HTML API: Reduce length checks in skip_script_data.

Apply an optimization to remove several repeated string length checks in `WP_HTML_Tag_Processor::skip_script_data()`.

Developed in WordPress/wordpress-develop#9230.

Props jonsurrell, dmsnell.
See #63738.

Built from https://develop.svn.wordpress.org/trunk@60617


git-svn-id: https://core.svn.wordpress.org/trunk@59953 1a063a9b-81f0-0310-95a4-ce76da25c4cd

Author: sirreal

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

@@ -1496,13 +1496,48 @@ private function skip_script_data(): bool {
 		while ( false !== $at && $at < $doc_length ) {
 			$at += strcspn( $html, '-<', $at );
 
+			/*
+			 * Optimization: Terminating a complete script element requires at least eight
+			 * additional bytes in the document. Some checks below may cause local escaped
+			 * state transitions when processing shorter strings, but those transitions are
+			 * irrelevant if the script tag is incomplete and the function must return false.
+			 *
+			 * This may need updating if those transitions become significant or exported from
+			 * this function in some way, such as when building safe methods to embed JavaScript
+			 * or data inside a SCRIPT element.
+			 *
+			 *     $at may be here.
+			 *        ↓
+			 *     ...</script>
+			 *         ╰──┬───╯
+			 *     $at + 8 additional bytes are required for a non-false return value.
+			 *
+			 * This single check eliminates the need to check lengths for the shorter spans:
+			 *
+			 *           $at may be here.
+			 *                  ↓
+			 *     <script><!-- --></script>
+			 *                   ├╯
+			 *             $at + 2 additional characters does not require a length check.
+			 *
+			 * The transition from "escaped" to "unescaped" is not relevant if the document ends:
+			 *
+			 *           $at may be here.
+			 *                  ↓
+			 *     <script><!-- -->[[END-OF-DOCUMENT]]
+			 *                   ╰──┬───╯
+			 *             $at + 8 additional bytes is not satisfied, return false.
+			 */
+			if ( $at + 8 >= $doc_length ) {
+				return false;
+			}
+
 			/*
 			 * For all script states a "-->"  transitions
 			 * back into the normal unescaped script mode,
 			 * even if that's the current state.
 			 */
 			if (
-				$at + 2 < $doc_length &&
 				'-' === $html[ $at ] &&
 				'-' === $html[ $at + 1 ] &&
 				'>' === $html[ $at + 2 ]
@@ -1512,10 +1547,6 @@ private function skip_script_data(): bool {
 				continue;
 			}
 
-			if ( $at + 1 >= $doc_length ) {
-				return false;
-			}
-
 			/*
 			 * Everything of interest past here starts with "<".
 			 * Check this character and advance position regardless.
@@ -1537,7 +1568,6 @@ private function skip_script_data(): bool {
 			 * parsing after updating the state.
 			 */
 			if (
-				$at + 2 < $doc_length &&
 				'!' === $html[ $at ] &&
 				'-' === $html[ $at + 1 ] &&
 				'-' === $html[ $at + 2 ]
@@ -1561,7 +1591,6 @@ private function skip_script_data(): bool {
 			 * proceed scanning to the next potential token in the text.
 			 */
 			if ( ! (
-				$at + 6 < $doc_length &&
 				( 's' === $html[ $at ] || 'S' === $html[ $at ] ) &&
 				( 'c' === $html[ $at + 1 ] || 'C' === $html[ $at + 1 ] ) &&
 				( 'r' === $html[ $at + 2 ] || 'R' === $html[ $at + 2 ] ) &&
@@ -1579,9 +1608,6 @@ private function skip_script_data(): bool {
 			 * "<script123" should not end a script region even though
 			 * "<script" is found within the text.
 			 */
-			if ( $at + 6 >= $doc_length ) {
-				continue;
-			}
 			$at += 6;
 			$c   = $html[ $at ];
 			if ( ' ' !== $c && "\t" !== $c && "\r" !== $c && "\n" !== $c && '/' !== $c && '>' !== $c ) {
@@ -1611,8 +1637,6 @@ private function skip_script_data(): bool {
 				}
 
 				if ( $this->bytes_already_parsed >= $doc_length ) {
-					$this->parser_state = self::STATE_INCOMPLETE_INPUT;
-
 					return false;
 				}
 

wp-includes/version.php

@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.9-alpha-60616';
+$wp_version = '6.9-alpha-60617';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.