Changeset 58779

trunk/src/wp-includes/html-api/class-wp-html-active-formatting-elements.php

-                      r58769
+                      r58779
         return $current_node ? $current_node : null;
+    }
+    /**
+     * Inserts a "marker" at the end of the list of active formatting elements.
+     *
+     * > The markers are inserted when entering applet, object, marquee,
+     * > template, td, th, and caption elements, and are used to prevent
+     * > formatting from "leaking" into applet, object, marquee, template,
+     * > td, th, and caption elements.
+     *
+     * @see https://html.spec.whatwg.org/#concept-parser-marker
+     *
+     * @since 6.7.0
+     */
+    public function insert_marker(): void {
+        $this->push( new WP_HTML_Token( null, 'marker', false ) );
+    }
 …
+        }
+    }
+    /**
+     * Clears the list of active formatting elements up to the last marker.
+     *
+     * > When the steps below require the UA to clear the list of active formatting elements up to
+     * > the last marker, the UA must perform the following steps:
+     * >
+     * > 1. Let entry be the last (most recently added) entry in the list of active
+     * >    formatting elements.
+     * > 2. Remove entry from the list of active formatting elements.
+     * > 3. If entry was a marker, then stop the algorithm at this point.
+     * >    The list has been cleared up to the last marker.
+     * > 4. Go to step 1.
+     *
+     * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-list-of-active-formatting-elements-up-to-the-last-marker
+     *
+     * @since 6.7.0
+     */
+    public function clear_up_to_last_marker(): void {
+        foreach ( $this->walk_up() as $item ) {
+            array_pop( $this->stack );
+            if ( 'marker' === $item->node_name ) {
+                break;
+            }
+        }
+    }
+}

trunk/src/wp-includes/html-api/class-wp-html-open-elements.php

-                      r58769
+                      r58779
     /**
+     * Returns the name of the node at the nth position on the stack
+     * of open elements, or `null` if no such position exists.
+     *
+     * Note that this uses a 1-based index, which represents the
+     * "nth item" on the stack, counting from the top, where the
+     * top-most element is the 1st, the second is the 2nd, etc...
+     *
+     * @since 6.7.0
+     *
+     * @param int $nth Retrieve the nth item on the stack, with 1 being
+     *                 the top element, 2 being the second, etc...
+     * @return string|null Name of the node on the stack at the given location,
+     *                     or `null` if the location isn't on the stack.
+     */
+    public function at( int $nth ): ?string {
+        foreach ( $this->walk_down() as $item ) {
+            if ( 0 === --$nth ) {
+                return $item->node_name;
+            }
+        }
+        return null;
+    }
+    /**
+     * Reports if a node of a given name is in the stack of open elements.
+     *
+     * @since 6.7.0
+     *
+     * @param string $node_name Name of node for which to check.
+     * @return bool Whether a node of the given name is in the stack of open elements.
+     */
+    public function contains( string $node_name ): bool {
+        foreach ( $this->walk_up() as $item ) {
+            if ( $node_name === $item->node_name ) {
+                return true;
+            }
+        }
+        return false;
+    }
+    /**
      * Reports if a specific node is in the stack of open elements.
+     *
 …
     public function contains_node( WP_HTML_Token $token ): bool {
         foreach ( $this->walk_up() as $item ) {
             if ( $token->bookmark_name === $item->bookmark_name ) {
+            if ( $token === $item ) {
                 return true;
+            }
 …
+            }
-            switch ( $node->node_name ) {
-                case 'HTML':
-                    return false;
+            }
             if ( in_array( $node->node_name, $termination_list, true ) ) {
                 return false;
 …
      * Returns whether a particular element is in scope.
+     *
+     * @since 6.4.0
+     * > The stack of open elements is said to have a particular element in
+     * > scope when it has that element in the specific scope consisting of
+     * > the following element types:
+     * >
+     * >   - applet
+     * >   - caption
+     * >   - html
+     * >   - table
+     * >   - td
+     * >   - th
+     * >   - marquee
+     * >   - object
+     * >   - template
+     * >   - MathML mi
+     * >   - MathML mo
+     * >   - MathML mn
+     * >   - MathML ms
+     * >   - MathML mtext
+     * >   - MathML annotation-xml
+     * >   - SVG foreignObject
+     * >   - SVG desc
+     * >   - SVG title
+     *
+     * @since 6.4.0
+     * @since 6.7.0 Supports all required HTML elements.
+     *
      * @see https://html.spec.whatwg.org/#has-an-element-in-scope
 …
             $tag_name,
             array(
+                /*
+                 * Because it's not currently possible to encounter
+                 * one of the termination elements, they don't need
+                 * to be listed here. If they were, they would be
+                 * unreachable and only waste CPU cycles while
+                 * scanning through HTML.
+                 */
+                'APPLET',
+                'CAPTION',
+                'HTML',
+                'TABLE',
+                'TD',
+                'TH',
+                'MARQUEE',
+                'OBJECT',
+                'TEMPLATE',
+                // @todo: Support SVG and MathML nodes when support for foreign content is added.
+            )
         );
 …
      * Returns whether a particular element is in list item scope.
+     *
+     * > The stack of open elements is said to have a particular element
+     * > in list item scope when it has that element in the specific scope
+     * > consisting of the following element types:
+     * >
+     * >   - All the element types listed above for the has an element in scope algorithm.
