PR Feedback

Co-authored-by: Jon Surrell <[email protected]>

src/wp-includes/html-api/class-wp-html-tag-processor.php

@@ -1174,7 +1174,10 @@ public function has_class( $wanted_class ) {
 	 */
 	public function set_bookmark( $name ) {
 		// It only makes sense to set a bookmark if the parser has paused on a concrete token.
-		if ( self::STATE_INCOMPLETE === $this->parser_state ) {
+		if (
+			self::STATE_COMPLETE === $this->parser_state ||
+			self::STATE_INCOMPLETE === $this->parser_state
+		) {
 			return false;
 		}
 
@@ -1555,12 +1558,12 @@ private function parse_next_tag() {
 			}
 
 			/*
-			 * <! transitions to markup declaration open state
+			 * `<!` transitions to markup declaration open state
 			 * https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
 			 */
 			if ( '!' === $html[ $at + 1 ] ) {
 				/*
-				 * <!-- transitions to a bogus comment state – skip to the nearest -->
+				 * `<!--` transitions to a comment state – apply further comment rules.
 				 * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
 				 */
 				if (
@@ -1579,7 +1582,14 @@ private function parse_next_tag() {
 					// Abruptly-closed empty comments are a sequence of dashes followed by `>`.
 					$span_of_dashes = strspn( $html, '-', $closer_at );
 					if ( '>' === $html[ $closer_at + $span_of_dashes ] ) {
-						// @todo This could go wrong if the closer is shorter than `<!---->` because there's no inside content.
+						/*
+						 * @todo When implementing `set_modifiable_text()` ensure that updates to this token
+						 *       don't break the syntax for short comments, e.g. `<!--->`. Unlike other comment
+						 *       and bogus comment syntax, these leave no clear insertion point for text and
+						 *       they need to be modified specially in order to contain text. E.g. to store
+						 *       `?` as the modifiable text, the `<!--->` needs to become `<!--?-->`, which
+						 *       involves inserting an additional `-` into the token after the modifiable text.
+						 */
 						$this->parser_state         = self::STATE_COMMENT;
 						$this->token_length         = $closer_at + $span_of_dashes + 1 - $this->token_starts_at;
 						$this->text_starts_at       = $this->token_starts_at + 4;
@@ -1628,7 +1638,7 @@ private function parse_next_tag() {
 				}
 
 				/*
-				 * <!DOCTYPE transitions to DOCTYPE state – skip to the nearest >
+				 * `<!DOCTYPE` transitions to DOCTYPE state – skip to the nearest >
 				 * These are ASCII-case-insensitive.
 				 * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
 				 */
@@ -1726,7 +1736,7 @@ private function parse_next_tag() {
 			}
 
 			/*
-			 * <? transitions to a bogus comment state – skip to the nearest >
+			 * `<?` transitions to a bogus comment state – skip to the nearest >
 			 * See https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
 			 */
 			if ( '?' === $html[ $at + 1 ] ) {
@@ -1789,6 +1799,9 @@ private function parse_next_tag() {
 			 * If a non-alpha starts the tag name in a tag closer it's a comment.
 			 * Find the first `>`, which closes the comment.
 			 *
+			 * This parser classifies these particular comments as special "funky comments"
+			 * which are made available for further processing.
+			 *
 			 * See https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
 			 */
 			if ( $this->is_closing_tag ) {
@@ -2576,6 +2589,7 @@ public function is_tag_closer() {
 	 *  - `#cdata-section` when matched on a CDATA node.
 	 *  - `#processing-instruction` when matched on a processing instruction.
 	 *  - `#comment` when matched on a comment.
+	 *  - `#doctype` when matched on a DOCTYPE declaration.
 	 *  - `#presumptuous-tag` when matched on an empty tag closer.
 	 *  - `#funky-comment` when matched on a funky comment.
 	 *
@@ -2667,20 +2681,25 @@ public function get_token_name() {
 	 * @return string
 	 */
 	public function get_modifiable_text() {
-		$at     = $this->text_starts_at;
-		$length = $this->text_length;
-		$text   = substr( $this->html, $at, $length );
+		if ( null === $this->text_starts_at ) {
+			return '';
+		}
+
+		$text = substr( $this->html, $this->text_starts_at, $this->text_length );
 
 		if (
 			self::STATE_CDATA_NODE === $this->parser_state ||
-			self::STATE_PI_NODE === $this->parser_state
+			self::STATE_COMMENT === $this->parser_state ||
+			self::STATE_DOCTYPE === $this->parser_state ||
+			self::STATE_PI_NODE === $this->parser_state ||
+			self::STATE_FUNKY_COMMENT === $this->parser_state
 		) {
 			return $text;
 		}
 
-		$text = html_entity_decode( $text, ENT_QUOTES | ENT_HTML5 | ENT_SUBSTITUTE );
+		$decoded = html_entity_decode( $text, ENT_QUOTES | ENT_HTML5 | ENT_SUBSTITUTE );
 
-		if ( empty( $text ) ) {
+		if ( empty( $decoded ) ) {
 			return '';
 		}
 
@@ -2694,14 +2713,14 @@ public function get_modifiable_text() {
 			switch ( $this->get_tag() ) {
 				case 'PRE':
 				case 'TEXTAREA':
-					if ( "\n" === $text[0] ) {
-						return substr( $text, 1 );
+					if ( "\n" === $decoded[0] ) {
+						return substr( $decoded, 1 );
 					}
 					break;
 			}
 		}
 
-		return $text;
+		return $decoded;
 	}
 
 	/**
@@ -3286,7 +3305,8 @@ private function matches() {
 	const STATE_DOCTYPE = 'STATE_DOCTYPE';
 
 	/**
-	 * Indicates that the parser has found an empty tag closer.
+	 * Indicates that the parser has found an empty tag closer `</>`.
+	 *
 	 * Note that in HTML there are no empty tag closers, and they
 	 * are ignored. Nonetheless, the Tag Processor still
 	 * recognizes them as they appear in the HTML stream.
@@ -3305,8 +3325,14 @@ private function matches() {
 	 * Indicates that the parser has found a "funky comment"
 	 * and it's possible to read and modify its modifiable text.
 	 *
+	 * Example:
+	 *
+	 *     </%url>
+	 *     </{"wp-bit":"query/post-author"}>
+	 *     </2>
+	 *
 	 * Funky comments are tag closers with invalid tag names. Note
-	 * that in HTML these are treated as HTML comments. Nonetheless,
+	 * that in HTML these are turn into bogus comments. Nonetheless,
 	 * the Tag Processor recognizes them in a stream of HTML and
 	 * exposes them for inspection and modification.
 	 *