From 44629e628672a77edb1d3100546b458973854015 Mon Sep 17 00:00:00 2001 From: Bernhard Reiter Date: Thu, 20 Jul 2023 13:43:25 +0000 Subject: [PATCH] HTML-API: Introduce minimal HTML Processor. This patch introduces the //first// of //many// iterations on the evolution of the HTML API, the HTML Processor, which is built in order to understand HTML structure including nesting, misnesting, and complicated semantic rules. In the first iteration, the HTML Processor is arbitrarily limited to a minimal subset of functionality so that we can review it, ship it, test it, and collect feedback before moving forward. This means that this patch is more or less an extension to the Tag Processor query language, providing the ability not only to scan for a tag of a given name, but also to find an HTML element in a specific nesting path. The HTML Processor also aborts any time it encounters: - a tag that isn't a `P`, `DIV`, `FIGURE`, `FIGCAPTION`, `IMG`, `STRONG`, `B`, `EM`, `I`, `A`, `BIG`, `CODE`, `FONT`, `SMALL`, `STRIKE`, `TT`, or `U` tag. this limit exists because many HTML elements require specific rules and we are trying to limit the number of rules introduced at once. this work is targeted at existing work in places like the image block. - certain misnesting constructs that evoke complicated resolution inside the HTML spec. where possible and where simple to do reliably, certain parse errors are handled. in most cases the HTML Processor aborts. The structure of the HTML Processor is established in this patch. Further spec-compliance comes through filling out //more of the same// kind and nature of code as is found in this patch. Certain critical HTML algorithms are partially supported, and where support requires more than is present, the HTML Processor acknowledges this and refuses to operate. In this patch are explorations for how to verify that new HTML support is fully added (instead of allowing for partial updates that leave some code paths non-compliant). Performance is hard to measure since support is so limited at the current time, but it should generally follow the performance of the Tag Processor somewhat close as the overhead is minimized as much as practical. Props dmsnell, zieladam, costdev. Fixes #58517. Built from https://develop.svn.wordpress.org/trunk@56274 git-svn-id: http://core.svn.wordpress.org/trunk@55786 1a063a9b-81f0-0310-95a4-ce76da25c4cd --- ...ass-wp-html-active-formatting-elements.php | 188 +++ .../html-api/class-wp-html-open-elements.php | 413 ++++++ .../class-wp-html-processor-state.php | 121 ++ .../html-api/class-wp-html-processor.php | 1266 +++++++++++++++++ .../html-api/class-wp-html-tag-processor.php | 8 +- wp-includes/html-api/class-wp-html-token.php | 95 ++ .../class-wp-html-unsupported-exception.php | 31 + wp-includes/version.php | 2 +- wp-settings.php | 6 + 9 files changed, 2125 insertions(+), 5 deletions(-) create mode 100644 wp-includes/html-api/class-wp-html-active-formatting-elements.php create mode 100644 wp-includes/html-api/class-wp-html-open-elements.php create mode 100644 wp-includes/html-api/class-wp-html-processor-state.php create mode 100644 wp-includes/html-api/class-wp-html-processor.php create mode 100644 wp-includes/html-api/class-wp-html-token.php create mode 100644 wp-includes/html-api/class-wp-html-unsupported-exception.php diff --git a/wp-includes/html-api/class-wp-html-active-formatting-elements.php b/wp-includes/html-api/class-wp-html-active-formatting-elements.php new file mode 100644 index 0000000000..73831e9f36 --- /dev/null +++ b/wp-includes/html-api/class-wp-html-active-formatting-elements.php @@ -0,0 +1,188 @@ + Initially, the list of active formatting elements is empty. + * > It is used to handle mis-nested formatting element tags. + * > + * > The list contains elements in the formatting category, and markers. + * > The markers are inserted when entering applet, object, marquee, + * > template, td, th, and caption elements, and are used to prevent + * > formatting from "leaking" into applet, object, marquee, template, + * > td, th, and caption elements. + * > + * > In addition, each element in the list of active formatting elements + * > is associated with the token for which it was created, so that + * > further elements can be created for that token if necessary. + * + * @since 6.4.0 + * + * @access private + * + * @see https://html.spec.whatwg.org/#list-of-active-formatting-elements + * @see WP_HTML_Processor + */ +class WP_HTML_Active_Formatting_Elements { + /** + * Holds the stack of active formatting element references. + * + * @since 6.4.0 + * + * @var WP_HTML_Token[] + */ + private $stack = array(); + + /** + * Reports if a specific node is in the stack of active formatting 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 active formatting elements. + * + */ + public function contains_node( $token ) { + foreach ( $this->walk_up() as $item ) { + if ( $token->bookmark_name === $item->bookmark_name ) { + return true; + } + } + + return false; + } + + /** + * Returns how many nodes are currently in the stack of active formatting elements. + * + * @since 6.4.0 + * + * @return int How many node are in the stack of active formatting elements. + */ + public function count() { + return count( $this->stack ); + } + + /** + * Returns the node at the end of the stack of active formatting 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 active formatting elements, if one exists, otherwise null. + */ + public function current_node() { + $current_node = end( $this->stack ); + + return $current_node ? $current_node : null; + } + + /** + * Pushes a node onto the stack of active formatting elements. + * + * @since 6.4.0 + * + * @see https://html.spec.whatwg.org/#push-onto-the-list-of-active-formatting-elements + * + * @param WP_HTML_Token $token Push this node onto the stack. + */ + public function push( $token ) { + /* + * > If there are already three elements in the list of active formatting elements after the last marker, + * > if any, or anywhere in the list if there are no markers, that have the same tag name, namespace, and + * > attributes as element, then remove the earliest such element from the list of active formatting + * > elements. For these purposes, the attributes must be compared as they were when the elements were + * > created by the parser; two elements have the same attributes if all their parsed attributes can be + * > paired such that the two attributes in each pair have identical names, namespaces, and values + * > (the order of the attributes does not matter). + * + * @TODO: Implement the "Noah's Ark clause" to only add up to three of any given kind of formatting elements to the stack. + */ + // > Add element to the list of active formatting elements. + $this->stack[] = $token; + } + + /** + * Removes a node from the stack of active formatting elements. + * + * @since 6.4.0 + * + * @param WP_HTML_Token $token Remove this node from the stack, if it's there already. + * @return bool Whether the node was found and removed from the stack of active formatting elements. + */ + public function remove_node( $token ) { + 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 ); + return true; + } + + return false; + } + + /** + * Steps through the stack of active formatting 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_Active_Formatting_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 active formatting 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_Active_Formatting_Elements::walk_down + * + * @since 6.4.0 + */ + public function walk_up() { + for ( $i = count( $this->stack ) - 1; $i >= 0; $i-- ) { + yield $this->stack[ $i ]; + } + } +} diff --git a/wp-includes/html-api/class-wp-html-open-elements.php b/wp-includes/html-api/class-wp-html-open-elements.php new file mode 100644 index 0000000000..fabac341c6 --- /dev/null +++ b/wp-includes/html-api/class-wp-html-open-elements.php @@ -0,0 +1,413 @@ + 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 + * + * @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; + + /** + * 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( $token ) { + foreach ( $this->walk_up() as $item ) { + if ( $token->bookmark_name === $item->bookmark_name ) { + 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() { + 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() { + $current_node = end( $this->stack ); + + return $current_node ? $current_node : null; + } + + /** + * Returns whether an element is in a specific scope. + * + * ## HTML Support + * + * This function skips checking for the termination list because there + * are no supported elements which appear in the termination list. + * + * @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( $tag_name, $termination_list ) { + foreach ( $this->walk_up() as $node ) { + if ( $node->node_name === $tag_name ) { + return true; + } + } + + return false; + } + + /** + * Returns whether a particular element is in scope. + * + * @since 6.4.0 + * + * @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( $tag_name ) { + return $this->has_element_in_specific_scope( + $tag_name, + array( + /* + * Because it's not currently possible to encounter + * one of the termination elements, they don't need + * to be listed here. If they were, they would be + * unreachable and only waste CPU cycles while + * scanning through HTML. + */ + ) + ); + } + + /** + * Returns whether a particular element is in list item scope. + * + * @since 6.4.0 + * + * @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( $tag_name ) { + throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on list item scope.' ); + } + + /** + * Returns whether a particular element is in button scope. + * + * @since 6.4.0 + * + * @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( $tag_name ) { + return $this->has_element_in_specific_scope( + $tag_name, + array( + /* + * Because it's not currently possible to encounter + * one of the termination elements, they don't need + * to be listed here. If they were, they would be + * unreachable and only waste CPU cycles while + * scanning through HTML. + */ + ) + ); + } + + /** + * Returns whether a particular element is in table scope. + * + * @since 6.4.0 + * + * @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( $tag_name ) { + throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on table scope.' ); + } + + /** + * Returns whether a particular element is in select scope. + * + * @since 6.4.0 + * + * @see https://html.spec.whatwg.org/#has-an-element-in-select-scope + * + * @param string $tag_name Name of tag to check. + * @return bool Whether given element is in scope. + */ + public function has_element_in_select_scope( $tag_name ) { + throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on select scope.' ); + } + + /** + * 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 + */ + public function has_p_in_button_scope() { + 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() { + $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 