else {
+				$this->closeCell();
+				return $this->inRow($token);
+			}
 
-        /* A start tag whose tag name is one of: "caption", "col", "colgroup",
+		/* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
-        array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
-        'thead', 'tr'))) {
-            /* If the stack of open elements does not have a td or th element
+		} elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+		array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
+		'thead', 'tr'))) {
+			/* If the stack of open elements does not have a td or th element
             in table scope, then this is a parse error; ignore the token.
             (innerHTML case) */
-            if(!$this->elementInScope(array('td', 'th'), true)) {
-                // Ignore.
+			if(!$this->elementInScope(array('td', 'th'), true)) {
+				// Ignore.
 
-            /* Otherwise, close the cell (see below) and reprocess the current
+			/* Otherwise, close the cell (see below) and reprocess the current
             token. */
-            } else {
-                $this->closeCell();
-                return $this->inRow($token);
-            }
+			} else {
+				$this->closeCell();
+				return $this->inRow($token);
+			}
 
-        /* An end tag whose tag name is one of: "body", "caption", "col",
+		/* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
-        array('body', 'caption', 'col', 'colgroup', 'html'))) {
-            /* Parse error. Ignore the token. */
+		} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+		array('body', 'caption', 'col', 'colgroup', 'html'))) {
+			/* Parse error. Ignore the token. */
 
-        /* An end tag whose tag name is one of: "table", "tbody", "tfoot",
+		/* An end tag whose tag name is one of: "table", "tbody", "tfoot",
         "thead", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
-        array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
-            /* If the stack of open elements does not have an element in table
+		} elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+		array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as that of the token (which can only
             happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
             then this is a parse error and the token must be ignored. */
-            if(!$this->elementInScope($token['name'], true)) {
-                // Ignore.
+			if(!$this->elementInScope($token['name'], true)) {
+				// Ignore.
 
-            /* Otherwise, close the cell (see below) and reprocess the current
+			/* Otherwise, close the cell (see below) and reprocess the current
             token. */
-            } else {
-                $this->closeCell();
-                return $this->inRow($token);
-            }
-
-        /* Anything else */
-        } else {
-            /* Process the token as if the insertion mode was "in body". */
-            $this->inBody($token);
-        }
-    }
-
-    private function inSelect($token) {
-        /* Handle the token as follows: */
-
-        /* A character token */
-        if($token['type'] === HTML5::CHARACTR) {
-            /* Append the token's character to the current node. */
-            $this->insertText($token['data']);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data
+			} else {
+				$this->closeCell();
+				return $this->inRow($token);
+			}
+
+		/* Anything else */
+		} else {
+			/* Process the token as if the insertion mode was "in body". */
+			$this->inBody($token);
+		}
+	}
+
+	private function inSelect($token) {
+		/* Handle the token as follows: */
+
+		/* A character token */
+		if($token['type'] === HTML5::CHARACTR) {
+			/* Append the token's character to the current node. */
+			$this->insertText($token['data']);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
-            $this->insertComment($token['data']);
+			$this->insertComment($token['data']);
 
-        /* A start tag token whose tag name is "option" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        $token['name'] === 'option') {
-            /* If the current node is an option element, act as if an end tag
+		/* A start tag token whose tag name is "option" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		$token['name'] === 'option') {
+			/* If the current node is an option element, act as if an end tag
             with the tag name "option" had been seen. */
-            if(end($this->stack)->nodeName === 'option') {
-                $this->inSelect(array(
-                    'name' => 'option',
-                    'type' => HTML5::ENDTAG
-                ));
-            }
-
-            /* Insert an HTML element for the token. */
-            $this->insertElement($token);
-
-        /* A start tag token whose tag name is "optgroup" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        $token['name'] === 'optgroup') {
-            /* If the current node is an option element, act as if an end tag
+			if(end($this->stack)->nodeName === 'option') {
+				$this->inSelect(array(
+					'name' => 'option',
+					'type' => HTML5::ENDTAG
+				));
+			}
+
+			/* Insert an HTML element for the token. */
+			$this->insertElement($token);
+
+		/* A start tag token whose tag name is "optgroup" */
+		} elseif($token['type'] === HTML5::STARTTAG &&
+		$token['name'] === 'optgroup') {
+			/* If the current node is an option element, act as if an end tag
             with the tag name "option" had been seen. */
-            if(end($this->stack)->nodeName === 'option') {
-                $this->inSelect(array(
-                    'name' => 'option',
-                    'type' => HTML5::ENDTAG
-                ));
-            }
-
-            /* If the current node is an optgroup element, act as if an end tag
+			if(end($this->stack)->nodeName === 'option') {
+				$this->inSelect(array(
+					'name' => 'option',
+					'type' => HTML5::ENDTAG
+				));
+			}
+
+			/* If the current node is an optgroup element, act as if an end tag
             with the tag name "optgroup" had been seen. */
-            if(end($this->stack)->nodeName === 'optgroup') {
-                $this->inSelect(array(
-                    'name' => 'optgroup',
-                    'type' => HTML5::ENDTAG
-                ));
-            }
-
-            /* Insert an HTML element for the token. */
-            $this->insertElement($token);
-
-        /* An end tag token whose tag name is "optgroup" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        $token['name'] === 'optgroup') {
-            /* First, if the current node is an option element, and the node
+			if(end($this->stack)->nodeName === 'optgroup') {
+				$this->inSelect(array(
+					'name' => 'optgroup',
+					'type' => HTML5::ENDTAG
+				));
+			}
+
+			/* Insert an HTML element for the token. */
+			$this->insertElement($token);
+
+		/* An end tag token whose tag name is "optgroup" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		$token['name'] === 'optgroup') {
+			/* First, if the current node is an option element, and the node
             immediately before it in the stack of open elements is an optgroup
             element, then act as if an end tag with the tag name "option" had
             been seen. */
-            $elements_in_stack = count($this->stack);
+			$elements_in_stack = count($this->stack);
 
-            if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
-            $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
-                $this->inSelect(array(
-                    'name' => 'option',
-                    'type' => HTML5::ENDTAG
-                ));
-            }
+			if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
+			$this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
+				$this->inSelect(array(
+					'name' => 'option',
+					'type' => HTML5::ENDTAG
+				));
+			}
 
-            /* If the current node is an optgroup element, then pop that node
+			/* If the current node is an optgroup element, then pop that node
             from the stack of open elements. Otherwise, this is a parse error,
             ignore the token. */
-            if($this->stack[$elements_in_stack - 1] === 'optgroup') {
-                array_pop($this->stack);
-            }
-
-        /* An end tag token whose tag name is "option" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        $token['name'] === 'option') {
-            /* If the current node is an option element, then pop that node
+			if($this->stack[$elements_in_stack - 1] === 'optgroup') {
+				array_pop($this->stack);
+			}
+
+		/* An end tag token whose tag name is "option" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		$token['name'] === 'option') {
+			/* If the current node is an option element, then pop that node
             from the stack of open elements. Otherwise, this is a parse error,
             ignore the token. */
-            if(end($this->stack)->nodeName === 'option') {
-                array_pop($this->stack);
-            }
-
-        /* An end tag whose tag name is "select" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
-        $token['name'] === 'select') {
-            /* If the stack of open elements does not have an element in table
+			if(end($this->stack)->nodeName === 'option') {
+				array_pop($this->stack);
+			}
+
+		/* An end tag whose tag name is "select" */
+		} elseif($token['type'] === HTML5::ENDTAG &&
+		$token['name'] === 'select') {
+			/* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
-                // w/e
+			if(!$this->elementInScope($token['name'], true)) {
+				// w/e
 
-            /* Otherwise: */
-            } else {
-                /* Pop elements from the stack of open elements until a select
+			/* Otherwise: */
+			} else {
+				/* Pop elements from the stack of open elements until a select
                 element has been popped from the stack. */
-                while(true) {
-                    $current = end($this->stack)->nodeName;
-                    array_pop($this->stack);
-
-                    if($current === 'select') {
-                        break;
-                    }
-                }
-
-                /* Reset the insertion mode appropriately. */
-                $this->resetInsertionMode();
-            }
-
-        /* A start tag whose tag name is "select" */
-        } elseif($token['name'] === 'select' &&
-        $token['type'] === HTML5::STARTTAG) {
-            /* Parse error. Act as if the token had been an end tag with the
+				while(true) {
+					$current = end($this->stack)->nodeName;
+					array_pop($this->stack);
+
+					if($current === 'select') {
+						break;
+					}
+				}
+
+				/* Reset the insertion mode appropriately. */
+				$this->resetInsertionMode();
+			}
+
+		/* A start tag whose tag name is "select" */
+		} elseif($token['name'] === 'select' &&
+		$token['type'] === HTML5::STARTTAG) {
+			/* Parse error. Act as if the token had been an end tag with the
             tag name "select" instead. */
-            $this->inSelect(array(
-                'name' => 'select',
-                'type' => HTML5::ENDTAG
-            ));
+			$this->inSelect(array(
+				'name' => 'select',
+				'type' => HTML5::ENDTAG
+			));
 
-        /* An end tag whose tag name is one of: "caption", "table", "tbody",
+		/* An end tag whose tag name is one of: "caption", "table", "tbody",
         "tfoot", "thead", "tr", "td", "th" */
-        } elseif(in_array($token['name'], array('caption', 'table', 'tbody',
-        'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
-            /* Parse error. */
-            // w/e
+		} elseif(in_array($token['name'], array('caption', 'table', 'tbody',
+		'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
+			/* Parse error. */
+			// w/e
 
-            /* If the stack of open elements has an element in table scope with
+			/* If the stack of open elements has an element in table scope with
             the same tag name as that of the token, then act as if an end tag
             with the tag name "select" had been seen, and reprocess the token.
             Otherwise, ignore the token. */
-            if($this->elementInScope($token['name'], true)) {
-                $this->inSelect(array(
-                    'name' => 'select',
-                    'type' => HTML5::ENDTAG
-                ));
+			if($this->elementInScope($token['name'], true)) {
+				$this->inSelect(array(
+					'name' => 'select',
+					'type' => HTML5::ENDTAG
+				));
 
-                $this->mainPhase($token);
-            }
+				$this->mainPhase($token);
+			}
 
-        /* Anything else */
-        } else {
-            /* Parse error. Ignore the token. */
-        }
-    }
+		/* Anything else */
+		} else {
+			/* Parse error. Ignore the token. */
+		}
+	}
 
-    private function afterBody($token) {
-        /* Handle the token as follows: */
+	private function afterBody($token) {
+		/* Handle the token as follows: */
 
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Process the token as it would be processed if the insertion mode
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Process the token as it would be processed if the insertion mode
             was "in body". */
-            $this->inBody($token);
+			$this->inBody($token);
 
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the first element in the stack of open
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the first element in the stack of open
             elements (the html element), with the data attribute set to the
             data given in the comment token. */
-            $comment = $this->dom->createComment($token['data']);
-            $this->stack[0]->appendChild($comment);
+			$comment = $this->dom->createComment($token['data']);
+			$this->stack[0]->appendChild($comment);
 
-        /* An end tag with the tag name "html" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
-            /* If the parser was originally created in order to handle the
+		/* An end tag with the tag name "html" */
+		} elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
+			/* If the parser was originally created in order to handle the
             setting of an element's innerHTML attribute, this is a parse error;
             ignore the token. (The element will be an html element in this
             case.) (innerHTML case) */
 
-            /* Otherwise, switch to the trailing end phase. */
-            $this->phase = self::END_PHASE;
+			/* Otherwise, switch to the trailing end phase. */
+			$this->phase = self::END_PHASE;
 
-        /* Anything else */
-        } else {
-            /* Parse error. Set the insertion mode to "in body" and reprocess
+		/* Anything else */
+		} else {
+			/* Parse error. Set the insertion mode to "in body" and reprocess
             the token. */
-            $this->mode = self::IN_BODY;
-            return $this->inBody($token);
-        }
-    }
+			$this->mode = self::IN_BODY;
+			return $this->inBody($token);
+		}
+	}
 
-    private function inFrameset($token) {
-        /* Handle the token as follows: */
+	private function inFrameset($token) {
+		/* Handle the token as follows: */
 
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append the character to the current node. */
-            $this->insertText($token['data']);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append the character to the current node. */
+			$this->insertText($token['data']);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
-            $this->insertComment($token['data']);
+			$this->insertComment($token['data']);
 
-        /* A start tag with the tag name "frameset" */
-        } elseif($token['name'] === 'frameset' &&
-        $token['type'] === HTML5::STARTTAG) {
-            $this->insertElement($token);
+		/* A start tag with the tag name "frameset" */
+		} elseif($token['name'] === 'frameset' &&
+		$token['type'] === HTML5::STARTTAG) {
+			$this->insertElement($token);
 
-        /* An end tag with the tag name "frameset" */
-        } elseif($token['name'] === 'frameset' &&
-        $token['type'] === HTML5::ENDTAG) {
-            /* If the current node is the root html element, then this is a
+		/* An end tag with the tag name "frameset" */
+		} elseif($token['name'] === 'frameset' &&
+		$token['type'] === HTML5::ENDTAG) {
+			/* If the current node is the root html element, then this is a
             parse error; ignore the token. (innerHTML case) */
-            if(end($this->stack)->nodeName === 'html') {
-                // Ignore
+			if(end($this->stack)->nodeName === 'html') {
+				// Ignore
 
-            } else {
-                /* Otherwise, pop the current node from the stack of open
+			} else {
+				/* Otherwise, pop the current node from the stack of open
                 elements. */
-                array_pop($this->stack);
+				array_pop($this->stack);
 
-                /* If the parser was not originally created in order to handle
+				/* If the parser was not originally created in order to handle
                 the setting of an element's innerHTML attribute (innerHTML case),
                 and the current node is no longer a frameset element, then change
                 the insertion mode to "after frameset". */
-                $this->mode = self::AFTR_FRAME;
-            }
-
-        /* A start tag with the tag name "frame" */
-        } elseif($token['name'] === 'frame' &&
-        $token['type'] === HTML5::STARTTAG) {
-            /* Insert an HTML element for the token. */
-            $this->insertElement($token);
-
-            /* Immediately pop the current node off the stack of open elements. */
-            array_pop($this->stack);
-
-        /* A start tag with the tag name "noframes" */
-        } elseif($token['name'] === 'noframes' &&
-        $token['type'] === HTML5::STARTTAG) {
-            /* Process the token as if the insertion mode had been "in body". */
-            $this->inBody($token);
-
-        /* Anything else */
-        } else {
-            /* Parse error. Ignore the token. */
-        }
-    }
-
-    private function afterFrameset($token) {
-        /* Handle the token as follows: */
-
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+				$this->mode = self::AFTR_FRAME;
+			}
+
+		/* A start tag with the tag name "frame" */
+		} elseif($token['name'] === 'frame' &&
+		$token['type'] === HTML5::STARTTAG) {
+			/* Insert an HTML element for the token. */
+			$this->insertElement($token);
+
+			/* Immediately pop the current node off the stack of open elements. */
+			array_pop($this->stack);
+
+		/* A start tag with the tag name "noframes" */
+		} elseif($token['name'] === 'noframes' &&
+		$token['type'] === HTML5::STARTTAG) {
+			/* Process the token as if the insertion mode had been "in body". */
+			$this->inBody($token);
+
+		/* Anything else */
+		} else {
+			/* Parse error. Ignore the token. */
+		}
+	}
+
+	private function afterFrameset($token) {
+		/* Handle the token as follows: */
+
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Append the character to the current node. */
-            $this->insertText($token['data']);
-
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the current node with the data
+		if($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Append the character to the current node. */
+			$this->insertText($token['data']);
+
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
-            $this->insertComment($token['data']);
-
-        /* An end tag with the tag name "html" */
-        } elseif($token['name'] === 'html' &&
-        $token['type'] === HTML5::ENDTAG) {
-            /* Switch to the trailing end phase. */
-            $this->phase = self::END_PHASE;
-
-        /* A start tag with the tag name "noframes" */
-        } elseif($token['name'] === 'noframes' &&
-        $token['type'] === HTML5::STARTTAG) {
-            /* Process the token as if the insertion mode had been "in body". */
-            $this->inBody($token);
-
-        /* Anything else */
-        } else {
-            /* Parse error. Ignore the token. */
-        }
-    }
-
-    private function trailingEndPhase($token) {
-        /* After the main phase, as each token is emitted from the tokenisation
+			$this->insertComment($token['data']);
+
+		/* An end tag with the tag name "html" */
+		} elseif($token['name'] === 'html' &&
+		$token['type'] === HTML5::ENDTAG) {
+			/* Switch to the trailing end phase. */
+			$this->phase = self::END_PHASE;
+
+		/* A start tag with the tag name "noframes" */
+		} elseif($token['name'] === 'noframes' &&
+		$token['type'] === HTML5::STARTTAG) {
+			/* Process the token as if the insertion mode had been "in body". */
+			$this->inBody($token);
+
+		/* Anything else */
+		} else {
+			/* Parse error. Ignore the token. */
+		}
+	}
+
+	private function trailingEndPhase($token) {
+		/* After the main phase, as each token is emitted from the tokenisation
         stage, it must be processed as described in this section. */
 
-        /* A DOCTYPE token */
-        if($token['type'] === HTML5::DOCTYPE) {
-            // Parse error. Ignore the token.
+		/* A DOCTYPE token */
+		if($token['type'] === HTML5::DOCTYPE) {
+			// Parse error. Ignore the token.
 
-        /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
-            /* Append a Comment node to the Document object with the data
+		/* A comment token */
+		} elseif($token['type'] === HTML5::COMMENT) {
+			/* Append a Comment node to the Document object with the data
             attribute set to the data given in the comment token. */
-            $comment = $this->dom->createComment($token['data']);
-            $this->dom->appendChild($comment);
+			$comment = $this->dom->createComment($token['data']);
+			$this->dom->appendChild($comment);
 
-        /* A character token that is one of one of U+0009 CHARACTER TABULATION,
+		/* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        } elseif($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
-            /* Process the token as it would be processed in the main phase. */
-            $this->mainPhase($token);
+		} elseif($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
+			/* Process the token as it would be processed in the main phase. */
+			$this->mainPhase($token);
 
-        /* A character token that is not one of U+0009 CHARACTER TABULATION,
+		/* A character token that is not one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE. Or a start tag token. Or an end tag token. */
-        } elseif(($token['type'] === HTML5::CHARACTR &&
-        preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
-        $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
-            /* Parse error. Switch back to the main phase and reprocess the
+		} elseif(($token['type'] === HTML5::CHARACTR &&
+		preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
+		$token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
+			/* Parse error. Switch back to the main phase and reprocess the
             token. */
-            $this->phase = self::MAIN_PHASE;
-            return $this->mainPhase($token);
-
-        /* An end-of-file token */
-        } elseif($token['type'] === HTML5::EOF) {
-            /* OMG DONE!! */
-        }
-    }
-
-    private function insertElement($token, $append = true, $check = false) {
-        // Proprietary workaround for libxml2's limitations with tag names
-        if ($check) {
-            // Slightly modified HTML5 tag-name modification,
-            // removing anything that's not an ASCII letter, digit, or hyphen
-            $token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']);
-            // Remove leading hyphens and numbers
-            $token['name'] = ltrim($token['name'], '-0..9');
-            // In theory, this should ever be needed, but just in case
-            if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
-        }
+			$this->phase = self::MAIN_PHASE;
+			return $this->mainPhase($token);
+
+		/* An end-of-file token */
+		} elseif($token['type'] === HTML5::EOF) {
+			/* OMG DONE!! */
+		}
+	}
+
+	private function insertElement($token, $append = true, $check = false) {
+		// Proprietary workaround for libxml2's limitations with tag names
+		if ($check) {
+			// Slightly modified HTML5 tag-name modification,
+			// removing anything that's not an ASCII letter, digit, or hyphen
+			$token['name'] = preg_replace('/[^a-z0-9-]/i', '', $token['name']);
+			// Remove leading hyphens and numbers
+			$token['name'] = ltrim($token['name'], '-0..9');
+			// In theory, this should ever be needed, but just in case
+			if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
+		}
         
-        $el = $this->dom->createElement($token['name']);
+		$el = $this->dom->createElement($token['name']);
 
-        foreach($token['attr'] as $attr) {
-            if(!$el->hasAttribute($attr['name'])) {
-                $el->setAttribute($attr['name'], $attr['value']);
-            }
-        }
+		foreach($token['attr'] as $attr) {
+			if(!$el->hasAttribute($attr['name'])) {
+				$el->setAttribute($attr['name'], $attr['value']);
+			}
+		}
 
-        $this->appendToRealParent($el);
-        $this->stack[] = $el;
+		$this->appendToRealParent($el);
+		$this->stack[] = $el;
 
-        return $el;
-    }
+		return $el;
+	}
 
-    private function insertText($data) {
-        $text = $this->dom->createTextNode($data);
-        $this->appendToRealParent($text);
-    }
+	private function insertText($data) {
+		$text = $this->dom->createTextNode($data);
+		$this->appendToRealParent($text);
+	}
 
-    private function insertComment($data) {
-        $comment = $this->dom->createComment($data);
-        $this->appendToRealParent($comment);
-    }
+	private function insertComment($data) {
+		$comment = $this->dom->createComment($data);
+		$this->appendToRealParent($comment);
+	}
 
-    private function appendToRealParent($node) {
-        if($this->foster_parent === null) {
-            end($this->stack)->appendChild($node);
+	private function appendToRealParent($node) {
+		if($this->foster_parent === null) {
+			end($this->stack)->appendChild($node);
 
-        } elseif($this->foster_parent !== null) {
-            /* If the foster parent element is the parent element of the
+		} elseif($this->foster_parent !== null) {
+			/* If the foster parent element is the parent element of the
             last table element in the stack of open elements, then the new
             node must be inserted immediately before the last table element
             in the stack of open elements in the foster parent element;
             otherwise, the new node must be appended to the foster parent
             element. */
-            for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                if($this->stack[$n]->nodeName === 'table' &&
-                $this->stack[$n]->parentNode !== null) {
-                    $table = $this->stack[$n];
-                    break;
-                }
-            }
-
-            if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
-                $this->foster_parent->insertBefore($node, $table);
-            else
-                $this->foster_parent->appendChild($node);
-
-            $this->foster_parent = null;
-        }
-    }
-
-    private function elementInScope($el, $table = false) {
-        if(is_array($el)) {
-            foreach($el as $element) {
-                if($this->elementInScope($element, $table)) {
-                    return true;
-                }
-            }
-
-            return false;
-        }
-
-        $leng = count($this->stack);
-
-        for($n = 0; $n < $leng; $n++) {
-            /* 1. Initialise node to be the current node (the bottommost node of
+			for($n = count($this->stack) - 1; $n >= 0; $n--) {
+				if($this->stack[$n]->nodeName === 'table' &&
+				$this->stack[$n]->parentNode !== null) {
+					$table = $this->stack[$n];
+					break;
+				}
+			}
+
+			if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
+				$this->foster_parent->insertBefore($node, $table);
+			else
+				$this->foster_parent->appendChild($node);
+
+			$this->foster_parent = null;
+		}
+	}
+
+	private function elementInScope($el, $table = false) {
+		if(is_array($el)) {
+			foreach($el as $element) {
+				if($this->elementInScope($element, $table)) {
+					return true;
+				}
+			}
+
+			return false;
+		}
+
+		$leng = count($this->stack);
+
+		for($n = 0; $n < $leng; $n++) {
+			/* 1. Initialise node to be the current node (the bottommost node of
             the stack). */
-            $node = $this->stack[$leng - 1 - $n];
+			$node = $this->stack[$leng - 1 - $n];
 
-            if($node->tagName === $el) {
-                /* 2. If node is the target node, terminate in a match state. */
-                return true;
+			if($node->tagName === $el) {
+				/* 2. If node is the target node, terminate in a match state. */
+				return true;
 
-            } elseif($node->tagName === 'table') {
-                /* 3. Otherwise, if node is a table element, terminate in a failure
+			} elseif($node->tagName === 'table') {
+				/* 3. Otherwise, if node is a table element, terminate in a failure
                 state. */
-                return false;
+				return false;
 
-            } elseif($table === true && in_array($node->tagName, array('caption', 'td',
-            'th', 'button', 'marquee', 'object'))) {
-                /* 4. Otherwise, if the algorithm is the "has an element in scope"
+			} elseif($table === true && in_array($node->tagName, array('caption', 'td',
+			'th', 'button', 'marquee', 'object'))) {
+				/* 4. Otherwise, if the algorithm is the "has an element in scope"
                 variant (rather than the "has an element in table scope" variant),
                 and node is one of the following, terminate in a failure state. */
-                return false;
+				return false;
 
-            } elseif($node === $node->ownerDocument->documentElement) {
-                /* 5. Otherwise, if node is an html element (root element), terminate
+			} elseif($node === $node->ownerDocument->documentElement) {
+				/* 5. Otherwise, if node is an html element (root element), terminate
                 in a failure state. (This can only happen if the node is the topmost
                 node of the    stack of open elements, and prevents the next step from
                 being invoked if there are no more elements in the stack.) */
-                return false;
-            }
+				return false;
+			}
 
-            /* Otherwise, set node to the previous entry in the stack of open
+			/* Otherwise, set node to the previous entry in the stack of open
             elements and return to step 2. (This will never fail, since the loop
             will always terminate in the previous step if the top of the stack
             is reached.) */
-        }
-    }
+		}
+	}
 
-    private function reconstructActiveFormattingElements() {
-        /* 1. If there are no entries in the list of active formatting elements,
+	private function reconstructActiveFormattingElements() {
+		/* 1. If there are no entries in the list of active formatting elements,
         then there is nothing to reconstruct; stop this algorithm. */
-        $formatting_elements = count($this->a_formatting);
+		$formatting_elements = count($this->a_formatting);
 
-        if($formatting_elements === 0) {
-            return false;
-        }
+		if($formatting_elements === 0) {
+			return false;
+		}
 
-        /* 3. Let entry be the last (most recently added) element in the list
+		/* 3. Let entry be the last (most recently added) element in the list
         of active formatting elements. */
-        $entry = end($this->a_formatting);
+		$entry = end($this->a_formatting);
 
-        /* 2. If the last (most recently added) entry in the list of active
+		/* 2. If the last (most recently added) entry in the list of active
         formatting elements is a marker, or if it is an element that is in the
         stack of open elements, then there is nothing to reconstruct; stop this
         algorithm. */
-        if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
-            return false;
-        }
+		if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+			return false;
+		}
 
-        for($a = $formatting_elements - 1; $a >= 0; true) {
-            /* 4. If there are no entries before entry in the list of active
+		for($a = $formatting_elements - 1; $a >= 0; true) {
+			/* 4. If there are no entries before entry in the list of active
             formatting elements, then jump to step 8. */
-            if($a === 0) {
-                $step_seven = false;
-                break;
-            }
+			if($a === 0) {
+				$step_seven = false;
+				break;
+			}
 
-            /* 5. Let entry be the entry one earlier than entry in the list of
+			/* 5. Let entry be the entry one earlier than entry in the list of
             active formatting elements. */
-            $a--;
-            $entry = $this->a_formatting[$a];
+			$a--;
+			$entry = $this->a_formatting[$a];
 
-            /* 6. If entry is neither a marker nor an element that is also in
+			/* 6. If entry is neither a marker nor an element that is also in
             thetack of open elements, go to step 4. */
-            if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
-                break;
-            }
-        }
+			if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+				break;
+			}
+		}
 
-        while(true) {
-            /* 7. Let entry be the element one later than entry in the list of
+		while(true) {
+			/* 7. Let entry be the element one later than entry in the list of
             active formatting elements. */
-            if(isset($step_seven) && $step_seven === true) {
-                $a++;
-                $entry = $this->a_formatting[$a];
-            }
+			if(isset($step_seven) && $step_seven === true) {
+				$a++;
+				$entry = $this->a_formatting[$a];
+			}
 
-            /* 8. Perform a shallow clone of the element entry to obtain clone. */
-            $clone = $entry->cloneNode();
+			/* 8. Perform a shallow clone of the element entry to obtain clone. */
+			$clone = $entry->cloneNode();
 
-            /* 9. Append clone to the current node and push it onto the stack
+			/* 9. Append clone to the current node and push it onto the stack
             of open elements  so that it is the new current node. */
-            end($this->stack)->appendChild($clone);
-            $this->stack[] = $clone;
+			end($this->stack)->appendChild($clone);
+			$this->stack[] = $clone;
 
-            /* 10. Replace the entry for entry in the list with an entry for
+			/* 10. Replace the entry for entry in the list with an entry for
             clone. */
-            $this->a_formatting[$a] = $clone;
+			$this->a_formatting[$a] = $clone;
 
-            /* 11. If the entry for clone in the list of active formatting
+			/* 11. If the entry for clone in the list of active formatting
             elements is not the last entry in the list, return to step 7. */
-            if(end($this->a_formatting) !== $clone) {
-                $step_seven = true;
-            } else {
-                break;
-            }
-        }
-    }
-
-    private function clearTheActiveFormattingElementsUpToTheLastMarker() {
-        /* When the steps below require the UA to clear the list of active
+			if(end($this->a_formatting) !== $clone) {
+				$step_seven = true;
+			} else {
+				break;
+			}
+		}
+	}
+
+	private function clearTheActiveFormattingElementsUpToTheLastMarker() {
+		/* When the steps below require the UA to clear the list of active
         formatting elements up to the last marker, the UA must perform the
         following steps: */
 
-        while(true) {
-            /* 1. Let entry be the last (most recently added) entry in the list
+		while(true) {
+			/* 1. Let entry be the last (most recently added) entry in the list
             of active formatting elements. */
-            $entry = end($this->a_formatting);
+			$entry = end($this->a_formatting);
 
-            /* 2. Remove entry from the list of active formatting elements. */
-            array_pop($this->a_formatting);
+			/* 2. Remove entry from the list of active formatting elements. */
+			array_pop($this->a_formatting);
 
-            /* 3. If entry was a marker, then stop the algorithm at this point.
+			/* 3. If entry was a marker, then stop the algorithm at this point.
             The list has been cleared up to the last marker. */
-            if($entry === self::MARKER) {
-                break;
-            }
-        }
-    }
-
-    private function generateImpliedEndTags($exclude = array()) {
-        /* When the steps below require the UA to generate implied end tags,
+			if($entry === self::MARKER) {
+				break;
+			}
+		}
+	}
+
+	private function generateImpliedEndTags($exclude = array()) {
+		/* When the steps below require the UA to generate implied end tags,
         then, if the current node is a dd element, a dt element, an li element,
         a p element, a td element, a th  element, or a tr element, the UA must
         act as if an end tag with the respective tag name had been seen and
         then generate implied end tags again. */
-        $node = end($this->stack);
-        $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
+		$node = end($this->stack);
+		$elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
 
-        while(in_array(end($this->stack)->nodeName, $elements)) {
-            array_pop($this->stack);
-        }
-    }
+		while(in_array(end($this->stack)->nodeName, $elements)) {
+			array_pop($this->stack);
+		}
+	}
 
-    private function getElementCategory($node) {
-        $name = $node->tagName;
-        if(in_array($name, $this->special))
-            return self::SPECIAL;
+	private function getElementCategory($node) {
+		$name = $node->tagName;
+		if(in_array($name, $this->special))
+			return self::SPECIAL;
 
-        elseif(in_array($name, $this->scoping))
-            return self::SCOPING;
+		elseif(in_array($name, $this->scoping))
+			return self::SCOPING;
 
-        elseif(in_array($name, $this->formatting))
-            return self::FORMATTING;
+		elseif(in_array($name, $this->formatting))
+			return self::FORMATTING;
 
-        else
-            return self::PHRASING;
-    }
+		else
+			return self::PHRASING;
+	}
 
-    private function clearStackToTableContext($elements) {
-        /* When the steps above require the UA to clear the stack back to a
+	private function clearStackToTableContext($elements) {
+		/* When the steps above require the UA to clear the stack back to a
         table context, it means that the UA must, while the current node is not
         a table element or an html element, pop elements from the stack of open
         elements. If this causes any elements to be popped from the stack, then
         this is a parse error. */
-        while(true) {
-            $node = end($this->stack)->nodeName;
-
-            if(in_array($node, $elements)) {
-                break;
-            } else {
-                array_pop($this->stack);
-            }
-        }
-    }
-
-    private function resetInsertionMode() {
-        /* 1. Let last be false. */
-        $last = false;
-        $leng = count($this->stack);
-
-        for($n = $leng - 1; $n >= 0; $n--) {
-            /* 2. Let node be the last node in the stack of open elements. */
-            $node = $this->stack[$n];
-
-            /* 3. If node is the first node in the stack of open elements, then
+		while(true) {
+			$node = end($this->stack)->nodeName;
+
+			if(in_array($node, $elements)) {
+				break;
+			} else {
+				array_pop($this->stack);
+			}
+		}
+	}
+
+	private function resetInsertionMode() {
+		/* 1. Let last be false. */
+		$last = false;
+		$leng = count($this->stack);
+
+		for($n = $leng - 1; $n >= 0; $n--) {
+			/* 2. Let node be the last node in the stack of open elements. */
+			$node = $this->stack[$n];
+
+			/* 3. If node is the first node in the stack of open elements, then
             set last to true. If the element whose innerHTML  attribute is being
             set is neither a td  element nor a th element, then set node to the
             element whose innerHTML  attribute is being set. (innerHTML  case) */
-            if($this->stack[0]->isSameNode($node)) {
-                $last = true;
-            }
+			if($this->stack[0]->isSameNode($node)) {
+				$last = true;
+			}
 