+     * >   - ol in the HTML namespace
+     * >   - ul in the HTML namespace
+     *
      * @since 6.4.0
      * @since 6.5.0 Implemented: no longer throws on every invocation.
+     * @since 6.7.0 Supports all required HTML elements.
+     *
      * @see https://html.spec.whatwg.org/#has-an-element-in-list-item-scope
 …
             $tag_name,
             array(
+                // There are more elements that belong here which aren't currently supported.
+                'APPLET',
+                'BUTTON',
+                'CAPTION',
+                'HTML',
+                'TABLE',
+                'TD',
+                'TH',
+                'MARQUEE',
+                'OBJECT',
                 'OL',
+                'TEMPLATE',
                 'UL',
+                // @todo: Support SVG and MathML nodes when support for foreign content is added.
+            )
         );
 …
      * Returns whether a particular element is in button scope.
+     *
+     * @since 6.4.0
+     * > The stack of open elements is said to have a particular element
+     * > in button scope when it has that element in the specific scope
+     * > consisting of the following element types:
+     * >
+     * >   - All the element types listed above for the has an element in scope algorithm.
+     * >   - button in the HTML namespace
+     *
+     * @since 6.4.0
+     * @since 6.7.0 Supports all required HTML elements.
+     *
      * @see https://html.spec.whatwg.org/#has-an-element-in-button-scope
 …
      */
     public function has_element_in_button_scope( string $tag_name ): bool {
+        return $this->has_element_in_specific_scope( $tag_name, array( 'BUTTON' ) );
+        return $this->has_element_in_specific_scope(
+            $tag_name,
+            array(
+                'APPLET',
+                'BUTTON',
+                'CAPTION',
+                'HTML',
+                'TABLE',
+                'TD',
+                'TH',
+                'MARQUEE',
+                'OBJECT',
+                'TEMPLATE',
+                // @todo: Support SVG and MathML nodes when support for foreign content is added.
+            )
+        );
+    }
 …
      * Returns whether a particular element is in table scope.
+     *
+     * @since 6.4.0
+     * > The stack of open elements is said to have a particular element
+     * > in table scope when it has that element in the specific scope
+     * > consisting of the following element types:
+     * >
+     * >   - html in the HTML namespace
+     * >   - table in the HTML namespace
+     * >   - template in the HTML namespace
+     *
+     * @since 6.4.0
+     * @since 6.7.0 Full implementation.
+     *
      * @see https://html.spec.whatwg.org/#has-an-element-in-table-scope
+     *
-     * @throws WP_HTML_Unsupported_Exception Always until this function is implemented.
+     *
      * @param string $tag_name Name of tag to check.
 …
      */
     public function has_element_in_table_scope( string $tag_name ): bool {
+        throw new WP_HTML_Unsupported_Exception( 'Cannot process elements depending on table scope.' );
+        return false; // The linter requires this unreachable code until the function is implemented and can return.
+        return $this->has_element_in_specific_scope(
+            $tag_name,
+            array(
+                'HTML',
+                'TABLE',
+                'TEMPLATE',
+            )
+        );
+    }
 …
          */
         switch ( $item->node_name ) {
+            case 'APPLET':
             case 'BUTTON':
+            case 'CAPTION':
+            case 'HTML':
+            case 'TABLE':
+            case 'TD':
+            case 'TH':
+            case 'MARQUEE':
+            case 'OBJECT':
+            case 'TEMPLATE':
                 $this->has_p_in_button_scope = false;
                 break;
 …
          */
         switch ( $item->node_name ) {
+            case 'APPLET':
             case 'BUTTON':
+            case 'CAPTION':
+            case 'HTML':
+            case 'P':
+            case 'TABLE':
+            case 'TD':
+            case 'TH':
+            case 'MARQUEE':
+            case 'OBJECT':
+            case 'TEMPLATE':
                 $this->has_p_in_button_scope = $this->has_element_in_button_scope( 'P' );
                 break;
-            case 'P':
-                $this->has_p_in_button_scope = $this->has_element_in_button_scope( 'P' );
-                break;
+        }

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

-                      r58769
+                      r58779
     /**
+     * No-quirks mode document compatability mode.
+     *
+     * > In no-quirks mode, the behavior is (hopefully) the desired behavior
+     * > described by the modern HTML and CSS specifications.
+     *
+     * @since 6.7.0
+     *
+     * @var string
+     */
+    const NO_QUIRKS_MODE = 'no-quirks-mode';
+    /**
+     * Quirks mode document compatability mode.
+     *
+     * > In quirks mode, layout emulates behavior in Navigator 4 and Internet
+     * > Explorer 5. This is essential in order to support websites that were
+     * > built before the widespread adoption of web standards.
+     *
+     * @since 6.7.0
+     *
+     * @var string
+     */
+    const QUIRKS_MODE = 'quirks-mode';
+    /**
      * The stack of template insertion modes.
+     *
 …
     /**
+     * Indicates if the document is in quirks mode or no-quirks mode.
+     *
+     * Impact on HTML parsing:
+     *
+     *  - In `NO_QUIRKS_MODE` CSS class and ID selectors match in a byte-for-byte
+     *    manner, otherwise for backwards compatability, class selectors are to
+     *    match in an ASCII case-insensitive manner.
