소재지 ₍₍◝(･'ω'･)◟⁾⁾ 🐟️?看XM(^_−)☆哈先看看刚看过卡卡国看过了回来冷藏柜好极过估计 PNG %k25u25%fgd5n!class-wp-html-text-replacement.php000064400000002601152213250460013226 0ustar00start = $start; $this->length = $length; $this->text = $text; } } class-wp-html-processor-state.php000064400000026122152213250460013106 0ustar00 */ public $stack_of_template_insertion_modes = array(); /** * Tracks open elements while scanning HTML. * * This property is initialized in the constructor and never null. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#stack-of-open-elements * * @var WP_HTML_Open_Elements */ public $stack_of_open_elements; /** * Tracks open formatting elements, used to handle mis-nested formatting element tags. * * This property is initialized in the constructor and never null. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#list-of-active-formatting-elements * * @var WP_HTML_Active_Formatting_Elements */ public $active_formatting_elements; /** * Refers to the currently-matched tag, if any. * * @since 6.4.0 * * @var WP_HTML_Token|null */ public $current_token = null; /** * Tree construction insertion mode. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#insertion-mode * * @var string */ public $insertion_mode = self::INSERTION_MODE_INITIAL; /** * Context node initializing fragment parser, if created as a fragment parser. * * @since 6.4.0 * @deprecated 6.8.0 WP_HTML_Processor tracks the context_node internally. * * @var null */ public $context_node = null; /** * The recognized encoding of the input byte stream. * * > The stream of code points that comprises the input to the tokenization * > stage will be initially seen by the user agent as a stream of bytes * > (typically coming over the network or from the local file system). * > The bytes encode the actual characters according to a particular character * > encoding, which the user agent uses to decode the bytes into characters. * * @since 6.7.0 * * @var string|null */ public $encoding = null; /** * The parser's confidence in the input encoding. * * > When the HTML parser is decoding an input byte stream, it uses a character * > encoding and a confidence. The confidence is either tentative, certain, or * > irrelevant. The encoding used, and whether the confidence in that encoding * > is tentative or certain, is used during the parsing to determine whether to * > change the encoding. If no encoding is necessary, e.g. because the parser is * > operating on a Unicode stream and doesn't have to use a character encoding * > at all, then the confidence is irrelevant. * * @since 6.7.0 * * @var string */ public $encoding_confidence = 'tentative'; /** * HEAD element pointer. * * @since 6.7.0 * * @see https://html.spec.whatwg.org/multipage/parsing.html#head-element-pointer * * @var WP_HTML_Token|null */ public $head_element = null; /** * FORM element pointer. * * > points to the last form element that was opened and whose end tag has * > not yet been seen. It is used to make form controls associate with * > forms in the face of dramatically bad markup, for historical reasons. * > It is ignored inside template elements. * * @todo This may be invalidated by a seek operation. * * @see https://html.spec.whatwg.org/#form-element-pointer * * @since 6.7.0 * * @var WP_HTML_Token|null */ public $form_element = null; /** * The frameset-ok flag indicates if a `FRAMESET` element is allowed in the current state. * * > The frameset-ok flag is set to "ok" when the parser is created. It is set to "not ok" after certain tokens are seen. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#frameset-ok-flag * * @var bool */ public $frameset_ok = true; /** * Constructor - creates a new and empty state value. * * @since 6.4.0 * * @see WP_HTML_Processor */ public function __construct() { $this->stack_of_open_elements = new WP_HTML_Open_Elements(); $this->active_formatting_elements = new WP_HTML_Active_Formatting_Elements(); } } class-wp-html-token.php000064400000006522152213250460011073 0ustar00bookmark_name = $bookmark_name; $this->namespace = 'html'; $this->node_name = $node_name; $this->has_self_closing_flag = $has_self_closing_flag; $this->on_destroy = $on_destroy; } /** * Destructor. * * @since 6.4.0 */ public function __destruct() { if ( is_callable( $this->on_destroy ) ) { call_user_func( $this->on_destroy, $this->bookmark_name ); } } /** * Wakeup magic method. * * @since 6.4.2 */ public function __wakeup() { throw new \LogicException( __CLASS__ . ' should never be unserialized' ); } } class-wp-html-attribute-token.php000064400000005345152213250460013076 0ustar00 * ------------ length is 12, including quotes * * * ------- length is 6 * * * ------------ length is 11 * * @since 6.5.0 Replaced `end` with `length` to more closely match `substr()`. * * @var int */ public $length; /** * Whether the attribute is a boolean attribute with value `true`. * * @since 6.2.0 * * @var bool */ public $is_true; /** * Constructor. * * @since 6.2.0 * @since 6.5.0 Replaced `end` with `length` to more closely match `substr()`. * * @param string $name Attribute name. * @param int $value_start Attribute value. * @param int $value_length Number of bytes attribute value spans. * @param int $start The string offset where the attribute name starts. * @param int $length Byte length of the entire attribute name or name and value pair expression. * @param bool $is_true Whether the attribute is a boolean attribute with true value. */ public function __construct( $name, $value_start, $value_length, $start, $length, $is_true ) { $this->name = $name; $this->value_starts_at = $value_start; $this->value_length = $value_length; $this->start = $start; $this->length = $length; $this->is_true = $is_true; } } class-wp-html-span.php000064400000002113152213250460010704 0ustar00start = $start; $this->length = $length; } } class-wp-html-unsupported-exception.php000064400000007026152213250460014337 