-            /* 4. If node is a select element, then switch the insertion mode to
+			/* 4. If node is a select element, then switch the insertion mode to
             "in select" and abort these steps. (innerHTML case) */
-            if($node->nodeName === 'select') {
-                $this->mode = self::IN_SELECT;
-                break;
+			if($node->nodeName === 'select') {
+				$this->mode = self::IN_SELECT;
+				break;
 
-            /* 5. If node is a td or th element, then switch the insertion mode
+			/* 5. If node is a td or th element, then switch the insertion mode
             to "in cell" and abort these steps. */
-            } elseif($node->nodeName === 'td' || $node->nodeName === 'th') {
-                $this->mode = self::IN_CELL;
-                break;
+			} elseif($node->nodeName === 'td' || $node->nodeName === 'th') {
+				$this->mode = self::IN_CELL;
+				break;
 
-            /* 6. If node is a tr element, then switch the insertion mode to
+			/* 6. If node is a tr element, then switch the insertion mode to
             "in    row" and abort these steps. */
-            } elseif($node->nodeName === 'tr') {
-                $this->mode = self::IN_ROW;
-                break;
+			} elseif($node->nodeName === 'tr') {
+				$this->mode = self::IN_ROW;
+				break;
 
-            /* 7. If node is a tbody, thead, or tfoot element, then switch the
+			/* 7. If node is a tbody, thead, or tfoot element, then switch the
             insertion mode to "in table body" and abort these steps. */
-            } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
-                $this->mode = self::IN_TBODY;
-                break;
+			} elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
+				$this->mode = self::IN_TBODY;
+				break;
 
-            /* 8. If node is a caption element, then switch the insertion mode
+			/* 8. If node is a caption element, then switch the insertion mode
             to "in caption" and abort these steps. */
-            } elseif($node->nodeName === 'caption') {
-                $this->mode = self::IN_CAPTION;
-                break;
+			} elseif($node->nodeName === 'caption') {
+				$this->mode = self::IN_CAPTION;
+				break;
 
-            /* 9. If node is a colgroup element, then switch the insertion mode
+			/* 9. If node is a colgroup element, then switch the insertion mode
             to "in column group" and abort these steps. (innerHTML case) */
-            } elseif($node->nodeName === 'colgroup') {
-                $this->mode = self::IN_CGROUP;
-                break;
+			} elseif($node->nodeName === 'colgroup') {
+				$this->mode = self::IN_CGROUP;
+				break;
 
-            /* 10. If node is a table element, then switch the insertion mode
+			/* 10. If node is a table element, then switch the insertion mode
             to "in table" and abort these steps. */
-            } elseif($node->nodeName === 'table') {
-                $this->mode = self::IN_TABLE;
-                break;
+			} elseif($node->nodeName === 'table') {
+				$this->mode = self::IN_TABLE;
+				break;
 
-            /* 11. If node is a head element, then switch the insertion mode
+			/* 11. If node is a head element, then switch the insertion mode
             to "in body" ("in body"! not "in head"!) and abort these steps.
             (innerHTML case) */
-            } elseif($node->nodeName === 'head') {
-                $this->mode = self::IN_BODY;
-                break;
+			} elseif($node->nodeName === 'head') {
+				$this->mode = self::IN_BODY;
+				break;
 
-            /* 12. If node is a body element, then switch the insertion mode to
+			/* 12. If node is a body element, then switch the insertion mode to
             "in body" and abort these steps. */
-            } elseif($node->nodeName === 'body') {
-                $this->mode = self::IN_BODY;
-                break;
+			} elseif($node->nodeName === 'body') {
+				$this->mode = self::IN_BODY;
+				break;
 
-            /* 13. If node is a frameset element, then switch the insertion
+			/* 13. If node is a frameset element, then switch the insertion
             mode to "in frameset" and abort these steps. (innerHTML case) */
-            } elseif($node->nodeName === 'frameset') {
-                $this->mode = self::IN_FRAME;
-                break;
+			} elseif($node->nodeName === 'frameset') {
+				$this->mode = self::IN_FRAME;
+				break;
 
-            /* 14. If node is an html element, then: if the head element
+			/* 14. If node is an html element, then: if the head element
             pointer is null, switch the insertion mode to "before head",
             otherwise, switch the insertion mode to "after head". In either
             case, abort these steps. (innerHTML case) */
-            } elseif($node->nodeName === 'html') {
-                $this->mode = ($this->head_pointer === null)
-                    ? self::BEFOR_HEAD
-                    : self::AFTER_HEAD;
+			} elseif($node->nodeName === 'html') {
+				$this->mode = ($this->head_pointer === null)
+					? self::BEFOR_HEAD
+					: self::AFTER_HEAD;
 
-                break;
+				break;
 
-            /* 15. If last is true, then set the insertion mode to "in body"
+			/* 15. If last is true, then set the insertion mode to "in body"
             and    abort these steps. (innerHTML case) */
-            } elseif($last) {
-                $this->mode = self::IN_BODY;
-                break;
-            }
-        }
-    }
-
-    private function closeCell() {
-        /* If the stack of open elements has a td or th element in table scope,
+			} elseif($last) {
+				$this->mode = self::IN_BODY;
+				break;
+			}
+		}
+	}
+
+	private function closeCell() {
+		/* If the stack of open elements has a td or th element in table scope,
         then act as if an end tag token with that tag name had been seen. */
-        foreach(array('td', 'th') as $cell) {
-            if($this->elementInScope($cell, true)) {
-                $this->inCell(array(
-                    'name' => $cell,
-                    'type' => HTML5::ENDTAG
-                ));
-
-                break;
-            }
-        }
-    }
-
-    public function save() {
-        return $this->dom;
-    }
+		foreach(array('td', 'th') as $cell) {
+			if($this->elementInScope($cell, true)) {
+				$this->inCell(array(
+					'name' => $cell,
+					'type' => HTML5::ENDTAG
+				));
+
+				break;
+			}
+		}
+	}
+
+	public function save() {
+		return $this->dom;
+	}
 }
 ?>

Braces +18 added lines, -16 removed lines

@@ -3542,7 +3542,10 @@ 
             // Remove leading hyphens and numbers
             $token['name'] = ltrim($token['name'], '-0..9');
             // In theory, this should ever be needed, but just in case
-            if ($token['name'] === '') $token['name'] = 'span'; // arbitrary generic choice
+            if ($token['name'] === '') {
+            	$token['name'] = 'span';
+            }
+            // arbitrary generic choice
         }
         
         $el = $this->dom->createElement($token['name']);
@@ -3588,10 +3591,11 @@ 
                 }
             }
 
-            if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
-                $this->foster_parent->insertBefore($node, $table);
-            else
-                $this->foster_parent->appendChild($node);
+            if(isset($table) && $this->foster_parent->isSameNode($table->parentNode)) {
+                            $this->foster_parent->insertBefore($node, $table);
+            } else {
+                            $this->foster_parent->appendChild($node);
+            }
 
             $this->foster_parent = null;
         }
@@ -3754,17 +3758,15 @@ 
 
     private function getElementCategory($node) {
         $name = $node->tagName;
-        if(in_array($name, $this->special))
-            return self::SPECIAL;
-
-        elseif(in_array($name, $this->scoping))
-            return self::SCOPING;
-
-        elseif(in_array($name, $this->formatting))
-            return self::FORMATTING;
-
-        else
-            return self::PHRASING;
+        if(in_array($name, $this->special)) {
+                    return self::SPECIAL;
+        } elseif(in_array($name, $this->scoping)) {
+                    return self::SCOPING;
+        } elseif(in_array($name, $this->formatting)) {
+                    return self::FORMATTING;
+        } else {
+                    return self::PHRASING;
+        }
     }
 
     private function clearStackToTableContext($elements) {

Spacing +384 added lines, -384 removed lines

@@ -69,48 +69,48 @@ 
     private $token;
     private $content_model;
     private $escape = false;
-    private $entities = array('AElig;','AElig','AMP;','AMP','Aacute;','Aacute',
-    'Acirc;','Acirc','Agrave;','Agrave','Alpha;','Aring;','Aring','Atilde;',
-    'Atilde','Auml;','Auml','Beta;','COPY;','COPY','Ccedil;','Ccedil','Chi;',
-    'Dagger;','Delta;','ETH;','ETH','Eacute;','Eacute','Ecirc;','Ecirc','Egrave;',
-    'Egrave','Epsilon;','Eta;','Euml;','Euml','GT;','GT','Gamma;','Iacute;',
-    'Iacute','Icirc;','Icirc','Igrave;','Igrave','Iota;','Iuml;','Iuml','Kappa;',
-    'LT;','LT','Lambda;','Mu;','Ntilde;','Ntilde','Nu;','OElig;','Oacute;',
-    'Oacute','Ocirc;','Ocirc','Ograve;','Ograve','Omega;','Omicron;','Oslash;',
-    'Oslash','Otilde;','Otilde','Ouml;','Ouml','Phi;','Pi;','Prime;','Psi;',
-    'QUOT;','QUOT','REG;','REG','Rho;','Scaron;','Sigma;','THORN;','THORN',
-    'TRADE;','Tau;','Theta;','Uacute;','Uacute','Ucirc;','Ucirc','Ugrave;',
-    'Ugrave','Upsilon;','Uuml;','Uuml','Xi;','Yacute;','Yacute','Yuml;','Zeta;',
-    'aacute;','aacute','acirc;','acirc','acute;','acute','aelig;','aelig',
-    'agrave;','agrave','alefsym;','alpha;','amp;','amp','and;','ang;','apos;',
-    'aring;','aring','asymp;','atilde;','atilde','auml;','auml','bdquo;','beta;',
-    'brvbar;','brvbar','bull;','cap;','ccedil;','ccedil','cedil;','cedil',
-    'cent;','cent','chi;','circ;','clubs;','cong;','copy;','copy','crarr;',
-    'cup;','curren;','curren','dArr;','dagger;','darr;','deg;','deg','delta;',
-    'diams;','divide;','divide','eacute;','eacute','ecirc;','ecirc','egrave;',
-    'egrave','empty;','emsp;','ensp;','epsilon;','equiv;','eta;','eth;','eth',
-    'euml;','euml','euro;','exist;','fnof;','forall;','frac12;','frac12',
-    'frac14;','frac14','frac34;','frac34','frasl;','gamma;','ge;','gt;','gt',
-    'hArr;','harr;','hearts;','hellip;','iacute;','iacute','icirc;','icirc',
-    'iexcl;','iexcl','igrave;','igrave','image;','infin;','int;','iota;',
-    'iquest;','iquest','isin;','iuml;','iuml','kappa;','lArr;','lambda;','lang;',
-    'laquo;','laquo','larr;','lceil;','ldquo;','le;','lfloor;','lowast;','loz;',
-    'lrm;','lsaquo;','lsquo;','lt;','lt','macr;','macr','mdash;','micro;','micro',
-    'middot;','middot','minus;','mu;','nabla;','nbsp;','nbsp','ndash;','ne;',
-    'ni;','not;','not','notin;','nsub;','ntilde;','ntilde','nu;','oacute;',
-    'oacute','ocirc;','ocirc','oelig;','ograve;','ograve','oline;','omega;',
-    'omicron;','oplus;','or;','ordf;','ordf','ordm;','ordm','oslash;','oslash',
-    'otilde;','otilde','otimes;','ouml;','ouml','para;','para','part;','permil;',
-    'perp;','phi;','pi;','piv;','plusmn;','plusmn','pound;','pound','prime;',
-    'prod;','prop;','psi;','quot;','quot','rArr;','radic;','rang;','raquo;',
-    'raquo','rarr;','rceil;','rdquo;','real;','reg;','reg','rfloor;','rho;',
-    'rlm;','rsaquo;','rsquo;','sbquo;','scaron;','sdot;','sect;','sect','shy;',
-    'shy','sigma;','sigmaf;','sim;','spades;','sub;','sube;','sum;','sup1;',
-    'sup1','sup2;','sup2','sup3;','sup3','sup;','supe;','szlig;','szlig','tau;',
-    'there4;','theta;','thetasym;','thinsp;','thorn;','thorn','tilde;','times;',
-    'times','trade;','uArr;','uacute;','uacute','uarr;','ucirc;','ucirc',
-    'ugrave;','ugrave','uml;','uml','upsih;','upsilon;','uuml;','uuml','weierp;',
-    'xi;','yacute;','yacute','yen;','yen','yuml;','yuml','zeta;','zwj;','zwnj;');
+    private $entities = array('AElig;', 'AElig', 'AMP;', 'AMP', 'Aacute;', 'Aacute',
+    'Acirc;', 'Acirc', 'Agrave;', 'Agrave', 'Alpha;', 'Aring;', 'Aring', 'Atilde;',
+    'Atilde', 'Auml;', 'Auml', 'Beta;', 'COPY;', 'COPY', 'Ccedil;', 'Ccedil', 'Chi;',
+    'Dagger;', 'Delta;', 'ETH;', 'ETH', 'Eacute;', 'Eacute', 'Ecirc;', 'Ecirc', 'Egrave;',
+    'Egrave', 'Epsilon;', 'Eta;', 'Euml;', 'Euml', 'GT;', 'GT', 'Gamma;', 'Iacute;',
+    'Iacute', 'Icirc;', 'Icirc', 'Igrave;', 'Igrave', 'Iota;', 'Iuml;', 'Iuml', 'Kappa;',
+    'LT;', 'LT', 'Lambda;', 'Mu;', 'Ntilde;', 'Ntilde', 'Nu;', 'OElig;', 'Oacute;',
+    'Oacute', 'Ocirc;', 'Ocirc', 'Ograve;', 'Ograve', 'Omega;', 'Omicron;', 'Oslash;',
+    'Oslash', 'Otilde;', 'Otilde', 'Ouml;', 'Ouml', 'Phi;', 'Pi;', 'Prime;', 'Psi;',
+    'QUOT;', 'QUOT', 'REG;', 'REG', 'Rho;', 'Scaron;', 'Sigma;', 'THORN;', 'THORN',
+    'TRADE;', 'Tau;', 'Theta;', 'Uacute;', 'Uacute', 'Ucirc;', 'Ucirc', 'Ugrave;',
+    'Ugrave', 'Upsilon;', 'Uuml;', 'Uuml', 'Xi;', 'Yacute;', 'Yacute', 'Yuml;', 'Zeta;',
+    'aacute;', 'aacute', 'acirc;', 'acirc', 'acute;', 'acute', 'aelig;', 'aelig',
+    'agrave;', 'agrave', 'alefsym;', 'alpha;', 'amp;', 'amp', 'and;', 'ang;', 'apos;',
+    'aring;', 'aring', 'asymp;', 'atilde;', 'atilde', 'auml;', 'auml', 'bdquo;', 'beta;',
+    'brvbar;', 'brvbar', 'bull;', 'cap;', 'ccedil;', 'ccedil', 'cedil;', 'cedil',
+    'cent;', 'cent', 'chi;', 'circ;', 'clubs;', 'cong;', 'copy;', 'copy', 'crarr;',
+    'cup;', 'curren;', 'curren', 'dArr;', 'dagger;', 'darr;', 'deg;', 'deg', 'delta;',
+    'diams;', 'divide;', 'divide', 'eacute;', 'eacute', 'ecirc;', 'ecirc', 'egrave;',
+    'egrave', 'empty;', 'emsp;', 'ensp;', 'epsilon;', 'equiv;', 'eta;', 'eth;', 'eth',
+    'euml;', 'euml', 'euro;', 'exist;', 'fnof;', 'forall;', 'frac12;', 'frac12',
+    'frac14;', 'frac14', 'frac34;', 'frac34', 'frasl;', 'gamma;', 'ge;', 'gt;', 'gt',
+    'hArr;', 'harr;', 'hearts;', 'hellip;', 'iacute;', 'iacute', 'icirc;', 'icirc',
+    'iexcl;', 'iexcl', 'igrave;', 'igrave', 'image;', 'infin;', 'int;', 'iota;',
+    'iquest;', 'iquest', 'isin;', 'iuml;', 'iuml', 'kappa;', 'lArr;', 'lambda;', 'lang;',
+    'laquo;', 'laquo', 'larr;', 'lceil;', 'ldquo;', 'le;', 'lfloor;', 'lowast;', 'loz;',
+    'lrm;', 'lsaquo;', 'lsquo;', 'lt;', 'lt', 'macr;', 'macr', 'mdash;', 'micro;', 'micro',
+    'middot;', 'middot', 'minus;', 'mu;', 'nabla;', 'nbsp;', 'nbsp', 'ndash;', 'ne;',
+    'ni;', 'not;', 'not', 'notin;', 'nsub;', 'ntilde;', 'ntilde', 'nu;', 'oacute;',
+    'oacute', 'ocirc;', 'ocirc', 'oelig;', 'ograve;', 'ograve', 'oline;', 'omega;',
+    'omicron;', 'oplus;', 'or;', 'ordf;', 'ordf', 'ordm;', 'ordm', 'oslash;', 'oslash',
+    'otilde;', 'otilde', 'otimes;', 'ouml;', 'ouml', 'para;', 'para', 'part;', 'permil;',
+    'perp;', 'phi;', 'pi;', 'piv;', 'plusmn;', 'plusmn', 'pound;', 'pound', 'prime;',
+    'prod;', 'prop;', 'psi;', 'quot;', 'quot', 'rArr;', 'radic;', 'rang;', 'raquo;',
+    'raquo', 'rarr;', 'rceil;', 'rdquo;', 'real;', 'reg;', 'reg', 'rfloor;', 'rho;',
+    'rlm;', 'rsaquo;', 'rsquo;', 'sbquo;', 'scaron;', 'sdot;', 'sect;', 'sect', 'shy;',
+    'shy', 'sigma;', 'sigmaf;', 'sim;', 'spades;', 'sub;', 'sube;', 'sum;', 'sup1;',
+    'sup1', 'sup2;', 'sup2', 'sup3;', 'sup3', 'sup;', 'supe;', 'szlig;', 'szlig', 'tau;',
+    'there4;', 'theta;', 'thetasym;', 'thinsp;', 'thorn;', 'thorn', 'tilde;', 'times;',
+    'times', 'trade;', 'uArr;', 'uacute;', 'uacute', 'uarr;', 'ucirc;', 'ucirc',
+    'ugrave;', 'ugrave', 'uml;', 'uml', 'upsih;', 'upsilon;', 'uuml;', 'uuml', 'weierp;',
+    'xi;', 'yacute;', 'yacute', 'yen;', 'yen', 'yuml;', 'yuml', 'zeta;', 'zwj;', 'zwnj;');
 
     const PCDATA    = 0;
     const RCDATA    = 1;
@@ -134,7 +134,7 @@ 
 
         $this->state = 'data';
 
-        while($this->state !== null) {
+        while ($this->state !== null) {
             $this->{$this->state.'State'}();
         }
     }
@@ -150,8 +150,8 @@ 
     }
 
     private function character($s, $l = 0) {
-        if($s + $l < $this->EOF) {
-            if($l === 0) {
+        if ($s + $l < $this->EOF) {
+            if ($l === 0) {
                 return $this->data[$s];
             } else {
                 return substr($this->data, $s, $l);
@@ -168,21 +168,21 @@ 
         $this->char++;
         $char = $this->char();
 
-        if($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
+        if ($char === '&' && ($this->content_model === self::PCDATA || $this->content_model === self::RCDATA)) {
             /* U+0026 AMPERSAND (&)
             When the content model flag is set to one of the PCDATA or RCDATA
             states: switch to the entity data state. Otherwise: treat it as per
             the "anything else"    entry below. */
             $this->state = 'entityData';
 
-        } elseif($char === '-') {
+        } elseif ($char === '-') {
             /* If the content model flag is set to either the RCDATA state or
             the CDATA state, and the escape flag is false, and there are at
             least three characters before this one in the input stream, and the
             last four characters in the input stream, including this one, are
             U+003C LESS-THAN SIGN, U+0021 EXCLAMATION MARK, U+002D HYPHEN-MINUS,
             and U+002D HYPHEN-MINUS ("<!--"), then set the escape flag to true. */
-            if(($this->content_model === self::RCDATA || $this->content_model ===
+            if (($this->content_model === self::RCDATA || $this->content_model ===
             self::CDATA) && $this->escape === false &&
             $this->char >= 3 && $this->character($this->char - 4, 4) === '<!--') {
                 $this->escape = true;
@@ -196,7 +196,7 @@ 
             ));
 
         /* U+003C LESS-THAN SIGN (<) */
-        } elseif($char === '<' && ($this->content_model === self::PCDATA ||
+        } elseif ($char === '<' && ($this->content_model === self::PCDATA ||
         (($this->content_model === self::RCDATA ||
         $this->content_model === self::CDATA) && $this->escape === false))) {
             /* When the content model flag is set to the PCDATA state: switch
@@ -210,13 +210,13 @@ 
             $this->state = 'tagOpen';
 
         /* U+003E GREATER-THAN SIGN (>) */
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* If the content model flag is set to either the RCDATA state or
             the CDATA state, and the escape flag is true, and the last three
             characters in the input stream including this one are U+002D
             HYPHEN-MINUS, U+002D HYPHEN-MINUS, U+003E GREATER-THAN SIGN ("-->"),
             set the escape flag to false. */
-            if(($this->content_model === self::RCDATA ||
+            if (($this->content_model === self::RCDATA ||
             $this->content_model === self::CDATA) && $this->escape === true &&
             $this->character($this->char, 3) === '-->') {
                 $this->escape = false;
@@ -229,12 +229,12 @@ 
                 'data' => $char
             ));
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Emit an end-of-file token. */
             $this->EOF();
 
-        } elseif($this->content_model === self::PLAINTEXT) {
+        } elseif ($this->content_model === self::PLAINTEXT) {
             /* When the content model flag is set to the PLAINTEXT state
             THIS DIFFERS GREATLY FROM THE SPEC: Get the remaining characters of
             the text and emit it as a character token. */
@@ -280,7 +280,7 @@ 
     }
 
     private function tagOpenState() {
-        switch($this->content_model) {
+        switch ($this->content_model) {
             case self::RCDATA:
             case self::CDATA:
                 /* If the next input character is a U+002F SOLIDUS (/) character,
@@ -288,7 +288,7 @@ 
                 input character is not a U+002F SOLIDUS (/) character, emit a
                 U+003C LESS-THAN SIGN character token and switch to the data
                 state to process the next input character. */
-                if($this->character($this->char + 1) === '/') {
+                if ($this->character($this->char + 1) === '/') {
                     $this->char++;
                     $this->state = 'closeTagOpen';
 
@@ -308,17 +308,17 @@ 
                 $this->char++;
                 $char = $this->char();
 
-                if($char === '!') {
+                if ($char === '!') {
                     /* U+0021 EXCLAMATION MARK (!)
                     Switch to the markup declaration open state. */
                     $this->state = 'markupDeclarationOpen';
 
-                } elseif($char === '/') {
+                } elseif ($char === '/') {
                     /* U+002F SOLIDUS (/)
                     Switch to the close tag open state. */
                     $this->state = 'closeTagOpen';
 
-                } elseif(preg_match('/^[A-Za-z]$/', $char)) {
+                } elseif (preg_match('/^[A-Za-z]$/', $char)) {
                     /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
                     Create a new start tag token, set its tag name to the lowercase
                     version of the input character (add 0x0020 to the character's code
@@ -332,7 +332,7 @@ 
 
                     $this->state = 'tagName';
 
-                } elseif($char === '>') {
+                } elseif ($char === '>') {
                     /* U+003E GREATER-THAN SIGN (>)
                     Parse error. Emit a U+003C LESS-THAN SIGN character token and a
                     U+003E GREATER-THAN SIGN character token. Switch to the data state. */
@@ -343,7 +343,7 @@ 
 
                     $this->state = 'data';
 
-                } elseif($char === '?') {
+                } elseif ($char === '?') {
                     /* U+003F QUESTION MARK (?)
                     Parse error. Switch to the bogus comment state. */
                     $this->state = 'bogusComment';
@@ -368,7 +368,7 @@ 
         $next_node = strtolower($this->characters('A-Za-z', $this->char + 1));
         $the_same = count($this->tree->stack) > 0 && $next_node === end($this->tree->stack)->nodeName;
 
-        if(($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
+        if (($this->content_model === self::RCDATA || $this->content_model === self::CDATA) &&
         (!$the_same || ($the_same && (!preg_match('/[\t\n\x0b\x0c >\/]/',
         $this->character($this->char + 1 + strlen($next_node))) || $this->EOF === $this->char)))) {
             /* If the content model flag is set to the RCDATA or CDATA states then
@@ -400,7 +400,7 @@ 
             $this->char++;
             $char = $this->char();
 
-            if(preg_match('/^[A-Za-z]$/', $char)) {
+            if (preg_match('/^[A-Za-z]$/', $char)) {
                 /* U+0041 LATIN LETTER A through to U+005A LATIN LETTER Z
                 Create a new end tag token, set its tag name to the lowercase version
                 of the input character (add 0x0020 to the character's code point), then
@@ -413,12 +413,12 @@ 
 
                 $this->state = 'tagName';
 
-            } elseif($char === '>') {
+            } elseif ($char === '>') {
                 /* U+003E GREATER-THAN SIGN (>)
                 Parse error. Switch to the data state. */
                 $this->state = 'data';
 
-            } elseif($this->char === $this->EOF) {
+            } elseif ($this->char === $this->EOF) {
                 /* EOF
                 Parse error. Emit a U+003C LESS-THAN SIGN character token and a U+002F
                 SOLIDUS character token. Reconsume the EOF character in the data state. */
@@ -442,7 +442,7 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             /* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
@@ -451,13 +451,13 @@ 
             Switch to the before attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
@@ -466,7 +466,7 @@ 
             $this->char--;
             $this->state = 'data';
 
-        } elseif($char === '/') {
+        } elseif ($char === '/') {
             /* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Switch to the before
             attribute name state. */
@@ -486,7 +486,7 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             /* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
@@ -495,19 +495,19 @@ 
             Stay in the before attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($char === '/') {
+        } elseif ($char === '/') {
             /* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Stay in the before
             attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
@@ -535,7 +535,7 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             /* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
@@ -544,24 +544,24 @@ 
             Stay in the before attribute name state. */
             $this->state = 'afterAttributeName';
 
-        } elseif($char === '=') {
+        } elseif ($char === '=') {
             /* U+003D EQUALS SIGN (=)
             Switch to the before attribute value state. */
             $this->state = 'beforeAttributeValue';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+        } elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
             /* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Switch to the before
             attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
@@ -586,7 +586,7 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             /* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
@@ -595,24 +595,24 @@ 
             Stay in the after attribute name state. */
             $this->state = 'afterAttributeName';
 
-        } elseif($char === '=') {
+        } elseif ($char === '=') {
             /* U+003D EQUALS SIGN (=)
             Switch to the before attribute value state. */
             $this->state = 'beforeAttributeValue';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($char === '/' && $this->character($this->char + 1) !== '>') {
+        } elseif ($char === '/' && $this->character($this->char + 1) !== '>') {
             /* U+002F SOLIDUS (/)
             Parse error unless this is a permitted slash. Switch to the
             before attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Parse error. Emit the current tag token. Reconsume the EOF
             character in the data state. */
@@ -640,7 +640,7 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             /* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
@@ -649,24 +649,24 @@ 
             Stay in the before attribute value state. */
             $this->state = 'beforeAttributeValue';
 
-        } elseif($char === '"') {
+        } elseif ($char === '"') {
             /* U+0022 QUOTATION MARK (")
             Switch to the attribute value (double-quoted) state. */
             $this->state = 'attributeValueDoubleQuoted';
 
-        } elseif($char === '&') {
+        } elseif ($char === '&') {
             /* U+0026 AMPERSAND (&)
             Switch to the attribute value (unquoted) state and reconsume
             this input character. */
             $this->char--;
             $this->state = 'attributeValueUnquoted';
 
-        } elseif($char === '\'') {
+        } elseif ($char === '\'') {
             /* U+0027 APOSTROPHE (')
             Switch to the attribute value (single-quoted) state. */
             $this->state = 'attributeValueSingleQuoted';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
             $this->emitToken($this->token);
@@ -688,17 +688,17 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if($char === '"') {
+        if ($char === '"') {
             /* U+0022 QUOTATION MARK (")
             Switch to the before attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($char === '&') {
+        } elseif ($char === '&') {
             /* U+0026 AMPERSAND (&)
             Switch to the entity in attribute value state. */
             $this->entityInAttributeValueState('double');
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Parse error. Emit the current tag token. Reconsume the character
             in the data state. */
@@ -723,17 +723,17 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if($char === '\'') {
+        if ($char === '\'') {
             /* U+0022 QUOTATION MARK (')
             Switch to the before attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($char === '&') {
+        } elseif ($char === '&') {
             /* U+0026 AMPERSAND (&)
             Switch to the entity in attribute value state. */
             $this->entityInAttributeValueState('single');
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* EOF
             Parse error. Emit the current tag token. Reconsume the character
             in the data state. */
@@ -758,7 +758,7 @@ 
         $this->char++;
         $char = $this->character($this->char);
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             /* U+0009 CHARACTER TABULATION
             U+000A LINE FEED (LF)
             U+000B LINE TABULATION
@@ -767,12 +767,12 @@ 
             Switch to the before attribute name state. */
             $this->state = 'beforeAttributeName';
 
-        } elseif($char === '&') {
+        } elseif ($char === '&') {
             /* U+0026 AMPERSAND (&)
             Switch to the entity in attribute value state. */
             $this->entityInAttributeValueState();
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             /* U+003E GREATER-THAN SIGN (>)
             Emit the current tag token. Switch to the data state. */
             $this->emitToken($this->token);
@@ -825,7 +825,7 @@ 
         $this->state = 'data';
 
         /* If the end of the file was reached, reconsume the EOF character. */
-        if($this->char === $this->EOF) {
+        if ($this->char === $this->EOF) {
             $this->char = $this->EOF - 1;
         }
     }
@@ -834,7 +834,7 @@ 
         /* If the next two characters are both U+002D HYPHEN-MINUS (-)
         characters, consume those two characters, create a comment token whose
         data is the empty string, and switch to the comment state. */
-        if($this->character($this->char + 1, 2) === '--') {
+        if ($this->character($this->char + 1, 2) === '--') {
             $this->char += 2;
             $this->state = 'comment';
             $this->token = array(
@@ -845,7 +845,7 @@ 
         /* Otherwise if the next seven chacacters are a case-insensitive match
         for the word "DOCTYPE", then consume those characters and switch to the
         DOCTYPE state. */
-        } elseif(strtolower($this->character($this->char + 1, 7)) === 'doctype') {
+        } elseif (strtolower($this->character($this->char + 1, 7)) === 'doctype') {
             $this->char += 7;
             $this->state = 'doctype';
 
@@ -864,12 +864,12 @@ 
         $char = $this->char();
 
         /* U+002D HYPHEN-MINUS (-) */
-        if($char === '-') {
+        if ($char === '-') {
             /* Switch to the comment dash state  */
             $this->state = 'commentDash';
 
         /* EOF */
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* Parse error. Emit the comment token. Reconsume the EOF character
             in the data state. */
             $this->emitToken($this->token);
@@ -890,12 +890,12 @@ 
         $char = $this->char();
 
         /* U+002D HYPHEN-MINUS (-) */
-        if($char === '-') {
+        if ($char === '-') {
             /* Switch to the comment end state  */
             $this->state = 'commentEnd';
 
         /* EOF */
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             /* Parse error. Emit the comment token. Reconsume the EOF character
             in the data state. */
             $this->emitToken($this->token);
@@ -916,14 +916,14 @@ 
         $this->char++;
         $char = $this->char();
 
-        if($char === '>') {
+        if ($char === '>') {
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($char === '-') {
+        } elseif ($char === '-') {
             $this->token['data'] .= '-';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             $this->emitToken($this->token);
             $this->char--;
             $this->state = 'data';
@@ -939,7 +939,7 @@ 
         $this->char++;
         $char = $this->char();
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             $this->state = 'beforeDoctypeName';
 
         } else {
@@ -953,10 +953,10 @@ 
         $this->char++;
         $char = $this->char();
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             // Stay in the before DOCTYPE name state.
 