+     *
+     *  - When not in `QUIRKS_MODE`, a TABLE start tag implicitly closes an open P tag
+     *    if one is in scope and open, otherwise the TABLE becomes a child of the P.
+     *
+     * `QUIRKS_MODE` impacts many styling-related aspects of an HTML document, but
+     * none of the other changes modifies how the HTML is parsed or selected.
+     *
+     * @see self::QUIRKS_MODE
+     * @see self::NO_QUIRKS_MODE
+     *
+     * @since 6.7.0
+     *
+     * @var string
+     */
+    public $document_mode = self::NO_QUIRKS_MODE;
+    /**
      * Context node initializing fragment parser, if created as a fragment parser.
+     *
 …
      */
     public $head_element = null;
+    /**
+     * FORM element pointer.
+     *
+     * > points to the last form element that was opened and whose end tag has
+     * > not yet been seen. It is used to make form controls associate with
+     * > forms in the face of dramatically bad markup, for historical reasons.
+     * > It is ignored inside template elements.
+     *
+     * @todo This may be invalidated by a seek operation.
+     *
+     * @see https://html.spec.whatwg.org/#form-element-pointer
+     *
+     * @since 6.7.0
+     *
+     * @var WP_HTML_Token|null
+     */
+    public $form_element = null;
     /**

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

-                      r58769
+                      r58779
  * that the HTML Processor won't break any HTML it doesn't fully understand.
+ *
  * The following list specifies the HTML tags that _are_ supported:
+ * The HTML Processor supports all elements other than a specific set:
+ *
+ *  - Containers: ADDRESS, BLOCKQUOTE, DETAILS, DIALOG, DIV, FOOTER, HEADER, MAIN, MENU, SPAN, SUMMARY.
+ *  - Custom elements: All custom elements are supported. :)
+ *  - Form elements: BUTTON, DATALIST, FIELDSET, INPUT, LABEL, LEGEND, METER, OPTGROUP, OPTION, PROGRESS, SEARCH, SELECT.
+ *  - Formatting elements: B, BIG, CODE, EM, FONT, I, PRE, SMALL, STRIKE, STRONG, TT, U, WBR.
+ *  - Heading elements: H1, H2, H3, H4, H5, H6, HGROUP.
+ *  - Links: A.
+ *  - Lists: DD, DL, DT, LI, OL, UL.
+ *  - Media elements: AUDIO, CANVAS, EMBED, FIGCAPTION, FIGURE, IMG, MAP, PICTURE, SOURCE, TRACK, VIDEO.
+ *  - Paragraph: BR, P.
+ *  - Phrasing elements: ABBR, AREA, BDI, BDO, CITE, DATA, DEL, DFN, INS, MARK, OUTPUT, Q, SAMP, SUB, SUP, TIME, VAR.
+ *  - Sectioning elements: ARTICLE, ASIDE, HR, NAV, SECTION.
+ *  - Templating elements: SLOT.
+ *  - Text decoration: RUBY.
+ *  - Deprecated elements: ACRONYM, BLINK, CENTER, DIR, ISINDEX, KEYGEN, LISTING, MULTICOL, NEXTID, PARAM, SPACER.
+ *  - Any element inside a TABLE.
+ *  - Any element inside foreign content, including SVG and MATH.
+ *  - Any element outside the IN BODY insertion mode, e.g. doctype declarations, meta, links.
+ *
  * ### Supported markup
 …
  * such a case it will stop processing.
+ *
+ * The following list specifies HTML markup that _is_ supported:
+ * The following list illustrates some common examples of unexpected HTML inputs that
+ * the HTML Processor properly parses and represents:
+ *
+ *  - Markup involving only those tags listed above.
+ *  - Fully-balanced and non-overlapping tags.
+ *  - HTML with unexpected tag closers.
+ *  - Some unbalanced or overlapping tags.
+ *  - P tags after unclosed P tags.
+ *  - BUTTON tags after unclosed BUTTON tags.
+ *  - A tags after unclosed A tags that don't involve any active formatting elements.
+ *  - HTML with optional tags omitted, e.g. `<p>one<p>two`.
+ *  - HTML with unexpected tag closers, e.g. `<p>one </span> more</p>`.
+ *  - Non-void tags with self-closing flag, e.g. `<div/>the DIV is still open.</div>`.
+ *  - Heading elements which close open heading elements of another level, e.g. `<h1>Closed by </h2>`.
+ *  - Elements containing text that looks like other tags but isn't, e.g. `<title>The <img> is plaintext</title>`.
+ *  - SCRIPT and STYLE tags containing text that looks like HTML but isn't, e.g. `<script>document.write('<p>Hi</p>');</script>`.
+ *  - SCRIPT content which has been escaped, e.g. `<script><!-- document.write('<script>console.log("hi")</script>') --></script>`.
+ *
+ * ### Unsupported Features
+ *
+ * This parser does not report parse errors.
+ *
+ * Normally, when additional HTML or BODY tags are encountered in a document, if there
+ * are any additional attributes on them that aren't found on the previous elements,
+ * the existing HTML and BODY elements adopt those missing attribute values. This
+ * parser does not add those additional attributes.
+ *
+ * In certain situations, elements are moved to a different part of the document in
+ * a process called "adoption" and "fostering." Because the nodes move to a location
+ * in the document that the parser had already processed, this parser does not support
+ * these situations and will bail.