one with the given tag name has been popped. + * + * @since 6.4.0 + * + * @see WP_HTML_Open_Elements::pop + * + * @param string $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( $tag_name ) { + foreach ( $this->walk_up() as $item ) { + $this->pop(); + + if ( $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( $stack_item ) { + $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( $token ) { + 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 + */ + public function walk_up() { + for ( $i = count( $this->stack ) - 1; $i >= 0; $i-- ) { + yield $this->stack[ $i ]; + } + } + + /* + * 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( $item ) { + /* + * When adding support for new elements, expand this switch to trap + * cases where the precalculated value needs to change. + */ + switch ( $item->node_name ) { + case 'P': + $this->has_p_in_button_scope = true; + break; + } + } + + /** + * 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( $item ) { + /* + * When adding support for new elements, expand this switch to trap + * cases where the precalculated value needs to change. + */ + switch ( $item->node_name ) { + case 'P': + $this->has_p_in_button_scope = $this->has_element_in_button_scope( 'P' ); + break; + } + } +} diff --git a/wp-includes/html-api/class-wp-html-processor-state.php b/wp-includes/html-api/class-wp-html-processor-state.php new file mode 100644 index 0000000000..b9fa53d0bd --- /dev/null +++ b/wp-includes/html-api/class-wp-html-processor-state.php @@ -0,0 +1,121 @@ +stack_of_open_elements = new WP_HTML_Open_Elements(); + $this->active_formatting_elements = new WP_HTML_Active_Formatting_Elements(); + } +} diff --git a/wp-includes/html-api/class-wp-html-processor.php b/wp-includes/html-api/class-wp-html-processor.php new file mode 100644 index 0000000000..68bd3418f2 --- /dev/null +++ b/wp-includes/html-api/class-wp-html-processor.php @@ -0,0 +1,1266 @@ +next_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 {@see 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 `createFragment()` 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. + * + * 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', 'IMG', '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 following list specifies the HTML tags that _are_ supported: + * + * - Links: A. + * - The formatting elements: B, BIG, CODE, EM, FONT, I, SMALL, STRIKE, STRONG, TT, U. + * - Containers: DIV, FIGCAPTION, FIGURE. + * - Paragraph: P. + * - Void elements: IMG. + * + * ### 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 specifies HTML markup that _is_ supported: + * + * - Markup involving only those tags listed above. + * - Fully-balanced and non-overlapping tags. + * - HTML with unexpected tag closers. + * - P tags after unclosed P tags. + * - A tags after unclosed A tags that don't involve any active formatting elements. + * + * @since 6.4.0 + * + * @see https://html.spec.whatwg.org/ + */ +class WP_HTML_Processor extends WP_HTML_Tag_Processor { + /** + * HTML processing requires more bookmarks than basic tag processing. + * + * @since 6.4.0 + * + * @var int + */ + const MAX_BOOKMARKS = 100; + + /** + * Static query for instructing the Tag Processor to visit every token. + * + * @since 6.4.0 + * + * @var array + */ + const VISIT_EVERYTHING = array( 'tag_closers' => 'visit' ); + + /** + * 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 = null; + + /** + * Used to create unique bookmark names. + * + * @since 6.4.0 + * + * @var int + */ + private $bookmark_counter = 0; + + /** + * Refers to the currently-matched tag, if any. + * + * @since 6.4.0 + * + * @var WP_HTML_Token|null + */ + private $current_token = null; + + /** + * 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; + + /** + * 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 + */ + private $release_internal_bookmark = 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 + * + * @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 WP_HTML_Processor|null The created processor if successful, otherwise null. + */ + public static function createFragment( $html, $context = '', $encoding = 'UTF-8' ) { + if ( '' !== $context ) { + return null; + } + + $p = new self( $html, self::CONSTRUCTOR_UNLOCK_CODE ); + $p->state->context_node = array( 'BODY', array() ); + $p->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_BODY; + + // @TODO: Create "fake" bookmarks for non-existent but implied nodes. + $p->bookmarks['root-node'] = new WP_HTML_Span( 0, 0 ); + $p->bookmarks['context-node'] = new WP_HTML_Span( 0, 0 ); + + $p->state->stack_of_open_elements->push( + new WP_HTML_Token( + 'root-node', + 'HTML', + false + ) + ); + + $p->state->stack_of_open_elements->push( + new WP_HTML_Token( + 'context-node', + $p->state->context_node[0], + false + ) + ); + + return $p; + } + + /** + * Constructor. + * + * @access private + * + * @since 6.4.0 + * + * @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::createFragment. */ + __( 'Call %s to create an HTML Processor instead of calling the constructor directly.' ), + 'WP_HTML_Processor::createFragment' + ), + '6.4.0' + ); + } + + $this->state = new WP_HTML_Processor_State(); + + /* + * 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 = function ( $name ) { + parent::release_bookmark( $name ); + }; + } + + /** + * 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 if it's possible to fix something or to give up. + * + * Example + * + * $p = WP_HTML_Processor::createFragment( '