-        } elseif(preg_match('/^[a-z]$/', $char)) {
+        } elseif (preg_match('/^[a-z]$/', $char)) {
             $this->token = array(
                 'name' => strtoupper($char),
                 'type' => self::DOCTYPE,
@@ -965,7 +965,7 @@ 
 
             $this->state = 'doctypeName';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             $this->emitToken(array(
                 'name' => null,
                 'type' => self::DOCTYPE,
@@ -974,7 +974,7 @@ 
 
             $this->state = 'data';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             $this->emitToken(array(
                 'name' => null,
                 'type' => self::DOCTYPE,
@@ -1000,17 +1000,17 @@ 
         $this->char++;
         $char = $this->char();
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             $this->state = 'AfterDoctypeName';
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif(preg_match('/^[a-z]$/', $char)) {
+        } elseif (preg_match('/^[a-z]$/', $char)) {
             $this->token['name'] .= strtoupper($char);
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             $this->emitToken($this->token);
             $this->char--;
             $this->state = 'data';
@@ -1029,14 +1029,14 @@ 
         $this->char++;
         $char = $this->char();
 
-        if(preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
+        if (preg_match('/^[\t\n\x0b\x0c ]$/', $char)) {
             // Stay in the DOCTYPE name state.
 
-        } elseif($char === '>') {
+        } elseif ($char === '>') {
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             $this->emitToken($this->token);
             $this->char--;
             $this->state = 'data';
@@ -1052,11 +1052,11 @@ 
         $this->char++;
         $char = $this->char();
 
-        if($char === '>') {
+        if ($char === '>') {
             $this->emitToken($this->token);
             $this->state = 'data';
 
-        } elseif($this->char === $this->EOF) {
+        } elseif ($this->char === $this->EOF) {
             $this->emitToken($this->token);
             $this->char--;
             $this->state = 'data';
@@ -1075,13 +1075,13 @@ 
         // The behaviour depends on the identity of the next character (the
         // one immediately after the U+0026 AMPERSAND character): 
 
-        switch($this->character($this->char + 1)) {
+        switch ($this->character($this->char + 1)) {
             // U+0023 NUMBER SIGN (#)
             case '#':
 
                 // The behaviour further depends on the character after the
                 // U+0023 NUMBER SIGN:
-                switch($this->character($this->char + 1)) {
+                switch ($this->character($this->char + 1)) {
                     // U+0078 LATIN SMALL LETTER X
                     // U+0058 LATIN CAPITAL LETTER X
                     case 'x':
@@ -1124,12 +1124,12 @@ 
                 $e_name = $this->characters('0-9A-Za-z;', $this->char + 1);
                 $len = strlen($e_name);
 
-                for($c = 1; $c <= $len; $c++) {
+                for ($c = 1; $c <= $len; $c++) {
                     $id = substr($e_name, 0, $c);
                     $this->char++;
 
-                    if(in_array($id, $this->entities)) {
-                        if ($e_name[$c-1] !== ';') {
+                    if (in_array($id, $this->entities)) {
+                        if ($e_name[$c - 1] !== ';') {
                             if ($c < $len && $e_name[$c] == ';') {
                                 $this->char++; // consume extra semicolon
                             }
@@ -1144,7 +1144,7 @@ 
             break;
         }
 
-        if(!$cond) {
+        if (!$cond) {
             // If no match can be made, then this is a parse error. No
             // characters are consumed, and nothing is returned.
             $this->char = $start;
@@ -1159,10 +1159,10 @@ 
     private function emitToken($token) {
         $emit = $this->tree->emitToken($token);
 
-        if(is_int($emit)) {
+        if (is_int($emit)) {
             $this->content_model = $emit;
 
-        } elseif($token['type'] === self::ENDTAG) {
+        } elseif ($token['type'] === self::ENDTAG) {
             $this->content_model = self::PCDATA;
         }
     }
@@ -1187,15 +1187,15 @@ 
     private $head_pointer = null;
     private $form_pointer = null;
 
-    private $scoping = array('button','caption','html','marquee','object','table','td','th');
-    private $formatting = array('a','b','big','em','font','i','nobr','s','small','strike','strong','tt','u');
-    private $special = array('address','area','base','basefont','bgsound',
-    'blockquote','body','br','center','col','colgroup','dd','dir','div','dl',
-    'dt','embed','fieldset','form','frame','frameset','h1','h2','h3','h4','h5',
-    'h6','head','hr','iframe','image','img','input','isindex','li','link',
-    'listing','menu','meta','noembed','noframes','noscript','ol','optgroup',
-    'option','p','param','plaintext','pre','script','select','spacer','style',
-    'tbody','textarea','tfoot','thead','title','tr','ul','wbr');
+    private $scoping = array('button', 'caption', 'html', 'marquee', 'object', 'table', 'td', 'th');
+    private $formatting = array('a', 'b', 'big', 'em', 'font', 'i', 'nobr', 's', 'small', 'strike', 'strong', 'tt', 'u');
+    private $special = array('address', 'area', 'base', 'basefont', 'bgsound',
+    'blockquote', 'body', 'br', 'center', 'col', 'colgroup', 'dd', 'dir', 'div', 'dl',
+    'dt', 'embed', 'fieldset', 'form', 'frame', 'frameset', 'h1', 'h2', 'h3', 'h4', 'h5',
+    'h6', 'head', 'hr', 'iframe', 'image', 'img', 'input', 'isindex', 'li', 'link',
+    'listing', 'menu', 'meta', 'noembed', 'noframes', 'noscript', 'ol', 'optgroup',
+    'option', 'p', 'param', 'plaintext', 'pre', 'script', 'select', 'spacer', 'style',
+    'tbody', 'textarea', 'tfoot', 'thead', 'title', 'tr', 'ul', 'wbr');
 
     // The different phases.
     const INIT_PHASE = 0;
@@ -1240,7 +1240,7 @@ 
 
     // Process tag tokens
     public function emitToken($token) {
-        switch($this->phase) {
+        switch ($this->phase) {
             case self::INIT_PHASE: return $this->initPhase($token); break;
             case self::ROOT_PHASE: return $this->rootElementPhase($token); break;
             case self::MAIN_PHASE: return $this->mainPhase($token); break;
@@ -1260,7 +1260,7 @@ 
             U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
             or U+0020 SPACE
         An end-of-file token */
-        if((isset($token['error']) && $token['error']) ||
+        if ((isset($token['error']) && $token['error']) ||
         $token['type'] === HTML5::COMMENT ||
         $token['type'] === HTML5::STARTTAG ||
         $token['type'] === HTML5::ENDTAG ||
@@ -1276,7 +1276,7 @@ 
             return $this->rootElementPhase($token);
 
         /* A DOCTYPE token marked as being correct */
-        } elseif(isset($token['error']) && !$token['error']) {
+        } elseif (isset($token['error']) && !$token['error']) {
             /* Append a DocumentType node to the Document  node, with the name
             attribute set to the name given in the DOCTYPE token (which will be
             "HTML"), and the other attributes specific to DocumentType objects
@@ -1290,7 +1290,7 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        } elseif(isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
+        } elseif (isset($token['data']) && preg_match('/^[\t\n\x0b\x0c ]+$/',
         $token['data'])) {
             /* Append that character  to the Document node. */
             $text = $this->dom->createTextNode($token['data']);
@@ -1303,11 +1303,11 @@ 
         stage, it must be processed as described in this section. */
 
         /* A DOCTYPE token */
-        if($token['type'] === HTML5::DOCTYPE) {
+        if ($token['type'] === HTML5::DOCTYPE) {
             // Parse error. Ignore the token.
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the Document object with the data
             attribute set to the data given in the comment token. */
             $comment = $this->dom->createComment($token['data']);
@@ -1316,7 +1316,7 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        } elseif($token['type'] === HTML5::CHARACTR &&
+        } elseif ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append that character  to the Document node. */
             $text = $this->dom->createTextNode($token['data']);
@@ -1328,7 +1328,7 @@ 
         A start tag token
         An end tag token
         An end-of-file token */
-        } elseif(($token['type'] === HTML5::CHARACTR &&
+        } elseif (($token['type'] === HTML5::CHARACTR &&
         !preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
         $token['type'] === HTML5::STARTTAG ||
         $token['type'] === HTML5::ENDTAG ||
@@ -1349,11 +1349,11 @@ 
         /* Tokens in the main phase must be handled as follows: */
 
         /* A DOCTYPE token */
-        if($token['type'] === HTML5::DOCTYPE) {
+        if ($token['type'] === HTML5::DOCTYPE) {
             // Parse error. Ignore the token.
 
         /* A start tag token with the tag name "html" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'html') {
             /* If this start tag token was not the first start tag token, then
             it is a parse error. */
 
@@ -1361,21 +1361,21 @@ 
             is already present on the top element of the stack of open elements.
             If it is not, add the attribute and its corresponding value to that
             element. */
-            foreach($token['attr'] as $attr) {
-                if(!$this->stack[0]->hasAttribute($attr['name'])) {
+            foreach ($token['attr'] as $attr) {
+                if (!$this->stack[0]->hasAttribute($attr['name'])) {
                     $this->stack[0]->setAttribute($attr['name'], $attr['value']);
                 }
             }
 
         /* An end-of-file token */
-        } elseif($token['type'] === HTML5::EOF) {
+        } elseif ($token['type'] === HTML5::EOF) {
             /* Generate implied end tags. */
             $this->generateImpliedEndTags();
 
         /* Anything else. */
         } else {
             /* Depends on the insertion mode: */
-            switch($this->mode) {
+            switch ($this->mode) {
                 case self::BEFOR_HEAD: return $this->beforeHead($token); break;
                 case self::IN_HEAD:    return $this->inHead($token); break;
                 case self::AFTER_HEAD: return $this->afterHead($token); break;
@@ -1401,19 +1401,19 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append the character to the current node. */
             $this->insertText($token['data']);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data attribute
             set to the data given in the comment token. */
             $this->insertComment($token['data']);
 
         /* A start tag token with the tag name "head" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') {
             /* Create an element for the token, append the new element to the
             current node and push it onto the stack of open elements. */
             $element = $this->insertElement($token);
@@ -1429,7 +1429,7 @@ 
         Or a character token that is not one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE. Or any other start tag token */
-        } elseif($token['type'] === HTML5::STARTTAG ||
+        } elseif ($token['type'] === HTML5::STARTTAG ||
         ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') ||
         ($token['type'] === HTML5::CHARACTR && !preg_match('/^[\t\n\x0b\x0c ]$/',
         $token['data']))) {
@@ -1444,7 +1444,7 @@ 
             return $this->inHead($token);
 
         /* Any other end tag */
-        } elseif($token['type'] === HTML5::ENDTAG) {
+        } elseif ($token['type'] === HTML5::ENDTAG) {
             /* Parse error. Ignore the token. */
         }
     }
@@ -1459,7 +1459,7 @@ 
         THIS DIFFERS FROM THE SPEC: If the current node is either a title, style
         or script element, append the character to the current node regardless
         of its content. */
-        if(($token['type'] === HTML5::CHARACTR &&
+        if (($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) || (
         $token['type'] === HTML5::CHARACTR && in_array(end($this->stack)->nodeName,
         array('title', 'style', 'script')))) {
@@ -1467,22 +1467,22 @@ 
             $this->insertText($token['data']);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data attribute
             set to the data given in the comment token. */
             $this->insertComment($token['data']);
 
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         in_array($token['name'], array('title', 'style', 'script'))) {
             array_pop($this->stack);
             return HTML5::PCDATA;
 
         /* A start tag with the tag name "title" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'title') {
             /* Create an element for the token and append the new element to the
             node pointed to by the head element pointer, or, if that is null
             (innerHTML case), to the current node. */
-            if($this->head_pointer !== null) {
+            if ($this->head_pointer !== null) {
                 $element = $this->insertElement($token, false);
                 $this->head_pointer->appendChild($element);
 
@@ -1494,11 +1494,11 @@ 
             return HTML5::RCDATA;
 
         /* A start tag with the tag name "style" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'style') {
             /* Create an element for the token and append the new element to the
             node pointed to by the head element pointer, or, if that is null
             (innerHTML case), to the current node. */
-            if($this->head_pointer !== null) {
+            if ($this->head_pointer !== null) {
                 $element = $this->insertElement($token, false);
                 $this->head_pointer->appendChild($element);
 
@@ -1510,7 +1510,7 @@ 
             return HTML5::CDATA;
 
         /* A start tag with the tag name "script" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'script') {
             /* Create an element for the token. */
             $element = $this->insertElement($token, false);
             $this->head_pointer->appendChild($element);
@@ -1519,12 +1519,12 @@ 
             return HTML5::CDATA;
 
         /* A start tag with the tag name "base", "link", or "meta" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('base', 'link', 'meta'))) {
             /* Create an element for the token and append the new element to the
             node pointed to by the head element pointer, or, if that is null
             (innerHTML case), to the current node. */
-            if($this->head_pointer !== null) {
+            if ($this->head_pointer !== null) {
                 $element = $this->insertElement($token, false);
                 $this->head_pointer->appendChild($element);
                 array_pop($this->stack);
@@ -1534,10 +1534,10 @@ 
             }
 
         /* An end tag with the tag name "head" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
+        } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'head') {
             /* If the current node is a head element, pop the current node off
             the stack of open elements. */
-            if($this->head_pointer->isSameNode(end($this->stack))) {
+            if ($this->head_pointer->isSameNode(end($this->stack))) {
                 array_pop($this->stack);
 
             /* Otherwise, this is a parse error. */
@@ -1549,7 +1549,7 @@ 
             $this->mode = self::AFTER_HEAD;
 
         /* A start tag with the tag name "head" or an end tag except "html". */
-        } elseif(($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
+        } elseif (($token['type'] === HTML5::STARTTAG && $token['name'] === 'head') ||
         ($token['type'] === HTML5::ENDTAG && $token['name'] !== 'html')) {
             // Parse error. Ignore the token.
 
@@ -1557,7 +1557,7 @@ 
         } else {
             /* If the current node is a head element, act as if an end tag
             token with the tag name "head" had been seen. */
-            if($this->head_pointer->isSameNode(end($this->stack))) {
+            if ($this->head_pointer->isSameNode(end($this->stack))) {
                 $this->inHead(array(
                     'name' => 'head',
                     'type' => HTML5::ENDTAG
@@ -1579,19 +1579,19 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append the character to the current node. */
             $this->insertText($token['data']);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data attribute
             set to the data given in the comment token. */
             $this->insertComment($token['data']);
 
         /* A start tag token with the tag name "body" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'body') {
             /* Insert a body element for the token. */
             $this->insertElement($token);
 
@@ -1599,7 +1599,7 @@ 
             $this->mode = self::IN_BODY;
 
         /* A start tag token with the tag name "frameset" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'frameset') {
             /* Insert a frameset element for the token. */
             $this->insertElement($token);
 
@@ -1608,7 +1608,7 @@ 
 
         /* A start tag token whose tag name is one of: "base", "link", "meta",
         "script", "style", "title" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('base', 'link', 'meta', 'script', 'style', 'title'))) {
             /* Parse error. Switch the insertion mode back to "in head" and
             reprocess the token. */
@@ -1632,7 +1632,7 @@ 
     private function inBody($token) {
         /* Handle the token as follows: */
 
-        switch($token['type']) {
+        switch ($token['type']) {
             /* A character token */
             case HTML5::CHARACTR:
                 /* Reconstruct the active formatting elements, if any. */
@@ -1650,7 +1650,7 @@ 
             break;
 
             case HTML5::STARTTAG:
-            switch($token['name']) {
+            switch ($token['name']) {
                 /* A start tag token whose tag name is one of: "script",
                 "style" */
                 case 'script': case 'style':
@@ -1673,7 +1673,7 @@ 
                     elements is not a body element, or, if the stack of open
                     elements has only one node on it, then ignore the token.
                     (innerHTML case) */
-                    if(count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
+                    if (count($this->stack) === 1 || $this->stack[1]->nodeName !== 'body') {
                         // Ignore
 
                     /* Otherwise, for each attribute on the token, check to see
@@ -1682,8 +1682,8 @@ 
                     add the attribute and its corresponding value to that
                     element. */
                     } else {
-                        foreach($token['attr'] as $attr) {
-                            if(!$this->stack[1]->hasAttribute($attr['name'])) {
+                        foreach ($token['attr'] as $attr) {
+                            if (!$this->stack[1]->hasAttribute($attr['name'])) {
                                 $this->stack[1]->setAttribute($attr['name'], $attr['value']);
                             }
                         }
@@ -1699,7 +1699,7 @@ 
                     /* If the stack of open elements has a p element in scope,
                     then act as if an end tag with the tag name p had been
                     seen. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->emitToken(array(
                             'name' => 'p',
                             'type' => HTML5::ENDTAG
@@ -1714,7 +1714,7 @@ 
                 case 'form':
                     /* If the form element pointer is not null, ignore the
                     token with a parse error. */
-                    if($this->form_pointer !== null) {
+                    if ($this->form_pointer !== null) {
                         // Ignore.
 
                     /* Otherwise: */
@@ -1722,7 +1722,7 @@ 
                         /* If the stack of open elements has a p element in
                         scope, then act as if an end tag with the tag name p
                         had been seen. */
-                        if($this->elementInScope('p')) {
+                        if ($this->elementInScope('p')) {
                             $this->emitToken(array(
                                 'name' => 'p',
                                 'type' => HTML5::ENDTAG
@@ -1741,7 +1741,7 @@ 
                     /* If the stack of open elements has a p  element in scope,
                     then act as if an end tag with the tag name p had been
                     seen. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->emitToken(array(
                             'name' => 'p',
                             'type' => HTML5::ENDTAG
@@ -1750,7 +1750,7 @@ 
 
                     $stack_length = count($this->stack) - 1;
 
-                    for($n = $stack_length; 0 <= $n; $n--) {
+                    for ($n = $stack_length; 0 <= $n; $n--) {
                         /* 1. Initialise node to be the current node (the
                         bottommost node of the stack). */
                         $stop = false;
@@ -1760,9 +1760,9 @@ 
                         /* 2. If node is an li, dd or dt element, then pop all
                         the    nodes from the current node up to node, including
                         node, then stop this algorithm. */
-                        if($token['name'] === $node->tagName ||    ($token['name'] !== 'li'
+                        if ($token['name'] === $node->tagName || ($token['name'] !== 'li'
                         && ($node->tagName === 'dd' || $node->tagName === 'dt'))) {
-                            for($x = $stack_length; $x >= $n ; $x--) {
+                            for ($x = $stack_length; $x >= $n; $x--) {
                                 array_pop($this->stack);
                             }
 
@@ -1772,7 +1772,7 @@ 
                         /* 3. If node is not in the formatting category, and is
                         not    in the phrasing category, and is not an address or
                         div element, then stop this algorithm. */
-                        if($cat !== self::FORMATTING && $cat !== self::PHRASING &&
+                        if ($cat !== self::FORMATTING && $cat !== self::PHRASING &&
                         $node->tagName !== 'address' && $node->tagName !== 'div') {
                             break;
                         }
@@ -1788,7 +1788,7 @@ 
                     /* If the stack of open elements has a p  element in scope,
                     then act as if an end tag with the tag name p had been
                     seen. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->emitToken(array(
                             'name' => 'p',
                             'type' => HTML5::ENDTAG
@@ -1806,7 +1806,7 @@ 
                 case 'h1': case 'h2': case 'h3': case 'h4': case 'h5': case 'h6':
                     /* If the stack of open elements has a p  element in scope,
                     then act as if an end tag with the tag name p had been seen. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->emitToken(array(
                             'name' => 'p',
                             'type' => HTML5::ENDTAG
@@ -1818,7 +1818,7 @@ 
                     this is a parse error; pop elements from the stack until an
                     element with one of those tag names has been popped from the
                     stack. */
-                    while($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
+                    while ($this->elementInScope(array('h1', 'h2', 'h3', 'h4', 'h5', 'h6'))) {
                         array_pop($this->stack);
                     }
 
@@ -1839,11 +1839,11 @@ 
                     might not have if the element is not in table scope). */
                     $leng = count($this->a_formatting);
 
-                    for($n = $leng - 1; $n >= 0; $n--) {
-                        if($this->a_formatting[$n] === self::MARKER) {
+                    for ($n = $leng - 1; $n >= 0; $n--) {
+                        if ($this->a_formatting[$n] === self::MARKER) {
                             break;
 
-                        } elseif($this->a_formatting[$n]->nodeName === 'a') {
+                        } elseif ($this->a_formatting[$n]->nodeName === 'a') {
                             $this->emitToken(array(
                                 'name' => 'a',
                                 'type' => HTML5::ENDTAG
@@ -1885,7 +1885,7 @@ 
                     then this is a parse error; act as if an end tag with the tag
                     name "button" had been seen, then reprocess the token. (We don't
                     do that. Unnecessary.) */
-                    if($this->elementInScope('button')) {
+                    if ($this->elementInScope('button')) {
                         $this->inBody(array(
                             'name' => 'button',
                             'type' => HTML5::ENDTAG
@@ -1932,7 +1932,7 @@ 
                 case 'table':
                     /* If the stack of open elements has a p element in scope,
                     then act as if an end tag with the tag name p had been seen. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->emitToken(array(
                             'name' => 'p',
                             'type' => HTML5::ENDTAG
@@ -1965,7 +1965,7 @@ 
                 case 'hr':
                     /* If the stack of open elements has a p element in scope,
                     then act as if an end tag with the tag name p had been seen. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->emitToken(array(
                             'name' => 'p',
                             'type' => HTML5::ENDTAG
@@ -2013,7 +2013,7 @@ 
 
                     /* If the form element pointer is not null,
                     then ignore the token. */
-                    if($this->form_pointer === null) {
+                    if ($this->form_pointer === null) {
                         /* Act as if a start tag token with the tag name "form" had
                         been seen. */
                         $this->inBody(array(
@@ -2158,18 +2158,18 @@ 
             break;
 
             case HTML5::ENDTAG:
-            switch($token['name']) {
+            switch ($token['name']) {
                 /* An end tag with the tag name "body" */
                 case 'body':
                     /* If the second element in the stack of open elements is
                     not a body element, this is a parse error. Ignore the token.
                     (innerHTML case) */
-                    if(count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
+                    if (count($this->stack) < 2 || $this->stack[1]->nodeName !== 'body') {
                         // Ignore.
 
                     /* If the current node is not the body element, then this
                     is a parse error. */
-                    } elseif(end($this->stack)->nodeName !== 'body') {
+                    } elseif (end($this->stack)->nodeName !== 'body') {
                         // Parse error.
                     }
 
@@ -2199,7 +2199,7 @@ 
                     /* If the stack of open elements has an element in scope
                     with the same tag name as that of the token, then generate
                     implied end tags. */
-                    if($this->elementInScope($token['name'])) {
+                    if ($this->elementInScope($token['name'])) {
                         $this->generateImpliedEndTags();
 
                         /* Now, if the current node is not an element with
@@ -2211,8 +2211,8 @@ 
                         scope with the same tag name as that of the token,
                         then pop elements from this stack until an element
                         with that tag name has been popped from the stack. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->stack[$n]->nodeName === $token['name']) {
+                        for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+                            if ($this->stack[$n]->nodeName === $token['name']) {
                                 $n = -1;
                             }
 
@@ -2226,12 +2226,12 @@ 
                     /* If the stack of open elements has an element in scope
                     with the same tag name as that of the token, then generate
                     implied    end tags. */
-                    if($this->elementInScope($token['name'])) {
+                    if ($this->elementInScope($token['name'])) {
                         $this->generateImpliedEndTags();
 
                     } 
 
-                    if(end($this->stack)->nodeName !== $token['name']) {
+                    if (end($this->stack)->nodeName !== $token['name']) {
                         /* Now, if the current node is not an element with the
                         same tag name as that of the token, then this is a parse
                         error. */
@@ -2252,7 +2252,7 @@ 
                 case 'p':
                     /* If the stack of open elements has a p element in scope,
                     then generate implied end tags, except for p elements. */
-                    if($this->elementInScope('p')) {
+                    if ($this->elementInScope('p')) {
                         $this->generateImpliedEndTags(array('p'));
 
                         /* If the current node is not a p element, then this is
@@ -2262,8 +2262,8 @@ 
                         /* If the stack of open elements has a p element in
                         scope, then pop elements from this stack until the stack
                         no longer has a p element in scope. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->elementInScope('p')) {
+                        for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+                            if ($this->elementInScope('p')) {
                                 array_pop($this->stack);
 
                             } else {
@@ -2279,7 +2279,7 @@ 
                     whose tag name matches the tag name of the token, then
                     generate implied end tags, except for elements with the
                     same tag name as the token. */
-                    if($this->elementInScope($token['name'])) {
+                    if ($this->elementInScope($token['name'])) {
                         $this->generateImpliedEndTags(array($token['name']));
 
                         /* If the current node is not an element with the same
@@ -2290,8 +2290,8 @@ 
                         whose tag name matches the tag name of the token, then
                         pop elements from this stack until an element with that
                         tag name has been popped from the stack. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->stack[$n]->nodeName === $token['name']) {
+                        for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+                            if ($this->stack[$n]->nodeName === $token['name']) {
                                 $n = -1;
                             }
 
@@ -2308,7 +2308,7 @@ 
                     /* If the stack of open elements has in scope an element whose
                     tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6", then
                     generate implied end tags. */
-                    if($this->elementInScope($elements)) {
+                    if ($this->elementInScope($elements)) {
                         $this->generateImpliedEndTags();
 
                         /* Now, if the current node is not an element with the same
@@ -2319,7 +2319,7 @@ 
                         whose tag name is one of "h1", "h2", "h3", "h4", "h5", or
                         "h6", then pop elements from the stack until an element
                         with one of those tag names has been popped from the stack. */
-                        while($this->elementInScope($elements)) {
+                        while ($this->elementInScope($elements)) {
                             array_pop($this->stack);
                         }
                     }
@@ -2337,12 +2337,12 @@ 
                         otherwise, and
                         * has the same tag name as the token.
                     */
-                    while(true) {
-                        for($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
-                            if($this->a_formatting[$a] === self::MARKER) {
+                    while (true) {
+                        for ($a = count($this->a_formatting) - 1; $a >= 0; $a--) {
+                            if ($this->a_formatting[$a] === self::MARKER) {
                                 break;
 
-                            } elseif($this->a_formatting[$a]->tagName === $token['name']) {
+                            } elseif ($this->a_formatting[$a]->tagName === $token['name']) {
                                 $formatting_element = $this->a_formatting[$a];
                                 $in_stack = in_array($formatting_element, $this->stack, true);
                                 $fe_af_pos = $a;
@@ -2354,7 +2354,7 @@ 
                         also in the stack of open elements but the element
                         is not in scope, then this is a parse error. Abort
                         these steps. The token is ignored. */
-                        if(!isset($formatting_element) || ($in_stack &&
+                        if (!isset($formatting_element) || ($in_stack &&
                         !$this->elementInScope($token['name']))) {
                             break;
 
@@ -2362,7 +2362,7 @@ 
                         is not in the stack of open elements, then this is a
                         parse error; remove the element from the list, and
                         abort these steps. */
-                        } elseif(isset($formatting_element) && !$in_stack) {
+                        } elseif (isset($formatting_element) && !$in_stack) {
                             unset($this->a_formatting[$fe_af_pos]);
                             $this->a_formatting = array_merge($this->a_formatting);
                             break;
@@ -2376,10 +2376,10 @@ 
                         $fe_s_pos = array_search($formatting_element, $this->stack, true);
                         $length = count($this->stack);
 
-                        for($s = $fe_s_pos + 1; $s < $length; $s++) {
+                        for ($s = $fe_s_pos + 1; $s < $length; $s++) {
                             $category = $this->getElementCategory($this->stack[$s]->nodeName);
 
-                            if($category !== self::PHRASING && $category !== self::FORMATTING) {
+                            if ($category !== self::PHRASING && $category !== self::FORMATTING) {
                                 $furthest_block = $this->stack[$s];
                             }
                         }
@@ -2390,8 +2390,8 @@ 
                         elements, from the current node up to the formatting
                         element, and remove the formatting element from the
                         list of active formatting elements. */
-                        if(!isset($furthest_block)) {
-                            for($n = $length - 1; $n >= $fe_s_pos; $n--) {
+                        if (!isset($furthest_block)) {
+                            for ($n = $length - 1; $n >= $fe_s_pos; $n--) {
                                 array_pop($this->stack);
                             }
 
@@ -2407,7 +2407,7 @@ 
 
                         /* 5. If the furthest block has a parent node, then
                         remove the furthest block from its parent node. */
-                        if($furthest_block->parentNode !== null) {
+                        if ($furthest_block->parentNode !== null) {
                             $furthest_block->parentNode->removeChild($furthest_block);
                         }
 
@@ -2422,8 +2422,8 @@ 
                         $node = $furthest_block;
                         $last_node = $furthest_block;
 
-                        while(true) {
-                            for($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
+                        while (true) {
+                            for ($n = array_search($node, $this->stack, true) - 1; $n >= 0; $n--) {
                                 /* 7.1 Let node be the element immediately
                                 prior to node in the stack of open elements. */
                                 $node = $this->stack[$n];
@@ -2432,7 +2432,7 @@ 
                                 formatting elements, then remove node from
                                 the stack of open elements and then go back
                                 to step 1. */
-                                if(!in_array($node, $this->a_formatting, true)) {
+                                if (!in_array($node, $this->a_formatting, true)) {
                                     unset($this->stack[$n]);
                                     $this->stack = array_merge($this->stack);
 
@@ -2444,14 +2444,14 @@ 
                             /* 7.3 Otherwise, if node is the formatting
                             element, then go to the next step in the overall
                             algorithm. */
-                            if($node === $formatting_element) {
+                            if ($node === $formatting_element) {
                                 break;
 
                             /* 7.4 Otherwise, if last node is the furthest
                             block, then move the aforementioned bookmark to
                             be immediately after the node in the list of
                             active formatting elements. */
-                            } elseif($last_node === $furthest_block) {
+                            } elseif ($last_node === $furthest_block) {
                                 $bookmark = array_search($node, $this->a_formatting, true) + 1;
                             }
 
@@ -2461,7 +2461,7 @@ 
                             with an entry for the clone, replace the entry
                             for node in the stack of open elements with an
                             entry for the clone, and let node be the clone. */
-                            if($node->hasChildNodes()) {
+                            if ($node->hasChildNodes()) {
                                 $clone = $node->cloneNode();
                                 $s_pos = array_search($node, $this->stack, true);
                                 $a_pos = array_search($node, $this->a_formatting, true);
@@ -2473,7 +2473,7 @@ 
 
                             /* 7.6 Insert last node into node, first removing
                             it from its previous parent node if any. */
-                            if($last_node->parentNode !== null) {
+                            if ($last_node->parentNode !== null) {
                                 $last_node->parentNode->removeChild($last_node);
                             }
 
@@ -2487,7 +2487,7 @@ 
                         the previous step into the common ancestor node,
                         first removing it from its previous parent node if
                         any. */
-                        if($last_node->parentNode !== null) {
+                        if ($last_node->parentNode !== null) {
                             $last_node->parentNode->removeChild($last_node);
                         }
 
@@ -2500,7 +2500,7 @@ 
                         /* 10. Take all of the child nodes of the furthest
                         block and append them to the clone created in the
                         last step. */
-                        while($furthest_block->hasChildNodes()) {
+                        while ($furthest_block->hasChildNodes()) {
                             $child = $furthest_block->firstChild;
                             $furthest_block->removeChild($child);
                             $clone->appendChild($child);
@@ -2545,7 +2545,7 @@ 
                     /* If the stack of open elements has an element in scope whose
                     tag name matches the tag name of the token, then generate implied
                     tags. */
-                    if($this->elementInScope($token['name'])) {
+                    if ($this->elementInScope($token['name'])) {
                         $this->generateImpliedEndTags();
 
                         /* Now, if the current node is not an element with the same
@@ -2557,8 +2557,8 @@ 
                         elements from the stack until that element has been popped from
                         the stack, and clear the list of active formatting elements up
                         to the last marker. */
-                        for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                            if($this->stack[$n]->nodeName === $token['name']) {
+                        for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+                            if ($this->stack[$n]->nodeName === $token['name']) {
                                 $n = -1;
                             }
 
@@ -2567,7 +2567,7 @@ 
 
                         $marker = end(array_keys($this->a_formatting, self::MARKER, true));
 
-                        for($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
+                        for ($n = count($this->a_formatting) - 1; $n > $marker; $n--) {
                             array_pop($this->a_formatting);
                         }
                     }
@@ -2587,14 +2587,14 @@ 
 
                 /* An end tag token not covered by the previous entries */
                 default:
-                    for($n = count($this->stack) - 1; $n >= 0; $n--) {
+                    for ($n = count($this->stack) - 1; $n >= 0; $n--) {
                         /* Initialise node to be the current node (the bottommost
                         node of the stack). */
                         $node = end($this->stack);
 
