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( '