| 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 * * @param string $message Explains support is missing in order to parse the current node. */ 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( ' |