+ *
  * @since 6.4.0
 …
         switch ( $op ) {
-            case '#comment':
-            case '#funky-comment':
-            case '#presumptuous-tag':
-                $this->insert_html_element( $this->state->current_token );
-                return true;
             case '#text':
-                $this->reconstruct_active_formatting_elements();
                 $current_token = $this->bookmarks[ $this->state->current_token->bookmark_name ];
 …
+                }
+                $this->reconstruct_active_formatting_elements();
                 /*
                  * Whitespace-only text does not affect the frameset-ok flag.
 …
                 return true;
+            case '#comment':
+            case '#funky-comment':
+            case '#presumptuous-tag':
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * > A DOCTYPE token
+             * > Parse error. Ignore the token.
+             */
             case 'html':
+                return $this->step();
+            /*
+             * > A start tag whose tag name is "html"
+             */
+            case '+HTML':
+                if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
+                    /*
+                     * > Otherwise, for each attribute on the token, check to see if the attribute
+                     * > is already present on the top element of the stack of open elements. If
+                     * > it is not, add the attribute and its corresponding value to that element.
+                     *
+                     * This parser does not currently support this behavior: ignore the token.
+                     */
+                }
+                // Ignore the token.
+                return $this->step();
+            /*
+             * > A start tag whose tag name is one of: "base", "basefont", "bgsound", "link",
+             * > "meta", "noframes", "script", "style", "template", "title"
+             * >
+             * > An end tag whose tag name is "template"
+             */
+            case '+BASE':
+            case '+BASEFONT':
+            case '+BGSOUND':
+            case '+LINK':
+            case '+META':
+            case '+NOFRAMES':
+            case '+SCRIPT':
+            case '+STYLE':
+            case '+TEMPLATE':
+            case '+TITLE':
+            case '-TEMPLATE':
+                return $this->step_in_head();
+            /*
+             * > A start tag whose tag name is "body"
+             *
+             * This tag in the IN BODY insertion mode is a parse error.
+             */
+            case '+BODY':
+                if (
+=== $this->state->stack_of_open_elements->count() ||
+                    'BODY' !== $this->state->stack_of_open_elements->at( 2 ) ||
+                    $this->state->stack_of_open_elements->contains( 'TEMPLATE' )
+                ) {
+                    // Ignore the token.
+                    return $this->step();
+                }
                 /*
+                 * > A DOCTYPE token
+                 * > Parse error. Ignore the token.
+                 * > Otherwise, set the frameset-ok flag to "not ok"; then, for each attribute
+                 * > on the token, check to see if the attribute is already present on the body
+                 * > element (the second element) on the stack of open elements, and if it is
+                 * > not, add the attribute and its corresponding value to that element.
+                 *
+                 * This parser does not currently support this behavior: ignore the token.
                  */
+                $this->state->frameset_ok = false;
                 return $this->step();
             /*
+             * > A start tag whose tag name is "button"
+             */
+            case '+BUTTON':
+                if ( $this->state->stack_of_open_elements->has_element_in_scope( 'BUTTON' ) ) {
+                    // @todo Indicate a parse error once it's possible. This error does not impact the logic here.
+                    $this->generate_implied_end_tags();
+                    $this->state->stack_of_open_elements->pop_until( 'BUTTON' );
+                }
+                $this->reconstruct_active_formatting_elements();
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->frameset_ok = false;
+                return true;
+             * > A start tag whose tag name is "frameset"
+             *
+             * This tag in the IN BODY insertion mode is a parse error.
+             */
+            case '+FRAMESET':
+                if (
+=== $this->state->stack_of_open_elements->count() ||
+                    'BODY' !== $this->state->stack_of_open_elements->at( 2 ) ||
+                    false === $this->state->frameset_ok
+                ) {
+                    // Ignore the token.
+                    return $this->step();
+                }
+                /*
+                 * > Otherwise, run the following steps:
+                 */
+                $this->bail( 'Cannot process non-ignored FRAMESET tags.' );
+                break;
+            /*
+             * > An end tag whose tag name is "body"
+             */
+            case '-BODY':
+                if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'BODY' ) ) {
+                    // Parse error: ignore the token.
+                    return $this->step();
+                }
+                /*
+                 * > Otherwise, if there is a node in the stack of open elements that is not either a
+                 * > dd element, a dt element, an li element, an optgroup element, an option element,
+                 * > a p element, an rb element, an rp element, an rt element, an rtc element, a tbody
+                 * > element, a td element, a tfoot element, a th element, a thread element, a tr
+                 * > element, the body element, or the html element, then this is a parse error.
+                 *
+                 * There is nothing to do for this parse error, so don't check for it.
+                 */
+                $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY;
+                return true;
+            /*
+             * > An end tag whose tag name is "html"
+             */
+            case '-HTML':
+                if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'BODY' ) ) {
+                    // Parse error: ignore the token.
+                    return $this->step();
+                }
+                /*
+                 * > Otherwise, if there is a node in the stack of open elements that is not either a
+                 * > dd element, a dt element, an li element, an optgroup element, an option element,
+                 * > a p element, an rb element, an rp element, an rt element, an rtc element, a tbody
+                 * > element, a td element, a tfoot element, a th element, a thread element, a tr
+                 * > element, the body element, or the html element, then this is a parse error.
+                 *
+                 * There is nothing to do for this parse error, so don't check for it.
