Changeset 58977 for trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php

Timestamp:

09/03/2024 07:48:57 PM (15 months ago)

Author:

dmsnell

Message:

HTML API: Ensure that NULL and whitespace-only CDATA sections don't forbid FRAMESET.

When CDATA sections (which can only occur inside SVG and MathML content) consist only of NULL bytes or whitespace characters they should not clear the "frameset ok" flag. Previously they have always been clearing this flag, but in this patch the logic is updated to detect these sequences properly.

Developed in ​https://github.com/WordPress/wordpress-develop/pull/7230
Discussed in https://core.trac.wordpress.org/ticket/61576

Follow-up to [58867].

Props dmsnell, jonsurrell.
See #61576.

File:

• trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php (modified) (2 diffs)

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

@@ -3338 +3338 @@
 
     /**
-     * Subdivides a matched text node or CDATA text node, splitting NULL byte sequences
-     * and decoded whitespace as distinct prefixes.
+     * Subdivides a matched text node, splitting NULL byte sequences and decoded whitespace as
+     * distinct nodes prefixes.
      *
      * Note that once anything that's neither a NULL byte nor decoded whitespace is
@@ -3369 +3369 @@
      */
     public function subdivide_text_appropriately(): bool {
+        if ( self::STATE_TEXT_NODE !== $this->parser_state ) {
+            return false;
+        }
+
         $this->text_node_classification = self::TEXT_IS_GENERIC;
 
-        if ( self::STATE_TEXT_NODE === $this->parser_state ) {
-            /*
-             * NULL bytes are treated categorically different than numeric character
-             * references whose number is zero. `�` is not the same as `"\x00"`.
-             */
-            $leading_nulls = strspn( $this->html, "\x00", $this->text_starts_at, $this->text_length );
-            if ( $leading_nulls > 0 ) {
-                $this->token_length             = $leading_nulls;
-                $this->text_length              = $leading_nulls;
-                $this->bytes_already_parsed     = $this->token_starts_at + $leading_nulls;
-                $this->text_node_classification = self::TEXT_IS_NULL_SEQUENCE;
-                return true;
-            }
-
-            /*
-             * Start a decoding loop to determine the point at which the
-             * text subdivides. This entails raw whitespace bytes and any
-             * character reference that decodes to the same.
-             */
-            $at  = $this->text_starts_at;
-            $end = $this->text_starts_at + $this->text_length;
-            while ( $at < $end ) {
-                $skipped = strspn( $this->html, " \t\f\r\n", $at, $end - $at );
-                $at     += $skipped;
-
-                if ( $at < $end && '&' === $this->html[ $at ] ) {
-                    $matched_byte_length = null;
-                    $replacement         = WP_HTML_Decoder::read_character_reference( 'data', $this->html, $at, $matched_byte_length );
-                    if ( isset( $replacement ) && 1 === strspn( $replacement, " \t\f\r\n" ) ) {
-                        $at += $matched_byte_length;
-                        continue;
-                    }
+        /*
+         * NULL bytes are treated categorically different than numeric character
+         * references whose number is zero. `&#x00;` is not the same as `"\x00"`.
+         */
+        $leading_nulls = strspn( $this->html, "\x00", $this->text_starts_at, $this->text_length );
+        if ( $leading_nulls > 0 ) {
+            $this->token_length             = $leading_nulls;
+            $this->text_length              = $leading_nulls;
+            $this->bytes_already_parsed     = $this->token_starts_at + $leading_nulls;
+            $this->text_node_classification = self::TEXT_IS_NULL_SEQUENCE;
+            return true;
+        }
+
+        /*
+         * Start a decoding loop to determine the point at which the
+         * text subdivides. This entails raw whitespace bytes and any
+         * character reference that decodes to the same.
+         */
+        $at  = $this->text_starts_at;
+        $end = $this->text_starts_at + $this->text_length;
+        while ( $at < $end ) {
+            $skipped = strspn( $this->html, " \t\f\r\n", $at, $end - $at );
+            $at     += $skipped;
+
+            if ( $at < $end && '&' === $this->html[ $at ] ) {
+                $matched_byte_length = null;
+                $replacement         = WP_HTML_Decoder::read_character_reference( 'data', $this->html, $at, $matched_byte_length );
+                if ( isset( $replacement ) && 1 === strspn( $replacement, " \t\f\r\n" ) ) {
+                    $at += $matched_byte_length;
+                    continue;
                 }
-
-                break;
-            }
-
-            if ( $at > $this->text_starts_at ) {
-                $new_length                     = $at - $this->text_starts_at;
-                $this->text_length              = $new_length;
-                $this->token_length             = $new_length;
-                $this->bytes_already_parsed     = $at;
-                $this->text_node_classification = self::TEXT_IS_WHITESPACE;
-                return true;
-            }
-
-            return false;
-        }
-
-        // Unlike text nodes, there are no character references within CDATA sections.
-        if ( self::STATE_CDATA_NODE === $this->parser_state ) {
-            $leading_nulls = strspn( $this->html, "\x00", $this->text_starts_at, $this->text_length );
-            if ( $leading_nulls === $this->text_length ) {
-                $this->text_node_classification = self::TEXT_IS_NULL_SEQUENCE;
-                return true;
-            }
-
-            $leading_ws = strspn( $this->html, " \t\f\r\n", $this->text_starts_at, $this->text_length );
-            if ( $leading_ws === $this->text_length ) {
-                $this->text_node_classification = self::TEXT_IS_WHITESPACE;
-                return true;
-            }
+            }
+
+            break;
+        }
+
+        if ( $at > $this->text_starts_at ) {
+            $new_length                     = $at - $this->text_starts_at;
+            $this->text_length              = $new_length;
+            $this->token_length             = $new_length;
+            $this->bytes_already_parsed     = $at;
+            $this->text_node_classification = self::TEXT_IS_WHITESPACE;
+            return true;
         }