Changeset 58839

Timestamp:

08/01/2024 10:04:44 PM (2 years ago)

Author:

dmsnell

Message:

HTML API: Add support for IN COLUMN GROUP parsing.

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

Developed in ​https://github.com/wordpress/wordpress-develop/pull/7042
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

@@ -3069 +3069 @@
          * 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.
@@ -3079 +3079 @@
          */
         private function step_in_column_group(): bool {
-                $this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP . ' state.' );
+                $token_name = $this->get_token_name();
+                $token_type = $this->get_token_type();
+                $op_sigil   = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
+                $op         = "{$op_sigil}{$token_name}";
+
+                switch ( $op ) {
+                        /*
+                         * > A character token that is one of U+0009 CHARACTER TABULATION, U+000A LINE FEED (LF),
+                         * > U+000C FORM FEED (FF), U+000D CARRIAGE RETURN (CR), or U+0020 SPACE
+                         */
+                        case '#text':
+                                $text = $this->get_modifiable_text();
+                                if ( '' === $text ) {
+                                        /*
+                                         * If the text is empty after processing HTML entities and stripping
+                                         * U+0000 NULL bytes then ignore the token.
+                                         */
+                                        return $this->step();
+                                }
+
+                                if ( strlen( $text ) === strspn( $text, " \t\n\f\r" ) ) {
+                                        // Insert the character.
+                                        $this->insert_html_element( $this->state->current_token );
+                                        return true;
+                                }
+
+                                goto in_column_group_anything_else;
+                                break;
+
+                        /*
+                         * > A comment token
+                         */
+                        case '#comment':
+                        case '#funky-comment':
+                        case '#presumptuous-tag':
+                                $this->insert_html_element( $this->state->current_token );
+                                return true;
+
+                        /*
+                         * > A DOCTYPE token
+                         */
+                        case 'html':
+                                // @todo Indicate a parse error once it's possible.
+                                return $this->step();
+
+                        /*
+                         * > A start tag whose tag name is "html"
+                         */
+                        case '+HTML':
+                                return $this->step_in_body();
+
+                        /*
+                         * > A start tag whose tag name is "col"
+                         */
+                        case '+COL':
+                                $this->insert_html_element( $this->state->current_token );
+                                $this->state->stack_of_open_elements->pop();
+                                return true;
+
+                        /*
+                         * > An end tag whose tag name is "colgroup"
+                         */
+                        case '-COLGROUP':
+                                if ( ! $this->state->stack_of_open_elements->current_node_is( 'COLGROUP' ) ) {
+                                        // @todo Indicate a parse error once it's possible.
+                                        return $this->step();
+                                }
+                                $this->state->stack_of_open_elements->pop();
+                                $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
+                                return true;
+
+                        /*
+                         * > An end tag whose tag name is "col"
+                         */
+                        case '-COL':
+                                // Parse error: ignore the token.
+                                return $this->step();
+
+                        /*
+                         * > A start tag whose tag name is "template"
+                         * > An end tag whose tag name is "template"
+                         */
+                        case '+TEMPLATE':
+                        case '-TEMPLATE':
+                                return $this->step_in_head();
+                }
+
+                in_column_group_anything_else:
+                /*
+                 * > Anything else
+                 */
+                if ( ! $this->state->stack_of_open_elements->current_node_is( 'COLGROUP' ) ) {
+                        // @todo Indicate a parse error once it's possible.
+                        return $this->step();
+                }
+                $this->state->stack_of_open_elements->pop();
+                $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
+                return $this->step( self::REPROCESS_CURRENT_NODE );
         }