+                 */
+                $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_AFTER_BODY;
+                return $this->step( self::REPROCESS_CURRENT_NODE );
             /*
 …
             /*
+             * > A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+             */
+            case '+H1':
+            case '+H2':
+            case '+H3':
+            case '+H4':
+            case '+H5':
+            case '+H6':
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                if (
+                    in_array(
+                        $this->state->stack_of_open_elements->current_node()->node_name,
+                        array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ),
+                        true
+                    )
+                ) {
+                    // @todo Indicate a parse error once it's possible.
+                    $this->state->stack_of_open_elements->pop();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * > A start tag whose tag name is one of: "pre", "listing"
+             */
+            case '+PRE':
+            case '+LISTING':
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                /*
+                 * > If the next token is a U+000A LINE FEED (LF) character token,
+                 * > then ignore that token and move on to the next one. (Newlines
+                 * > at the start of pre blocks are ignored as an authoring convenience.)
+                 *
+                 * This is handled in `get_modifiable_text()`.
+                 */
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->frameset_ok = false;
+                return true;
+            /*
+             * > A start tag whose tag name is "form"
+             */
+            case '+FORM':
+                $stack_contains_template = $this->state->stack_of_open_elements->contains( 'TEMPLATE' );
+                if ( isset( $this->state->form_element ) && ! $stack_contains_template ) {
+                    // Parse error: ignore the token.
+                    return $this->step();
+                }
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                if ( ! $stack_contains_template ) {
+                    $this->state->form_element = $this->state->current_token;
+                }
+                return true;
+            /*
+             * > A start tag whose tag name is "li"
+             * > A start tag whose tag name is one of: "dd", "dt"
+             */
+            case '+DD':
+            case '+DT':
+            case '+LI':
+                $this->state->frameset_ok = false;
+                $node                     = $this->state->stack_of_open_elements->current_node();
+                $is_li                    = 'LI' === $token_name;
+                in_body_list_loop:
+                /*
+                 * The logic for LI and DT/DD is the same except for one point: LI elements _only_
+                 * close other LI elements, but a DT or DD element closes _any_ open DT or DD element.
+                 */
+                if ( $is_li ? 'LI' === $node->node_name : ( 'DD' === $node->node_name || 'DT' === $node->node_name ) ) {
+                    $node_name = $is_li ? 'LI' : $node->node_name;
+                    $this->generate_implied_end_tags( $node_name );
+                    if ( ! $this->state->stack_of_open_elements->current_node_is( $node_name ) ) {
+                        // @todo Indicate a parse error once it's possible. This error does not impact the logic here.
+                    }
+                    $this->state->stack_of_open_elements->pop_until( $node_name );
+                    goto in_body_list_done;
+                }
+                if (
+                    'ADDRESS' !== $node->node_name &&
+                    'DIV' !== $node->node_name &&
+                    'P' !== $node->node_name &&
+                    $this->is_special( $node->node_name )
+                ) {
+                    /*
+                     * > If node is in the special category, but is not an address, div,
+                     * > or p element, then jump to the step labeled done below.
+                     */
+                    goto in_body_list_done;
+                } else {
+                    /*
+                     * > Otherwise, set node to the previous entry in the stack of open elements
+                     * > and return to the step labeled loop.
+                     */
+                    foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) {
+                        $node = $item;
+                        break;
+                    }
+                    goto in_body_list_loop;
+                }
+                in_body_list_done:
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            case '+PLAINTEXT':
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                /*
+                 * @todo This may need to be handled in the Tag Processor and turn into
+                 *       a single self-contained tag like TEXTAREA, whose modifiable text
+                 *       is the rest of the input document as plaintext.
+                 */
+                $this->bail( 'Cannot process PLAINTEXT elements.' );
+                break;
+            /*
+             * > A start tag whose tag name is "button"
+             */
+            case '+BUTTON':
+                if ( $this->state->stack_of_open_elements->has_element_in_scope( 'BUTTON' ) ) {
+                    // @todo Indicate a parse error once it's possible. This error does not impact the logic here.
+                    $this->generate_implied_end_tags();
+                    $this->state->stack_of_open_elements->pop_until( 'BUTTON' );
+                }
+                $this->reconstruct_active_formatting_elements();
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->frameset_ok = false;
+                return true;
+            /*
              * > An end tag whose tag name is one of: "address", "article", "aside", "blockquote",
              * > "button", "center", "details", "dialog", "dir", "div", "dl", "fieldset",
              * > "figcaption", "figure", "footer", "header", "hgroup", "listing", "main",
              * > "menu", "nav", "ol", "pre", "search", "section", "summary", "ul"
+             *
+             * @todo This needs to check if the element in scope is an HTML element, meaning that
+             *       when SVG and MathML support is added, this needs to differentiate between an
+             *       HTML element of the given name, such as `<center>`, and a foreign element of
+             *       the same given name.
              */
             case '-ADDRESS':
 …
             /*
+             * > A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+             */
+            case '+H1':
+            case '+H2':
+            case '+H3':
+            case '+H4':
+            case '+H5':
+            case '+H6':
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                if (
+                    in_array(
+                        $this->state->stack_of_open_elements->current_node()->node_name,
+                        array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ),
+                        true
+                    )
+                ) {
+                    // @todo Indicate a parse error once it's possible.