                         /* If node has the same tag name as the end tag token,
                         then: */
-                        if($token['name'] === $node->nodeName) {
+                        if ($token['name'] === $node->nodeName) {
                             /* Generate implied end tags. */
                             $this->generateImpliedEndTags();
 
@@ -2605,14 +2605,14 @@ 
 
                             /* Pop all the nodes from the current node up to
                             node, including node, then stop this algorithm. */
-                            for($x = count($this->stack) - $n; $x >= $n; $x--) {
+                            for ($x = count($this->stack) - $n; $x >= $n; $x--) {
                                 array_pop($this->stack);
                             }
                                     
                         } else {
                             $category = $this->getElementCategory($node);
 
-                            if($category !== self::SPECIAL && $category !== self::SCOPING) {
+                            if ($category !== self::SPECIAL && $category !== self::SCOPING) {
                                 /* Otherwise, if node is in neither the formatting
                                 category nor the phrasing category, then this is a
                                 parse error. Stop this algorithm. The end tag token
@@ -2633,21 +2633,21 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append the character to the current node. */
             $text = $this->dom->createTextNode($token['data']);
             end($this->stack)->appendChild($text);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
             $comment = $this->dom->createComment($token['data']);
             end($this->stack)->appendChild($comment);
 
         /* A start tag whose tag name is "caption" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         $token['name'] === 'caption') {
             /* Clear the stack back to a table context. */
             $this->clearStackToTableContext($clear);
@@ -2662,7 +2662,7 @@ 
             $this->mode = self::IN_CAPTION;
 
         /* A start tag whose tag name is "colgroup" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         $token['name'] === 'colgroup') {
             /* Clear the stack back to a table context. */
             $this->clearStackToTableContext($clear);
@@ -2673,7 +2673,7 @@ 
             $this->mode = self::IN_CGROUP;
 
         /* A start tag whose tag name is "col" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         $token['name'] === 'col') {
             $this->inTable(array(
                 'name' => 'colgroup',
@@ -2684,7 +2684,7 @@ 
             $this->inColumnGroup($token);
 
         /* A start tag whose tag name is one of: "tbody", "tfoot", "thead" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('tbody', 'tfoot', 'thead'))) {
             /* Clear the stack back to a table context. */
             $this->clearStackToTableContext($clear);
@@ -2695,7 +2695,7 @@ 
             $this->mode = self::IN_TBODY;
 
         /* A start tag whose tag name is one of: "td", "th", "tr" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         in_array($token['name'], array('td', 'th', 'tr'))) {
             /* Act as if a start tag token with the tag name "tbody" had been
             seen, then reprocess the current token. */
@@ -2708,7 +2708,7 @@ 
             return $this->inTableBody($token);
 
         /* A start tag whose tag name is "table" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         $token['name'] === 'table') {
             /* Parse error. Act as if an end tag token with the tag name "table"
             had been seen, then, if that token wasn't ignored, reprocess the
@@ -2721,12 +2721,12 @@ 
             return $this->mainPhase($token);
 
         /* An end tag whose tag name is "table" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         $token['name'] === 'table') {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 return false;
 
             /* Otherwise: */
@@ -2740,11 +2740,11 @@ 
 
                 /* Pop elements from this stack until a table element has been
                 popped from the stack. */
-                while(true) {
+                while (true) {
                     $current = end($this->stack)->nodeName;
                     array_pop($this->stack);
 
-                    if($current === 'table') {
+                    if ($current === 'table') {
                         break;
                     }
                 }
@@ -2755,7 +2755,7 @@ 
 
         /* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'],
         array('body', 'caption', 'col', 'colgroup', 'html', 'tbody', 'td',
         'tfoot', 'th', 'thead', 'tr'))) {
             // Parse error. Ignore the token.
@@ -2768,7 +2768,7 @@ 
             /* If the current node is a table, tbody, tfoot, thead, or tr
             element, then, whenever a node would be inserted into the current
             node, it must instead be inserted into the foster parent element. */
-            if(in_array(end($this->stack)->nodeName,
+            if (in_array(end($this->stack)->nodeName,
             array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
                 /* The foster parent element is the parent element of the last
                 table element in the stack of open elements, if there is a
@@ -2781,20 +2781,20 @@ 
                 its parent node is not an element, then the foster parent
                 element is the element before the last table element in the
                 stack of open elements. */
-                for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                    if($this->stack[$n]->nodeName === 'table') {
+                for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+                    if ($this->stack[$n]->nodeName === 'table') {
                         $table = $this->stack[$n];
                         break;
                     }
                 }
 
-                if(isset($table) && $table->parentNode !== null) {
+                if (isset($table) && $table->parentNode !== null) {
                     $this->foster_parent = $table->parentNode;
 
-                } elseif(!isset($table)) {
+                } elseif (!isset($table)) {
                     $this->foster_parent = $this->stack[0];
 
-                } elseif(isset($table) && ($table->parentNode === null ||
+                } elseif (isset($table) && ($table->parentNode === null ||
                 $table->parentNode->nodeType !== XML_ELEMENT_NODE)) {
                     $this->foster_parent = $this->stack[$n - 1];
                 }
@@ -2806,11 +2806,11 @@ 
 
     private function inCaption($token) {
         /* An end tag whose tag name is "caption" */
-        if($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
+        if ($token['type'] === HTML5::ENDTAG && $token['name'] === 'caption') {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // Ignore
 
             /* Otherwise: */
@@ -2824,11 +2824,11 @@ 
 
                 /* Pop elements from this stack until a caption element has
                 been popped from the stack. */
-                while(true) {
+                while (true) {
                     $node = end($this->stack)->nodeName;
                     array_pop($this->stack);
 
-                    if($node === 'caption') {
+                    if ($node === 'caption') {
                         break;
                     }
                 }
@@ -2844,7 +2844,7 @@ 
         /* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "td", "tfoot", "th", "thead", "tr", or an end tag whose tag
         name is "table" */
-        } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif (($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
         'thead', 'tr'))) || ($token['type'] === HTML5::ENDTAG &&
         $token['name'] === 'table')) {
@@ -2860,7 +2860,7 @@ 
 
         /* An end tag whose tag name is one of: "body", "col", "colgroup",
         "html", "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'],
         array('body', 'col', 'colgroup', 'html', 'tbody', 'tfoot', 'th',
         'thead', 'tr'))) {
             // Parse error. Ignore the token.
@@ -2876,32 +2876,32 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append the character to the current node. */
             $text = $this->dom->createTextNode($token['data']);
             end($this->stack)->appendChild($text);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
             $comment = $this->dom->createComment($token['data']);
             end($this->stack)->appendChild($comment);
 
         /* A start tag whose tag name is "col" */
-        } elseif($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
+        } elseif ($token['type'] === HTML5::STARTTAG && $token['name'] === 'col') {
             /* Insert a col element for the token. Immediately pop the current
             node off the stack of open elements. */
             $this->insertElement($token);
             array_pop($this->stack);
 
         /* An end tag whose tag name is "colgroup" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         $token['name'] === 'colgroup') {
             /* If the current node is the root html element, then this is a
             parse error, ignore the token. (innerHTML case) */
-            if(end($this->stack)->nodeName === 'html') {
+            if (end($this->stack)->nodeName === 'html') {
                 // Ignore
 
             /* Otherwise, pop the current node (which will be a colgroup
@@ -2913,7 +2913,7 @@ 
             }
 
         /* An end tag whose tag name is "col" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
+        } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'col') {
             /* Parse error. Ignore the token. */
 
         /* Anything else */
@@ -2933,7 +2933,7 @@ 
         $clear = array('tbody', 'tfoot', 'thead', 'html');
 
         /* A start tag whose tag name is "tr" */
-        if($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
+        if ($token['type'] === HTML5::STARTTAG && $token['name'] === 'tr') {
             /* Clear the stack back to a table body context. */
             $this->clearStackToTableContext($clear);
 
@@ -2943,8 +2943,8 @@ 
             $this->mode = self::IN_ROW;
 
         /* A start tag whose tag name is one of: "th", "td" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
-        ($token['name'] === 'th' ||    $token['name'] === 'td')) {
+        } elseif ($token['type'] === HTML5::STARTTAG &&
+        ($token['name'] === 'th' || $token['name'] === 'td')) {
             /* Parse error. Act as if a start tag with the tag name "tr" had
             been seen, then reprocess the current token. */
             $this->inTableBody(array(
@@ -2956,12 +2956,12 @@ 
             return $this->inRow($token);
 
         /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // Ignore
 
             /* Otherwise: */
@@ -2977,13 +2977,13 @@ 
 
         /* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "tfoot", "thead", or an end tag whose tag name is "table" */
-        } elseif(($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif (($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('caption', 'col', 'colgroup', 'tbody', 'tfoor', 'thead'))) ||
         ($token['type'] === HTML5::STARTTAG && $token['name'] === 'table')) {
             /* If the stack of open elements does not have a tbody, thead, or
             tfoot element in table scope, this is a parse error. Ignore the
             token. (innerHTML case) */
-            if(!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
+            if (!$this->elementInScope(array('tbody', 'thead', 'tfoot'), true)) {
                 // Ignore.
 
             /* Otherwise: */
@@ -3004,7 +3004,7 @@ 
 
         /* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html", "td", "th", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'],
         array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
             /* Parse error. Ignore the token. */
 
@@ -3019,7 +3019,7 @@ 
         $clear = array('tr', 'html');
 
         /* A start tag whose tag name is one of: "th", "td" */
-        if($token['type'] === HTML5::STARTTAG &&
+        if ($token['type'] === HTML5::STARTTAG &&
         ($token['name'] === 'th' || $token['name'] === 'td')) {
             /* Clear the stack back to a table row context. */
             $this->clearStackToTableContext($clear);
@@ -3034,11 +3034,11 @@ 
             $this->a_formatting[] = self::MARKER;
 
         /* An end tag whose tag name is "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
+        } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'tr') {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // Ignore.
 
             /* Otherwise: */
@@ -3055,7 +3055,7 @@ 
 
         /* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "tfoot", "thead", "tr" or an end tag whose tag name is "table" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('caption', 'col', 'colgroup', 'tbody', 'tfoot', 'thead', 'tr'))) {
             /* Act as if an end tag with the tag name "tr" had been seen, then,
             if that token wasn't ignored, reprocess the current token. */
@@ -3067,12 +3067,12 @@ 
             return $this->inCell($token);
 
         /* An end tag whose tag name is one of: "tbody", "tfoot", "thead" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         in_array($token['name'], array('tbody', 'tfoot', 'thead'))) {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // Ignore.
 
             /* Otherwise: */
@@ -3089,7 +3089,7 @@ 
 
         /* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html", "td", "th" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'],
         array('body', 'caption', 'col', 'colgroup', 'html', 'td', 'th', 'tr'))) {
             /* Parse error. Ignore the token. */
 
@@ -3102,12 +3102,12 @@ 
 
     private function inCell($token) {
         /* An end tag whose tag name is one of: "td", "th" */
-        if($token['type'] === HTML5::ENDTAG &&
+        if ($token['type'] === HTML5::ENDTAG &&
         ($token['name'] === 'td' || $token['name'] === 'th')) {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as that of the token, then this is a
             parse error and the token must be ignored. */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // Ignore.
 
             /* Otherwise: */
@@ -3122,11 +3122,11 @@ 
 
                 /* Pop elements from this stack until an element with the same
                 tag name as the token has been popped from the stack. */
-                while(true) {
+                while (true) {
                     $node = end($this->stack)->nodeName;
                     array_pop($this->stack);
 
-                    if($node === $token['name']) {
+                    if ($node === $token['name']) {
                         break;
                     }
                 }
@@ -3142,13 +3142,13 @@ 
 
         /* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
         'thead', 'tr'))) {
             /* If the stack of open elements does not have a td or th element
             in table scope, then this is a parse error; ignore the token.
             (innerHTML case) */
-            if(!$this->elementInScope(array('td', 'th'), true)) {
+            if (!$this->elementInScope(array('td', 'th'), true)) {
                 // Ignore.
 
             /* Otherwise, close the cell (see below) and reprocess the current
@@ -3160,13 +3160,13 @@ 
 
         /* A start tag whose tag name is one of: "caption", "col", "colgroup",
         "tbody", "td", "tfoot", "th", "thead", "tr" */
-        } elseif($token['type'] === HTML5::STARTTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::STARTTAG && in_array($token['name'],
         array('caption', 'col', 'colgroup', 'tbody', 'td', 'tfoot', 'th',
         'thead', 'tr'))) {
             /* If the stack of open elements does not have a td or th element
             in table scope, then this is a parse error; ignore the token.
             (innerHTML case) */
-            if(!$this->elementInScope(array('td', 'th'), true)) {
+            if (!$this->elementInScope(array('td', 'th'), true)) {
                 // Ignore.
 
             /* Otherwise, close the cell (see below) and reprocess the current
@@ -3178,19 +3178,19 @@ 
 
         /* An end tag whose tag name is one of: "body", "caption", "col",
         "colgroup", "html" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'],
         array('body', 'caption', 'col', 'colgroup', 'html'))) {
             /* Parse error. Ignore the token. */
 
         /* An end tag whose tag name is one of: "table", "tbody", "tfoot",
         "thead", "tr" */
-        } elseif($token['type'] === HTML5::ENDTAG && in_array($token['name'],
+        } elseif ($token['type'] === HTML5::ENDTAG && in_array($token['name'],
         array('table', 'tbody', 'tfoot', 'thead', 'tr'))) {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as that of the token (which can only
             happen for "tbody", "tfoot" and "thead", or, in the innerHTML case),
             then this is a parse error and the token must be ignored. */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // Ignore.
 
             /* Otherwise, close the cell (see below) and reprocess the current
@@ -3211,22 +3211,22 @@ 
         /* Handle the token as follows: */
 
         /* A character token */
-        if($token['type'] === HTML5::CHARACTR) {
+        if ($token['type'] === HTML5::CHARACTR) {
             /* Append the token's character to the current node. */
             $this->insertText($token['data']);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
             $this->insertComment($token['data']);
 
         /* A start tag token whose tag name is "option" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         $token['name'] === 'option') {
             /* If the current node is an option element, act as if an end tag
             with the tag name "option" had been seen. */
-            if(end($this->stack)->nodeName === 'option') {
+            if (end($this->stack)->nodeName === 'option') {
                 $this->inSelect(array(
                     'name' => 'option',
                     'type' => HTML5::ENDTAG
@@ -3237,11 +3237,11 @@ 
             $this->insertElement($token);
 
         /* A start tag token whose tag name is "optgroup" */
-        } elseif($token['type'] === HTML5::STARTTAG &&
+        } elseif ($token['type'] === HTML5::STARTTAG &&
         $token['name'] === 'optgroup') {
             /* If the current node is an option element, act as if an end tag
             with the tag name "option" had been seen. */
-            if(end($this->stack)->nodeName === 'option') {
+            if (end($this->stack)->nodeName === 'option') {
                 $this->inSelect(array(
                     'name' => 'option',
                     'type' => HTML5::ENDTAG
@@ -3250,7 +3250,7 @@ 
 
             /* If the current node is an optgroup element, act as if an end tag
             with the tag name "optgroup" had been seen. */
-            if(end($this->stack)->nodeName === 'optgroup') {
+            if (end($this->stack)->nodeName === 'optgroup') {
                 $this->inSelect(array(
                     'name' => 'optgroup',
                     'type' => HTML5::ENDTAG
@@ -3261,7 +3261,7 @@ 
             $this->insertElement($token);
 
         /* An end tag token whose tag name is "optgroup" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         $token['name'] === 'optgroup') {
             /* First, if the current node is an option element, and the node
             immediately before it in the stack of open elements is an optgroup
@@ -3269,7 +3269,7 @@ 
             been seen. */
             $elements_in_stack = count($this->stack);
 
-            if($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
+            if ($this->stack[$elements_in_stack - 1]->nodeName === 'option' &&
             $this->stack[$elements_in_stack - 2]->nodeName === 'optgroup') {
                 $this->inSelect(array(
                     'name' => 'option',
@@ -3280,38 +3280,38 @@ 
             /* If the current node is an optgroup element, then pop that node
             from the stack of open elements. Otherwise, this is a parse error,
             ignore the token. */
-            if($this->stack[$elements_in_stack - 1] === 'optgroup') {
+            if ($this->stack[$elements_in_stack - 1] === 'optgroup') {
                 array_pop($this->stack);
             }
 
         /* An end tag token whose tag name is "option" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         $token['name'] === 'option') {
             /* If the current node is an option element, then pop that node
             from the stack of open elements. Otherwise, this is a parse error,
             ignore the token. */
-            if(end($this->stack)->nodeName === 'option') {
+            if (end($this->stack)->nodeName === 'option') {
                 array_pop($this->stack);
             }
 
         /* An end tag whose tag name is "select" */
-        } elseif($token['type'] === HTML5::ENDTAG &&
+        } elseif ($token['type'] === HTML5::ENDTAG &&
         $token['name'] === 'select') {
             /* If the stack of open elements does not have an element in table
             scope with the same tag name as the token, this is a parse error.
             Ignore the token. (innerHTML case) */
-            if(!$this->elementInScope($token['name'], true)) {
+            if (!$this->elementInScope($token['name'], true)) {
                 // w/e
 
             /* Otherwise: */
             } else {
                 /* Pop elements from the stack of open elements until a select
                 element has been popped from the stack. */
-                while(true) {
+                while (true) {
                     $current = end($this->stack)->nodeName;
                     array_pop($this->stack);
 
-                    if($current === 'select') {
+                    if ($current === 'select') {
                         break;
                     }
                 }
@@ -3321,7 +3321,7 @@ 
             }
 
         /* A start tag whose tag name is "select" */
-        } elseif($token['name'] === 'select' &&
+        } elseif ($token['name'] === 'select' &&
         $token['type'] === HTML5::STARTTAG) {
             /* Parse error. Act as if the token had been an end tag with the
             tag name "select" instead. */
@@ -3332,7 +3332,7 @@ 
 
         /* An end tag whose tag name is one of: "caption", "table", "tbody",
         "tfoot", "thead", "tr", "td", "th" */
-        } elseif(in_array($token['name'], array('caption', 'table', 'tbody',
+        } elseif (in_array($token['name'], array('caption', 'table', 'tbody',
         'tfoot', 'thead', 'tr', 'td', 'th')) && $token['type'] === HTML5::ENDTAG) {
             /* Parse error. */
             // w/e
@@ -3341,7 +3341,7 @@ 
             the same tag name as that of the token, then act as if an end tag
             with the tag name "select" had been seen, and reprocess the token.
             Otherwise, ignore the token. */
-            if($this->elementInScope($token['name'], true)) {
+            if ($this->elementInScope($token['name'], true)) {
                 $this->inSelect(array(
                     'name' => 'select',
                     'type' => HTML5::ENDTAG
@@ -3362,14 +3362,14 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Process the token as it would be processed if the insertion mode
             was "in body". */
             $this->inBody($token);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the first element in the stack of open
             elements (the html element), with the data attribute set to the
             data given in the comment token. */
@@ -3377,7 +3377,7 @@ 
             $this->stack[0]->appendChild($comment);
 
         /* An end tag with the tag name "html" */
-        } elseif($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
+        } elseif ($token['type'] === HTML5::ENDTAG && $token['name'] === 'html') {
             /* If the parser was originally created in order to handle the
             setting of an element's innerHTML attribute, this is a parse error;
             ignore the token. (The element will be an html element in this
@@ -3401,28 +3401,28 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append the character to the current node. */
             $this->insertText($token['data']);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
             $this->insertComment($token['data']);
 
         /* A start tag with the tag name "frameset" */
-        } elseif($token['name'] === 'frameset' &&
+        } elseif ($token['name'] === 'frameset' &&
         $token['type'] === HTML5::STARTTAG) {
             $this->insertElement($token);
 
         /* An end tag with the tag name "frameset" */
-        } elseif($token['name'] === 'frameset' &&
+        } elseif ($token['name'] === 'frameset' &&
         $token['type'] === HTML5::ENDTAG) {
             /* If the current node is the root html element, then this is a
             parse error; ignore the token. (innerHTML case) */
-            if(end($this->stack)->nodeName === 'html') {
+            if (end($this->stack)->nodeName === 'html') {
                 // Ignore
 
             } else {
@@ -3438,7 +3438,7 @@ 
             }
 
         /* A start tag with the tag name "frame" */
-        } elseif($token['name'] === 'frame' &&
+        } elseif ($token['name'] === 'frame' &&
         $token['type'] === HTML5::STARTTAG) {
             /* Insert an HTML element for the token. */
             $this->insertElement($token);
@@ -3447,7 +3447,7 @@ 
             array_pop($this->stack);
 
         /* A start tag with the tag name "noframes" */
-        } elseif($token['name'] === 'noframes' &&
+        } elseif ($token['name'] === 'noframes' &&
         $token['type'] === HTML5::STARTTAG) {
             /* Process the token as if the insertion mode had been "in body". */
             $this->inBody($token);
@@ -3464,25 +3464,25 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         U+000D CARRIAGE RETURN (CR), or U+0020 SPACE */
-        if($token['type'] === HTML5::CHARACTR &&
+        if ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Append the character to the current node. */
             $this->insertText($token['data']);
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the current node with the data
             attribute set to the data given in the comment token. */
             $this->insertComment($token['data']);
 
         /* An end tag with the tag name "html" */
-        } elseif($token['name'] === 'html' &&
+        } elseif ($token['name'] === 'html' &&
         $token['type'] === HTML5::ENDTAG) {
             /* Switch to the trailing end phase. */
             $this->phase = self::END_PHASE;
 
         /* A start tag with the tag name "noframes" */
-        } elseif($token['name'] === 'noframes' &&
+        } elseif ($token['name'] === 'noframes' &&
         $token['type'] === HTML5::STARTTAG) {
             /* Process the token as if the insertion mode had been "in body". */
             $this->inBody($token);
@@ -3498,11 +3498,11 @@ 
         stage, it must be processed as described in this section. */
 
         /* A DOCTYPE token */
-        if($token['type'] === HTML5::DOCTYPE) {
+        if ($token['type'] === HTML5::DOCTYPE) {
             // Parse error. Ignore the token.
 
         /* A comment token */
-        } elseif($token['type'] === HTML5::COMMENT) {
+        } elseif ($token['type'] === HTML5::COMMENT) {
             /* Append a Comment node to the Document object with the data
             attribute set to the data given in the comment token. */
             $comment = $this->dom->createComment($token['data']);
@@ -3511,7 +3511,7 @@ 
         /* A character token that is one of one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE */
-        } elseif($token['type'] === HTML5::CHARACTR &&
+        } elseif ($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) {
             /* Process the token as it would be processed in the main phase. */
             $this->mainPhase($token);
@@ -3519,7 +3519,7 @@ 
         /* A character token that is not one of U+0009 CHARACTER TABULATION,
         U+000A LINE FEED (LF), U+000B LINE TABULATION, U+000C FORM FEED (FF),
         or U+0020 SPACE. Or a start tag token. Or an end tag token. */
-        } elseif(($token['type'] === HTML5::CHARACTR &&
+        } elseif (($token['type'] === HTML5::CHARACTR &&
         preg_match('/^[\t\n\x0b\x0c ]+$/', $token['data'])) ||
         $token['type'] === HTML5::STARTTAG || $token['type'] === HTML5::ENDTAG) {
             /* Parse error. Switch back to the main phase and reprocess the
@@ -3528,7 +3528,7 @@ 
             return $this->mainPhase($token);
 
         /* An end-of-file token */
-        } elseif($token['type'] === HTML5::EOF) {
+        } elseif ($token['type'] === HTML5::EOF) {
             /* OMG DONE!! */
         }
     }
@@ -3547,8 +3547,8 @@ 
         
         $el = $this->dom->createElement($token['name']);
 
-        foreach($token['attr'] as $attr) {
-            if(!$el->hasAttribute($attr['name'])) {
+        foreach ($token['attr'] as $attr) {
+            if (!$el->hasAttribute($attr['name'])) {
                 $el->setAttribute($attr['name'], $attr['value']);
             }
         }
@@ -3570,25 +3570,25 @@ 
     }
 
     private function appendToRealParent($node) {
-        if($this->foster_parent === null) {
+        if ($this->foster_parent === null) {
             end($this->stack)->appendChild($node);
 
-        } elseif($this->foster_parent !== null) {
+        } elseif ($this->foster_parent !== null) {
             /* If the foster parent element is the parent element of the
             last table element in the stack of open elements, then the new
             node must be inserted immediately before the last table element
             in the stack of open elements in the foster parent element;
             otherwise, the new node must be appended to the foster parent
             element. */
-            for($n = count($this->stack) - 1; $n >= 0; $n--) {
-                if($this->stack[$n]->nodeName === 'table' &&
+            for ($n = count($this->stack) - 1; $n >= 0; $n--) {
+                if ($this->stack[$n]->nodeName === 'table' &&
                 $this->stack[$n]->parentNode !== null) {
                     $table = $this->stack[$n];
                     break;
                 }
             }
 
-            if(isset($table) && $this->foster_parent->isSameNode($table->parentNode))
+            if (isset($table) && $this->foster_parent->isSameNode($table->parentNode))
                 $this->foster_parent->insertBefore($node, $table);
             else
                 $this->foster_parent->appendChild($node);
@@ -3598,9 +3598,9 @@ 
     }
 
     private function elementInScope($el, $table = false) {
-        if(is_array($el)) {
-            foreach($el as $element) {
-                if($this->elementInScope($element, $table)) {
+        if (is_array($el)) {
+            foreach ($el as $element) {
+                if ($this->elementInScope($element, $table)) {
                     return true;
                 }
             }
@@ -3610,28 +3610,28 @@ 
 
         $leng = count($this->stack);
 
-        for($n = 0; $n < $leng; $n++) {
+        for ($n = 0; $n < $leng; $n++) {
             /* 1. Initialise node to be the current node (the bottommost node of
             the stack). */
             $node = $this->stack[$leng - 1 - $n];
 
-            if($node->tagName === $el) {
+            if ($node->tagName === $el) {
                 /* 2. If node is the target node, terminate in a match state. */
                 return true;
 
-            } elseif($node->tagName === 'table') {
+            } elseif ($node->tagName === 'table') {
                 /* 3. Otherwise, if node is a table element, terminate in a failure
                 state. */
                 return false;
 
-            } elseif($table === true && in_array($node->tagName, array('caption', 'td',
+            } elseif ($table === true && in_array($node->tagName, array('caption', 'td',
             'th', 'button', 'marquee', 'object'))) {
                 /* 4. Otherwise, if the algorithm is the "has an element in scope"
                 variant (rather than the "has an element in table scope" variant),
                 and node is one of the following, terminate in a failure state. */
                 return false;
 
-            } elseif($node === $node->ownerDocument->documentElement) {
+            } elseif ($node === $node->ownerDocument->documentElement) {
                 /* 5. Otherwise, if node is an html element (root element), terminate
                 in a failure state. (This can only happen if the node is the topmost
                 node of the    stack of open elements, and prevents the next step from
@@ -3651,7 +3651,7 @@ 
         then there is nothing to reconstruct; stop this algorithm. */
         $formatting_elements = count($this->a_formatting);
 
-        if($formatting_elements === 0) {
+        if ($formatting_elements === 0) {
             return false;
         }
 
@@ -3663,14 +3663,14 @@ 
         formatting elements is a marker, or if it is an element that is in the
         stack of open elements, then there is nothing to reconstruct; stop this
         algorithm. */
-        if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+        if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
             return false;
         }
 
-        for($a = $formatting_elements - 1; $a >= 0; true) {
+        for ($a = $formatting_elements - 1; $a >= 0; true) {
             /* 4. If there are no entries before entry in the list of active
             formatting elements, then jump to step 8. */
-            if($a === 0) {
+            if ($a === 0) {
                 $step_seven = false;
                 break;
             }
@@ -3682,15 +3682,15 @@ 
 
             /* 6. If entry is neither a marker nor an element that is also in
             thetack of open elements, go to step 4. */
-            if($entry === self::MARKER || in_array($entry, $this->stack, true)) {
+            if ($entry === self::MARKER || in_array($entry, $this->stack, true)) {
                 break;
             }
         }
 
-        while(true) {
+        while (true) {
             /* 7. Let entry be the element one later than entry in the list of
             active formatting elements. */
-            if(isset($step_seven) && $step_seven === true) {
+            if (isset($step_seven) && $step_seven === true) {
                 $a++;
                 $entry = $this->a_formatting[$a];
             }
@@ -3709,7 +3709,7 @@ 
 
             /* 11. If the entry for clone in the list of active formatting
             elements is not the last entry in the list, return to step 7. */
-            if(end($this->a_formatting) !== $clone) {
+            if (end($this->a_formatting) !== $clone) {
                 $step_seven = true;
             } else {
                 break;
@@ -3722,7 +3722,7 @@ 
         formatting elements up to the last marker, the UA must perform the
         following steps: */
 
-        while(true) {
+        while (true) {
             /* 1. Let entry be the last (most recently added) entry in the list
             of active formatting elements. */
             $entry = end($this->a_formatting);
@@ -3732,7 +3732,7 @@ 
 
             /* 3. If entry was a marker, then stop the algorithm at this point.
             The list has been cleared up to the last marker. */
-            if($entry === self::MARKER) {
+            if ($entry === self::MARKER) {
                 break;
             }
         }
@@ -3747,20 +3747,20 @@ 
         $node = end($this->stack);
         $elements = array_diff(array('dd', 'dt', 'li', 'p', 'td', 'th', 'tr'), $exclude);
 
-        while(in_array(end($this->stack)->nodeName, $elements)) {
+        while (in_array(end($this->stack)->nodeName, $elements)) {
             array_pop($this->stack);
         }
     }
 
     private function getElementCategory($node) {
         $name = $node->tagName;
-        if(in_array($name, $this->special))
+        if (in_array($name, $this->special))
             return self::SPECIAL;
 
-        elseif(in_array($name, $this->scoping))
+        elseif (in_array($name, $this->scoping))
             return self::SCOPING;
 
-        elseif(in_array($name, $this->formatting))
+        elseif (in_array($name, $this->formatting))
             return self::FORMATTING;
 
         else
@@ -3773,10 +3773,10 @@ 
         a table element or an html element, pop elements from the stack of open
         elements. If this causes any elements to be popped from the stack, then
         this is a parse error. */
-        while(true) {
+        while (true) {
             $node = end($this->stack)->nodeName;
 
-            if(in_array($node, $elements)) {
+            if (in_array($node, $elements)) {
                 break;
             } else {
                 array_pop($this->stack);
@@ -3789,7 +3789,7 @@ 
         $last = false;
         $leng = count($this->stack);
 
-        for($n = $leng - 1; $n >= 0; $n--) {
+        for ($n = $leng - 1; $n >= 0; $n--) {
             /* 2. Let node be the last node in the stack of open elements. */
             $node = $this->stack[$n];
 
@@ -3797,68 +3797,68 @@ 
             set last to true. If the element whose innerHTML  attribute is being
             set is neither a td  element nor a th element, then set node to the
             element whose innerHTML  attribute is being set. (innerHTML  case) */
-            if($this->stack[0]->isSameNode($node)) {
+            if ($this->stack[0]->isSameNode($node)) {
                 $last = true;
             }
 
             /* 4. If node is a select element, then switch the insertion mode to
             "in select" and abort these steps. (innerHTML case) */
-            if($node->nodeName === 'select') {
+            if ($node->nodeName === 'select') {
                 $this->mode = self::IN_SELECT;
                 break;
 
             /* 5. If node is a td or th element, then switch the insertion mode
             to "in cell" and abort these steps. */
-            } elseif($node->nodeName === 'td' || $node->nodeName === 'th') {
+            } elseif ($node->nodeName === 'td' || $node->nodeName === 'th') {
                 $this->mode = self::IN_CELL;
                 break;
 
             /* 6. If node is a tr element, then switch the insertion mode to
             "in    row" and abort these steps. */
-            } elseif($node->nodeName === 'tr') {
+            } elseif ($node->nodeName === 'tr') {
                 $this->mode = self::IN_ROW;
                 break;
 
             /* 7. If node is a tbody, thead, or tfoot element, then switch the
             insertion mode to "in table body" and abort these steps. */
-            } elseif(in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
+            } elseif (in_array($node->nodeName, array('tbody', 'thead', 'tfoot'))) {
                 $this->mode = self::IN_TBODY;
                 break;
 
             /* 8. If node is a caption element, then switch the insertion mode
             to "in caption" and abort these steps. */
-            } elseif($node->nodeName === 'caption') {
+            } elseif ($node->nodeName === 'caption') {
                 $this->mode = self::IN_CAPTION;
                 break;
 
             /* 9. If node is a colgroup element, then switch the insertion mode
             to "in column group" and abort these steps. (innerHTML case) */
-            } elseif($node->nodeName === 'colgroup') {
+            } elseif ($node->nodeName === 'colgroup') {
                 $this->mode = self::IN_CGROUP;
                 break;
 