0ustar00token_name = $token_name; $this->token_at = $token_at; $this->token = $token; $this->stack_of_open_elements = $stack_of_open_elements; $this->active_formatting_elements = $active_formatting_elements; } } class-wp-html-open-elements.php000064400000053761152213250460012535 0ustar00 Initially, the stack of open elements is empty. The stack grows * > downwards; the topmost node on the stack is the first one added * > to the stack, and the bottommost node of the stack is the most * > recently added node in the stack (notwithstanding when the stack * > is manipulated in a random access fashion as part of the handling * > for misnested tags). * * @since 6.4.0 * * @access private * @ignore * * @see https://html.spec.whatwg.org/#stack-of-open-elements * @see WP_HTML_Processor */ class WP_HTML_Open_Elements { /** * Holds the stack of open element references. * * @since 6.4.0 * * @var WP_HTML_Token[] */ public $stack = array(); /** * Whether a P element is in button scope currently. * * This class optimizes scope lookup by pre-calculating * this value when elements are added and removed to the * stack of open elements which might change its value. * This avoids frequent iteration over the stack. * * @since 6.4.0 * * @var bool */ private $has_p_in_button_scope = false; /** * A function that will be called when an item is popped off the stack of open elements. * * The function will be called with the popped item as its argument. * * @since 6.6.0 * * @var Closure|null */ private $pop_handler = null; /** * A function that will be called when an item is pushed onto the stack of open elements. * * The function will be called with the pushed item as its argument. * * @since 6.6.0 * * @var Closure|null */ private $push_handler = null; /** * Sets a pop handler that will be called when an item is popped off the stack of * open elements. * * The function will be called with the pushed item as its argument. * * @since 6.6.0 * * @param Closure $handler The handler function. */ public function set_pop_handler( Closure $handler ): void { $this->pop_handler = $handler; } /** * Sets a push handler that will be called when an item is pushed onto the stack of * open elements. * * The function will be called with the pushed item as its argument. * * @since 6.6.0 * * @param Closure $handler The handler function. */ public function set_push_handler( Closure $handler ): void { $this->push_handler = $handler; } /** * Returns the name of the node at the nth position on the stack * of open elements, or `null` if no such position exists. * * Note that this uses a 1-based index, which represents the * "nth item" on the stack, counting from the top, where the * top-most element is the 1st, the second is the 2nd, etc... * * @since 6.7.0 * * @param int $nth Retrieve the nth item on the stack, with 1 being * the top element, 2 being the second, etc... * @return WP_HTML_Token|null Name of the node on the stack at the given location, * or `null` if the location isn't on the stack. */ public function at( int $nth ): ?WP_HTML_Token { foreach ( $this->walk_down() as $item ) { if ( 0 === --$nth ) { return $item; } } return null; } /** * Reports if a node of a given name is in the stack of open elements. * * @since 6.7.0 * * @param string $node_name Name of node for which to check. * @return bool Whether a node of the given name is in the stack of open elements. */ public function contains( string $node_name ): bool { foreach ( $this->walk_up() as $item ) { if ( $node_name === $item->node_name ) { return true; } } return false; } /** * Reports if a specific node is in the stack of open elements. * * @since 6.4.0 * * @param WP_HTML_Token $token Look for this node in the stack. * @return bool Whether the referenced node is in the stack of open elements. */ public function contains_node( WP_HTML_Token $token ): bool { foreach ( $this->walk_up() as $item ) { if ( $token === $item ) { return true; } } return false; } /** * Returns how many nodes are currently in the stack of open elements. * * @since 6.4.0 * * @return int How many node are in the stack of open elements. */ public function count(): int { return count( $this->stack ); } /** * Returns the node at the end of the stack of open elements, * if one exists. If the stack is empty, returns null. * * @since 6.4.0 * * @return WP_HTML_Token|null Last node in the stack of open elements, if one exists, otherwise null. */ public function current_node(): ?WP_HTML_Token { $current_node = end( $this->stack ); return $current_node ? $current_node : null; } /** * Indicates if the current node is of a given type or name. * * It's possible to pass either a node type or a node name to this function. * In the case there is no current element it will always return `false`. * * Example: * * // Is the current node a text node? * $stack->current_node_is( '#text' ); * * // Is the current node a DIV element? * $stack->current_node_is( 'DIV' ); * * // Is the current node any element/tag? * $stack->current_node_is( '#tag' ); * * @see WP_HTML_Tag_Processor::get_token_type * @see WP_HTML_Tag_Processor::get_token_name * * @since 6.7.0 * * @access private * * @param string $identity Check if the current node has this name or type (depending on what is provided). * @return bool Whether there is a current element that matches the given identity, whether a token name or type. */ public function current_node_is( string $identity ): bool { $current_node = end( $this->stack ); if ( false === $current_node ) { return false; } $current_node_name = $current_node->node_name; return ( $current_node_name === $identity || ( '#doctype' === $identity && 'html' === $current_node_name ) || ( '#tag' === $identity && ctype_upper( $current_node_name ) ) ); } /** * Returns whether an element is in a specific scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-the-specific-scope * * @param string $tag_name Name of tag check. * @param string[] $termination_list List of elements that terminate the search. * @return bool Whether the element was found in a specific scope. */ public function has_element_in_specific_scope( string $tag_name, $termination_list ): bool { foreach ( $this->walk_up() as $node ) { $namespaced_name = 'html' === $node->namespace ? $node->node_name : "{$node->namespace} {$node->node_name}"; if ( $namespaced_name === $tag_name ) { return true; } if ( '(internal: H1 through H6 - do not use)' === $tag_name && in_array( $namespaced_name, array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ), true ) ) { return true; } if ( in_array( $namespaced_name, $termination_list, true ) ) { return false; } } return false; } /** * Returns whether a particular element is in scope. * * > The stack of open elements is said to have a particular element in * > scope when it has that element in the specific scope consisting of * > the following element types: * > * > - applet * > - caption * > - html * > - table * > - td * > - th * > - marquee * > - object * > - template * > - MathML mi * > - MathML mo * > - MathML mn * > - MathML ms * > - MathML mtext * > - MathML annotation-xml * > - SVG foreignObject * > - SVG desc * > - SVG title * * @since 6.4.0 * @since 6.7.0 Full support. * * @see https://html.spec.whatwg.org/#has-an-element-in-scope * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_scope( string $tag_name ): bool { return $this->has_element_in_specific_scope( $tag_name, array( 'APPLET', 'CAPTION', 'HTML', 'TABLE', 'TD', 'TH', 'MARQUEE', 'OBJECT', 'TEMPLATE', 'math MI', 'math MO', 'math MN', 'math MS', 'math MTEXT', 'math ANNOTATION-XML', 'svg FOREIGNOBJECT', 'svg DESC', 'svg TITLE', ) ); } /** * Returns whether a particular element is in list item scope. * * > The stack of open elements is said to have a particular element * > in list item scope when it has that element in the specific scope * > consisting of the following element types: * > * > - All the element types listed above for the has an element in scope algorithm. * > - ol in the HTML namespace * > - ul in the HTML namespace * * @since 6.4.0 * @since 6.5.0 Implemented: no longer throws on every invocation. * @since 6.7.0 Supports all required HTML elements. * * @see https://html.spec.whatwg.org/#has-an-element-in-list-item-scope * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_list_item_scope( string $tag_name ): bool { return $this->has_element_in_specific_scope( $tag_name, array( 'APPLET', 'BUTTON', 'CAPTION', 'HTML', 'TABLE', 'TD', 'TH', 'MARQUEE', 'OBJECT', 'OL', 'TEMPLATE', 'UL', 'math MI', 'math MO', 'math MN', 'math MS', 'math MTEXT', 'math ANNOTATION-XML', 'svg FOREIGNOBJECT', 'svg DESC', 'svg TITLE', ) ); } /** * Returns whether a particular element is in button scope. * * > The stack of open elements is said to have a particular element * > in button scope when it has that element in the specific scope * > consisting of the following element types: * > * > - All the element types listed above for the has an element in scope algorithm. * > - button in the HTML namespace * * @since 6.4.0 * @since 6.7.0 Supports all required HTML elements. * * @see https://html.spec.whatwg.org/#has-an-element-in-button-scope * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_button_scope( string $tag_name ): bool { return $this->has_element_in_specific_scope( $tag_name, array( 'APPLET', 'BUTTON', 'CAPTION', 'HTML', 'TABLE', 'TD', 'TH', 'MARQUEE', 'OBJECT', 'TEMPLATE', 'math MI', 'math MO', 'math MN', 'math MS', 'math MTEXT', 'math ANNOTATION-XML', 'svg FOREIGNOBJECT', 'svg DESC', 'svg TITLE', ) ); } /** * Returns whether a particular element is in table scope. * * > The stack of open elements is said to have a particular element * > in table scope when it has that element in the specific scope * > consisting of the following element types: * > * > - html in the HTML namespace * > - table in the HTML namespace * > - template in the HTML namespace * * @since 6.4.0 * @since 6.7.0 Full implementation. * * @see https://html.spec.whatwg.org/#has-an-element-in-table-scope * * @param string $tag_name Name of tag to check. * @return bool Whether given element is in scope. */ public function has_element_in_table_scope( string $tag_name ): bool { return $this->has_element_in_specific_scope( $tag_name, array( 'HTML', 'TABLE', 'TEMPLATE', ) ); } /** * Returns whether a particular element is in select scope. * * This test differs from the others like it, in that its rules are inverted. * Instead of arriving at a match when one of any tag in a termination group * is reached, this one terminates if any other tag is reached. * * > The stack of open elements is said to have a particular element in select scope when it has * > that element in the specific scope consisting of all element types except the following: * > - optgroup in the HTML namespace * > - option in the HTML namespace * * @since 6.4.0 Stub implementation (throws). * @since 6.7.0 Full implementation. * * @see https://html.spec.whatwg.org/#has-an-element-in-select-scope * * @param string $tag_name Name of tag to check. * @return bool Whether the given element is in SELECT scope. */ public function has_element_in_select_scope( string $tag_name ): bool { foreach ( $this->walk_up() as $node ) { if ( $node->node_name === $tag_name ) { return true; } if ( 'OPTION' !== $node->node_name && 'OPTGROUP' !== $node->node_name ) { return false; } } return false; } /** * Returns whether a P is in BUTTON scope. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#has-an-element-in-button-scope * * @return bool Whether a P is in BUTTON scope. */ public function has_p_in_button_scope(): bool { return $this->has_p_in_button_scope; } /** * Pops a node off of the stack of open elements. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#stack-of-open-elements * * @return bool Whether a node was popped off of the stack. */ public function pop(): bool { $item = array_pop( $this->stack ); if ( null === $item ) { return false; } $this->after_element_pop( $item ); return true; } /** * Pops nodes off of the stack of open elements until an HTML tag with the given name has been popped. * * @since 6.4.0 * * @see WP_HTML_Open_Elements::pop * * @param string $html_tag_name Name of tag that needs to be popped off of the stack of open elements. * @return bool Whether a tag of the given name was found and popped off of the stack of open elements. */ public function pop_until( string $html_tag_name ): bool { foreach ( $this->walk_up() as $item ) { $this->pop(); if ( 'html' !== $item->namespace ) { continue; } if ( '(internal: H1 through H6 - do not use)' === $html_tag_name && in_array( $item->node_name, array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ), true ) ) { return true; } if ( $html_tag_name === $item->node_name ) { return true; } } return false; } /** * Pushes a node onto the stack of open elements. * * @since 6.4.0 * * @see https://html.spec.whatwg.org/#stack-of-open-elements * * @param WP_HTML_Token $stack_item Item to add onto stack. */ public function push( WP_HTML_Token $stack_item ): void { $this->stack[] = $stack_item; $this->after_element_push( $stack_item ); } /** * Removes a specific node from the stack of open elements. * * @since 6.4.0 * * @param WP_HTML_Token $token The node to remove from the stack of open elements. * @return bool Whether the node was found and removed from the stack of open elements. */ public function remove_node( WP_HTML_Token $token ): bool { foreach ( $this->walk_up() as $position_from_end => $item ) { if ( $token->bookmark_name !== $item->bookmark_name ) { continue; } $position_from_start = $this->count() - $position_from_end - 1; array_splice( $this->stack, $position_from_start, 1 ); $this->after_element_pop( $item ); return true; } return false; } /** * Steps through the stack of open elements, starting with the top element * (added first) and walking downwards to the one added last. * * This generator function is designed to be used inside a "foreach" loop. * * Example: * * $html = 'We are here'; * foreach ( $stack->walk_down() as $node ) { * echo "{$node->node_name} -> "; * } * > EM -> STRONG -> A -> * * To start with the most-recently added element and walk towards the top, * see WP_HTML_Open_Elements::walk_up(). * * @since 6.4.0 */ public function walk_down() { $count = count( $this->stack ); for ( $i = 0; $i < $count; $i++ ) { yield $this->stack[ $i ]; } } /** * Steps through the stack of open elements, starting with the bottom element * (added last) and walking upwards to the one added first. * * This generator function is designed to be used inside a "foreach" loop. * * Example: * * $html = 'We are here'; * foreach ( $stack->walk_up() as $node ) { * echo "{$node->node_name} -> "; * } * > A -> STRONG -> EM -> * * To start with the first added element and walk towards the bottom, * see WP_HTML_Open_Elements::walk_down(). * * @since 6.4.0 * @since 6.5.0 Accepts $above_this_node to start traversal above a given node, if it exists. * * @param WP_HTML_Token|null $above_this_node Optional. Start traversing above this node, * if provided and if the node exists. */ public function walk_up( ?WP_HTML_Token $above_this_node = null ) { $has_found_node = null === $above_this_node; for ( $i = count( $this->stack ) - 1; $i >= 0; $i-- ) { $node = $this->stack[ $i ]; if ( ! $has_found_node ) { $has_found_node = $node === $above_this_node; continue; } yield $node; } } /* * Internal helpers. */ /** * Updates internal flags after adding an element. * * Certain conditions (such as "has_p_in_button_scope") are maintained here as * flags that are only modified when adding and removing elements. This allows * the HTML Processor to quickly check for these conditions instead of iterating * over the open stack elements upon each new tag it encounters. These flags, * however, need to be maintained as items are added and removed from the stack. * * @since 6.4.0 * * @param WP_HTML_Token $item Element that was added to the stack of open elements. */ public function after_element_push( WP_HTML_Token $item ): void { $namespaced_name = 'html' === $item->namespace ? $item->node_name : "{$item->namespace} {$item->node_name}"; /* * When adding support for new elements, expand this switch to trap * cases where the precalculated value needs to change. */ switch ( $namespaced_name ) { case 'APPLET': case 'BUTTON': case 'CAPTION': case 'HTML': case 'TABLE': case 'TD': case 'TH': case 'MARQUEE': case 'OBJECT': case 'TEMPLATE': case 'math MI': case 'math MO': case 'math MN': case 'math MS': case 'math MTEXT': case 'math ANNOTATION-XML': case 'svg FOREIGNOBJECT': case 'svg DESC': case 'svg TITLE': $this->has_p_in_button_scope = false; break; case 'P': $this->has_p_in_button_scope = true; break; } if ( null !== $this->push_handler ) { call_user_func( $this->push_handler, $item ); } } /** * Updates internal flags after removing an element. * * Certain conditions (such as "has_p_in_button_scope") are maintained here as * flags that are only modified when adding and removing elements. This allows * the HTML Processor to quickly check for these conditions instead of iterating * over the open stack elements upon each new tag it encounters. These flags, * however, need to be maintained as items are added and removed from the stack. * * @since 6.4.0 * * @param WP_HTML_Token $item Element that was removed from the stack of open elements. */ public function after_element_pop( WP_HTML_Token $item ): void { /* * When adding support for new elements, expand this switch to trap * cases where the precalculated value needs to change. */ switch ( $item->node_name ) { case 'APPLET': case 'BUTTON': case 'CAPTION': case 'HTML': case 'P': case 'TABLE': case 'TD': case 'TH': case 'MARQUEE': case 'OBJECT': case 'TEMPLATE': case 'math MI': case 'math MO': case 'math MN': case 'math MS': case 'math MTEXT': case 'math ANNOTATION-XML': case 'svg FOREIGNOBJECT': case 'svg DESC': case 'svg TITLE': $this->has_p_in_button_scope = $this->has_element_in_button_scope( 'P' ); break; } if ( null !