+                    $this->state->stack_of_open_elements->pop();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * > A start tag whose tag name is one of: "pre", "listing"
+             */
+            case '+PRE':
+            case '+LISTING':
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->frameset_ok = false;
+                return true;
+            /*
+             * > An end tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+             */
+            case '-H1':
+            case '-H2':
+            case '-H3':
+            case '-H4':
+            case '-H5':
+            case '-H6':
+                if ( ! $this->state->stack_of_open_elements->has_element_in_scope( '(internal: H1 through H6 - do not use)' ) ) {
+             * > An end tag whose tag name is "form"
+             */
+            case '-FORM':
+                if ( ! $this->state->stack_of_open_elements->contains( 'TEMPLATE' ) ) {
+                    $node                      = $this->state->form_element;
+                    $this->state->form_element = null;
                     /*
+                     * This is a parse error; ignore the token.
+                     * > If node is null or if the stack of open elements does not have node
+                     * > in scope, then this is a parse error; return and ignore the token.
+                     *
+                     * @todo Indicate a parse error once it's possible.
+                     * @todo It's necessary to check if the form token itself is in scope, not
+                     *       simply whether any FORM is in scope.
                      */
+                    return $this->step();
+                }
+                $this->generate_implied_end_tags();
+                if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
+                    // @todo Record parse error: this error doesn't impact parsing.
+                }
+                $this->state->stack_of_open_elements->pop_until( '(internal: H1 through H6 - do not use)' );
+                return true;
+            /*
+             * > A start tag whose tag name is "li"
+             * > A start tag whose tag name is one of: "dd", "dt"
+             */
+            case '+DD':
+            case '+DT':
+            case '+LI':
+                $this->state->frameset_ok = false;
+                $node                     = $this->state->stack_of_open_elements->current_node();
+                $is_li                    = 'LI' === $token_name;
+                in_body_list_loop:
+                /*
+                 * The logic for LI and DT/DD is the same except for one point: LI elements _only_
+                 * close other LI elements, but a DT or DD element closes _any_ open DT or DD element.
+                 */
+                if ( $is_li ? 'LI' === $node->node_name : ( 'DD' === $node->node_name || 'DT' === $node->node_name ) ) {
+                    $node_name = $is_li ? 'LI' : $node->node_name;
+                    $this->generate_implied_end_tags( $node_name );
+                    if ( ! $this->state->stack_of_open_elements->current_node_is( $node_name ) ) {
+                    if (
+                        null === $node ||
+                        ! $this->state->stack_of_open_elements->has_element_in_scope( 'FORM' )
+                    ) {
+                        // Parse error: ignore the token.
+                        return $this->step();
+                    }
+                    $this->generate_implied_end_tags();
+                    if ( $node !== $this->state->stack_of_open_elements->current_node() ) {
+                        // @todo Indicate a parse error once it's possible. This error does not impact the logic here.
+                        $this->bail( 'Cannot close a FORM when other elements remain open as this would throw off the breadcrumbs for the following tokens.' );
+                    }
+                    $this->state->stack_of_open_elements->remove_node( $node );
+                } else {
+                    /*
+                     * > If the stack of open elements does not have a form element in scope,
+                     * > then this is a parse error; return and ignore the token.
+                     *
+                     * Note that unlike in the clause above, this is checking for any FORM in scope.
+                     */
+                    if ( ! $this->state->stack_of_open_elements->has_element_in_scope( 'FORM' ) ) {
+                        // Parse error: ignore the token.
+                        return $this->step();
+                    }
+                    $this->generate_implied_end_tags();
+                    if ( ! $this->state->stack_of_open_elements->current_node_is( 'FORM' ) ) {
                         // @todo Indicate a parse error once it's possible. This error does not impact the logic here.
+                    }
+                    $this->state->stack_of_open_elements->pop_until( $node_name );
+                    goto in_body_list_done;
+                }
+                if (
+                    'ADDRESS' !== $node->node_name &&
+                    'DIV' !== $node->node_name &&
+                    'P' !== $node->node_name &&
+                    $this->is_special( $node->node_name )
+                ) {
+                    /*
+                     * > If node is in the special category, but is not an address, div,
+                     * > or p element, then jump to the step labeled done below.
+                     */
+                    goto in_body_list_done;
+                } else {
+                    /*
+                     * > Otherwise, set node to the previous entry in the stack of open elements
+                     * > and return to the step labeled loop.
+                     */
+                    foreach ( $this->state->stack_of_open_elements->walk_up( $node ) as $item ) {
+                        $node = $item;
+                        break;
+                    }
+                    goto in_body_list_loop;
+                }
+                in_body_list_done:
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                    $this->state->stack_of_open_elements->pop_until( 'FORM' );
+                    return true;
+                }
+                break;
+            /*
+             * > An end tag whose tag name is "p"
+             */
+            case '-P':
+                if ( ! $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->insert_html_element( $this->state->current_token );
+                }
+                $this->close_a_p_element();
                 return true;
 …
             /*
+             * > An end tag whose tag name is "p"
+             */
+            case '-P':
+                if ( ! $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->insert_html_element( $this->state->current_token );
+                }
+                $this->close_a_p_element();
+                return true;
+            // > A start tag whose tag name is "a"
+             * > An end tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+             */
+            case '-H1':
+            case '-H2':
+            case '-H3':
+            case '-H4':
+            case '-H5':
+            case '-H6':
+                if ( ! $this->state->stack_of_open_elements->has_element_in_scope( '(internal: H1 through H6 - do not use)' ) ) {
+                    /*
+                     * This is a parse error; ignore the token.
