Changeset 58840

Timestamp:

08/01/2024 10:34:29 PM (2 years ago)

Author:

dmsnell

Message:

HTML API: Add support for IN CAPTION parsing.

As part of work to add more spec support to the HTML API, this patch adds
support for the IN CAPTION insertion mode. This small section of the
spec handles rules for the <caption> element.

Developed in ​https://github.com/wordpress/wordpress-develop/pull/7041
Discussed in https://core.trac.wordpress.org/ticket/61576

Props: dmsnell, jonsurrell.
See #61576.

File:

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

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

@@ -3050 +3050 @@
          * logic for the generalized WP_HTML_Processor::step() function.
          *
-         * @since 6.7.0 Stub implementation.
+         * @since 6.7.0
          *
          * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
@@ -3060 +3060 @@
          */
         private function step_in_caption(): bool {
-                $this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION . ' state.' );
+                $tag_name = $this->get_tag();
+                $op_sigil = $this->is_tag_closer() ? '-' : '+';
+                $op       = "{$op_sigil}{$tag_name}";
+
+                switch ( $op ) {
+                        /*
+                         * > An end tag whose tag name is "caption"
+                         * > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "td", "tfoot", "th", "thead", "tr"
+                         * > An end tag whose tag name is "table"
+                         *
+                         * These tag handling rules are identical except for the final instruction.
+                         * Handle them in a single block.
+                         */
+                        case '-CAPTION':
+                        case '+CAPTION':
+                        case '+COL':
+                        case '+COLGROUP':
+                        case '+TBODY':
+                        case '+TD':
+                        case '+TFOOT':
+                        case '+TH':
+                        case '+THEAD':
+                        case '+TR':
+                        case '-TABLE':
+                                if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'CAPTION' ) ) {
+                                        // Parse error: ignore the token.
+                                        return $this->step();
+                                }
+
+                                $this->generate_implied_end_tags();
+                                if ( ! $this->state->stack_of_open_elements->current_node_is( 'CAPTION' ) ) {
+                                        // @todo Indicate a parse error once it's possible.
+                                }
+
+                                $this->state->stack_of_open_elements->pop_until( 'CAPTION' );
+                                $this->state->active_formatting_elements->clear_up_to_last_marker();
+                                $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
+
+                                // If this is not a CAPTION end tag, the token should be reprocessed.
+                                if ( '-CAPTION' === $op ) {
+                                        return true;
+                                }
+                                return $this->step( self::REPROCESS_CURRENT_NODE );
+
+                        /**
+                         * > An end tag whose tag name is one of: "body", "col", "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr"
+                         */
+                        case '-BODY':
+                        case '-COL':
+                        case '-COLGROUP':
+                        case '-HTML':
+                        case '-TBODY':
+                        case '-TD':
+                        case '-TFOOT':
+                        case '-TH':
+                        case '-THEAD':
+                        case '-TR':
+                                // Parse error: ignore the token.
+                                return $this->step();
+                }
+
+                /**
+                 * > Anything else
+                 * >   Process the token using the rules for the "in body" insertion mode.
+                 */
+                return $this->step_in_body();
         }