Bits: Introduce the ability to store and render bits

Author: dmsnell

src/wp-includes/blocks.php

@@ -1714,6 +1714,8 @@ function render_block( $parsed_block ) {
  * @return array[] Array of parsed block objects.
  */
 function parse_blocks( $content ) {
+	$content = wp_replace_bits( $content );
+
 	/**
 	 * Filter to allow plugins to replace the server-side block parser.
 	 *

src/wp-includes/html-api/class-wp-bits.php

@@ -0,0 +1,77 @@
+<?php
+
+function wp_replace_bits( $content ) {
+	$processor = new class ( $content ) extends WP_HTML_Tag_Processor {
+		private $deferred_updates = array();
+
+		public function replace_token( $new_content ) {
+			$this->set_bookmark( 'here' );
+			$here = $this->bookmarks['here'];
+
+			$this->deferred_updates[] = new WP_HTML_Text_Replacement(
+				$here->start,
+				$here->length,
+				$new_content
+			);
+		}
+
+		public function flush_updates() {
+			foreach ( $this->deferred_updates as $update ) {
+				$this->lexical_updates[] = $update;
+			}
+		}
+	};
+
+	while ( $processor->next_token() ) {
+		switch ( $processor->get_token_type() ) {
+			case '#funky-comment':
+				$processor->replace_token( '<b>bl<em>ar</em>g</b>' );
+				break;
+
+			case '#tag':
+				foreach ( $processor->get_attribute_names_with_prefix( '' ) ?? [] as $name ) {
+					$value = $processor->get_attribute( $name );
+					if ( is_string( $value ) ) {
+						$new_value = preg_replace_callback(
+							'~<//wp:([^>]+)>~',
+							static function ( $bit ) {
+								return 'blarg';
+							},
+							$value
+						);
+
+						if ( $new_value !== $value ) {
+							$processor->set_attribute( $name, $new_value );
+						}
+					}
+				}
+				break;
+
+			case '#comment':
+				if ( WP_HTML_Tag_Processor::COMMENT_AS_HTML_COMMENT !== $processor->get_comment_type() ) {
+					break;
+				}
+
+				$text = $processor->get_modifiable_text();
+				if ( 1 === preg_match( '~^<//wp:([^>]+)>$~', $text ) ) {
+					$processor->replace_token( '<b>Bla<em>rg</em>!</b>' );
+					break;
+				}
+
+				$new_value = preg_replace_callback(
+					'~<//wp:([^>]+)>~',
+					static function ( $bit ) {
+						return 'blarg';
+					},
+					$text
+				);
+
+				$processor->replace_token( "<!--{$new_value}-->" );
+				break;
+		}
+	}
+	$processor->flush_updates();
+	$content = $processor->get_updated_html();
+
+	return $content;
+}

src/wp-includes/kses.php

@@ -981,7 +981,7 @@ function wp_kses_split( $content, $allowed_html, $allowed_protocols ) {
 	$pass_allowed_html      = $allowed_html;
 	$pass_allowed_protocols = $allowed_protocols;
 
-	return preg_replace_callback( '%(<!--.*?(-->|$))|(<[^>]*(>|$)|>)%', '_wp_kses_split_callback', $content );
+	return preg_replace_callback( '%((?:<!--.*?(-->|$))|</[^a-z][^>]*>)|(<[^>]*(>|$)|>)%', '_wp_kses_split_callback', $content );
 }
 
 /**
@@ -1085,6 +1085,11 @@ function wp_kses_split2( $content, $allowed_html, $allowed_protocols ) {
 		return '&gt;';
 	}
 
+	// Allows Bits.
+	if ( 1 === preg_match( '~</[^a-z][^>]*>~', $content ) ) {
+		return $content;
+	}
+
 	// Allow HTML comments.
 	if ( str_starts_with( $content, '<!--' ) ) {
 		$content = str_replace( array( '<!--', '-->' ), '', $content );

src/wp-settings.php

@@ -258,6 +258,7 @@
 require ABSPATH . WPINC . '/html-api/class-wp-html-token.php';
 require ABSPATH . WPINC . '/html-api/class-wp-html-processor-state.php';
 require ABSPATH . WPINC . '/html-api/class-wp-html-processor.php';
+require ABSPATH . WPINC . '/html-api/class-wp-bits.php';
 require ABSPATH . WPINC . '/class-wp-http.php';
 require ABSPATH . WPINC . '/class-wp-http-streams.php';
 require ABSPATH . WPINC . '/class-wp-http-curl.php';