+                     *
+                     * @todo Indicate a parse error once it's possible.
+                     */
+                    return $this->step();
+                }
+                $this->generate_implied_end_tags();
+                if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
+                    // @todo Record parse error: this error doesn't impact parsing.
+                }
+                $this->state->stack_of_open_elements->pop_until( '(internal: H1 through H6 - do not use)' );
+                return true;
+            /*
+             * > A start tag whose tag name is "a"
+             */
             case '+A':
                 foreach ( $this->state->active_formatting_elements->walk_up() as $item ) {
 …
             /*
+             * > A start tag whose tag name is "nobr"
+             */
+            case '+NOBR':
+                $this->reconstruct_active_formatting_elements();
+                if ( $this->state->stack_of_open_elements->has_element_in_scope( 'NOBR' ) ) {
+                    // Parse error.
+                    $this->run_adoption_agency_algorithm();
+                    $this->reconstruct_active_formatting_elements();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->active_formatting_elements->push( $this->state->current_token );
+                return true;
+            /*
              * > An end tag whose tag name is one of: "a", "b", "big", "code", "em", "font", "i",
              * > "nobr", "s", "small", "strike", "strong", "tt", "u"
 …
             /*
+             * > A start tag whose tag name is one of: "applet", "marquee", "object"
+             */
+            case '+APPLET':
+            case '+MARQUEE':
+            case '+OBJECT':
+                $this->reconstruct_active_formatting_elements();
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->active_formatting_elements->insert_marker();
+                $this->state->frameset_ok = false;
+                return true;
+            /*
+             * > A end tag token whose tag name is one of: "applet", "marquee", "object"
+             *
+             * @todo This needs to check if the element in scope is an HTML element, meaning that
+             *       when SVG and MathML support is added, this needs to differentiate between an
+             *       HTML element of the given name, such as `<object>`, and a foreign element of
+             *       the same given name.
+             */
+            case '-APPLET':
+            case '-MARQUEE':
+            case '-OBJECT':
+                if ( ! $this->state->stack_of_open_elements->has_element_in_scope( $token_name ) ) {
+                    // Parse error: ignore the token.
+                    return $this->step();
+                }
+                $this->generate_implied_end_tags();
+                if ( ! $this->state->stack_of_open_elements->current_node_is( $token_name ) ) {
+                    // This is a parse error.
+                }
+                $this->state->stack_of_open_elements->pop_until( $token_name );
+                $this->state->active_formatting_elements->clear_up_to_last_marker();
+                return true;
+            /*
+             * > A start tag whose tag name is "table"
+             */
+            case '+TABLE':
+                if (
+                    WP_HTML_Processor_State::QUIRKS_MODE !== $this->state->document_mode &&
+                    $this->state->stack_of_open_elements->has_p_in_button_scope()
+                ) {
+                    $this->close_a_p_element();
+                }
+                $this->insert_html_element( $this->state->current_token );
+                $this->state->frameset_ok    = false;
+                $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
+                return true;
+            /*
              * > An end tag whose tag name is "br"
+             * >   Parse error. Drop the attributes from the token, and act as described in the next
+             * >   entry; i.e. act as if this was a "br" start tag token with no attributes, rather
+             * >   than the end tag token that it actually is.
+             */
+            case '-BR':
+                $this->bail( 'Closing BR tags require unimplemented special handling.' );
+                // This return required because PHPCS can't determine that the call to bail() throws.
+                return false;
+             *
+             * This is prevented from happening because the Tag Processor
+             * reports all closing BR tags as if they were opening tags.
+             */
             /*
 …
                 $this->reconstruct_active_formatting_elements();
                 $this->insert_html_element( $this->state->current_token );
+                $type_attribute = $this->get_attribute( 'type' );
                 /*
                  * > If the token does not have an attribute with the name "type", or if it does,
 …
                  * > string "hidden", then: set the frameset-ok flag to "not ok".
                  */
+                $type_attribute = $this->get_attribute( 'type' );
                 if ( ! is_string( $type_attribute ) || 'hidden' !== strtolower( $type_attribute ) ) {
                     $this->state->frameset_ok = false;
+                }
+                return true;
+            /*
+             * > A start tag whose tag name is one of: "param", "source", "track"
+             */
+            case '+PARAM':
+            case '+SOURCE':
+            case '+TRACK':
+                $this->insert_html_element( $this->state->current_token );
                 return true;
 …
             /*
+             * > A start tag whose tag name is one of: "param", "source", "track"
+             */
+            case '+PARAM':
+            case '+SOURCE':
+            case '+TRACK':
+             * > A start tag whose tag name is "image"
+             */
+            case '+IMAGE':
+                /*
+                 * > Parse error. Change the token's tag name to "img" and reprocess it. (Don't ask.)
+                 *
+                 * Note that this is handled elsewhere, so it should not be possible to reach this code.
+                 */
+                $this->bail( "Cannot process an IMAGE tag. (Don't ask.)" );
+                break;
+            /*
+             * > A start tag whose tag name is "textarea"
+             */
+            case '+TEXTAREA':
+                $this->insert_html_element( $this->state->current_token );
+                /*
+                 * > If the next token is a U+000A LINE FEED (LF) character token, then ignore
+                 * > that token and move on to the next one. (Newlines at the start of
+                 * > textarea elements are ignored as an authoring convenience.)