             /* 10. If node is a table element, then switch the insertion mode
             to "in table" and abort these steps. */
-            } elseif($node->nodeName === 'table') {
+            } elseif ($node->nodeName === 'table') {
                 $this->mode = self::IN_TABLE;
                 break;
 
             /* 11. If node is a head element, then switch the insertion mode
             to "in body" ("in body"! not "in head"!) and abort these steps.
             (innerHTML case) */
-            } elseif($node->nodeName === 'head') {
+            } elseif ($node->nodeName === 'head') {
                 $this->mode = self::IN_BODY;
                 break;
 
             /* 12. If node is a body element, then switch the insertion mode to
             "in body" and abort these steps. */
-            } elseif($node->nodeName === 'body') {
+            } elseif ($node->nodeName === 'body') {
                 $this->mode = self::IN_BODY;
                 break;
 
             /* 13. If node is a frameset element, then switch the insertion
             mode to "in frameset" and abort these steps. (innerHTML case) */
-            } elseif($node->nodeName === 'frameset') {
+            } elseif ($node->nodeName === 'frameset') {
                 $this->mode = self::IN_FRAME;
                 break;
 
@@ -3866,7 +3866,7 @@ 
             pointer is null, switch the insertion mode to "before head",
             otherwise, switch the insertion mode to "after head". In either
             case, abort these steps. (innerHTML case) */
-            } elseif($node->nodeName === 'html') {
+            } elseif ($node->nodeName === 'html') {
                 $this->mode = ($this->head_pointer === null)
                     ? self::BEFOR_HEAD
                     : self::AFTER_HEAD;
@@ -3875,7 +3875,7 @@ 
 
             /* 15. If last is true, then set the insertion mode to "in body"
             and    abort these steps. (innerHTML case) */
-            } elseif($last) {
+            } elseif ($last) {
                 $this->mode = self::IN_BODY;
                 break;
             }
@@ -3885,8 +3885,8 @@ 
     private function closeCell() {
         /* If the stack of open elements has a td or th element in table scope,
         then act as if an end tag token with that tag name had been seen. */
-        foreach(array('td', 'th') as $cell) {
-            if($this->elementInScope($cell, true)) {
+        foreach (array('td', 'th') as $cell) {
+            if ($this->elementInScope($cell, true)) {
                 $this->inCell(array(
                     'name' => $cell,
                     'type' => HTML5::ENDTAG

classes/security/htmlpurifier/library/HTMLPurifier/Printer.php

Doc Comments +4 added lines, -1 removed lines

@@ -60,7 +60,7 @@ 
 
     /**
      * Prints a complete element with content inside
-     * @param $tag Tag name
+     * @param string $tag Tag name
      * @param $contents Element contents
      * @param $attr Tag attributes
      * @param $escape Bool whether or not to escape contents
@@ -71,6 +71,9 @@ 
                $this->end($tag);
     }
 
+    /**
+     * @param string $tag
+     */
     protected function elementEmpty($tag, $attr = array()) {
         return $this->generator->generateFromToken(
             new HTMLPurifier_Token_Empty($tag, $attr)

Indentation +164 added lines, -164 removed lines

@@ -6,170 +6,170 @@
 class HTMLPurifier_Printer
 {
 
-    /**
-     * Instance of HTMLPurifier_Generator for HTML generation convenience funcs
-     */
-    protected $generator;
-
-    /**
-     * Instance of HTMLPurifier_Config, for easy access
-     */
-    protected $config;
-
-    /**
-     * Initialize $generator.
-     */
-    public function __construct() {
-    }
-
-    /**
-     * Give generator necessary configuration if possible
-     */
-    public function prepareGenerator($config) {
-        $all = $config->getAll();
-        $context = new HTMLPurifier_Context();
-        $this->generator = new HTMLPurifier_Generator($config, $context);
-    }
-
-    /**
-     * Main function that renders object or aspect of that object
-     * @note Parameters vary depending on printer
-     */
-    // function render() {}
-
-    /**
-     * Returns a start tag
-     * @param $tag Tag name
-     * @param $attr Attribute array
-     */
-    protected function start($tag, $attr = array()) {
-        return $this->generator->generateFromToken(
-                    new HTMLPurifier_Token_Start($tag, $attr ? $attr : array())
-               );
-    }
-
-    /**
-     * Returns an end teg
-     * @param $tag Tag name
-     */
-    protected function end($tag) {
-        return $this->generator->generateFromToken(
-                    new HTMLPurifier_Token_End($tag)
-               );
-    }
-
-    /**
-     * Prints a complete element with content inside
-     * @param $tag Tag name
-     * @param $contents Element contents
-     * @param $attr Tag attributes
-     * @param $escape Bool whether or not to escape contents
-     */
-    protected function element($tag, $contents, $attr = array(), $escape = true) {
-        return $this->start($tag, $attr) .
-               ($escape ? $this->escape($contents) : $contents) .
-               $this->end($tag);
-    }
-
-    protected function elementEmpty($tag, $attr = array()) {
-        return $this->generator->generateFromToken(
-            new HTMLPurifier_Token_Empty($tag, $attr)
-        );
-    }
-
-    protected function text($text) {
-        return $this->generator->generateFromToken(
-            new HTMLPurifier_Token_Text($text)
-        );
-    }
-
-    /**
-     * Prints a simple key/value row in a table.
-     * @param $name Key
-     * @param $value Value
-     */
-    protected function row($name, $value) {
-        if (is_bool($value)) $value = $value ? 'On' : 'Off';
-        return
-            $this->start('tr') . "\n" .
-                $this->element('th', $name) . "\n" .
-                $this->element('td', $value) . "\n" .
-            $this->end('tr')
-        ;
-    }
-
-    /**
-     * Escapes a string for HTML output.
-     * @param $string String to escape
-     */
-    protected function escape($string) {
-        $string = HTMLPurifier_Encoder::cleanUTF8($string);
-        $string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8', false);
-        return $string;
-    }
-
-    /**
-     * Takes a list of strings and turns them into a single list
-     * @param $array List of strings
-     * @param $polite Bool whether or not to add an end before the last
-     */
-    protected function listify($array, $polite = false) {
-        if (empty($array)) return 'None';
-        $ret = '';
-        $i = count($array);
-        foreach ($array as $value) {
-            $i--;
-            $ret .= $value;
-            if ($i > 0 && !($polite && $i == 1)) $ret .= ', ';
-            if ($polite && $i == 1) $ret .= 'and ';
-        }
-        return $ret;
-    }
-
-    /**
-     * Retrieves the class of an object without prefixes, as well as metadata
-     * @param $obj Object to determine class of
-     * @param $prefix Further prefix to remove
-     */
-    protected function getClass($obj, $sec_prefix = '') {
-        static $five = null;
-        if ($five === null) $five = version_compare(PHP_VERSION, '5', '>=');
-        $prefix = 'HTMLPurifier_' . $sec_prefix;
-        if (!$five) $prefix = strtolower($prefix);
-        $class = str_replace($prefix, '', get_class($obj));
-        $lclass = strtolower($class);
-        $class .= '(';
-        switch ($lclass) {
-            case 'enum':
-                $values = array();
-                foreach ($obj->valid_values as $value => $bool) {
-                    $values[] = $value;
-                }
-                $class .= implode(', ', $values);
-                break;
-            case 'css_composite':
-                $values = array();
-                foreach ($obj->defs as $def) {
-                    $values[] = $this->getClass($def, $sec_prefix);
-                }
-                $class .= implode(', ', $values);
-                break;
-            case 'css_multiple':
-                $class .= $this->getClass($obj->single, $sec_prefix) . ', ';
-                $class .= $obj->max;
-                break;
-            case 'css_denyelementdecorator':
-                $class .= $this->getClass($obj->def, $sec_prefix) . ', ';
-                $class .= $obj->element;
-                break;
-            case 'css_importantdecorator':
-                $class .= $this->getClass($obj->def, $sec_prefix);
-                if ($obj->allow) $class .= ', !important';
-                break;
-        }
-        $class .= ')';
-        return $class;
-    }
+	/**
+	 * Instance of HTMLPurifier_Generator for HTML generation convenience funcs
+	 */
+	protected $generator;
+
+	/**
+	 * Instance of HTMLPurifier_Config, for easy access
+	 */
+	protected $config;
+
+	/**
+	 * Initialize $generator.
+	 */
+	public function __construct() {
+	}
+
+	/**
+	 * Give generator necessary configuration if possible
+	 */
+	public function prepareGenerator($config) {
+		$all = $config->getAll();
+		$context = new HTMLPurifier_Context();
+		$this->generator = new HTMLPurifier_Generator($config, $context);
+	}
+
+	/**
+	 * Main function that renders object or aspect of that object
+	 * @note Parameters vary depending on printer
+	 */
+	// function render() {}
+
+	/**
+	 * Returns a start tag
+	 * @param $tag Tag name
+	 * @param $attr Attribute array
+	 */
+	protected function start($tag, $attr = array()) {
+		return $this->generator->generateFromToken(
+					new HTMLPurifier_Token_Start($tag, $attr ? $attr : array())
+			   );
+	}
+
+	/**
+	 * Returns an end teg
+	 * @param $tag Tag name
+	 */
+	protected function end($tag) {
+		return $this->generator->generateFromToken(
+					new HTMLPurifier_Token_End($tag)
+			   );
+	}
+
+	/**
+	 * Prints a complete element with content inside
+	 * @param $tag Tag name
+	 * @param $contents Element contents
+	 * @param $attr Tag attributes
+	 * @param $escape Bool whether or not to escape contents
+	 */
+	protected function element($tag, $contents, $attr = array(), $escape = true) {
+		return $this->start($tag, $attr) .
+			   ($escape ? $this->escape($contents) : $contents) .
+			   $this->end($tag);
+	}
+
+	protected function elementEmpty($tag, $attr = array()) {
+		return $this->generator->generateFromToken(
+			new HTMLPurifier_Token_Empty($tag, $attr)
+		);
+	}
+
+	protected function text($text) {
+		return $this->generator->generateFromToken(
+			new HTMLPurifier_Token_Text($text)
+		);
+	}
+
+	/**
+	 * Prints a simple key/value row in a table.
+	 * @param $name Key
+	 * @param $value Value
+	 */
+	protected function row($name, $value) {
+		if (is_bool($value)) $value = $value ? 'On' : 'Off';
+		return
+			$this->start('tr') . "\n" .
+				$this->element('th', $name) . "\n" .
+				$this->element('td', $value) . "\n" .
+			$this->end('tr')
+		;
+	}
+
+	/**
+	 * Escapes a string for HTML output.
+	 * @param $string String to escape
+	 */
+	protected function escape($string) {
+		$string = HTMLPurifier_Encoder::cleanUTF8($string);
+		$string = htmlspecialchars($string, ENT_COMPAT, 'UTF-8', false);
+		return $string;
+	}
+
+	/**
+	 * Takes a list of strings and turns them into a single list
+	 * @param $array List of strings
+	 * @param $polite Bool whether or not to add an end before the last
+	 */
+	protected function listify($array, $polite = false) {
+		if (empty($array)) return 'None';
+		$ret = '';
+		$i = count($array);
+		foreach ($array as $value) {
+			$i--;
+			$ret .= $value;
+			if ($i > 0 && !($polite && $i == 1)) $ret .= ', ';
+			if ($polite && $i == 1) $ret .= 'and ';
+		}
+		return $ret;
+	}
+
+	/**
+	 * Retrieves the class of an object without prefixes, as well as metadata
+	 * @param $obj Object to determine class of
+	 * @param $prefix Further prefix to remove
+	 */
+	protected function getClass($obj, $sec_prefix = '') {
+		static $five = null;
+		if ($five === null) $five = version_compare(PHP_VERSION, '5', '>=');
+		$prefix = 'HTMLPurifier_' . $sec_prefix;
+		if (!$five) $prefix = strtolower($prefix);
+		$class = str_replace($prefix, '', get_class($obj));
+		$lclass = strtolower($class);
+		$class .= '(';
+		switch ($lclass) {
+			case 'enum':
+				$values = array();
+				foreach ($obj->valid_values as $value => $bool) {
+					$values[] = $value;
+				}
+				$class .= implode(', ', $values);
+				break;
+			case 'css_composite':
+				$values = array();
+				foreach ($obj->defs as $def) {
+					$values[] = $this->getClass($def, $sec_prefix);
+				}
+				$class .= implode(', ', $values);
+				break;
+			case 'css_multiple':
+				$class .= $this->getClass($obj->single, $sec_prefix) . ', ';
+				$class .= $obj->max;
+				break;
+			case 'css_denyelementdecorator':
+				$class .= $this->getClass($obj->def, $sec_prefix) . ', ';
+				$class .= $obj->element;
+				break;
+			case 'css_importantdecorator':
+				$class .= $this->getClass($obj->def, $sec_prefix);
+				if ($obj->allow) $class .= ', !important';
+				break;
+		}
+		$class .= ')';
+		return $class;
+	}
 
 }
 

Braces +21 added lines, -7 removed lines

@@ -89,7 +89,9 @@ 
      * @param $value Value
      */
     protected function row($name, $value) {
-        if (is_bool($value)) $value = $value ? 'On' : 'Off';
+        if (is_bool($value)) {
+        	$value = $value ? 'On' : 'Off';
+        }
         return
             $this->start('tr') . "\n" .
                 $this->element('th', $name) . "\n" .
@@ -114,14 +116,20 @@ 
      * @param $polite Bool whether or not to add an end before the last
      */
     protected function listify($array, $polite = false) {
-        if (empty($array)) return 'None';
+        if (empty($array)) {
+        	return 'None';
+        }
         $ret = '';
         $i = count($array);
         foreach ($array as $value) {
             $i--;
             $ret .= $value;
-            if ($i > 0 && !($polite && $i == 1)) $ret .= ', ';
-            if ($polite && $i == 1) $ret .= 'and ';
+            if ($i > 0 && !($polite && $i == 1)) {
+            	$ret .= ', ';
+            }
+            if ($polite && $i == 1) {
+            	$ret .= 'and ';
+            }
         }
         return $ret;
     }
@@ -133,9 +141,13 @@ 
      */
     protected function getClass($obj, $sec_prefix = '') {
         static $five = null;
-        if ($five === null) $five = version_compare(PHP_VERSION, '5', '>=');
+        if ($five === null) {
+        	$five = version_compare(PHP_VERSION, '5', '>=');
+        }
         $prefix = 'HTMLPurifier_' . $sec_prefix;
-        if (!$five) $prefix = strtolower($prefix);
+        if (!$five) {
+        	$prefix = strtolower($prefix);
+        }
         $class = str_replace($prefix, '', get_class($obj));
         $lclass = strtolower($class);
         $class .= '(';
@@ -164,7 +176,9 @@ 
                 break;
             case 'css_importantdecorator':
                 $class .= $this->getClass($obj->def, $sec_prefix);
-                if ($obj->allow) $class .= ', !important';
+                if ($obj->allow) {
+                	$class .= ', !important';
+                }
                 break;
         }
         $class .= ')';

Spacing +8 added lines, -8 removed lines

@@ -66,8 +66,8 @@ 
      * @param $escape Bool whether or not to escape contents
      */
     protected function element($tag, $contents, $attr = array(), $escape = true) {
-        return $this->start($tag, $attr) .
-               ($escape ? $this->escape($contents) : $contents) .
+        return $this->start($tag, $attr).
+               ($escape ? $this->escape($contents) : $contents).
                $this->end($tag);
     }
 
@@ -91,9 +91,9 @@ 
     protected function row($name, $value) {
         if (is_bool($value)) $value = $value ? 'On' : 'Off';
         return
-            $this->start('tr') . "\n" .
-                $this->element('th', $name) . "\n" .
-                $this->element('td', $value) . "\n" .
+            $this->start('tr')."\n".
+                $this->element('th', $name)."\n".
+                $this->element('td', $value)."\n".
             $this->end('tr')
         ;
     }
@@ -134,7 +134,7 @@ 
     protected function getClass($obj, $sec_prefix = '') {
         static $five = null;
         if ($five === null) $five = version_compare(PHP_VERSION, '5', '>=');
-        $prefix = 'HTMLPurifier_' . $sec_prefix;
+        $prefix = 'HTMLPurifier_'.$sec_prefix;
         if (!$five) $prefix = strtolower($prefix);
         $class = str_replace($prefix, '', get_class($obj));
         $lclass = strtolower($class);
@@ -155,11 +155,11 @@ 
                 $class .= implode(', ', $values);
                 break;
             case 'css_multiple':
-                $class .= $this->getClass($obj->single, $sec_prefix) . ', ';
+                $class .= $this->getClass($obj->single, $sec_prefix).', ';
                 $class .= $obj->max;
                 break;
             case 'css_denyelementdecorator':
-                $class .= $this->getClass($obj->def, $sec_prefix) . ', ';
+                $class .= $this->getClass($obj->def, $sec_prefix).', ';
                 $class .= $obj->element;
                 break;
             case 'css_importantdecorator':

classes/security/htmlpurifier/library/HTMLPurifier/UnitConverter.php

Doc Comments +3 added lines

@@ -192,6 +192,7 @@ 
 
     /**
      * Multiples two numbers, using arbitrary precision when available.
+     * @param integer $scale
      */
     private function mul($s1, $s2, $scale) {
         if ($this->bcmath) return bcmul($s1, $s2, $scale);
@@ -200,6 +201,7 @@ 
 
     /**
      * Divides two numbers, using arbitrary precision when available.
+     * @param integer $scale
      */
     private function div($s1, $s2, $scale) {
         if ($this->bcmath) return bcdiv($s1, $s2, $scale);
@@ -209,6 +211,7 @@ 
     /**
      * Rounds a number according to the number of sigfigs it should have,
      * using arbitrary precision when available.
+     * @param integer $sigfigs
      */
     private function round($n, $sigfigs) {
         $new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1

Indentation +241 added lines, -241 removed lines

@@ -7,247 +7,247 @@
 class HTMLPurifier_UnitConverter
 {
 
-    const ENGLISH = 1;
-    const METRIC = 2;
-    const DIGITAL = 3;
-
-    /**
-     * Units information array. Units are grouped into measuring systems
-     * (English, Metric), and are assigned an integer representing
-     * the conversion factor between that unit and the smallest unit in
-     * the system. Numeric indexes are actually magical constants that
-     * encode conversion data from one system to the next, with a O(n^2)
-     * constraint on memory (this is generally not a problem, since
-     * the number of measuring systems is small.)
-     */
-    protected static $units = array(
-        self::ENGLISH => array(
-            'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary
-            'pt' => 4,
-            'pc' => 48,
-            'in' => 288,
-            self::METRIC => array('pt', '0.352777778', 'mm'),
-        ),
-        self::METRIC => array(
-            'mm' => 1,
-            'cm' => 10,
-            self::ENGLISH => array('mm', '2.83464567', 'pt'),
-        ),
-    );
-
-    /**
-     * Minimum bcmath precision for output.
-     */
-    protected $outputPrecision;
-
-    /**
-     * Bcmath precision for internal calculations.
-     */
-    protected $internalPrecision;
-
-    /**
-     * Whether or not BCMath is available
-     */
-    private $bcmath;
-
-    public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) {
-        $this->outputPrecision = $output_precision;
-        $this->internalPrecision = $internal_precision;
-        $this->bcmath = !$force_no_bcmath && function_exists('bcmul');
-    }
-
-    /**
-     * Converts a length object of one unit into another unit.
-     * @param HTMLPurifier_Length $length
-     *      Instance of HTMLPurifier_Length to convert. You must validate()
-     *      it before passing it here!
-     * @param string $to_unit
-     *      Unit to convert to.
-     * @note
-     *      About precision: This conversion function pays very special
-     *      attention to the incoming precision of values and attempts
-     *      to maintain a number of significant figure. Results are
-     *      fairly accurate up to nine digits. Some caveats:
-     *          - If a number is zero-padded as a result of this significant
-     *            figure tracking, the zeroes will be eliminated.
-     *          - If a number contains less than four sigfigs ($outputPrecision)
-     *            and this causes some decimals to be excluded, those
-     *            decimals will be added on.
-     */
-    public function convert($length, $to_unit) {
-
-        if (!$length->isValid()) return false;
-
-        $n    = $length->getN();
-        $unit = $length->getUnit();
-
-        if ($n === '0' || $unit === false) {
-            return new HTMLPurifier_Length('0', false);
-        }
-
-        $state = $dest_state = false;
-        foreach (self::$units as $k => $x) {
-            if (isset($x[$unit])) $state = $k;
-            if (isset($x[$to_unit])) $dest_state = $k;
-        }
-        if (!$state || !$dest_state) return false;
-
-        // Some calculations about the initial precision of the number;
-        // this will be useful when we need to do final rounding.
-        $sigfigs = $this->getSigFigs($n);
-        if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision;
-
-        // BCMath's internal precision deals only with decimals. Use
-        // our default if the initial number has no decimals, or increase
-        // it by how ever many decimals, thus, the number of guard digits
-        // will always be greater than or equal to internalPrecision.
-        $log = (int) floor(log(abs($n), 10));
-        $cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision
-
-        for ($i = 0; $i < 2; $i++) {
-
-            // Determine what unit IN THIS SYSTEM we need to convert to
-            if ($dest_state === $state) {
-                // Simple conversion
-                $dest_unit = $to_unit;
-            } else {
-                // Convert to the smallest unit, pending a system shift
-                $dest_unit = self::$units[$state][$dest_state][0];
-            }
-
-            // Do the conversion if necessary
-            if ($dest_unit !== $unit) {
-                $factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp);
-                $n = $this->mul($n, $factor, $cp);
-                $unit = $dest_unit;
-            }
-
-            // Output was zero, so bail out early. Shouldn't ever happen.
-            if ($n === '') {
-                $n = '0';
-                $unit = $to_unit;
-                break;
-            }
-
-            // It was a simple conversion, so bail out
-            if ($dest_state === $state) {
-                break;
-            }
-
-            if ($i !== 0) {
-                // Conversion failed! Apparently, the system we forwarded
-                // to didn't have this unit. This should never happen!
-                return false;
-            }
-
-            // Pre-condition: $i == 0
-
-            // Perform conversion to next system of units
-            $n = $this->mul($n, self::$units[$state][$dest_state][1], $cp);
-            $unit = self::$units[$state][$dest_state][2];
-            $state = $dest_state;
-
-            // One more loop around to convert the unit in the new system.
-
-        }
-
-        // Post-condition: $unit == $to_unit
-        if ($unit !== $to_unit) return false;
-
-        // Useful for debugging:
-        //echo "<pre>n";
-        //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n";
-
-        $n = $this->round($n, $sigfigs);
-        if (strpos($n, '.') !== false) $n = rtrim($n, '0');
-        $n = rtrim($n, '.');
-
-        return new HTMLPurifier_Length($n, $unit);
-    }
-
-    /**
-     * Returns the number of significant figures in a string number.
-     * @param string $n Decimal number
-     * @return int number of sigfigs
-     */
-    public function getSigFigs($n) {
-        $n = ltrim($n, '0+-');
-        $dp = strpos($n, '.'); // decimal position
-        if ($dp === false) {
-            $sigfigs = strlen(rtrim($n, '0'));
-        } else {
-            $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character
-            if ($dp !== 0) $sigfigs--;
-        }
-        return $sigfigs;
-    }
-
-    /**
-     * Adds two numbers, using arbitrary precision when available.
-     */
-    private function add($s1, $s2, $scale) {
-        if ($this->bcmath) return bcadd($s1, $s2, $scale);
-        else return $this->scale($s1 + $s2, $scale);
-    }
-
-    /**
-     * Multiples two numbers, using arbitrary precision when available.
-     */
-    private function mul($s1, $s2, $scale) {
-        if ($this->bcmath) return bcmul($s1, $s2, $scale);
-        else return $this->scale($s1 * $s2, $scale);
-    }
-
-    /**
-     * Divides two numbers, using arbitrary precision when available.
-     */
-    private function div($s1, $s2, $scale) {
-        if ($this->bcmath) return bcdiv($s1, $s2, $scale);
-        else return $this->scale($s1 / $s2, $scale);
-    }
-
-    /**
-     * Rounds a number according to the number of sigfigs it should have,
-     * using arbitrary precision when available.
-     */
-    private function round($n, $sigfigs) {
-        $new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1
-        $rp = $sigfigs - $new_log - 1; // Number of decimal places needed
-        $neg = $n < 0 ? '-' : ''; // Negative sign
-        if ($this->bcmath) {
-            if ($rp >= 0) {
-                $n = bcadd($n, $neg . '0.' .  str_repeat('0', $rp) . '5', $rp + 1);
-                $n = bcdiv($n, '1', $rp);
-            } else {
-                // This algorithm partially depends on the standardized
-                // form of numbers that comes out of bcmath.
-                $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0);
-                $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1);
-            }
-            return $n;
-        } else {
-            return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1);
-        }
-    }
-
-    /**
-     * Scales a float to $scale digits right of decimal point, like BCMath.
-     */
-    private function scale($r, $scale) {
-        if ($scale < 0) {
-            // The f sprintf type doesn't support negative numbers, so we
-            // need to cludge things manually. First get the string.
-            $r = sprintf('%.0f', (float) $r);
-            // Due to floating point precision loss, $r will more than likely
-            // look something like 4652999999999.9234. We grab one more digit
-            // than we need to precise from $r and then use that to round
-            // appropriately.
-            $precise = (string) round(substr($r, 0, strlen($r) + $scale), -1);
-            // Now we return it, truncating the zero that was rounded off.
-            return substr($precise, 0, -1) . str_repeat('0', -$scale + 1);
-        }
-        return sprintf('%.' . $scale . 'f', (float) $r);
-    }
+	const ENGLISH = 1;
+	const METRIC = 2;
+	const DIGITAL = 3;
+
+	/**
+	 * Units information array. Units are grouped into measuring systems
+	 * (English, Metric), and are assigned an integer representing
+	 * the conversion factor between that unit and the smallest unit in
+	 * the system. Numeric indexes are actually magical constants that
+	 * encode conversion data from one system to the next, with a O(n^2)
+	 * constraint on memory (this is generally not a problem, since
+	 * the number of measuring systems is small.)
+	 */
+	protected static $units = array(
+		self::ENGLISH => array(
+			'px' => 3, // This is as per CSS 2.1 and Firefox. Your mileage may vary
+			'pt' => 4,
+			'pc' => 48,
+			'in' => 288,
+			self::METRIC => array('pt', '0.352777778', 'mm'),
+		),
+		self::METRIC => array(
+			'mm' => 1,
+			'cm' => 10,
+			self::ENGLISH => array('mm', '2.83464567', 'pt'),
+		),
+	);
+
+	/**
+	 * Minimum bcmath precision for output.
+	 */
+	protected $outputPrecision;
+
+	/**
+	 * Bcmath precision for internal calculations.
+	 */
+	protected $internalPrecision;
+
+	/**
+	 * Whether or not BCMath is available
+	 */
+	private $bcmath;
+
+	public function __construct($output_precision = 4, $internal_precision = 10, $force_no_bcmath = false) {
+		$this->outputPrecision = $output_precision;
+		$this->internalPrecision = $internal_precision;
+		$this->bcmath = !$force_no_bcmath && function_exists('bcmul');
+	}
+
+	/**
+	 * Converts a length object of one unit into another unit.
+	 * @param HTMLPurifier_Length $length
+	 *      Instance of HTMLPurifier_Length to convert. You must validate()
+	 *      it before passing it here!
+	 * @param string $to_unit
+	 *      Unit to convert to.
+	 * @note
+	 *      About precision: This conversion function pays very special
+	 *      attention to the incoming precision of values and attempts
+	 *      to maintain a number of significant figure. Results are
+	 *      fairly accurate up to nine digits. Some caveats:
+	 *          - If a number is zero-padded as a result of this significant
+	 *            figure tracking, the zeroes will be eliminated.
+	 *          - If a number contains less than four sigfigs ($outputPrecision)
+	 *            and this causes some decimals to be excluded, those
+	 *            decimals will be added on.
+	 */
+	public function convert($length, $to_unit) {
+
+		if (!$length->isValid()) return false;
+
+		$n    = $length->getN();
+		$unit = $length->getUnit();
+
+		if ($n === '0' || $unit === false) {
+			return new HTMLPurifier_Length('0', false);
+		}
+
+		$state = $dest_state = false;
+		foreach (self::$units as $k => $x) {
+			if (isset($x[$unit])) $state = $k;
+			if (isset($x[$to_unit])) $dest_state = $k;
+		}
+		if (!$state || !$dest_state) return false;
+
+		// Some calculations about the initial precision of the number;
+		// this will be useful when we need to do final rounding.
+		$sigfigs = $this->getSigFigs($n);
+		if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision;
+
+		// BCMath's internal precision deals only with decimals. Use
+		// our default if the initial number has no decimals, or increase
+		// it by how ever many decimals, thus, the number of guard digits
+		// will always be greater than or equal to internalPrecision.
+		$log = (int) floor(log(abs($n), 10));
+		$cp = ($log < 0) ? $this->internalPrecision - $log : $this->internalPrecision; // internal precision
+
+		for ($i = 0; $i < 2; $i++) {
+
+			// Determine what unit IN THIS SYSTEM we need to convert to
+			if ($dest_state === $state) {
+				// Simple conversion
+				$dest_unit = $to_unit;
+			} else {
+				// Convert to the smallest unit, pending a system shift
+				$dest_unit = self::$units[$state][$dest_state][0];
+			}
+
+			// Do the conversion if necessary
+			if ($dest_unit !== $unit) {
+				$factor = $this->div(self::$units[$state][$unit], self::$units[$state][$dest_unit], $cp);
+				$n = $this->mul($n, $factor, $cp);
+				$unit = $dest_unit;
+			}
+
+			// Output was zero, so bail out early. Shouldn't ever happen.
+			if ($n === '') {
+				$n = '0';
+				$unit = $to_unit;
+				break;
+			}
+
+			// It was a simple conversion, so bail out
+			if ($dest_state === $state) {
+				break;
+			}
+
+			if ($i !== 0) {
+				// Conversion failed! Apparently, the system we forwarded
+				// to didn't have this unit. This should never happen!
+				return false;
+			}
+
+			// Pre-condition: $i == 0
+
+			// Perform conversion to next system of units
+			$n = $this->mul($n, self::$units[$state][$dest_state][1], $cp);
+			$unit = self::$units[$state][$dest_state][2];
+			$state = $dest_state;
+
+			// One more loop around to convert the unit in the new system.
+
+		}
+
+		// Post-condition: $unit == $to_unit
+		if ($unit !== $to_unit) return false;
+
+		// Useful for debugging:
+		//echo "<pre>n";
+		//echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n";
+
+		$n = $this->round($n, $sigfigs);
+		if (strpos($n, '.') !== false) $n = rtrim($n, '0');
+		$n = rtrim($n, '.');
+
+		return new HTMLPurifier_Length($n, $unit);
+	}
+
+	/**
+	 * Returns the number of significant figures in a string number.
+	 * @param string $n Decimal number
+	 * @return int number of sigfigs
+	 */
+	public function getSigFigs($n) {
+		$n = ltrim($n, '0+-');
+		$dp = strpos($n, '.'); // decimal position
+		if ($dp === false) {
+			$sigfigs = strlen(rtrim($n, '0'));
+		} else {
+			$sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character
+			if ($dp !== 0) $sigfigs--;
+		}
+		return $sigfigs;
+	}
+
+	/**
+	 * Adds two numbers, using arbitrary precision when available.
+	 */
+	private function add($s1, $s2, $scale) {
+		if ($this->bcmath) return bcadd($s1, $s2, $scale);
+		else return $this->scale($s1 + $s2, $scale);
+	}
+
+	/**
+	 * Multiples two numbers, using arbitrary precision when available.
+	 */
+	private function mul($s1, $s2, $scale) {
+		if ($this->bcmath) return bcmul($s1, $s2, $scale);
+		else return $this->scale($s1 * $s2, $scale);
+	}
+
+	/**
+	 * Divides two numbers, using arbitrary precision when available.
+	 */
+	private function div($s1, $s2, $scale) {
+		if ($this->bcmath) return bcdiv($s1, $s2, $scale);
+		else return $this->scale($s1 / $s2, $scale);
+	}
+
+	/**
+	 * Rounds a number according to the number of sigfigs it should have,
+	 * using arbitrary precision when available.
+	 */
+	private function round($n, $sigfigs) {
+		$new_log = (int) floor(log(abs($n), 10)); // Number of digits left of decimal - 1
+		$rp = $sigfigs - $new_log - 1; // Number of decimal places needed
+		$neg = $n < 0 ? '-' : ''; // Negative sign
+		if ($this->bcmath) {
+			if ($rp >= 0) {
+				$n = bcadd($n, $neg . '0.' .  str_repeat('0', $rp) . '5', $rp + 1);
+				$n = bcdiv($n, '1', $rp);
+			} else {
+				// This algorithm partially depends on the standardized
+				// form of numbers that comes out of bcmath.
+				$n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0);
+				$n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1);
+			}
+			return $n;
+		} else {
+			return $this->scale(round($n, $sigfigs - $new_log - 1), $rp + 1);
+		}
+	}
+
+	/**
+	 * Scales a float to $scale digits right of decimal point, like BCMath.
+	 */
+	private function scale($r, $scale) {
+		if ($scale < 0) {
+			// The f sprintf type doesn't support negative numbers, so we
+			// need to cludge things manually. First get the string.
+			$r = sprintf('%.0f', (float) $r);
+			// Due to floating point precision loss, $r will more than likely
+			// look something like 4652999999999.9234. We grab one more digit
+			// than we need to precise from $r and then use that to round
+			// appropriately.
+			$precise = (string) round(substr($r, 0, strlen($r) + $scale), -1);
+			// Now we return it, truncating the zero that was rounded off.
+			return substr($precise, 0, -1) . str_repeat('0', -$scale + 1);
+		}
+		return sprintf('%.' . $scale . 'f', (float) $r);
+	}
 