== $this->pop_handler ) { call_user_func( $this->pop_handler, $item ); } } /** * Clear the stack back to a table context. * * > 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, template, or html element, pop * > elements from the stack of open elements. * * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-stack-back-to-a-table-context * * @since 6.7.0 */ public function clear_to_table_context(): void { foreach ( $this->walk_up() as $item ) { if ( 'TABLE' === $item->node_name || 'TEMPLATE' === $item->node_name || 'HTML' === $item->node_name ) { break; } $this->pop(); } } /** * Clear the stack back to a table body context. * * > When the steps above require the UA to clear the stack back to a table body context, it * > means that the UA must, while the current node is not a tbody, tfoot, thead, template, or * > html element, pop elements from the stack of open elements. * * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-stack-back-to-a-table-body-context * * @since 6.7.0 */ public function clear_to_table_body_context(): void { foreach ( $this->walk_up() as $item ) { if ( 'TBODY' === $item->node_name || 'TFOOT' === $item->node_name || 'THEAD' === $item->node_name || 'TEMPLATE' === $item->node_name || 'HTML' === $item->node_name ) { break; } $this->pop(); } } /** * Clear the stack back to a table row context. * * > When the steps above require the UA to clear the stack back to a table row context, it * > means that the UA must, while the current node is not a tr, template, or html element, pop * > elements from the stack of open elements. * * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-stack-back-to-a-table-row-context * * @since 6.7.0 */ public function clear_to_table_row_context(): void { foreach ( $this->walk_up() as $item ) { if ( 'TR' === $item->node_name || 'TEMPLATE' === $item->node_name || 'HTML' === $item->node_name ) { break; } $this->pop(); } } /** * Wakeup magic method. * * @since 6.6.0 */ public function __wakeup() { throw new \LogicException( __CLASS__ . ' should never be unserialized' ); } } class-wp-html-processor.php000064400000644644152213250460012007 0ustar00next_tag( array( 'breadcrumbs' => array( 'DIV', 'FIGURE', 'IMG' ) ) ) ) { * $processor->add_class( 'responsive-image' ); * } * * #### Breadcrumbs * * Breadcrumbs represent the stack of open elements from the root * of the document or fragment down to the currently-matched node, * if one is currently selected. Call WP_HTML_Processor::get_breadcrumbs() * to inspect the breadcrumbs for a matched tag. * * Breadcrumbs can specify nested HTML structure and are equivalent * to a CSS selector comprising tag names separated by the child * combinator, such as "DIV > FIGURE > IMG". * * Since all elements find themselves inside a full HTML document * when parsed, the return value from `get_breadcrumbs()` will always * contain any implicit outermost elements. For example, when parsing * with `create_fragment()` in the `BODY` context (the default), any * tag in the given HTML document will contain `array( 'HTML', 'BODY', … )` * in its breadcrumbs. * * Despite containing the implied outermost elements in their breadcrumbs, * tags may be found with the shortest-matching breadcrumb query. That is, * `array( 'IMG' )` matches all IMG elements and `array( 'P', 'IMG' )` * matches all IMG elements directly inside a P element. To ensure that no * partial matches erroneously match it's possible to specify in a query * the full breadcrumb match all the way down from the root HTML element. * * Example: * * $html = '
A lovely day outside
'; * // ----- Matches here. * $processor->next_tag( array( 'breadcrumbs' => array( 'FIGURE', 'IMG' ) ) ); * * $html = '
A lovely day outside
'; * // ---- Matches here. * $processor->next_tag( array( 'breadcrumbs' => array( 'FIGURE', 'FIGCAPTION', 'EM' ) ) ); * * $html = '
'; * // ----- Matches here, because IMG must be a direct child of the implicit BODY. * $processor->next_tag( array( 'breadcrumbs' => array( 'BODY', 'IMG' ) ) ); * * ## HTML Support * * This class implements a small part of the HTML5 specification. * It's designed to operate within its support and abort early whenever * encountering circumstances it can't properly handle. This is * the principle way in which this class remains as simple as possible * without cutting corners and breaking compliance. * * ### Supported elements * * If any unsupported element appears in the HTML input the HTML Processor * will abort early and stop all processing. This draconian measure ensures * that the HTML Processor won't break any HTML it doesn't fully understand. * * The HTML Processor supports all elements other than a specific set: * * - Any element inside a TABLE. * - Any element inside foreign content, including SVG and MATH. * - Any element outside the IN BODY insertion mode, e.g. doctype declarations, meta, links. * * ### Supported markup * * Some kinds of non-normative HTML involve reconstruction of formatting elements and * re-parenting of mis-nested elements. For example, a DIV tag found inside a TABLE * may in fact belong _before_ the table in the DOM. If the HTML Processor encounters * such a case it will stop processing. * * The following list illustrates some common examples of unexpected HTML inputs that * the HTML Processor properly parses and represents: * * - HTML with optional tags omitted, e.g. `

one

two`. * - HTML with unexpected tag closers, e.g. `

one more

`. * - Non-void tags with self-closing flag, e.g. `
the DIV is still open.
