Changeset 60617

Timestamp:

08/07/2025 08:31:07 AM (14 months ago)

Author:

jonsurrell

Message:

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 ​https://github.com/WordPress/wordpress-develop/pull/9230.

Props jonsurrell, dmsnell.
See #63738.

Location:

trunk

Files:

• src/wp-includes/html-api/class-wp-html-tag-processor.php (modified) (7 diffs)
• tests/phpunit/tests/html-api/wpHtmlTagProcessor.php (modified) (1 diff)

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

@@ -1498 +1498 @@
 
                         /*
+                         * 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,
@@ -1503 +1539 @@
                          */
                         if (
-                                $at + 2 < $doc_length &&
                                 '-' === $html[ $at ] &&
                                 '-' === $html[ $at + 1 ] &&
@@ -1511 +1546 @@
                                 $state = 'unescaped';
                                 continue;
-                        }
-
-                        if ( $at + 1 >= $doc_length ) {
-                                return false;
                         }
 
@@ -1538 +1569 @@
                          */
                         if (
-                                $at + 2 < $doc_length &&
                                 '!' === $html[ $at ] &&
                                 '-' === $html[ $at + 1 ] &&
@@ -1562 +1592 @@
                          */
                         if ( ! (
-                                $at + 6 < $doc_length &&
                                 ( 's' === $html[ $at ] || 'S' === $html[ $at ] ) &&
                                 ( 'c' === $html[ $at + 1 ] || 'C' === $html[ $at + 1 ] ) &&
@@ -1580 +1609 @@
                          * "<script" is found within the text.
                          */
-                        if ( $at + 6 >= $doc_length ) {
-                                continue;
-                        }
                         $at += 6;
                         $c   = $html[ $at ];
@@ -1612 +1638 @@
 
                                 if ( $this->bytes_already_parsed >= $doc_length ) {
-                                        $this->parser_state = self::STATE_INCOMPLETE_INPUT;
-
                                         return false;
                                 }

trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php

@@ -1979 +1979 @@
                                 '<script class="d-md-none"><!--<script>--><scRipt><span><!--<span><Script</script>--></scripT><div></div>-->',
                         ),
+                );
+        }
+
+        /**
+         * Test that script tags are parsed correctly.
+         *
+         * Script tag parsing is very complicated, see the following resources for more details:
+         *
+         * - https://html.spec.whatwg.org/multipage/parsing.html#script-data-state
+         * - https://html.spec.whatwg.org/multipage/scripting.html#restrictions-for-contents-of-script-elements
+         *
+         * @ticket 63738
+         *
+         * @dataProvider data_script_tag
+         */
+        public function test_script_tag_parsing( string $input, bool $closes ) {
+                $processor = new WP_HTML_Tag_Processor( $input );
+
+                if ( $closes ) {
+                        $this->assertTrue( $processor->next_token(), 'Expected to find complete script tag.' );
+                        $this->assertSame( 'SCRIPT', $processor->get_tag() );
+                        return;
+                }
+
+                $this->assertFalse( $processor->next_token(), 'Expected to fail next_token().' );
+                $this->assertTrue( $processor->paused_at_incomplete_token(), 'Expected an incomplete SCRIPT tag token.' );
+        }
+
+        /**
+         * Data provider.
+         */
+        public static function data_script_tag(): array {
+                return array(
+                        'Basic script tag'                          => array( '<script></script>', true ),
+                        'Script with type attribute'                => array( '<script type="text/javascript"></script>', true ),
+                        'Script data escaped'                       => array( '<script><!--</script>', true ),
+                        'Script data double-escaped exit (comment)' => array( '<script><!--<script>--></script>', true ),
+                        'Script data double-escaped exit (closed)'  => array( '<script><!--<script></script></script>', true ),
+                        'Script data double-escaped exit (closed/truncated)' => array( '<script><!--<script></script </script>', true ),
+                        'Script data no double-escape'              => array( '<script><!-- --><script></script>', true ),
+
+                        'Script tag with self-close flag (ignored)' => array( '<script />', false ),
+                        'Script data double-escaped'                => array( '<script><!--<script></script>', false ),
                 );
         }