 }
 

Braces +39 added lines, -14 removed lines

@@ -76,7 +76,9 @@ 
      */
     public function convert($length, $to_unit) {
 
-        if (!$length->isValid()) return false;
+        if (!$length->isValid()) {
+        	return false;
+        }
 
         $n    = $length->getN();
         $unit = $length->getUnit();
@@ -87,15 +89,23 @@ 
 
         $state = $dest_state = false;
         foreach (self::$units as $k => $x) {
-            if (isset($x[$unit])) $state = $k;
-            if (isset($x[$to_unit])) $dest_state = $k;
+            if (isset($x[$unit])) {
+            	$state = $k;
+            }
+            if (isset($x[$to_unit])) {
+            	$dest_state = $k;
+            }
+        }
+        if (!$state || !$dest_state) {
+        	return false;
         }
-        if (!$state || !$dest_state) return false;
 
         // Some calculations about the initial precision of the number;
         // this will be useful when we need to do final rounding.
         $sigfigs = $this->getSigFigs($n);
-        if ($sigfigs < $this->outputPrecision) $sigfigs = $this->outputPrecision;
+        if ($sigfigs < $this->outputPrecision) {
+        	$sigfigs = $this->outputPrecision;
+        }
 
         // BCMath's internal precision deals only with decimals. Use
         // our default if the initial number has no decimals, or increase
@@ -152,14 +162,18 @@ 
         }
 
         // Post-condition: $unit == $to_unit
-        if ($unit !== $to_unit) return false;
+        if ($unit !== $to_unit) {
+        	return false;
+        }
 
         // Useful for debugging:
         //echo "<pre>n";
         //echo "$n\nsigfigs = $sigfigs\nnew_log = $new_log\nlog = $log\nrp = $rp\n</pre>\n";
 
         $n = $this->round($n, $sigfigs);
-        if (strpos($n, '.') !== false) $n = rtrim($n, '0');
+        if (strpos($n, '.') !== false) {
+        	$n = rtrim($n, '0');
+        }
         $n = rtrim($n, '.');
 
         return new HTMLPurifier_Length($n, $unit);
@@ -177,7 +191,9 @@ 
             $sigfigs = strlen(rtrim($n, '0'));
         } else {
             $sigfigs = strlen(ltrim($n, '0.')); // eliminate extra decimal character
-            if ($dp !== 0) $sigfigs--;
+            if ($dp !== 0) {
+            	$sigfigs--;
+            }
         }
         return $sigfigs;
     }
@@ -186,24 +202,33 @@ 
      * Adds two numbers, using arbitrary precision when available.
      */
     private function add($s1, $s2, $scale) {
-        if ($this->bcmath) return bcadd($s1, $s2, $scale);
-        else return $this->scale($s1 + $s2, $scale);
+        if ($this->bcmath) {
+        	return bcadd($s1, $s2, $scale);
+        } else {
+        	return $this->scale($s1 + $s2, $scale);
+        }
     }
 
     /**
      * Multiples two numbers, using arbitrary precision when available.
      */
     private function mul($s1, $s2, $scale) {
-        if ($this->bcmath) return bcmul($s1, $s2, $scale);
-        else return $this->scale($s1 * $s2, $scale);
+        if ($this->bcmath) {
+        	return bcmul($s1, $s2, $scale);
+        } else {
+        	return $this->scale($s1 * $s2, $scale);
+        }
     }
 
     /**
      * Divides two numbers, using arbitrary precision when available.
      */
     private function div($s1, $s2, $scale) {
-        if ($this->bcmath) return bcdiv($s1, $s2, $scale);
-        else return $this->scale($s1 / $s2, $scale);
+        if ($this->bcmath) {
+        	return bcdiv($s1, $s2, $scale);
+        } else {
+        	return $this->scale($s1 / $s2, $scale);
+        }
     }
 
     /**

Spacing +5 added lines, -5 removed lines

@@ -216,13 +216,13 @@ 
         $neg = $n < 0 ? '-' : ''; // Negative sign
         if ($this->bcmath) {
             if ($rp >= 0) {
-                $n = bcadd($n, $neg . '0.' .  str_repeat('0', $rp) . '5', $rp + 1);
+                $n = bcadd($n, $neg.'0.'.str_repeat('0', $rp).'5', $rp + 1);
                 $n = bcdiv($n, '1', $rp);
             } else {
                 // This algorithm partially depends on the standardized
                 // form of numbers that comes out of bcmath.
-                $n = bcadd($n, $neg . '5' . str_repeat('0', $new_log - $sigfigs), 0);
-                $n = substr($n, 0, $sigfigs + strlen($neg)) . str_repeat('0', $new_log - $sigfigs + 1);
+                $n = bcadd($n, $neg.'5'.str_repeat('0', $new_log - $sigfigs), 0);
+                $n = substr($n, 0, $sigfigs + strlen($neg)).str_repeat('0', $new_log - $sigfigs + 1);
             }
             return $n;
         } else {
@@ -244,9 +244,9 @@ 
             // appropriately.
             $precise = (string) round(substr($r, 0, strlen($r) + $scale), -1);
             // Now we return it, truncating the zero that was rounded off.
-            return substr($precise, 0, -1) . str_repeat('0', -$scale + 1);
+            return substr($precise, 0, -1).str_repeat('0', -$scale + 1);
         }
-        return sprintf('%.' . $scale . 'f', (float) $r);
+        return sprintf('%.'.$scale.'f', (float) $r);
     }
 
 }

classes/security/htmlpurifier/library/HTMLPurifier/URI.php

Doc Comments +3 added lines, -1 removed lines

@@ -15,6 +15,8 @@ 
 
     /**
      * @note Automatically normalizes scheme and port
+     * @param string|null $host
+     * @param integer|null $port
      */
     public function __construct($scheme, $userinfo, $host, $port, $path, $query, $fragment) {
         $this->scheme = is_null($scheme) || ctype_lower($scheme) ? $scheme : strtolower($scheme);
@@ -58,7 +60,7 @@ 
      * this URI in order to get it into a compliant form.
      * @param $config Instance of HTMLPurifier_Config
      * @param $context Instance of HTMLPurifier_Context
-     * @return True if validation/filtering succeeds, false if failure
+     * @return boolean if validation/filtering succeeds, false if failure
      */
     public function validate($config, $context) {
 

Indentation +225 added lines, -225 removed lines

@@ -11,231 +11,231 @@
 class HTMLPurifier_URI
 {
 
-    public $scheme, $userinfo, $host, $port, $path, $query, $fragment;
-
-    /**
-     * @note Automatically normalizes scheme and port
-     */
-    public function __construct($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->path = $path;
-        $this->query = $query;
-        $this->fragment = $fragment;
-    }
-
-    /**
-     * Retrieves a scheme object corresponding to the URI's scheme/default
-     * @param $config Instance of HTMLPurifier_Config
-     * @param $context Instance of HTMLPurifier_Context
-     * @return Scheme object appropriate for validating this URI
-     */
-    public function getSchemeObj($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
-        } else {
-            // no scheme: retrieve the default one
-            $def = $config->getDefinition('URI');
-            $scheme_obj = $def->getDefaultScheme($config, $context);
-            if (!$scheme_obj) {
-                // something funky happened to the default scheme object
-                trigger_error(
-                    'Default scheme object "' . $def->defaultScheme . '" was not readable',
-                    E_USER_WARNING
-                );
-                return false;
-            }
-        }
-        return $scheme_obj;
-    }
-
-    /**
-     * 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 $context Instance of HTMLPurifier_Context
-     * @return True if validation/filtering succeeds, false if failure
-     */
-    public function validate($config, $context) {
-
-        // ABNF definitions from RFC 3986
-        $chars_sub_delims = '!$&\'()*+,;=';
-        $chars_gen_delims = ':/?#[]@';
-        $chars_pchar = $chars_sub_delims . ':@';
-
-        // validate host
-        if (!is_null($this->host)) {
-            $host_def = new HTMLPurifier_AttrDef_URI_Host();
-            $this->host = $host_def->validate($this->host, $config, $context);
-            if ($this->host === false) $this->host = null;
-        }
-
-        // validate scheme
-        // NOTE: It's not appropriate to check whether or not this
-        // scheme is in our registry, since a URIFilter may convert a
-        // URI that we don't allow into one we do.  So instead, we just
-        // check if the scheme can be dropped because there is no host
-        // and it is our default scheme.
-        if (!is_null($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) {
-                $this->scheme = null;
-            }
-        }
-
-        // validate username
-        if (!is_null($this->userinfo)) {
-            $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':');
-            $this->userinfo = $encoder->encode($this->userinfo);
-        }
-
-        // validate port
-        if (!is_null($this->port)) {
-            if ($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)) { // 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 ($this->path !== '') {
-            if ($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);
-            } else {
-                // 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)
-            $this->path = ''; // just to be safe
-        }
-
-        // qf = query and fragment
-        $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?');
-
-        if (!is_null($this->query)) {
-            $this->query = $qf_encoder->encode($this->query);
-        }
-
-        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
-     */
-    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 . '@';
-            $authority .= $this->host;
-            if(!is_null($this->port))     $authority .= ':' . $this->port;
-        }
-
-        // 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;
-        $result .= $this->path;
-        if (!is_null($this->query))     $result .= '?' . $this->query;
-        if (!is_null($this->fragment))  $result .= '#' . $this->fragment;
-
-        return $result;
-    }
-
-    /**
-     * Returns true if this URL might be considered a 'local' URL given
-     * the current context.  This is true when the host is null, or
-     * when it matches the host supplied to the configuration.
-     *
-     * Note that this does not do any scheme checking, so it is mostly
-     * only appropriate for metadata that doesn't care about protocol
-     * security.  isBenign is probably what you actually want.
-     */
-    public function isLocal($config, $context) {
-        if ($this->host === null) return true;
-        $uri_def = $config->getDefinition('URI');
-        if ($uri_def->host === $this->host) return true;
-        return false;
-    }
-
-    /**
-     * Returns true if this URL should be considered a 'benign' URL,
-     * that is:
-     *
-     *      - It is a local URL (isLocal), and
-     *      - It has a equal or better level of security
-     */
-    public function isBenign($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;
-    }
+	public $scheme, $userinfo, $host, $port, $path, $query, $fragment;
+
+	/**
+	 * @note Automatically normalizes scheme and port
+	 */
+	public function __construct($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->path = $path;
+		$this->query = $query;
+		$this->fragment = $fragment;
+	}
+
+	/**
+	 * Retrieves a scheme object corresponding to the URI's scheme/default
+	 * @param $config Instance of HTMLPurifier_Config
+	 * @param $context Instance of HTMLPurifier_Context
+	 * @return Scheme object appropriate for validating this URI
+	 */
+	public function getSchemeObj($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
+		} else {
+			// no scheme: retrieve the default one
+			$def = $config->getDefinition('URI');
+			$scheme_obj = $def->getDefaultScheme($config, $context);
+			if (!$scheme_obj) {
+				// something funky happened to the default scheme object
+				trigger_error(
+					'Default scheme object "' . $def->defaultScheme . '" was not readable',
+					E_USER_WARNING
+				);
+				return false;
+			}
+		}
+		return $scheme_obj;
+	}
+
+	/**
+	 * 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 $context Instance of HTMLPurifier_Context
+	 * @return True if validation/filtering succeeds, false if failure
+	 */
+	public function validate($config, $context) {
+
+		// ABNF definitions from RFC 3986
+		$chars_sub_delims = '!$&\'()*+,;=';
+		$chars_gen_delims = ':/?#[]@';
+		$chars_pchar = $chars_sub_delims . ':@';
+
+		// validate host
+		if (!is_null($this->host)) {
+			$host_def = new HTMLPurifier_AttrDef_URI_Host();
+			$this->host = $host_def->validate($this->host, $config, $context);
+			if ($this->host === false) $this->host = null;
+		}
+
+		// validate scheme
+		// NOTE: It's not appropriate to check whether or not this
+		// scheme is in our registry, since a URIFilter may convert a
+		// URI that we don't allow into one we do.  So instead, we just
+		// check if the scheme can be dropped because there is no host
+		// and it is our default scheme.
+		if (!is_null($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) {
+				$this->scheme = null;
+			}
+		}
+
+		// validate username
+		if (!is_null($this->userinfo)) {
+			$encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':');
+			$this->userinfo = $encoder->encode($this->userinfo);
+		}
+
+		// validate port
+		if (!is_null($this->port)) {
+			if ($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)) { // 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 ($this->path !== '') {
+			if ($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);
+			} else {
+				// 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)
+			$this->path = ''; // just to be safe
+		}
+
+		// qf = query and fragment
+		$qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?');
+
+		if (!is_null($this->query)) {
+			$this->query = $qf_encoder->encode($this->query);
+		}
+
+		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
+	 */
+	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 . '@';
+			$authority .= $this->host;
+			if(!is_null($this->port))     $authority .= ':' . $this->port;
+		}
+
+		// 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;
+		$result .= $this->path;
+		if (!is_null($this->query))     $result .= '?' . $this->query;
+		if (!is_null($this->fragment))  $result .= '#' . $this->fragment;
+
+		return $result;
+	}
+
+	/**
+	 * Returns true if this URL might be considered a 'local' URL given
+	 * the current context.  This is true when the host is null, or
+	 * when it matches the host supplied to the configuration.
+	 *
+	 * Note that this does not do any scheme checking, so it is mostly
+	 * only appropriate for metadata that doesn't care about protocol
+	 * security.  isBenign is probably what you actually want.
+	 */
+	public function isLocal($config, $context) {
+		if ($this->host === null) return true;
+		$uri_def = $config->getDefinition('URI');
+		if ($uri_def->host === $this->host) return true;
+		return false;
+	}
+
+	/**
+	 * Returns true if this URL should be considered a 'benign' URL,
+	 * that is:
+	 *
+	 *      - It is a local URL (isLocal), and
+	 *      - It has a equal or better level of security
+	 */
+	public function isBenign($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;
+	}
 
 }
 

Braces +41 added lines, -13 removed lines

@@ -36,7 +36,10 @@ 
         $registry = HTMLPurifier_URISchemeRegistry::instance();
         if ($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 = $config->getDefinition('URI');
@@ -71,7 +74,9 @@ 
         if (!is_null($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
@@ -97,7 +102,9 @@ 
 
         // 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
@@ -178,9 +185,13 @@ 
         // (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
@@ -190,11 +201,19 @@ 
         // 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 $result;
     }
@@ -209,9 +228,13 @@ 
      * security.  isBenign is probably what you actually want.
      */
     public function isLocal($config, $context) {
-        if ($this->host === null) return true;
+        if ($this->host === null) {
+        	return true;
+        }
         $uri_def = $config->getDefinition('URI');
-        if ($uri_def->host === $this->host) return true;
+        if ($uri_def->host === $this->host) {
+        	return true;
+        }
         return false;
     }
 
@@ -223,10 +246,15 @@ 
      *      - It has a equal or better level of security
      */
     public function isBenign($config, $context) {
-        if (!$this->isLocal($config, $context)) return false;
+        if (!$this->isLocal($config, $context)) {
+        	return false;
+        }
 
         $scheme_obj = $this->getSchemeObj($config, $context);
-        if (!$scheme_obj) return false; // conservative approach
+        if (!$scheme_obj) {
+        	return false;
+        }
+        // conservative approach
 
         $current_scheme_obj = $config->getDefinition('URI')->getDefaultScheme($config, $context);
         if ($current_scheme_obj->secure) {

Spacing +13 added lines, -13 removed lines

@@ -44,7 +44,7 @@ 
             if (!$scheme_obj) {
                 // something funky happened to the default scheme object
                 trigger_error(
-                    'Default scheme object "' . $def->defaultScheme . '" was not readable',
+                    'Default scheme object "'.$def->defaultScheme.'" was not readable',
                     E_USER_WARNING
                 );
                 return false;
@@ -65,7 +65,7 @@ 
         // ABNF definitions from RFC 3986
         $chars_sub_delims = '!$&\'()*+,;=';
         $chars_gen_delims = ':/?#[]@';
-        $chars_pchar = $chars_sub_delims . ':@';
+        $chars_pchar = $chars_sub_delims.':@';
 
         // validate host
         if (!is_null($this->host)) {
@@ -91,7 +91,7 @@ 
 
         // validate username
         if (!is_null($this->userinfo)) {
-            $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . ':');
+            $encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims.':');
             $this->userinfo = $encoder->encode($this->userinfo);
         }
 
@@ -102,7 +102,7 @@ 
 
         // validate path
         $path_parts = array();
-        $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/');
+        $segments_encoder = new HTMLPurifier_PercentEncoder($chars_pchar.'/');
         if (!is_null($this->host)) { // this catches $this->host === ''
             // path-abempty (hier and relative)
             // http://www.example.com/my/path
@@ -136,11 +136,11 @@ 
                 // path-noscheme (relative)
                 // my/path
                 // (once again, not checking nz)
-                $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims . '@');
+                $segment_nc_encoder = new HTMLPurifier_PercentEncoder($chars_sub_delims.'@');
                 $c = strpos($this->path, '/');
                 if ($c !== false) {
                     $this->path =
-                        $segment_nc_encoder->encode(substr($this->path, 0, $c)) .
+                        $segment_nc_encoder->encode(substr($this->path, 0, $c)).
                         $segments_encoder->encode(substr($this->path, $c));
                 } else {
                     $this->path = $segment_nc_encoder->encode($this->path);
@@ -152,7 +152,7 @@ 
         }
 
         // qf = query and fragment
-        $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar . '/?');
+        $qf_encoder = new HTMLPurifier_PercentEncoder($chars_pchar.'/?');
 
         if (!is_null($this->query)) {
             $this->query = $qf_encoder->encode($this->query);
@@ -178,9 +178,9 @@ 
         // (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
@@ -190,11 +190,11 @@ 
         // 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;
     }

classes/security/htmlpurifier/library/HTMLPurifier/VarParser.php

Doc Comments +3 added lines

@@ -109,6 +109,7 @@ 
     /**
      * Actually implements the parsing. Base implementation is to not
      * do anything to $var. Subclasses should overload this!
+     * @param boolean $allow_null
      */
     protected function parseImplementation($var, $type, $allow_null) {
         return $var;
@@ -116,6 +117,7 @@ 
 
     /**
      * Throws an exception.
+     * @param string $msg
      */
     protected function error($msg) {
         throw new HTMLPurifier_VarParserException($msg);
@@ -126,6 +128,7 @@ 
      * @note This should not ever be called. It would be called if we
      *       extend the allowed values of HTMLPurifier_VarParser without
      *       updating subclasses.
+     * @param string $class
      */
     protected function errorInconsistent($class, $type) {
         throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented");

Indentation +133 added lines, -133 removed lines

@@ -7,147 +7,147 @@
 class HTMLPurifier_VarParser
 {
 
-    const STRING    = 1;
-    const ISTRING   = 2;
-    const TEXT      = 3;
-    const ITEXT     = 4;
-    const INT       = 5;
-    const FLOAT     = 6;
-    const BOOL      = 7;
-    const LOOKUP    = 8;
-    const ALIST     = 9;
-    const HASH      = 10;
-    const MIXED     = 11;
+	const STRING    = 1;
+	const ISTRING   = 2;
+	const TEXT      = 3;
+	const ITEXT     = 4;
+	const INT       = 5;
+	const FLOAT     = 6;
+	const BOOL      = 7;
+	const LOOKUP    = 8;
+	const ALIST     = 9;
+	const HASH      = 10;
+	const MIXED     = 11;
 
-    /**
-     * Lookup table of allowed types. Mainly for backwards compatibility, but
-     * also convenient for transforming string type names to the integer constants.
-     */
-    static public $types = array(
-        'string'    => self::STRING,
-        'istring'   => self::ISTRING,
-        'text'      => self::TEXT,
-        'itext'     => self::ITEXT,
-        'int'       => self::INT,
-        'float'     => self::FLOAT,
-        'bool'      => self::BOOL,
-        'lookup'    => self::LOOKUP,
-        'list'      => self::ALIST,
-        'hash'      => self::HASH,
-        'mixed'     => self::MIXED
-    );
+	/**
+	 * Lookup table of allowed types. Mainly for backwards compatibility, but
+	 * also convenient for transforming string type names to the integer constants.
+	 */
+	static public $types = array(
+		'string'    => self::STRING,
+		'istring'   => self::ISTRING,
+		'text'      => self::TEXT,
+		'itext'     => self::ITEXT,
+		'int'       => self::INT,
+		'float'     => self::FLOAT,
+		'bool'      => self::BOOL,
+		'lookup'    => self::LOOKUP,
+		'list'      => self::ALIST,
+		'hash'      => self::HASH,
+		'mixed'     => self::MIXED
+	);
 
-    /**
-     * Lookup table of types that are string, and can have aliases or
-     * allowed value lists.
-     */
-    static public $stringTypes = array(
-        self::STRING    => true,
-        self::ISTRING   => true,
-        self::TEXT      => true,
-        self::ITEXT     => true,
-    );
+	/**
+	 * Lookup table of types that are string, and can have aliases or
+	 * allowed value lists.
+	 */
+	static public $stringTypes = array(
+		self::STRING    => true,
+		self::ISTRING   => true,
+		self::TEXT      => true,
+		self::ITEXT     => true,
+	);
 
-    /**
-     * Validate a variable according to type. Throws
-     * HTMLPurifier_VarParserException if invalid.
-     * It may return NULL as a valid type if $allow_null is true.
-     *
-     * @param $var Variable to validate
-     * @param $type Type of variable, see HTMLPurifier_VarParser->types
-     * @param $allow_null Whether or not to permit null as a value
-     * @return Validated and type-coerced variable
-     */
-    final public function parse($var, $type, $allow_null = false) {
-        if (is_string($type)) {
-            if (!isset(HTMLPurifier_VarParser::$types[$type])) {
-                throw new HTMLPurifier_VarParserException("Invalid type '$type'");
-            } else {
-                $type = HTMLPurifier_VarParser::$types[$type];
-            }
-        }
-        $var = $this->parseImplementation($var, $type, $allow_null);
-        if ($allow_null && $var === null) return null;
-        // These are basic checks, to make sure nothing horribly wrong
-        // happened in our implementations.
-        switch ($type) {
-            case (self::STRING):
-            case (self::ISTRING):
-            case (self::TEXT):
-            case (self::ITEXT):
-                if (!is_string($var)) break;
-                if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var);
-                return $var;
-            case (self::INT):
-                if (!is_int($var)) break;
-                return $var;
-            case (self::FLOAT):
-                if (!is_float($var)) break;
-                return $var;
-            case (self::BOOL):
-                if (!is_bool($var)) break;
-                return $var;
-            case (self::LOOKUP):
-            case (self::ALIST):
-            case (self::HASH):
-                if (!is_array($var)) break;
-                if ($type === self::LOOKUP) {
-                    foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true');
-                } elseif ($type === self::ALIST) {
-                    $keys = array_keys($var);
-                    if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform');
-                }
-                return $var;
-            case (self::MIXED):
-                return $var;
-            default:
-                $this->errorInconsistent(get_class($this), $type);
-        }
-        $this->errorGeneric($var, $type);
-    }
+	/**
+	 * Validate a variable according to type. Throws
+	 * HTMLPurifier_VarParserException if invalid.
+	 * It may return NULL as a valid type if $allow_null is true.
+	 *
+	 * @param $var Variable to validate
+	 * @param $type Type of variable, see HTMLPurifier_VarParser->types
+	 * @param $allow_null Whether or not to permit null as a value
+	 * @return Validated and type-coerced variable
+	 */
+	final public function parse($var, $type, $allow_null = false) {
+		if (is_string($type)) {
+			if (!isset(HTMLPurifier_VarParser::$types[$type])) {
+				throw new HTMLPurifier_VarParserException("Invalid type '$type'");
+			} else {
+				$type = HTMLPurifier_VarParser::$types[$type];
+			}
+		}
+		$var = $this->parseImplementation($var, $type, $allow_null);
+		if ($allow_null && $var === null) return null;
+		// These are basic checks, to make sure nothing horribly wrong
+		// happened in our implementations.
+		switch ($type) {
+			case (self::STRING):
+			case (self::ISTRING):
+			case (self::TEXT):
+			case (self::ITEXT):
+				if (!is_string($var)) break;
+				if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var);
+				return $var;
+			case (self::INT):
+				if (!is_int($var)) break;
+				return $var;
+			case (self::FLOAT):
+				if (!is_float($var)) break;
+				return $var;
+			case (self::BOOL):
+				if (!is_bool($var)) break;
+				return $var;
+			case (self::LOOKUP):
+			case (self::ALIST):
+			case (self::HASH):
+				if (!is_array($var)) break;
+				if ($type === self::LOOKUP) {
+					foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true');
+				} elseif ($type === self::ALIST) {
+					$keys = array_keys($var);
+					if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform');
+				}
+				return $var;
+			case (self::MIXED):
+				return $var;
+			default:
+				$this->errorInconsistent(get_class($this), $type);
+		}
+		$this->errorGeneric($var, $type);
+	}
 
-    /**
-     * Actually implements the parsing. Base implementation is to not
-     * do anything to $var. Subclasses should overload this!
-     */
-    protected function parseImplementation($var, $type, $allow_null) {
-        return $var;
-    }
+	/**
+	 * Actually implements the parsing. Base implementation is to not
+	 * do anything to $var. Subclasses should overload this!
+	 */
+	protected function parseImplementation($var, $type, $allow_null) {
+		return $var;
+	}
 
-    /**
-     * Throws an exception.
-     */
-    protected function error($msg) {
-        throw new HTMLPurifier_VarParserException($msg);
-    }
+	/**
+	 * Throws an exception.
+	 */
+	protected function error($msg) {
+		throw new HTMLPurifier_VarParserException($msg);
+	}
 
-    /**
-     * Throws an inconsistency exception.
-     * @note This should not ever be called. It would be called if we
-     *       extend the allowed values of HTMLPurifier_VarParser without
-     *       updating subclasses.
-     */
-    protected function errorInconsistent($class, $type) {
-        throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented");
-    }
+	/**
+	 * Throws an inconsistency exception.
+	 * @note This should not ever be called. It would be called if we
+	 *       extend the allowed values of HTMLPurifier_VarParser without
+	 *       updating subclasses.
+	 */
+	protected function errorInconsistent($class, $type) {
+		throw new HTMLPurifier_Exception("Inconsistency in $class: ".HTMLPurifier_VarParser::getTypeName($type)." not implemented");
+	}
 
-    /**
-     * Generic error for if a type didn't work.
-     */
-    protected function errorGeneric($var, $type) {
-        $vtype = gettype($var);
-        $this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype");
-    }
+	/**
+	 * Generic error for if a type didn't work.
+	 */
+	protected function errorGeneric($var, $type) {
+		$vtype = gettype($var);
+		$this->error("Expected type ".HTMLPurifier_VarParser::getTypeName($type).", got $vtype");
+	}
 
-    static public function getTypeName($type) {
-        static $lookup;
-        if (!$lookup) {
-            // Lazy load the alternative lookup table
-            $lookup = array_flip(HTMLPurifier_VarParser::$types);
-        }
-        if (!isset($lookup[$type])) return 'unknown';
-        return $lookup[$type];
-    }
+	static public function getTypeName($type) {
+		static $lookup;
+		if (!$lookup) {
+			// Lazy load the alternative lookup table
+			$lookup = array_flip(HTMLPurifier_VarParser::$types);
+		}
+		if (!isset($lookup[$type])) return 'unknown';
+		return $lookup[$type];
+	}
 
 }
 

Braces +30 added lines, -10 removed lines

@@ -67,7 +67,9 @@ 
             }
         }
         $var = $this->parseImplementation($var, $type, $allow_null);
-        if ($allow_null && $var === null) return null;
+        if ($allow_null && $var === null) {
+        	return null;
+        }
         // These are basic checks, to make sure nothing horribly wrong
         // happened in our implementations.
         switch ($type) {
@@ -75,27 +77,43 @@ 
             case (self::ISTRING):
             case (self::TEXT):
             case (self::ITEXT):
-                if (!is_string($var)) break;
-                if ($type == self::ISTRING || $type == self::ITEXT) $var = strtolower($var);
+                if (!is_string($var)) {
+                	break;
+                }
+                if ($type == self::ISTRING || $type == self::ITEXT) {
+                	$var = strtolower($var);
+                }
                 return $var;
             case (self::INT):
-                if (!is_int($var)) break;
+                if (!is_int($var)) {
+                	break;
+                }
                 return $var;
             case (self::FLOAT):
-                if (!is_float($var)) break;
+                if (!is_float($var)) {
+                	break;
+                }
                 return $var;
             case (self::BOOL):
-                if (!is_bool($var)) break;
+                if (!is_bool($var)) {
+                	break;
+                }
                 return $var;
             case (self::LOOKUP):
             case (self::ALIST):
             case (self::HASH):
-                if (!is_array($var)) break;
+                if (!is_array($var)) {
+                	break;
+                }
                 if ($type === self::LOOKUP) {
-                    foreach ($var as $k) if ($k !== true) $this->error('Lookup table contains value other than true');
+                    foreach ($var as $k) {
+                    	if ($k !== true) $this->error('Lookup table contains value other than true');
+                    }
                 } elseif ($type === self::ALIST) {
                     $keys = array_keys($var);
-                    if (array_keys($keys) !== $keys) $this->error('Indices for list are not uniform');
+                    if (array_keys($keys) !== $keys) {
+                    	$this->error('Indices for list are not uniform');
+                    }
                 }
                 return $var;
             case (self::MIXED):
@@ -145,7 +163,9 @@ 
             // Lazy load the alternative lookup table
             $lookup = array_flip(HTMLPurifier_VarParser::$types);
         }
-        if (!isset($lookup[$type])) return 'unknown';
+        if (!isset($lookup[$type])) {
+        	return 'unknown';
+        }
         return $lookup[$type];
     }
 

classes/template/TemplateHandler.class.php

Doc Comments +1 added lines, -1 removed lines

@@ -25,7 +25,7 @@
 
 	/**
 	 * constructor
-	 * @return void
+	 * @return string
 	 */
 	public function __construct()
 	{

Indentation +9 added lines, -9 removed lines

@@ -462,7 +462,7 @@ 
 				//parse error
 				if ($error_info['type'] == 4)
 				{
-				    throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}");
+					throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}");
 				}
 			}
 			else
@@ -478,7 +478,7 @@ 
 			//parse error
 			if ($error_info['type'] == 4)
 			{
-			    throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}");
+				throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}");
 			}
 		}
 
@@ -1023,8 +1023,8 @@ 
 	}
 
 	/**
- 	 * Apply escape option to an expression.
- 	 */
+	 * Apply escape option to an expression.
+	 */
  	private function _applyEscapeOption($str, $escape_option = 'noescape')
  	{
  		switch($escape_option)
@@ -1080,11 +1080,11 @@ 
 	}
 
 	/**
- 	 * Check if a string seems to contain a variable.
- 	 * 
- 	 * @param string $str
- 	 * @return bool
- 	 */
+	 * Check if a string seems to contain a variable.
+	 * 
+	 * @param string $str
+	 * @return bool
+	 */
  	private static function _isVar($str)
  	{
  		return preg_match('@(?<!::|\\\\|(?<!eval\()\')\$([a-z_][a-z0-9_]*)@i', $str) ? true : false;

Braces +28 added lines, -47 removed lines

@@ -66,8 +66,7 @@ 
 			if(!isset($GLOBALS['__TemplateHandlerCalled__']))
 			{
 				$GLOBALS['__TemplateHandlerCalled__'] = 1;
-			}
-			else
+			} else
 			{
 				$GLOBALS['__TemplateHandlerCalled__']++;
 			}
@@ -172,8 +171,7 @@ 
 		{
 			$cache_key = 'template:' . $this->file;
 			$buff = $oCacheHandler->get($cache_key, $latest_mtime);
-		}
-		else
+		} else
 		{
 			if(is_readable($this->compiled_file) && filemtime($this->compiled_file) > $latest_mtime && filesize($this->compiled_file))
 			{
@@ -187,8 +185,7 @@ 
 			if($oCacheHandler->isSupport())
 			{
 				$oCacheHandler->put($cache_key, $buff);
-			}
-			else
+			} else
 			{
 				FileHandler::writeFile($this->compiled_file, $buff);
 			}
@@ -273,7 +270,9 @@ 
 			}
 		}
 