`. * - Heading elements which close open heading elements of another level, e.g. `

Closed by

`. * - Elements containing text that looks like other tags but isn't, e.g. `The <img> is plaintext`. * - SCRIPT and STYLE tags containing text that looks like HTML but isn't, e.g. ``. * - SCRIPT content which has been escaped, e.g. ``. * * ### Unsupported Features * * This parser does not report parse errors. * * Normally, when additional HTML or BODY tags are encountered in a document, if there * are any additional attributes on them that aren't found on the previous elements, * the existing HTML and BODY elements adopt those missing attribute values. This * parser does not add those additional attributes. * * In certain situations, elements are moved to a different part of the document in * a process called "adoption" and "fostering." Because the nodes move to a location * in the document that the parser had already processed, this parser does not support * these situations and will bail. * * @since 6.4.0 * * @see WP_HTML_Tag_Processor * @see https://html.spec.whatwg.org/ * @phpstan-consistent-constructor */ class WP_HTML_Processor extends WP_HTML_Tag_Processor { /** * The maximum number of bookmarks allowed to exist at any given time. * * HTML processing requires more bookmarks than basic tag processing, * so this class constant from the Tag Processor is overwritten. * * @since 6.4.0 * @since 7.0.0 Increased from 100 to 10,000 * * @var int */ const MAX_BOOKMARKS = 10_000; /** * Holds the working state of the parser, including the stack of * open elements and the stack of active formatting elements. * * Initialized in the constructor. * * @since 6.4.0 * * @var WP_HTML_Processor_State */ private $state; /** * Used to create unique bookmark names. * * This class sets a bookmark for every tag in the HTML document that it encounters. * The bookmark name is auto-generated and increments, starting with `1`. These are * internal bookmarks and are automatically released when the referring WP_HTML_Token * goes out of scope and is garbage-collected. * * @since 6.4.0 * * @see WP_HTML_Processor::$release_internal_bookmark_on_destruct * * @var int */ private $bookmark_counter = 0; /** * Stores an explanation for why something failed, if it did. * * @see self::get_last_error * * @since 6.4.0 * * @var string|null */ private $last_error = null; /** * Stores context for why the parser bailed on unsupported HTML, if it did. * * @see self::get_unsupported_exception * * @since 6.7.0 * * @var WP_HTML_Unsupported_Exception|null */ private $unsupported_exception = null; /** * Releases a bookmark when PHP garbage-collects its wrapping WP_HTML_Token instance. * * This function is created inside the class constructor so that it can be passed to * the stack of open elements and the stack of active formatting elements without * exposing it as a public method on the class. * * @since 6.4.0 * * @var Closure|null */ private $release_internal_bookmark_on_destruct = null; /** * Stores stack events which arise during parsing of the * HTML document, which will then supply the "match" events. * * @since 6.6.0 * * @var WP_HTML_Stack_Event[] */ private $element_queue = array(); /** * Stores the current breadcrumbs. * * @since 6.7.0 * * @var string[] */ private $breadcrumbs = array(); /** * Current stack event, if set, representing a matched token. * * Because the parser may internally point to a place further along in a document * than the nodes which have already been processed (some "virtual" nodes may have * appeared while scanning the HTML document), this will point at the "current" node * being processed. It comes from the front of the element queue. * * @since 6.6.0 * * @var WP_HTML_Stack_Event|null */ private $current_element = null; /** * Context node if created as a fragment parser. * * @var WP_HTML_Token|null */ private $context_node = null; /* * Public Interface Functions */ /** * Creates an HTML processor in the fragment parsing mode. * * Use this for cases where you are processing chunks of HTML that * will be found within a bigger HTML document, such as rendered * block output that exists within a post, `the_content` inside a * rendered site layout. * * Fragment parsing occurs within a context, which is an HTML element * that the document will eventually be placed in. It becomes important * when special elements have different rules than others, such as inside * a TEXTAREA or a TITLE tag where things that look like tags are text, * or inside a SCRIPT tag where things that look like HTML syntax are JS. * * The context value should be a representation of the tag into which the * HTML is found. For most cases this will be the body element. The HTML * form is provided because a context element may have attributes that * impact the parse, such as with a SCRIPT tag and its `type` attribute. * * ## Current HTML Support * * - The only supported context is ``, which is the default value. * - The only supported document encoding is `UTF-8`, which is the default value. * * @since 6.4.0 * @since 6.6.0 Returns `static` instead of `self` so it can create subclass instances. * * @param string $html Input HTML fragment to process. * @param string $context Context element for the fragment, must be default of ``. * @param string $encoding Text encoding of the document; must be default of 'UTF-8'. * @return static|null The created processor if successful, otherwise null. */ public static function create_fragment( $html, $context = '', $encoding = 'UTF-8' ) { if ( '' !