diff --git a/src/wp-includes/html-api/class-wp-html-processor.php b/src/wp-includes/html-api/class-wp-html-processor.php
index 28e5c150a8635..ed68efc52979c 100644
--- a/src/wp-includes/html-api/class-wp-html-processor.php
+++ b/src/wp-includes/html-api/class-wp-html-processor.php
@@ -422,6 +422,55 @@ function ( WP_HTML_Token $token ): void {
};
}
+ /**
+ * Creates a fragment processor with the current node as its context element.
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#html-fragment-parsing-algorithm
+ *
+ * @param string $html Input HTML fragment to process.
+ * @return static|null The created processor if successful, otherwise null.
+ */
+ private function spawn_fragment_parser( string $html ): ?self {
+ if ( $this->get_token_type() !== '#tag' ) {
+ return null;
+ }
+
+ /*
+ * Prevent creating fragments at "self-contained" nodes.
+ *
+ * @see https://github.com/WordPress/wordpress-develop/pull/7141
+ * @see https://github.com/WordPress/wordpress-develop/pull/7198
+ */
+ if (
+ 'html' === $this->get_namespace() &&
+ in_array( $this->get_tag(), array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true )
+ ) {
+ return null;
+ }
+
+ $fragment_processor = self::create_fragment( $html );
+ $fragment_processor->compat_mode = $this->compat_mode;
+
+ // @todo The context element probably needs a namespace{
+ $context_element = array( $this->get_tag(), array() );
+ foreach ( $this->get_attribute_names_with_prefix( '' ) as $name => $value ) {
+ $context_element[1][ $name ] = $value;
+ }
+ $fragment_processor->state->context_node = $context_element;
+
+ if ( 'TEMPLATE' === $context_element[0] ) {
+ $fragment_processor->state->stack_of_template_insertion_modes[] = WP_HTML_Processor_State::INSERTION_MODE_IN_TEMPLATE;
+ }
+
+ $fragment_processor->reset_insertion_mode_appropriately();
+
+ // @todo Set the parser's form element pointer.
+
+ $fragment_processor->state->encoding_confidence = 'irrelevant';
+
+ return $fragment_processor;
+ }
+
/**
* Stops the parser and terminates its execution when encountering unsupported markup.
*
@@ -5020,6 +5069,158 @@ public function get_comment_type(): ?string {
return $this->is_virtual() ? null : parent::get_comment_type();
}
+ /**
+ * Normalize an HTML string by serializing it.
+ *
+ * This removes any partial syntax at the end of the string.
+ *
+ * @since 6.7.0
+ *
+ * @param string $html Input HTML to normalize.
+ *
+ * @return string|null Normalized output, or `null` if unable to normalize.
+ */
+ public static function normalize( string $html ): ?string {
+ return static::create_fragment( $html )->serialize();
+ }
+
+ /**
+ * Generate normalized markup for the HTML in the provided processor.
+ *
+ * This removes any partial syntax at the end of the string.
+ *
+ * @since 6.7.0
+ *
+ * @return string|null Normalized HTML markup represented by processor,
+ * or `null` if unable to generate serialization.