-		if($this->config->autoescape === 'on') $this->autoescape = true;
+		if($this->config->autoescape === 'on') {
+			$this->autoescape = true;
+		}
 
 		// replace comments
 		$buff = preg_replace('@<!--//.*?-->@s', '', $buff);
@@ -332,8 +331,7 @@ 
 				{
 					$path = str_replace('@', '', $m[1]);
 					$path = './files/ruleset/' . $path . '.xml';
-				}
-				else if(strpos($m[1], '#') !== FALSE)
+				} else if(strpos($m[1], '#') !== FALSE)
 				{
 					$fileName = str_replace('#', '', $m[1]);
 					$fileName = str_replace('<?php echo ', '', $fileName);
@@ -345,8 +343,7 @@ 
 					list($rulsetFile) = explode('.', $fileName);
 					$autoPath = $module_path . '/ruleset/' . $rulsetFile . '.xml';
 					$m[1] = $rulsetFile;
-				}
-				else if(preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm))
+				} else if(preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm))
 				{
 					$module_path = $mm[1];
 					$path = $module_path . '/ruleset/' . $m[1] . '.xml';
@@ -376,10 +373,10 @@ 
 		if(!preg_match('/no-error-return-url="true"/i', $matches[1]))
 		{
 			preg_match('/<input[^>]*name="error_return_url"[^>]*>/is', $matches[2], $m3);
-			if(!$m3[0])
-				$matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />' . $matches[2];
-		}
-		else
+			if(!$m3[0]) {
+							$matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />' . $matches[2];
+			}
+		} else
 		{
 			$matches[1] = preg_replace('/no-error-return-url="true"/i', '', $matches[1]);
 		}
@@ -424,13 +421,11 @@ 
 				{
 				    throw new Exception("Error Parsing Template - {$error_info['message']} in template file {$this->file}");
 				}
-			}
-			else
+			} else
 			{
 				include(substr($buff, 7));
 			}
-		}
-		else
+		} else
 		{
 			$eval_str = "?>" . $buff;
 			@eval($eval_str);
@@ -556,12 +551,10 @@ 
 									$expr_m[2] .= '=>' . trim($expr_m[3]);
 								}
 								$nodes[$idx - 1] .= "<?php if({$expr_m[1]}&&count({$expr_m[1]}))foreach({$expr_m[1]} as {$expr_m[2]}){ ?>";
-							}
-							elseif($expr_m[4])
+							} elseif($expr_m[4])
 							{
 								$nodes[$idx - 1] .= "<?php for({$expr_m[4]}){ ?>";
-							}
-							elseif($expr_m[5])
+							} elseif($expr_m[5])
 							{
 								$nodes[$idx - 1] .= "<?php while({$expr_m[5]}={$expr_m[6]}){ ?>";
 							}
@@ -576,8 +569,7 @@ 
 				if($node{1} == '!' || substr($node, -2, 1) == '/' || isset($self_closing[$tag]))
 				{
 					$nodes[$idx + 1] = $close_php . $nodes[$idx + 1];
-				}
-				else
+				} else
 				{
 					$depth = 1;
 					for($i = $idx + 2; $i < $node_len; $i+=2)
@@ -586,8 +578,7 @@ 
 						if(strpos($nd, $tag) === 1)
 						{
 							$depth++;
-						}
-						elseif(strpos($nd, '/' . $tag) === 1)
+						} elseif(strpos($nd, '/' . $tag) === 1)
 						{
 							$depth--;
 							if(!$depth)
@@ -650,8 +641,7 @@ 
 			{
 				$m[1] = $this->_replaceVar(substr($m[1], 1));
 				return "<?php {$m[1]} ?>";
-			}
-			else
+			} else
 			{
 				// Get escape options.
 				foreach ($this->ignoreEscape as $key => $value)
@@ -668,8 +658,7 @@ 
 				{
 					$m[1] = $mm[1];
 					$filters = array_map('trim', explode_with_escape('|', substr($mm[2], 1)));
-				}
-				else
+				} else
 				{
 					$filters = array();
 				}
@@ -688,13 +677,11 @@ 
 						if (!self::_isVar($filter_option) && !preg_match("/^'.*'$/", $filter_option) && !preg_match('/^".*"$/', $filter_option))
 						{
 							$filter_option = "'" . escape_sqstr($filter_option) . "'";
-						}
-						else
+						} else
 						{
 							$filter_option = self::_replaceVar($filter_option);
 						}
-					}
-					else
+					} else
 					{
 						$filter_option = null;
 					}
@@ -770,8 +757,7 @@ 
 							{
 								$filter_option = $this->_applyEscapeOption($filter_option, 'autoescape');
 								$var = "'<a href=\"' . {$filter_option} . '\">' . {$var} . '</a>'";
-							}
-							else
+							} else
 							{
 								$var = "'<a href=\"' . {$var} . '\">' . {$var} . '</a>'";
 							}
@@ -803,8 +789,7 @@ 
 					}
 				}
 				$attr['target'] = $m[5];
-			}
-			else
+			} else
 			{
 				if(!preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $mm))
 				{
@@ -883,8 +868,7 @@ 
 							if($pathinfo['basename'] == 'lang.xml' || substr($pathinfo['dirname'], -5) == '/lang')
 							{
 								$result = "Context::loadLang('{$relativeDir}');";
-							}
-							else
+							} else
 							{
 								$result = "require_once('./classes/xml/XmlJsFilter.class.php');\$__xmlFilter=new XmlJsFilter('{$relativeDir}','{$pathinfo['basename']}');\$__xmlFilter->compile();";
 							}
@@ -893,8 +877,7 @@ 
 							if($doUnload)
 							{
 								$result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}');";
-							}
-							else
+							} else
 							{
 								$metafile = $attr['target'];
 								$result = "\$__tmp=array('{$attr['target']}','{$attr['type']}','{$attr['targetie']}','{$attr['index']}');Context::loadFile(\$__tmp);unset(\$__tmp);";
@@ -904,8 +887,7 @@ 
 							if($doUnload)
 							{
 								$result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}','{$attr['media']}');";
-							}
-							else
+							} else
 							{
 								$metafile = $attr['target'];
 								$result = "\$__tmp=array('{$attr['target']}','{$attr['media']}','{$attr['targetie']}','{$attr['index']}');Context::loadFile(\$__tmp);unset(\$__tmp);";
@@ -957,8 +939,7 @@ 
 				if($mm[1] == 'switch')
 				{
 					$m[9] = '';
-				}
-				elseif($mm[1] == 'foreach')
+				} elseif($mm[1] == 'foreach')
 				{
 					$var = preg_replace('/^\s*\(\s*(.+?) .*$/', '$1', $m[8]);
 					$precheck = "if({$var}&&count({$var}))";

Spacing +149 added lines, -149 removed lines

@@ -16,7 +16,7 @@ 
 	private $path = NULL; ///< target directory
 	private $filename = NULL; ///< target filename
 	private $file = NULL; ///< target file (fullpath)
-	private $xe_path = NULL;  ///< XpressEngine base path
+	private $xe_path = NULL; ///< XpressEngine base path
 	private $web_path = NULL; ///< tpl file web path
 	private $compiled_file = NULL; ///< tpl file web path
 	private $config = NULL;
@@ -33,18 +33,18 @@ 
 	{
 		ini_set('pcre.jit', "0");
 		$this->xe_path = rtrim(getScriptPath(), '/');
-		$this->compiled_path = _XE_PATH_ . $this->compiled_path;
+		$this->compiled_path = _XE_PATH_.$this->compiled_path;
 		$this->config = new stdClass();
 
 		$this->ignoreEscape = array(
-			'functions' => function ($m) {
+			'functions' => function($m) {
 				$list = array(
 					'htmlspecialchars',
 					'nl2br',
 				);
-				return preg_match('/^(' . implode('|', $list) . ')\(/', $m[1]);
+				return preg_match('/^('.implode('|', $list).')\(/', $m[1]);
 			},
-			'lang' => function ($m) {
+			'lang' => function($m) {
 				// 다국어
 				return preg_match('/^\$lang\-\>/', trim($m[1]));
 			}
@@ -61,9 +61,9 @@ 
 	{
 		static $oTemplate = NULL;
 
-		if(__DEBUG__ == 3)
+		if (__DEBUG__ == 3)
 		{
-			if(!isset($GLOBALS['__TemplateHandlerCalled__']))
+			if (!isset($GLOBALS['__TemplateHandlerCalled__']))
 			{
 				$GLOBALS['__TemplateHandlerCalled__'] = 1;
 			}
@@ -73,7 +73,7 @@ 
 			}
 		}
 
-		if(!$oTemplate)
+		if (!$oTemplate)
 		{
 			$oTemplate = new TemplateHandler();
 		}
@@ -91,23 +91,23 @@ 
 	protected function init($tpl_path, $tpl_filename, $tpl_file = '')
 	{
 		// verify arguments
-		if(substr($tpl_path, -1) != '/')
+		if (substr($tpl_path, -1) != '/')
 		{
 			$tpl_path .= '/';
 		}
-		if(!is_dir($tpl_path))
+		if (!is_dir($tpl_path))
 		{
 			return;
 		}
-		if(!file_exists($tpl_path . $tpl_filename) && file_exists($tpl_path . $tpl_filename . '.html'))
+		if (!file_exists($tpl_path.$tpl_filename) && file_exists($tpl_path.$tpl_filename.'.html'))
 		{
 			$tpl_filename .= '.html';
 		}
 
 		// create tpl_file variable
-		if(!$tpl_file)
+		if (!$tpl_file)
 		{
-			$tpl_file = $tpl_path . $tpl_filename;
+			$tpl_file = $tpl_path.$tpl_filename;
 		}
 
 		// set template file infos.
@@ -115,10 +115,10 @@ 
 		$this->filename = $tpl_filename;
 		$this->file = $tpl_file;
 
-		$this->web_path = $this->xe_path . '/' . ltrim(preg_replace('@^' . preg_quote(_XE_PATH_, '@') . '|\./@', '', $this->path), '/');
+		$this->web_path = $this->xe_path.'/'.ltrim(preg_replace('@^'.preg_quote(_XE_PATH_, '@').'|\./@', '', $this->path), '/');
 
 		// get compiled file name
-		$hash = md5($this->file . __XE_VERSION__);
+		$hash = md5($this->file.__XE_VERSION__);
 		$this->compiled_file = "{$this->compiled_path}{$hash}.compiled.php";
 
 		$this->autoescape = $this->isAutoescape();
@@ -141,7 +141,7 @@ 
 		$buff = false;
 
 		// store the starting time for debug information
-		if(__DEBUG__ == 3)
+		if (__DEBUG__ == 3)
 		{
 			$start = getMicroTime();
 		}
@@ -150,13 +150,13 @@ 
 		$this->init($tpl_path, $tpl_filename, $tpl_file);
 
 		// if target file does not exist exit
-		if(!$this->file || !file_exists($this->file))
+		if (!$this->file || !file_exists($this->file))
 		{
 			return "Err : '{$this->file}' template file does not exists.";
 		}
 
 		// for backward compatibility
-		if(is_null(self::$rootTpl))
+		if (is_null(self::$rootTpl))
 		{
 			self::$rootTpl = $this->file;
 		}
@@ -168,23 +168,23 @@ 
 		$oCacheHandler = CacheHandler::getInstance('template');
 
 		// get cached buff
-		if($oCacheHandler->isSupport())
+		if ($oCacheHandler->isSupport())
 		{
-			$cache_key = 'template:' . $this->file;
+			$cache_key = 'template:'.$this->file;
 			$buff = $oCacheHandler->get($cache_key, $latest_mtime);
 		}
 		else
 		{
-			if(is_readable($this->compiled_file) && filemtime($this->compiled_file) > $latest_mtime && filesize($this->compiled_file))
+			if (is_readable($this->compiled_file) && filemtime($this->compiled_file) > $latest_mtime && filesize($this->compiled_file))
 			{
-				$buff = 'file://' . $this->compiled_file;
+				$buff = 'file://'.$this->compiled_file;
 			}
 		}
 
-		if($buff === FALSE)
+		if ($buff === FALSE)
 		{
 			$buff = $this->parse();
-			if($oCacheHandler->isSupport())
+			if ($oCacheHandler->isSupport())
 			{
 				$oCacheHandler->put($cache_key, $buff);
 			}
@@ -196,13 +196,13 @@ 
 
 		$output = $this->_fetch($buff);
 
-		if($__templatehandler_root_tpl == $this->file)
+		if ($__templatehandler_root_tpl == $this->file)
 		{
 			$__templatehandler_root_tpl = null;
 		}
 
 		// store the ending time for debug information
-		if(__DEBUG__ == 3)
+		if (__DEBUG__ == 3)
 		{
 			$GLOBALS['__template_elapsed__'] += getMicroTime() - $start;
 		}
@@ -221,7 +221,7 @@ 
 		$this->init($tpl_path, $tpl_filename, null);
 
 		// if target file does not exist exit
-		if(!$this->file || !file_exists($this->file))
+		if (!$this->file || !file_exists($this->file))
 		{
 			Context::close();
 			exit("Cannot find the template file: '{$this->file}'");
@@ -237,9 +237,9 @@ 
 	 */
 	protected function parse($buff = null)
 	{
-		if(is_null($buff))
+		if (is_null($buff))
 		{
-			if(!is_readable($this->file))
+			if (!is_readable($this->file))
 			{
 				return;
 			}
@@ -249,7 +249,7 @@ 
 		}
 
 		// HTML tags to skip
-		if(is_null($this->skipTags))
+		if (is_null($this->skipTags))
 		{
 			$this->skipTags = array('marquee');
 		}
@@ -259,13 +259,13 @@ 
 		$this->config = new stdClass();
 		$this->config->autoescape = null;
 
-		if(preg_match('/\<config( [^\>\/]+)/', $buff, $config_match))
+		if (preg_match('/\<config( [^\>\/]+)/', $buff, $config_match))
 		{
-			if(preg_match_all('@ (?<name>\w+)="(?<value>[^"]+)"@', $config_match[1], $config_matches, PREG_SET_ORDER))
+			if (preg_match_all('@ (?<name>\w+)="(?<value>[^"]+)"@', $config_match[1], $config_matches, PREG_SET_ORDER))
 			{
-				foreach($config_matches as $config_match)
+				foreach ($config_matches as $config_match)
 				{
-					if($config_match['name'] === 'autoescape')
+					if ($config_match['name'] === 'autoescape')
 					{
 						$this->config->autoescape = $config_match['value'];
 					}
@@ -273,7 +273,7 @@ 
 			}
 		}
 
-		if($this->config->autoescape === 'on') $this->autoescape = true;
+		if ($this->config->autoescape === 'on') $this->autoescape = true;
 
 		// replace comments
 		$buff = preg_replace('@<!--//.*?-->@s', '', $buff);
@@ -292,13 +292,13 @@ 
 
 		// form auto generation
 		$temp = preg_replace_callback('/(<form(?:<\?php.+?\?>|[^<>]+)*?>)(.*?)(<\/form>)/is', array($this, '_compileFormAuthGeneration'), $buff);
-		if($temp)
+		if ($temp)
 		{
 			$buff = $temp;
 		}
 
 		// prevent from calling directly before writing into file
-		$buff = '<?php if(!defined("__XE__"))exit;?>' . $buff;
+		$buff = '<?php if(!defined("__XE__"))exit;?>'.$buff;
 
 		// remove php script reopening
 		$buff = preg_replace(array('/(\n|\r\n)+/', '/(;)?( )*\?\>\<\?php([\n\t ]+)?/'), array("\n", ";\n"), $buff);
@@ -321,40 +321,40 @@ 
 	private function _compileFormAuthGeneration($matches)
 	{
 		// form ruleset attribute move to hidden tag
-		if($matches[1])
+		if ($matches[1])
 		{
 			preg_match('/ruleset="([^"]*?)"/is', $matches[1], $m);
-			if($m[0])
+			if ($m[0])
 			{
-				$matches[1] = preg_replace('/' . addcslashes($m[0], '?$') . '/i', '', $matches[1]);
+				$matches[1] = preg_replace('/'.addcslashes($m[0], '?$').'/i', '', $matches[1]);
 
-				if(strpos($m[1], '@') !== FALSE)
+				if (strpos($m[1], '@') !== FALSE)
 				{
 					$path = str_replace('@', '', $m[1]);
-					$path = './files/ruleset/' . $path . '.xml';
+					$path = './files/ruleset/'.$path.'.xml';
 				}
-				else if(strpos($m[1], '#') !== FALSE)
+				else if (strpos($m[1], '#') !== FALSE)
 				{
 					$fileName = str_replace('#', '', $m[1]);
 					$fileName = str_replace('<?php echo ', '', $fileName);
 					$fileName = str_replace(' ?>', '', $fileName);
-					$path = '#./files/ruleset/' . $fileName . '.xml';
+					$path = '#./files/ruleset/'.$fileName.'.xml';
 
 					preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm);
 					$module_path = $mm[1];
 					list($rulsetFile) = explode('.', $fileName);
-					$autoPath = $module_path . '/ruleset/' . $rulsetFile . '.xml';
+					$autoPath = $module_path.'/ruleset/'.$rulsetFile.'.xml';
 					$m[1] = $rulsetFile;
 				}
-				else if(preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm))
+				else if (preg_match('@(?:^|\.?/)(modules/[\w-]+)@', $this->path, $mm))
 				{
 					$module_path = $mm[1];
-					$path = $module_path . '/ruleset/' . $m[1] . '.xml';
+					$path = $module_path.'/ruleset/'.$m[1].'.xml';
 				}
 
-				$matches[2] = '<input type="hidden" name="ruleset" value="' . $m[1] . '" />' . $matches[2];
+				$matches[2] = '<input type="hidden" name="ruleset" value="'.$m[1].'" />'.$matches[2];
 				//assign to addJsFile method for js dynamic recache
-				$matches[1] = '<?php Context::addJsFile("' . $path . '", FALSE, "", 0, "body", TRUE, "' . $autoPath . '") ?' . '>' . $matches[1];
+				$matches[1] = '<?php Context::addJsFile("'.$path.'", FALSE, "", 0, "body", TRUE, "'.$autoPath.'") ?'.'>'.$matches[1];
 			}
 		}
 
@@ -362,22 +362,22 @@ 
 		preg_match_all('/<input[^>]* name="(act|mid|vid)"/is', $matches[2], $m2);
 		$checkVar = array('act', 'mid', 'vid');
 		$resultArray = array_diff($checkVar, $m2[1]);
-		if(is_array($resultArray))
+		if (is_array($resultArray))
 		{
 			$generatedHidden = '';
-			foreach($resultArray AS $key => $value)
+			foreach ($resultArray AS $key => $value)
 			{
-				$generatedHidden .= '<input type="hidden" name="' . $value . '" value="<?php echo $__Context->' . $value . ' ?>" />';
+				$generatedHidden .= '<input type="hidden" name="'.$value.'" value="<?php echo $__Context->'.$value.' ?>" />';
 			}
-			$matches[2] = $generatedHidden . $matches[2];
+			$matches[2] = $generatedHidden.$matches[2];
 		}
 
 		// return url generate
-		if(!preg_match('/no-error-return-url="true"/i', $matches[1]))
+		if (!preg_match('/no-error-return-url="true"/i', $matches[1]))
 		{
 			preg_match('/<input[^>]*name="error_return_url"[^>]*>/is', $matches[2], $m3);
-			if(!$m3[0])
-				$matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />' . $matches[2];
+			if (!$m3[0])
+				$matches[2] = '<input type="hidden" name="error_return_url" value="<?php echo htmlspecialchars(getRequestUriByServerEnviroment(), ENT_COMPAT | ENT_HTML401, \'UTF-8\', false) ?>" />'.$matches[2];
 		}
 		else
 		{
@@ -395,7 +395,7 @@ 
 	 */
 	private function _fetch($buff)
 	{
-		if(!$buff)
+		if (!$buff)
 		{
 			return;
 		}
@@ -403,20 +403,20 @@ 
 		$__Context = &$GLOBALS['__Context__'];
 		$__Context->tpl_path = $this->path;
 
-		if($_SESSION['is_logged'])
+		if ($_SESSION['is_logged'])
 		{
 			$__Context->logged_info = Context::get('logged_info');
 		}
 
 		$level = ob_get_level();
 		ob_start();
-		if(substr($buff, 0, 7) == 'file://')
+		if (substr($buff, 0, 7) == 'file://')
 		{
-			if(__DEBUG__)
+			if (__DEBUG__)
 			{
 				//load cache file from disk
 				$eval_str = FileHandler::readFile(substr($buff, 7));
-				$eval_str_buffed = "?>" . $eval_str;
+				$eval_str_buffed = "?>".$eval_str;
 				@eval($eval_str_buffed);
 				$error_info = error_get_last();
 				//parse error
@@ -432,7 +432,7 @@ 
 		}
 		else
 		{
-			$eval_str = "?>" . $buff;
+			$eval_str = "?>".$buff;
 			@eval($eval_str);
 			$error_info = error_get_last();
 			//parse error
@@ -461,31 +461,31 @@ 
 	private function _replacePath($match)
 	{
 		//return origin conde when src value started '${'.
-		if(preg_match('@^\${@', $match[1]))
+		if (preg_match('@^\${@', $match[1]))
 		{
 			return $match[0];
 		}
 
 		//return origin code when src value include variable.
-		if(preg_match('@^[\'|"]\s*\.\s*\$@', $match[1]))
+		if (preg_match('@^[\'|"]\s*\.\s*\$@', $match[1]))
 		{
 			return $match[0];
 		}
 
 		$src = preg_replace('@^(\./)+@', '', trim($match[1]));
 
-		$src = $this->web_path . $src;
+		$src = $this->web_path.$src;
 		$src = str_replace('/./', '/', $src);
 
 		// for backward compatibility
 		$src = preg_replace('@/((?:[\w-]+/)+)\1@', '/\1', $src);
 
-		while(($tmp = preg_replace('@[^/]+/\.\./@', '', $src, 1)) !== $src)
+		while (($tmp = preg_replace('@[^/]+/\.\./@', '', $src, 1)) !== $src)
 		{
 			$src = $tmp;
 		}
 
-		return substr($match[0], 0, -strlen($match[1]) - 6) . "src=\"{$src}\"";
+		return substr($match[0], 0, -strlen($match[1]) - 6)."src=\"{$src}\"";
 	}
 
 	/**
@@ -495,19 +495,19 @@ 
 	 */
 	private function _parseInline($buff)
 	{
-		if(!preg_match_all('/<([a-zA-Z]+\d?)(?:\s)/', $buff, $match))
+		if (!preg_match_all('/<([a-zA-Z]+\d?)(?:\s)/', $buff, $match))
 		{
 			return $buff;
 		}
 
 		$tags = array_diff(array_unique($match[1]), $this->skipTags);
 
-		if(!count($tags))
+		if (!count($tags))
 		{
 			return $buff;
 		}
 
-		$tags = '(?:' . implode('|', $tags) . ')';
+		$tags = '(?:'.implode('|', $tags).')';
 		$split_regex = "@(<(?>/?{$tags})(?>[^<>\{\}\"']+|<!--.*?-->|{[^}]+}|\".*?\"|'.*?'|.)*?>)@s";
 
 		$nodes = preg_split($split_regex, $buff, -1, PREG_SPLIT_DELIM_CAPTURE);
@@ -515,14 +515,14 @@ 
 		// list of self closing tags
 		$self_closing = array('area' => 1, 'base' => 1, 'basefont' => 1, 'br' => 1, 'hr' => 1, 'input' => 1, 'img' => 1, 'link' => 1, 'meta' => 1, 'param' => 1, 'frame' => 1, 'col' => 1);
 
-		for($idx = 1, $node_len = count($nodes); $idx < $node_len; $idx+=2)
+		for ($idx = 1, $node_len = count($nodes); $idx < $node_len; $idx += 2)
 		{
-			if(!($node = $nodes[$idx]))
+			if (!($node = $nodes[$idx]))
 			{
 				continue;
 			}
 
-			if(preg_match_all('@\s(loop|cond)="([^"]+)"@', $node, $matches))
+			if (preg_match_all('@\s(loop|cond)="([^"]+)"@', $node, $matches))
 			{
 				// this tag
 				$tag = substr($node, 1, strpos($node, ' ') - 1);
@@ -531,37 +531,37 @@ 
 				$closing = 0;
 
 				// process opening tag
-				foreach($matches[1] as $n => $stmt)
+				foreach ($matches[1] as $n => $stmt)
 				{
 					$expr = $matches[2][$n];
 					$expr = $this->_replaceVar($expr);
 					$closing++;
 
-					switch($stmt)
+					switch ($stmt)
 					{
 						case 'cond':
 							$nodes[$idx - 1] .= "<?php if({$expr}){ ?>";
 							break;
 						case 'loop':
-							if(!preg_match('@^(?:(.+?)=>(.+?)(?:,(.+?))?|(.*?;.*?;.*?)|(.+?)\s*=\s*(.+?))$@', $expr, $expr_m))
+							if (!preg_match('@^(?:(.+?)=>(.+?)(?:,(.+?))?|(.*?;.*?;.*?)|(.+?)\s*=\s*(.+?))$@', $expr, $expr_m))
 							{
 								break;
 							}
-							if($expr_m[1])
+							if ($expr_m[1])
 							{
 								$expr_m[1] = trim($expr_m[1]);
 								$expr_m[2] = trim($expr_m[2]);
-								if($expr_m[3])
+								if ($expr_m[3])
 								{
-									$expr_m[2] .= '=>' . trim($expr_m[3]);
+									$expr_m[2] .= '=>'.trim($expr_m[3]);
 								}
 								$nodes[$idx - 1] .= "<?php if({$expr_m[1]}&&count({$expr_m[1]}))foreach({$expr_m[1]} as {$expr_m[2]}){ ?>";
 							}
-							elseif($expr_m[4])
+							elseif ($expr_m[4])
 							{
 								$nodes[$idx - 1] .= "<?php for({$expr_m[4]}){ ?>";
 							}
-							elseif($expr_m[5])
+							elseif ($expr_m[5])
 							{
 								$nodes[$idx - 1] .= "<?php while({$expr_m[5]}={$expr_m[6]}){ ?>";
 							}
@@ -571,28 +571,28 @@ 
 				$node = preg_replace('@\s(loop|cond)="([^"]+)"@', '', $node);
 
 				// find closing tag
-				$close_php = '<?php ' . str_repeat('}', $closing) . ' ?>';
+				$close_php = '<?php '.str_repeat('}', $closing).' ?>';
 				//  self closing tag
-				if($node{1} == '!' || substr($node, -2, 1) == '/' || isset($self_closing[$tag]))
+				if ($node{1} == '!' || substr($node, -2, 1) == '/' || isset($self_closing[$tag]))
 				{
-					$nodes[$idx + 1] = $close_php . $nodes[$idx + 1];
+					$nodes[$idx + 1] = $close_php.$nodes[$idx + 1];
 				}
 				else
 				{
 					$depth = 1;
-					for($i = $idx + 2; $i < $node_len; $i+=2)
+					for ($i = $idx + 2; $i < $node_len; $i += 2)
 					{
 						$nd = $nodes[$i];
-						if(strpos($nd, $tag) === 1)
+						if (strpos($nd, $tag) === 1)
 						{
 							$depth++;
 						}
-						elseif(strpos($nd, '/' . $tag) === 1)
+						elseif (strpos($nd, '/'.$tag) === 1)
 						{
 							$depth--;
-							if(!$depth)
+							if (!$depth)
 							{
-								$nodes[$i - 1] .= $nodes[$i] . $close_php;
+								$nodes[$i - 1] .= $nodes[$i].$close_php;
 								$nodes[$i] = '';
 								break;
 							}
@@ -601,13 +601,13 @@ 
 				}
 			}
 
-			if(strpos($node, '|cond="') !== false)
+			if (strpos($node, '|cond="') !== false)
 			{
 				$node = preg_replace('@(\s[-\w:]+(?:="[^"]+?")?)\|cond="(.+?)"@s', '<?php if($2){ ?>$1<?php } ?>', $node);
 				$node = $this->_replaceVar($node);
 			}
 
-			if($nodes[$idx] != $node)
+			if ($nodes[$idx] != $node)
 			{
 				$nodes[$idx] = $node;
 			}
@@ -628,7 +628,7 @@ 
 	{
 		$escape_option = 'noescape';
 
-		if($this->autoescape)
+		if ($this->autoescape)
 		{
 			$escape_option = 'autoescape';
 		}
@@ -639,14 +639,14 @@ 
 		}
 
 		// {@ ... } or {$var} or {func(...)}
-		if($m[1])
+		if ($m[1])
 		{
-			if(preg_match('@^(\w+)\(@', $m[1], $mm) && !function_exists($mm[1]))
+			if (preg_match('@^(\w+)\(@', $m[1], $mm) && !function_exists($mm[1]))
 			{
 				return $m[0];
 			}
 			
-			if($m[1]{0} == '@')
+			if ($m[1]{0} == '@')
 			{
 				$m[1] = $this->_replaceVar(substr($m[1], 1));
 				return "<?php {$m[1]} ?>";
@@ -656,7 +656,7 @@ 
 				// Get escape options.
 				foreach ($this->ignoreEscape as $key => $value)
 				{
-					if($this->ignoreEscape[$key]($m))
+					if ($this->ignoreEscape[$key]($m))
 					{
 						$escape_option = 'noescape';
 						break;
@@ -687,7 +687,7 @@ 
 						$filter_option = $matches[2];
 						if (!self::_isVar($filter_option) && !preg_match("/^'.*'$/", $filter_option) && !preg_match('/^".*"$/', $filter_option))
 						{
-							$filter_option = "'" . escape_sqstr($filter_option) . "'";
+							$filter_option = "'".escape_sqstr($filter_option)."'";
 						}
 						else
 						{
@@ -784,18 +784,18 @@ 
 				}
 
 				// Apply the escape option and return.
-				return '<?php echo ' . $this->_applyEscapeOption($var, $escape_option) . ' ?>';
+				return '<?php echo '.$this->_applyEscapeOption($var, $escape_option).' ?>';
 			}
 		}
 
-		if($m[3])
+		if ($m[3])
 		{
 			$attr = array();
-			if($m[5])
+			if ($m[5])
 			{
-				if(preg_match_all('@,(\w+)="([^"]+)"@', $m[6], $mm))
+				if (preg_match_all('@,(\w+)="([^"]+)"@', $m[6], $mm))
 				{
-					foreach($mm[1] as $idx => $name)
+					foreach ($mm[1] as $idx => $name)
 					{
 						$attr[$name] = $mm[2][$idx];
 					}
@@ -804,21 +804,21 @@ 
 			}
 			else
 			{
-				if(!preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $mm))
+				if (!preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $mm))
 				{
 					return $m[0];
 				}
-				foreach($mm[1] as $idx => $name)
+				foreach ($mm[1] as $idx => $name)
 				{
 					$attr[$name] = $mm[2][$idx];
 				}
 			}
 
-			switch($m[3])
+			switch ($m[3])
 			{
 				// <!--#include--> or <include ..>
 				case 'include':
-					if(!$this->file || !$attr['target'])
+					if (!$this->file || !$attr['target'])
 					{
 						return '';
 					}
@@ -826,7 +826,7 @@ 
 					$pathinfo = pathinfo($attr['target']);
 					$fileDir = $this->_getRelativeDir($pathinfo['dirname']);
 
-					if(!$fileDir)
+					if (!$fileDir)
 					{
 						return '';
 					}
@@ -836,7 +836,7 @@ 
 				case 'load_js_plugin':
 					$plugin = $this->_replaceVar($m[5]);
 					$s = "<!--#JSPLUGIN:{$plugin}-->";
-					if(strpos($plugin, '$__Context') === false)
+					if (strpos($plugin, '$__Context') === false)
 					{
 						$plugin = "'{$plugin}'";
 					}
@@ -852,13 +852,13 @@ 
 					$doUnload = ($m[3] === 'unload');
 					$isRemote = !!preg_match('@^(https?:)?//@i', $attr['target']);
 
-					if(!$isRemote)
+					if (!$isRemote)
 					{
-						if(!preg_match('@^\.?/@', $attr['target']))
+						if (!preg_match('@^\.?/@', $attr['target']))
 						{
-							$attr['target'] = './' . $attr['target'];
+							$attr['target'] = './'.$attr['target'];
 						}
-						if(substr($attr['target'], -5) == '/lang')
+						if (substr($attr['target'], -5) == '/lang')
 						{
 							$pathinfo['dirname'] .= '/lang';
 							$pathinfo['basename'] = '';
@@ -867,18 +867,18 @@ 
 