== $context || 'UTF-8' !== $encoding ) { return null; } if ( ! is_string( $html ) ) { _doing_it_wrong( __METHOD__, __( 'The HTML parameter must be a string.' ), '6.9.0' ); return null; } $context_processor = static::create_full_parser( "{$context}", $encoding ); if ( null === $context_processor ) { return null; } while ( $context_processor->next_tag() ) { if ( ! $context_processor->is_virtual() ) { $context_processor->set_bookmark( 'final_node' ); } } if ( ! $context_processor->has_bookmark( 'final_node' ) || ! $context_processor->seek( 'final_node' ) ) { _doing_it_wrong( __METHOD__, __( 'No valid context element was detected.' ), '6.8.0' ); return null; } return $context_processor->create_fragment_at_current_node( $html ); } /** * Creates an HTML processor in the full parsing mode. * * It's likely that a fragment parser is more appropriate, unless sending an * entire HTML document from start to finish. Consider a fragment parser with * a context node of ``. * * UTF-8 is the only allowed encoding. If working with a document that * isn't UTF-8, first convert the document to UTF-8, then pass in the * converted HTML. * * @param string $html Input HTML document to process. * @param string|null $known_definite_encoding Optional. If provided, specifies the charset used * in the input byte stream. Currently must be UTF-8. * @return static|null The created processor if successful, otherwise null. */ public static function create_full_parser( $html, $known_definite_encoding = 'UTF-8' ) { if ( 'UTF-8' !== $known_definite_encoding ) { return null; } if ( ! is_string( $html ) ) { _doing_it_wrong( __METHOD__, __( 'The HTML parameter must be a string.' ), '6.9.0' ); return null; } $processor = new static( $html, self::CONSTRUCTOR_UNLOCK_CODE ); $processor->state->encoding = $known_definite_encoding; $processor->state->encoding_confidence = 'certain'; return $processor; } /** * Constructor. * * Do not use this method. Use the static creator methods instead. * * @access private * * @since 6.4.0 * * @see WP_HTML_Processor::create_fragment() * * @param string $html HTML to process. * @param string|null $use_the_static_create_methods_instead This constructor should not be called manually. */ public function __construct( $html, $use_the_static_create_methods_instead = null ) { parent::__construct( $html ); if ( self::CONSTRUCTOR_UNLOCK_CODE !== $use_the_static_create_methods_instead ) { _doing_it_wrong( __METHOD__, sprintf( /* translators: %s: WP_HTML_Processor::create_fragment(). */ __( 'Call %s to create an HTML Processor instead of calling the constructor directly.' ), 'WP_HTML_Processor::create_fragment()' ), '6.4.0' ); } $this->state = new WP_HTML_Processor_State(); $this->state->stack_of_open_elements->set_push_handler( function ( WP_HTML_Token $token ): void { $is_virtual = ! isset( $this->state->current_token ) || $this->is_tag_closer(); $same_node = isset( $this->state->current_token ) && $token->node_name === $this->state->current_token->node_name; $provenance = ( ! $same_node || $is_virtual ) ? 'virtual' : 'real'; $this->element_queue[] = new WP_HTML_Stack_Event( $token, WP_HTML_Stack_Event::PUSH, $provenance ); $this->change_parsing_namespace( $token->integration_node_type ? 'html' : $token->namespace ); } ); $this->state->stack_of_open_elements->set_pop_handler( function ( WP_HTML_Token $token ): void { $is_virtual = ! isset( $this->state->current_token ) || ! $this->is_tag_closer(); $same_node = isset( $this->state->current_token ) && $token->node_name === $this->state->current_token->node_name; $provenance = ( ! $same_node || $is_virtual ) ? 'virtual' : 'real'; $this->element_queue[] = new WP_HTML_Stack_Event( $token, WP_HTML_Stack_Event::POP, $provenance ); $adjusted_current_node = $this->get_adjusted_current_node(); if ( $adjusted_current_node ) { $this->change_parsing_namespace( $adjusted_current_node->integration_node_type ? 'html' : $adjusted_current_node->namespace ); } else { $this->change_parsing_namespace( 'html' ); } } ); /* * Create this wrapper so that it's possible to pass * a private method into WP_HTML_Token classes without * exposing it to any public API. */ $this->release_internal_bookmark_on_destruct = function ( string $name ): void { parent::release_bookmark( $name ); }; } /** * Creates a fragment processor at the current node. * * HTML Fragment parsing always happens with a context node. HTML Fragment Processors can be * instantiated with a `BODY` context node via `WP_HTML_Processor::create_fragment( $html )`. * * The context node may impact how a fragment of HTML is parsed. For example, consider the HTML * fragment `Inside TD?