+ */
+ public function serialize(): ?string {
+ if ( WP_HTML_Tag_Processor::STATE_READY !== $this->parser_state ) {
+ return null;
+ }
+
+ $html = '';
+ while ( $this->next_token() ) {
+ $token_type = $this->get_token_type();
+
+ switch ( $token_type ) {
+ case '#text':
+ $html .= htmlspecialchars( $this->get_modifiable_text(), ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5, 'UTF-8' );
+ break;
+
+ case '#funky-comment':
+ case '#comment':
+ $html .= "";
+ break;
+
+ case '#cdata-section':
+ $html .= "get_modifiable_text()}]]>";
+ break;
+
+ case 'html':
+ $html .= '';
+ break;
+ }
+
+ if ( '#tag' !== $token_type ) {
+ continue;
+ }
+
+ if ( $this->is_tag_closer() ) {
+ $html .= "get_qualified_tag_name()}>";
+ continue;
+ }
+
+ $attribute_names = $this->get_attribute_names_with_prefix( '' );
+ if ( ! isset( $attribute_names ) ) {
+ $html .= "<{$this->get_qualified_tag_name()}>";
+ continue;
+ }
+
+ $html .= "<{$this->get_qualified_tag_name()}";
+ foreach ( $attribute_names as $attribute_name ) {
+ $html .= " {$this->get_qualified_attribute_name( $attribute_name )}";
+ $value = $this->get_attribute( $attribute_name );
+
+ if ( is_string( $value ) ) {
+ $html .= '="' . htmlspecialchars( $value, ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML5 ) . '"';
+ }
+ }
+
+ if ( 'html' !== $this->get_namespace() && $this->has_self_closing_flag() ) {
+ $html .= '/';
+ }
+
+ $html .= '>';
+ }
+
+ if ( null !== $this->get_last_error() ) {
+ return null;
+ }
+
+ return $html;
+ }
+
+ /**
+ * Replaces the inner markup of the currently-matched tag with provided HTML.
+ *
+ * This function will normalize the given input and enforce the boundaries
+ * within the existing HTML where it's called.
+ *
+ * @since 6.8.0
+ *
+ * @param string $new_inner_html New HTML to inject as inner HTML for the currently-matched tag.
+ * @return bool Whether the inner markup was modified for the currently-matched tag, or `NULL`
+ * if called on a node which doesn't allow changing the inner HTML.
+ */
+ public function set_inner_html( string $new_inner_html ): ?bool {
+ $tag_name = $this->get_tag();
+
+ if (
+ WP_HTML_Tag_Processor::STATE_MATCHED_TAG !== $this->parser_state ||
+ $this->is_tag_closer() ||
+ ( 'html' === $this->get_namespace() &&
+ (
+ self::is_void( $tag_name ) ||
+ in_array( $tag_name, array( 'IFRAME', 'NOEMBED', 'NOFRAMES', 'SCRIPT', 'STYLE', 'TEXTAREA', 'TITLE', 'XMP' ), true )
+ )
+ )
+ ) {
+ // @todo Support setting inner HTML for SCRIPT, STYLE, TEXTAREA, and TITLE.
+ return null;
+ }
+
+ $fragment = $this->spawn_fragment_parser( $new_inner_html );
+ $new_markup = $fragment->serialize();
+
+ $this->set_bookmark( 'start' );
+ $depth = $this->get_current_depth();
+ while ( $this->get_current_depth() >= $depth && $this->next_token() ) {
+ continue;
+ }
+
+ if (
+ $this->paused_at_incomplete_token() ||
+ null !== $this->get_last_error()
+ ) {
+ return false;
+ }
+
+ $this->set_bookmark( 'end' );
+ $start = $this->bookmarks['_start'];
+ $end = $this->bookmarks['_end'];
+
+ $this->lexical_updates[] = new WP_HTML_Text_Replacement(
+ $start->start + $start->length,
+ $end->start - ( $start->start + $start->length ),
+ $new_markup
+ );
+
+ $this->get_updated_html();
+ $this->seek( 'start' );
+ return true;
+ }
+
/**
* Removes a bookmark that is no longer needed.
*
diff --git a/src/wp-includes/html-api/class-wp-html-tag-processor.php b/src/wp-includes/html-api/class-wp-html-tag-processor.php
index 233d47eb8da95..355a7bb001923 100644
--- a/src/wp-includes/html-api/class-wp-html-tag-processor.php
+++ b/src/wp-includes/html-api/class-wp-html-tag-processor.php
@@ -2840,7 +2840,7 @@ public function get_qualified_tag_name(): ?string {
}
if ( 'html' === $this->get_namespace() ) {
- return $tag_name;
+ return strtolower( $tag_name );
}
$lower_tag_name = strtolower( $tag_name );