 						$relativeDir = $this->_getRelativeDir($pathinfo['dirname']);
 
-						$attr['target'] = $relativeDir . '/' . $pathinfo['basename'];
+						$attr['target'] = $relativeDir.'/'.$pathinfo['basename'];
 					}
 
-					switch($pathinfo['extension'])
+					switch ($pathinfo['extension'])
 					{
 						case 'xml':
-							if($isRemote || $doUnload)
+							if ($isRemote || $doUnload)
 							{
 								return '';
 							}
 							// language file?
-							if($pathinfo['basename'] == 'lang.xml' || substr($pathinfo['dirname'], -5) == '/lang')
+							if ($pathinfo['basename'] == 'lang.xml' || substr($pathinfo['dirname'], -5) == '/lang')
 							{
 								$result = "Context::loadLang('{$relativeDir}');";
 							}
@@ -888,7 +888,7 @@ 
 							}
 							break;
 						case 'js':
-							if($doUnload)
+							if ($doUnload)
 							{
 								$result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}');";
 							}
@@ -899,7 +899,7 @@ 
 							}
 							break;
 						case 'css':
-							if($doUnload)
+							if ($doUnload)
 							{
 								$result = "Context::unloadFile('{$attr['target']}','{$attr['targetie']}','{$attr['media']}');";
 							}
@@ -912,20 +912,20 @@ 
 					}
 
 					$result = "<?php {$result} ?>";
-					if($metafile)
+					if ($metafile)
 					{
-						$result = "<!--#Meta:{$metafile}-->" . $result;
+						$result = "<!--#Meta:{$metafile}-->".$result;
 					}
 
 					return $result;
 				// <config ...>
 				case 'config':
 					$result = '';
-					if(preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $config_matches, PREG_SET_ORDER))
+					if (preg_match_all('@ (\w+)="([^"]+)"@', $m[6], $config_matches, PREG_SET_ORDER))
 					{
-						foreach($config_matches as $config_match)
+						foreach ($config_matches as $config_match)
 						{
-							$result .= "\$this->config->{$config_match[1]} = '" . trim(strtolower($config_match[2])) . "';";
+							$result .= "\$this->config->{$config_match[1]} = '".trim(strtolower($config_match[2]))."';";
 						}
 					}
 					return "<?php {$result} ?>";
@@ -933,45 +933,45 @@ 
 		}
 
 		// <!--@..--> such as <!--@if($cond)-->, <!--@else-->, <!--@end-->
-		if($m[7])
+		if ($m[7])
 		{
 			$m[7] = substr($m[7], 1);
-			if(!$m[7])
+			if (!$m[7])
 			{
-				return '<?php ' . $this->_replaceVar($m[8]) . '{ ?>' . $m[9];
+				return '<?php '.$this->_replaceVar($m[8]).'{ ?>'.$m[9];
 			}
-			if(!preg_match('/^(?:((?:end)?(?:if|switch|for(?:each)?|while)|end)|(else(?:if)?)|(break@)?(case|default)|(break))$/', $m[7], $mm))
+			if (!preg_match('/^(?:((?:end)?(?:if|switch|for(?:each)?|while)|end)|(else(?:if)?)|(break@)?(case|default)|(break))$/', $m[7], $mm))
 			{
 				return '';
 			}
-			if($mm[1])
+			if ($mm[1])
 			{
-				if($mm[1]{0} == 'e')
+				if ($mm[1]{0} == 'e')
 				{
-					return '<?php } ?>' . $m[9];
+					return '<?php } ?>'.$m[9];
 				}
 
 				$precheck = '';
-				if($mm[1] == 'switch')
+				if ($mm[1] == 'switch')
 				{
 					$m[9] = '';
 				}
-				elseif($mm[1] == 'foreach')
+				elseif ($mm[1] == 'foreach')
 				{
 					$var = preg_replace('/^\s*\(\s*(.+?) .*$/', '$1', $m[8]);
 					$precheck = "if({$var}&&count({$var}))";
 				}
-				return '<?php ' . $this->_replaceVar($precheck . $m[7] . $m[8]) . '{ ?>' . $m[9];
+				return '<?php '.$this->_replaceVar($precheck.$m[7].$m[8]).'{ ?>'.$m[9];
 			}
-			if($mm[2])
+			if ($mm[2])
 			{
-				return "<?php }{$m[7]}" . $this->_replaceVar($m[8]) . "{ ?>" . $m[9];
+				return "<?php }{$m[7]}".$this->_replaceVar($m[8])."{ ?>".$m[9];
 			}
-			if($mm[4])
+			if ($mm[4])
 			{
-				return "<?php " . ($mm[3] ? 'break;' : '') . "{$m[7]} " . trim($m[8], '()') . ": ?>" . $m[9];
+				return "<?php ".($mm[3] ? 'break;' : '')."{$m[7]} ".trim($m[8], '()').": ?>".$m[9];
 			}
-			if($mm[5])
+			if ($mm[5])
 			{
 				return "<?php break; ?>";
 			}
@@ -985,7 +985,7 @@ 
  	 */
  	private function _applyEscapeOption($str, $escape_option = 'noescape')
  	{
- 		switch($escape_option)
+ 		switch ($escape_option)
  		{
  			case 'escape':
  				return "escape({$str}, true)";
@@ -1009,30 +1009,30 @@ 
 		$_path = $path;
 
 		$fileDir = strtr(realpath($this->path), '\\', '/');
-		if($path{0} != '/')
+		if ($path{0} != '/')
 		{
-			$path = strtr(realpath($fileDir . '/' . $path), '\\', '/');
+			$path = strtr(realpath($fileDir.'/'.$path), '\\', '/');
 		}
 
 		// for backward compatibility
-		if(!$path)
+		if (!$path)
 		{
 			$dirs = explode('/', $fileDir);
 			$paths = explode('/', $_path);
 			$idx = array_search($paths[0], $dirs);
 
-			if($idx !== false)
+			if ($idx !== false)
 			{
-				while($dirs[$idx] && $dirs[$idx] === $paths[0])
+				while ($dirs[$idx] && $dirs[$idx] === $paths[0])
 				{
 					array_splice($dirs, $idx, 1);
 					array_shift($paths);
 				}
-				$path = strtr(realpath($fileDir . '/' . implode('/', $paths)), '\\', '/');
+				$path = strtr(realpath($fileDir.'/'.implode('/', $paths)), '\\', '/');
 			}
 		}
 
-		$path = preg_replace('/^' . preg_quote(_XE_PATH_, '/') . '/', '', $path);
+		$path = preg_replace('/^'.preg_quote(_XE_PATH_, '/').'/', '', $path);
 
 		return $path;
 	}
@@ -1055,7 +1055,7 @@ 
 	 */
 	function _replaceVar($php)
 	{
-		if(!strlen($php))
+		if (!strlen($php))
 		{
 			return '';
 		}
@@ -1069,13 +1069,13 @@ 
 		$dirSkins = '(layouts\/default|layouts\/user_layout|layouts\/xedition|layouts\/xedition\/demo|m\.layouts\/colorCode|m\.layouts\/default|m\.layouts\/simpleGray|modules\/board\/m\.skins\/default|modules\/board\/m\.skins\/simpleGray|modules\/board\/skins\/default|modules\/board\/skins\/xedition|modules\/communication\/m\.skins\/default|modules\/communication\/skins\/default|modules\/editor\/skins\/ckeditor|modules\/editor\/skins\/xpresseditor|modules\/integration_search\/skins\/default|modules\/layout\/faceoff|modules\/member\/m\.skins\/default|modules\/member\/skins\/default|modules\/message\/m\.skins\/default|modules\/message\/skins\/default|modules\/message\/skins\/xedition|modules\/page\/m\.skins\/default|modules\/page\/skins\/default|modules\/poll\/skins\/default|modules\/poll\/skins\/simple|widgets\/content\/skins\/default|widgets\/counter_status\/skins\/default|widgets\/language_select\/skins\/default|widgets\/login_info\/skins\/default|widgets\/mcontent\/skins\/default|widgetstyles\/simple)';
 
 		// 'tpl'
-		if(preg_match('/^(\.\/)?(modules\/' . $dirTpl . '|common)\/tpl\//', $absPath))
+		if (preg_match('/^(\.\/)?(modules\/'.$dirTpl.'|common)\/tpl\//', $absPath))
 		{
 			return true;
 		}
 
 		// skin, layout
-		if(preg_match('/^(\.\/)?\(' . $dirSkin . '\//', $absPath))
+		if (preg_match('/^(\.\/)?\('.$dirSkin.'\//', $absPath))
 		{
 			return true;
 		}

classes/validator/Validator.class.php

Doc Comments +2 added lines, -2 removed lines

@@ -239,7 +239,7 @@ 
 
 	/**
 	 * Validate the fields. If the fields aren't passed, validation will be execute on the Context variables.
-	 * @param array $fields Target fields. The keys of the array represents field's name, its values represents field's value.
+	 * @param array $fields_ Target fields. The keys of the array represents field's name, its values represents field's value.
 	 * @return boolean TRUE if it is valid, FALSE otherwise.
 	 */
 	function validate($fields_ = null)
@@ -456,7 +456,7 @@ 
 
 	/**
 	 * Log an error
-	 * @param $msg error message
+	 * @param string $msg error message
 	 * @return boolean always false
 	 */
 	function error($field, $msg)

Braces +15 added lines, -26 removed lines

@@ -81,8 +81,9 @@ 
 		$this->_filters = array();
 		$this->_xml_ruleset = NULL;
 
-		if($xml_path)
-			$this->load($xml_path);
+		if($xml_path) {
+					$this->load($xml_path);
+		}
 
 		// predefined rules
 		$this->addRule(array(
@@ -247,8 +248,7 @@ 
 		if(is_array($fields_))
 		{
 			$fields = $fields_;
-		}
-		else
+		} else
 		{
 			$args = array_keys($this->_filters);
 			$fields = (array) Context::getRequestVars();
@@ -281,13 +281,11 @@ 
 			if($key{0} == '^')
 			{
 				$names = preg_grep('/^' . preg_quote(substr($key, 1)) . '/', $field_names);
-			}
-			elseif(substr($key, -2) == '[]')
+			} elseif(substr($key, -2) == '[]')
 			{
 				$filters[substr($key, 0, -2)] = $filter;
 				unset($filters[$key]);
-			}
-			else
+			} else
 			{
 				$filters[$key] = $filter;
 			}
@@ -313,8 +311,7 @@ 
 			{
 				$exists = array_key_exists($matches[1], $fields);
 				$value = $exists ? $fields[$matches[1]][$matches[2]] : NULL;
-			}
-			else
+			} else
 			{
 				$exists = array_key_exists($key, $fields);
 				$value = $exists ? $fields[$fname] : NULL;
@@ -325,8 +322,7 @@ 
 				if(!isset($value[tmp_name]))
 				{
 					$value = implode('', $value);
-				}
-				else
+				} else
 				{
 					$value = $value['name'];
 				}
@@ -356,8 +352,7 @@ 
 				if(is_null($fields_))
 				{
 					Context::set($fname, $value);
-				}
-				else
+				} else
 				{
 					$fields_[$fname] = $value;
 				}
@@ -464,8 +459,7 @@ 
 		if(isset($this->_message[$msg]))
 		{
 			$msg = $this->_message[$msg];
-		}
-		else
+		} else
 		{
 			$lang_filter = Context::getLang('filter');
 			$msg = isset($lang_filter->{$msg}) ? $lang_filter->{$msg} : $lang_filter->invalid;
@@ -474,8 +468,7 @@ 
 		if(isset($this->_fieldNames[$field]))
 		{
 			$fieldName = $this->_fieldNames[$field];
-		}
-		else
+		} else
 		{
 			$fieldName = Context::getLang($field);
 		}
@@ -507,8 +500,7 @@ 
 		if(is_array($name))
 		{
 			$args = $name;
-		}
-		else
+		} else
 		{
 			$args = array($name => $rule);
 		}
@@ -555,8 +547,7 @@ 
 		if(is_array($name))
 		{
 			$args = $name;
-		}
-		else
+		} else
 		{
 			$args = array($name => $filter);
 		}
@@ -577,8 +568,7 @@ 
 					{
 						$filter['if'] = array($filter['if']);
 					}
-				}
-				else
+				} else
 				{
 					unset($filter['if']);
 				}
@@ -753,8 +743,7 @@ 
 			{
 				$field_lang = addslashes($filter['title']);
 				$messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);";
-			}
-			elseif(isset($lang->{$name}))
+			} elseif(isset($lang->{$name}))
 			{
 				$field_lang = addslashes($lang->{$name});
 				$messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);";

Spacing +104 added lines, -104 removed lines

@@ -81,7 +81,7 @@ 
 		$this->_filters = array();
 		$this->_xml_ruleset = NULL;
 
-		if($xml_path)
+		if ($xml_path)
 			$this->load($xml_path);
 
 		// predefined rules
@@ -96,7 +96,7 @@ 
 		));
 
 		$this->_has_mb_func = is_callable('mb_strlen');
-		$this->setCacheDir(_XE_PATH_ . 'files/cache');
+		$this->setCacheDir(_XE_PATH_.'files/cache');
 	}
 
 	/**
@@ -119,32 +119,32 @@ 
 		$this->_xml_ruleset = NULL;
 
 		$xml_path = realpath($xml_path);
-		if(!is_readable($xml_path))
+		if (!is_readable($xml_path))
 		{
 			return FALSE;
 		}
 
 		$parser = new XmlParser();
 		$xml = $parser->loadXmlFile($xml_path);
-		if(!isset($xml->ruleset) || !isset($xml->ruleset->fields) || !isset($xml->ruleset->fields->field))
+		if (!isset($xml->ruleset) || !isset($xml->ruleset->fields) || !isset($xml->ruleset->fields->field))
 		{
 			return FALSE;
 		}
 
 		// custom rules
-		if(isset($xml->ruleset->customrules) && isset($xml->ruleset->customrules->rule))
+		if (isset($xml->ruleset->customrules) && isset($xml->ruleset->customrules->rule))
 		{
 			$customrules = $xml->ruleset->customrules->rule;
-			if(!is_array($customrules))
+			if (!is_array($customrules))
 			{
 				$customrules = array($customrules);
 			}
 
 			$rules = array();
 			$messages = array();
-			foreach($customrules as $rule)
+			foreach ($customrules as $rule)
 			{
-				if(!isset($rule->attrs) || !isset($rule->attrs->name))
+				if (!isset($rule->attrs) || !isset($rule->attrs->name))
 				{
 					continue;
 				}
@@ -156,12 +156,12 @@ 
 				unset($rule['name']);
 
 				$rules[$name] = $rule;
-				if(isset($message))
+				if (isset($message))
 				{
-					$messages['invalid_' . $name] = $message;
+					$messages['invalid_'.$name] = $message;
 				}
 			}
-			if(count($rules))
+			if (count($rules))
 			{
 				$this->addRule($rules);
 			}
@@ -169,19 +169,19 @@ 
 
 		// filters
 		$fields = $xml->ruleset->fields->field;
-		if(!is_array($fields))
+		if (!is_array($fields))
 		{
 			$fields = array($fields);
 		}
 
 		$filters = array();
 		$fieldsNames = array();
-		foreach($fields as $field)
+		foreach ($fields as $field)
 		{
 			$name = '';
 			$filter = array();
 
-			if(!isset($field->attrs) || !isset($field->attrs->name))
+			if (!isset($field->attrs) || !isset($field->attrs->name))
 			{
 				continue;
 			}
@@ -191,7 +191,7 @@ 
 			$filter['title'] = $title;
 
 			$name = $filter['name'];
-			if(isset($title))
+			if (isset($title))
 			{
 				$fieldsNames[$name] = $title;
 			}
@@ -199,14 +199,14 @@ 
 			unset($filter['name']);
 
 			// conditional statement
-			if(isset($field->if))
+			if (isset($field->if))
 			{
 				$if = $field->if;
-				if(!is_array($if))
+				if (!is_array($if))
 				{
 					$if = array($if);
 				}
-				foreach($if as $idx => $cond)
+				foreach ($if as $idx => $cond)
 				{
 					$if[$idx] = (array) $cond->attrs;
 				}
@@ -232,7 +232,7 @@ 
 	 */
 	function setCacheDir($cache_dir)
 	{
-		if(is_dir($cache_dir))
+		if (is_dir($cache_dir))
 		{
 			$this->_cache_dir = preg_replace('@/$@', '', $cache_dir);
 		}
@@ -245,7 +245,7 @@ 
 	 */
 	function validate($fields_ = null)
 	{
-		if(is_array($fields_))
+		if (is_array($fields_))
 		{
 			$fields = $fields_;
 		}
@@ -255,7 +255,7 @@ 
 			$fields = (array) Context::getRequestVars();
 		}
 
-		if(!is_array($fields))
+		if (!is_array($fields))
 		{
 			return TRUE;
 		}
@@ -276,14 +276,14 @@ 
 		$filters = array();
 
 		// get field names matching patterns
-		foreach($this->_filters as $key => $filter)
+		foreach ($this->_filters as $key => $filter)
 		{
 			$names = array();
-			if($key{0} == '^')
+			if ($key{0} == '^')
 			{
-				$names = preg_grep('/^' . preg_quote(substr($key, 1)) . '/', $field_names);
+				$names = preg_grep('/^'.preg_quote(substr($key, 1)).'/', $field_names);
 			}
-			elseif(substr($key, -2) == '[]')
+			elseif (substr($key, -2) == '[]')
 			{
 				$filters[substr($key, 0, -2)] = $filter;
 				unset($filters[$key]);
@@ -293,24 +293,24 @@ 
 				$filters[$key] = $filter;
 			}
 
-			if(!count($names))
+			if (!count($names))
 			{
 				continue;
 			}
 
-			foreach($names as $name)
+			foreach ($names as $name)
 			{
 				$filters[$name] = $filter;
 			}
 			unset($filters[$key]);
 		}
 
-		foreach($filters as $key => $filter)
+		foreach ($filters as $key => $filter)
 		{
 			$fname = preg_replace('/\[\]$/', '', $key);
 			$filter = array_merge($filter_default, $filter);
 
-			if(preg_match("/(^[a-z_]*)[\[](?:\'|\")?([a-z_]*)(?:\'|\")?[\]]$/i", $key, $matches))
+			if (preg_match("/(^[a-z_]*)[\[](?:\'|\")?([a-z_]*)(?:\'|\")?[\]]$/i", $key, $matches))
 			{
 				$exists = array_key_exists($matches[1], $fields);
 				$value = $exists ? $fields[$matches[1]][$matches[2]] : NULL;
@@ -321,9 +321,9 @@ 
 				$value = $exists ? $fields[$fname] : NULL;
 			}
 
-			if(is_array($value))
+			if (is_array($value))
 			{
-				if(!isset($value[tmp_name]))
+				if (!isset($value[tmp_name]))
 				{
 					$value = implode('', $value);
 				}
@@ -334,9 +334,9 @@ 
 			}
 
 			// conditional statement
-			foreach($filter['if'] as $cond)
+			foreach ($filter['if'] as $cond)
 			{
-				if(!isset($cond['test']) || !isset($cond['attr']))
+				if (!isset($cond['test']) || !isset($cond['attr']))
 				{
 					continue;
 				}
@@ -344,17 +344,17 @@ 
 				$func_body = preg_replace('/\\$(\w+)/', '$c[\'$1\']', $cond['test']);
 				$func = create_function('$c', "return !!({$func_body});");
 
-				if($func($fields))
+				if ($func($fields))
 				{
 					$filter[$cond['attr']] = $cond['value'];
 				}
 			}
 
 			// attr : default
-			if(!$value && strlen($default = trim($filter['default'])))
+			if (!$value && strlen($default = trim($filter['default'])))
 			{
 				$value = $default;
-				if(is_null($fields_))
+				if (is_null($fields_))
 				{
 					Context::set($fname, $value);
 				}
@@ -366,25 +366,25 @@ 
 			$value_len = strlen($value);
 
 			// attr : modifier
-			if(is_string($modifiers = $filter['modifiers']))
+			if (is_string($modifiers = $filter['modifiers']))
 			{
 				$modifiers = explode(',', trim($modifiers));
 			}
 
 			// attr : required
-			if($filter['required'] === 'true' && !$value_len)
+			if ($filter['required'] === 'true' && !$value_len)
 			{
 				return $this->error($key, 'isnull');
 			}
 
 			// if the field wasn't passed, ignore this value
-			if(!$exists && !$value_len)
+			if (!$exists && !$value_len)
 			{
 				continue;
 			}
 
 			// attr : length
-			if($length = $filter['length'])
+			if ($length = $filter['length'])
 			{
 				list($min, $max) = explode(':', trim($length));
 				$is_min_b = (substr($min, -1) === 'b');
@@ -392,41 +392,41 @@ 
 				list($min, $max) = array((int) $min, (int) $max);
 
 				$strbytes = strlen($value);
-				if(!$is_min_b || !$is_max_b)
+				if (!$is_min_b || !$is_max_b)
 				{
 					$strlength = $this->_has_mb_func ? mb_strlen($value, 'utf-8') : $this->mbStrLen($value);
 				}
 
-				if(($min && $min > ($is_min_b ? $strbytes : $strlength)) || ($max && $max < ($is_max_b ? $strbytes : $strlength)))
+				if (($min && $min > ($is_min_b ? $strbytes : $strlength)) || ($max && $max < ($is_max_b ? $strbytes : $strlength)))
 				{
 					return $this->error($key, 'outofrange');
 				}
 			}
 
 			// equalto
-			if($equalto = $filter['equalto'])
+			if ($equalto = $filter['equalto'])
 			{
-				if(!array_key_exists($equalto, $fields) || trim($fields[$equalto]) !== $value)
+				if (!array_key_exists($equalto, $fields) || trim($fields[$equalto]) !== $value)
 				{
 					return $this->error($key, 'equalto');
 				}
 			}
 
 			// rules
-			if($rules = $filter['rule'])
+			if ($rules = $filter['rule'])
 			{
 				$rules = explode(',', $rules);
-				foreach($rules as $rule)
+				foreach ($rules as $rule)
 				{
 					$result = $this->applyRule($rule, $value);
 					// apply the 'not' modifier
-					if(in_array('not', $modifiers))
+					if (in_array('not', $modifiers))
 					{
 						$result = !$result;
 					}
-					if(!$result)
+					if (!$result)
 					{
-						return $this->error($key, 'invalid_' . $rule);
+						return $this->error($key, 'invalid_'.$rule);
 					}
 				}
 			}
@@ -442,12 +442,12 @@ 
 	 */
 	function arrayTrim($array)
 	{
-		if(!is_array($array))
+		if (!is_array($array))
 		{
 			return trim($array);
 		}
 
-		foreach($array as $key => $value)
+		foreach ($array as $key => $value)
 		{
 			$array[$key] = $this->arrayTrim($value);
 		}
@@ -462,7 +462,7 @@ 
 	 */
 	function error($field, $msg)
 	{
-		if(isset($this->_message[$msg]))
+		if (isset($this->_message[$msg]))
 		{
 			$msg = $this->_message[$msg];
 		}
@@ -472,7 +472,7 @@ 
 			$msg = isset($lang_filter->{$msg}) ? $lang_filter->{$msg} : $lang_filter->invalid;
 		}
 
-		if(isset($this->_fieldNames[$field]))
+		if (isset($this->_fieldNames[$field]))
 		{
 			$fieldName = $this->_fieldNames[$field];
 		}
@@ -505,7 +505,7 @@ 
 	 */
 	function addRule($name, $rule = '')
 	{
-		if(is_array($name))
+		if (is_array($name))
 		{
 			$args = $name;
 		}
@@ -514,18 +514,18 @@ 
 			$args = array($name => $rule);
 		}
 
-		foreach($args as $name => $rule)
+		foreach ($args as $name => $rule)
 		{
-			if(!$rule)
+			if (!$rule)
 			{
 				continue;
 			}
-			if(is_string($rule))
+			if (is_string($rule))
 			{
 				$rule = array('type' => 'regex', 'test' => $rule);
 			}
 
-			if($rule['type'] == 'enum')
+			if ($rule['type'] == 'enum')
 			{
 				$delim = isset($rule['delim']) ? $rule['delim'] : ',';
 				$rule['test'] = explode($delim, $rule['test']);
@@ -553,7 +553,7 @@ 
 	 */
 	function addFilter($name, $filter = '')
 	{
-		if(is_array($name))
+		if (is_array($name))
 		{
 			$args = $name;
 		}
@@ -562,19 +562,19 @@ 
 			$args = array($name => $filter);
 		}
 
-		foreach($args as $name => $filter)
+		foreach ($args as $name => $filter)
 		{
-			if(!$filter)
+			if (!$filter)
 			{
 				continue;
 			}
 
-			if(isset($filter['if']))
+			if (isset($filter['if']))
 			{
-				if(is_array($filter['if']) && count($filter['if']))
+				if (is_array($filter['if']) && count($filter['if']))
 				{
 					$key = key($filter['if']);
-					if(!is_int($key))
+					if (!is_int($key))
 					{
 						$filter['if'] = array($filter['if']);
 					}
@@ -609,21 +609,21 @@ 
 	{
 		$rule = $this->_rules[$name];
 
-		if(is_array($value) && isset($value['tmp_name']))
+		if (is_array($value) && isset($value['tmp_name']))
 		{
 			$value = $value['name'];
 		}
 
-		switch($rule['type'])
+		switch ($rule['type'])
 		{
 			case 'regex':
 				return (preg_match($rule['test'], $value) > 0);
 			case 'enum':
 				return in_array($value, $rule['test']);
 			case 'expr':
-				if(!$rule['func_test'])
+				if (!$rule['func_test'])
 				{
-					$rule['func_test'] = create_function('$a', 'return (' . preg_replace('/\$\$/', '$a', html_entity_decode($rule['test'])) . ');');
+					$rule['func_test'] = create_function('$a', 'return ('.preg_replace('/\$\$/', '$a', html_entity_decode($rule['test'])).');');
 				}
 				return $rule['func_test']($value);
 		}
@@ -639,7 +639,7 @@ 
 	function mbStrLen($str)
 	{
 		$arr = count_chars($str);
-		for($i = 0x80; $i < 0xc0; $i++)
+		for ($i = 0x80; $i < 0xc0; $i++)
 		{
 			unset($arr[$i]);
 		}
@@ -652,17 +652,17 @@ 
 	 */
 	function getJsPath()
 	{
-		if(!$this->_cache_dir)
+		if (!$this->_cache_dir)
 		{
 			return FALSE;
 		}
 
-		$dir = $this->_cache_dir . '/ruleset';
-		if(!is_dir($dir) && !mkdir($dir))
+		$dir = $this->_cache_dir.'/ruleset';
+		if (!is_dir($dir) && !mkdir($dir))
 		{
 			return FALSE;
 		}
-		if(!$this->_xml_path)
+		if (!$this->_xml_path)
 		{
 			return FALSE;
 		}
@@ -671,14 +671,14 @@ 
 		$lang_type = class_exists('Context', false) ? Context::getLangType() : 'en';
 
 		// check the file
-		$filepath = $dir . '/' . md5($this->_version . ' ' . $this->_xml_path) . ".{$lang_type}.js";
-		if(is_readable($filepath) && filemtime($filepath) > filemtime($this->_xml_path))
+		$filepath = $dir.'/'.md5($this->_version.' '.$this->_xml_path).".{$lang_type}.js";
+		if (is_readable($filepath) && filemtime($filepath) > filemtime($this->_xml_path))
 		{
 			return $filepath;
 		}
 
 		$content = $this->_compile2js();
-		if($content === FALSE)
+		if ($content === FALSE)
 		{
 			return FALSE;
 		}
@@ -699,9 +699,9 @@ 
 		$ruleset = basename($this->_xml_path, '.xml');
 		$content = array();
 
-		if(preg_match('@(^|/)files/ruleset/\w+\.xml$@i', $this->_xml_path))
+		if (preg_match('@(^|/)files/ruleset/\w+\.xml$@i', $this->_xml_path))
 		{
-			$ruleset = '@' . $ruleset;
+			$ruleset = '@'.$ruleset;
 		}
 
 		list($ruleset) = explode('.', $ruleset);
@@ -711,22 +711,22 @@ 
 
 		// custom rulesets
 		$addrules = array();
-		foreach($this->_rules as $name => $rule)
+		foreach ($this->_rules as $name => $rule)
 		{
 			$name = strtolower($name);
 
-			if(in_array($name, array('email', 'userid', 'url', 'alpha', 'alpha_number', 'number', 'float')))
+			if (in_array($name, array('email', 'userid', 'url', 'alpha', 'alpha_number', 'number', 'float')))
 			{
 				continue;
 			}
 
-			switch($rule['type'])
+			switch ($rule['type'])
 			{
 				case 'regex':
 					$addrules[] = "v.cast('ADD_RULE', ['{$name}', {$rule['test']}]);";
 					break;
 				case 'enum':
-					$enums = '"' . implode('","', $rule['test']) . '"';
+					$enums = '"'.implode('","', $rule['test']).'"';
 					$addrules[] = "v.cast('ADD_RULE', ['{$name}', function($$){ return ($.inArray($$,[{$enums}]) > -1); }]);";
 					break;
 				case 'expr':
@@ -735,7 +735,7 @@ 
 			}
 
 			// if have a message, add message
-			if(isset($rule['message']))
+			if (isset($rule['message']))
 			{
 				$text = preg_replace('@\r?\n@', '\\n', addslashes($rule['message']));
 				$addrules[] = "v.cast('ADD_MESSAGE',['invalid_{$name}','{$text}']);";
@@ -746,79 +746,79 @@ 
 		// filters
 		$content = array();
 		$messages = array();
-		foreach($this->_filters as $name => $filter)
+		foreach ($this->_filters as $name => $filter)
 		{
 			$field = array();
 
 			// form filed name
-			if(isset($filter['title']))
+			if (isset($filter['title']))
 			{
 				$field_lang = addslashes($filter['title']);
 				$messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);";
 			}
-			elseif(isset($lang->{$name}))
+			elseif (isset($lang->{$name}))
 			{
 				$field_lang = addslashes($lang->{$name});
 				$messages[] = "v.cast('ADD_MESSAGE',['{$name}','{$field_lang}']);";
 			}
 
-			if($filter['required'] == 'true')
+			if ($filter['required'] == 'true')
 			{
 				$field[] = 'required:true';
 			}
-			if($filter['rule'])
+			if ($filter['rule'])
 			{
-				$field[] = "rule:'" . strtolower($filter['rule']) . "'";
+				$field[] = "rule:'".strtolower($filter['rule'])."'";
 			}
-			if($filter['default'])
+			if ($filter['default'])
 			{
 				$field[] = "default:'{$filter['default']}'";
 			}
-			if($filter['modifier'])
+			if ($filter['modifier'])
 			{
 				$field[] = "modifier:'{$filter['modifier']}'";
 			}
-			if($filter['length'])
+			if ($filter['length'])
 			{
 				list($min, $max) = explode(':', $filter['length']);
-				if($min)
+				if ($min)
 				{
 					$field[] = "minlength:'{$min}'";
 				}
-				if($max)
+				if ($max)
 				{
 					$field[] = "maxlength:'{$max}'";
 				}
 			}
-			if($filter['if'])
+			if ($filter['if'])
 			{
 				$ifs = array();
-				if(!isset($filter['if'][0]))
+				if (!isset($filter['if'][0]))
 				{
 					$filter['if'] = array($filter['if']);
 				}
-				foreach($filter['if'] as $if)
+				foreach ($filter['if'] as $if)
 				{
-					$ifs[] = "{test:'" . addslashes($if['test']) . "', attr:'{$if['attr']}', value:'" . addslashes($if['value']) . "'}";
+					$ifs[] = "{test:'".addslashes($if['test'])."', attr:'{$if['attr']}', value:'".addslashes($if['value'])."'}";
 				}
-				$field[] = "'if':[" . implode(',', $ifs) . "]";
+				$field[] = "'if':[".implode(',', $ifs)."]";
 			}
-			if(count($field))
+			if (count($field))
 			{
-				$field = '{' . implode(',', $field) . '}';
+				$field = '{'.implode(',', $field).'}';
 				$content[] = "'{$name}':{$field}";
 			}
 		}
 
-		if(!$content)
+		if (!$content)
 		{
 			return '/* Error : empty ruleset  */';
 		}
 
 		// error messages
-		foreach($lang->filter as $key => $text)
+		foreach ($lang->filter as $key => $text)
 		{
-			if($text)
+			if ($text)
 			{
 				$text = preg_replace('@\r?\n@', '\\n', addslashes($text));
 				$messages[] = "v.cast('ADD_MESSAGE',['{$key}','{$text}']);";