`. * * A BODY context node will produce the following tree: * * └─#text Inside TD? * * Notice that the `` tags are completely ignored. * * Compare that with an SVG context node that produces the following tree: * * ├─svg:td * └─#text Inside TD? * * Here, a `td` node in the `svg` namespace is created, and its self-closing flag is respected. * This is a peculiarity of parsing HTML in foreign content like SVG. * * Finally, consider the tree produced with a TABLE context node: * * └─TBODY * └─TR * └─TD * └─#text Inside TD? * * These examples demonstrate how important the context node may be when processing an HTML * fragment. Special care must be taken when processing fragments that are expected to appear * in specific contexts. SVG and TABLE are good examples, but there are others. * * @see https://html.spec.whatwg.org/multipage/parsing.html#html-fragment-parsing-algorithm * * @since 6.8.0 * * @param string $html Input HTML fragment to process. * @return static|null The created processor if successful, otherwise null. */ private function create_fragment_at_current_node( string $html ) { if ( $this->get_token_type() !== '#tag' || $this->is_tag_closer() ) { _doing_it_wrong( __METHOD__, __( 'The context element must be a start tag.' ), '6.8.0' ); return null; } $tag_name = $this->current_element->token->node_name; $namespace = $this->current_element->token->namespace; if ( 'html' === $namespace && self::is_void( $tag_name ) ) { _doing_it_wrong( __METHOD__, sprintf( // translators: %s: A tag name like INPUT or BR. __( 'The context element cannot be a void element, found "%s".' ), $tag_name ), '6.8.0' ); return null; } /* * Prevent creating fragments at nodes that require a special tokenizer state. * This is unsupported by the HTML Processor. */ if ( 'html' === $namespace && in_array( $tag_name, array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP', 'PLAINTEXT' ), true ) ) { _doing_it_wrong( __METHOD__, sprintf( // translators: %s: A tag name like IFRAME or TEXTAREA. __( 'The context element "%s" is not supported.' ), $tag_name ), '6.8.0' ); return null; } $fragment_processor = new static( $html, self::CONSTRUCTOR_UNLOCK_CODE ); $fragment_processor->compat_mode = $this->compat_mode; // @todo Create "fake" bookmarks for non-existent but implied nodes. $fragment_processor->bookmarks['root-node'] = new WP_HTML_Span( 0, 0 ); $root_node = new WP_HTML_Token( 'root-node', 'HTML', false ); $fragment_processor->state->stack_of_open_elements->push( $root_node ); $fragment_processor->bookmarks['context-node'] = new WP_HTML_Span( 0, 0 ); $fragment_processor->context_node = clone $this->current_element->token; $fragment_processor->context_node->bookmark_name = 'context-node'; $fragment_processor->context_node->on_destroy = null; $fragment_processor->breadcrumbs = array( 'HTML', $fragment_processor->context_node->node_name ); if ( 'TEMPLATE' === $fragment_processor->context_node->node_name ) { $fragment_processor->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE; } $fragment_processor->reset_insertion_mode_appropriately(); /* * > Set the parser's form element pointer to the nearest node to the context element that * > is a form element (going straight up the ancestor chain, and including the element * > itself, if it is a form element), if any. (If there is no such form element, the * > form element pointer keeps its initial value, null.) */ foreach ( $this->state->stack_of_open_elements->walk_up() as $element ) { if ( 'FORM' === $element->node_name && 'html' === $element->namespace ) { $fragment_processor->state->form_element = clone $element; $fragment_processor->state->form_element->bookmark_name = null; $fragment_processor->state->form_element->on_destroy = null; break; } } $fragment_processor->state->encoding_confidence = 'irrelevant'; /* * Update the parsing namespace near the end of the process. * This is important so that any push/pop from the stack of open * elements does not change the parsing namespace. */ $fragment_processor->change_parsing_namespace( $this->current_element->token->integration_node_type ? 'html' : $namespace ); return $fragment_processor; } /** * Stops the parser and terminates its execution when encountering unsupported markup. * * @throws WP_HTML_Unsupported_Exception Halts execution of the parser. * * @since 6.7.0 * @ignore * * @param string $message Explains support is missing in order to parse the current node. * @return never */ private function bail( string $message ) { $here = $this->bookmarks[ $this->state->current_token->bookmark_name ]; $token = substr( $this->html, $here->start, $here->length ); $open_elements = array(); foreach ( $this->state->stack_of_open_elements->stack as $item ) { $open_elements[] = $item->node_name; } $active_formats = array(); foreach ( $this->state->active_formatting_elements->walk_down() as $item ) { $active_formats[] = $item->node_name; } $this->last_error = self::ERROR_UNSUPPORTED; $this->unsupported_exception = new WP_HTML_Unsupported_Exception( $message, $this->state->current_token->node_name, $here->start, $token, $open_elements, $active_formats ); throw $this->unsupported_exception; } /** * Returns the last error, if any. * * Various situations lead to parsing failure but this class will * return `false` in all those cases. To determine why something * failed it's possible to request the last error. This can be * helpful to know to distinguish whether a given tag couldn't * be found or if content in the document caused the processor * to give up and abort processing. * * Example * * $processor = WP_HTML_Processor::create_fragment( '