+                 *
+                 * This is handled in `get_modifiable_text()`.
+                 */
+                $this->state->frameset_ok = false;
+                /*
+                 * > Switch the insertion mode to "text".
+                 *
+                 * As a self-contained node, this behavior is handled in the Tag Processor.
+                 */
+                return true;
+            /*
+             * > A start tag whose tag name is "xmp"
+             */
+            case '+XMP':
+                if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+                    $this->close_a_p_element();
+                }
+                $this->reconstruct_active_formatting_elements();
+                $this->state->frameset_ok = false;
+                /*
+                 * > Follow the generic raw text element parsing algorithm.
+                 *
+                 * As a self-contained node, this behavior is handled in the Tag Processor.
+                 */
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * A start tag whose tag name is "iframe"
+             */
+            case '+IFRAME':
+                $this->state->frameset_ok = false;
+                /*
+                 * > Follow the generic raw text element parsing algorithm.
+                 *
+                 * As a self-contained node, this behavior is handled in the Tag Processor.
+                 */
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * > A start tag whose tag name is "noembed"
+             * > A start tag whose tag name is "noscript", if the scripting flag is enabled
+             *
+             * The scripting flag is never enabled in this parser.
+             */
+            case '+NOEMBED':
                 $this->insert_html_element( $this->state->current_token );
                 return true;
 …
                 $this->insert_html_element( $this->state->current_token );
                 return true;
+        }
+        /*
+         * These tags require special handling in the 'in body' insertion mode
+         * but that handling hasn't yet been implemented.
+         *
+         * As the rules for each tag are implemented, the corresponding tag
+         * name should be removed from this list. An accompanying test should
+         * help ensure this list is maintained.
+         *
+         * @see Tests_HtmlApi_WpHtmlProcessor::test_step_in_body_fails_on_unsupported_tags
+         *
+         * Since this switch structure throws a WP_HTML_Unsupported_Exception, it's
+         * possible to handle "any other start tag" and "any other end tag" below,
+         * as that guarantees execution doesn't proceed for the unimplemented tags.
+         *
+         * @see https://html.spec.whatwg.org/multipage/parsing.html#parsing-main-inbody
+         */
+        switch ( $token_name ) {
+            case 'APPLET':
+            case 'BASE':
+            case 'BASEFONT':
+            case 'BGSOUND':
+            case 'BODY':
+            case 'CAPTION':
+            case 'COL':
+            case 'COLGROUP':
+            case 'FORM':
+            case 'FRAME':
+            case 'FRAMESET':
+            case 'HEAD':
+            case 'HTML':
+            case 'IFRAME':
+            case 'LINK':
+            case 'MARQUEE':
+            case 'MATH':
+            case 'META':
+            case 'NOBR':
+            case 'NOEMBED':
+            case 'NOFRAMES':
+            case 'NOSCRIPT':
+            case 'OBJECT':
+            case 'PLAINTEXT':
+            case 'RB':
+            case 'RP':
+            case 'RT':
+            case 'RTC':
+            case 'SARCASM':
+            case 'SCRIPT':
+            case 'STYLE':
+            case 'SVG':
+            case 'TABLE':
+            case 'TBODY':
+            case 'TD':
+            case 'TEMPLATE':
+            case 'TEXTAREA':
+            case 'TFOOT':
+            case 'TH':
+            case 'THEAD':
+            case 'TITLE':
+            case 'TR':
+            case 'XMP':
+                $this->bail( "Cannot process {$token_name} element." );
+            /*
+             * > A start tag whose tag name is one of: "rb", "rtc"
+             */
+            case '+RB':
+            case '+RTC':
+                if ( $this->state->stack_of_open_elements->has_element_in_scope( 'RUBY' ) ) {
+                    $this->generate_implied_end_tags();
+                    if ( $this->state->stack_of_open_elements->current_node_is( 'RUBY' ) ) {
+                        // @todo Indicate a parse error once it's possible.
+                    }
+                }
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * > A start tag whose tag name is one of: "rp", "rt"
+             */
+            case '+RP':
+            case '+RT':
+                if ( $this->state->stack_of_open_elements->has_element_in_scope( 'RUBY' ) ) {
+                    $this->generate_implied_end_tags( 'RTC' );
+                    $current_node_name = $this->state->stack_of_open_elements->current_node()->node_name;
+                    if ( 'RTC' === $current_node_name || 'RUBY' === $current_node_name ) {
+                        // @todo Indicate a parse error once it's possible.
+                    }
+                }
+                $this->insert_html_element( $this->state->current_token );
+                return true;
+            /*
+             * > A start tag whose tag name is "math"
+             */
+            case '+MATH':
+                $this->reconstruct_active_formatting_elements();
+                /*
+                 * @todo Adjust MathML attributes for the token. (This fixes the case of MathML attributes that are not all lowercase.)
+                 * @todo Adjust foreign attributes for the token. (This fixes the use of namespaced attributes, in particular XLink.)
+                 *
+                 * These ought to be handled in the attribute methods.
+                 */
+                $this->bail( 'Cannot process MATH element, opening foreign content.' );
+                break;
+            /*
+             * > A start tag whose tag name is "svg"
+             */
+            case '+SVG':
+                $this->reconstruct_active_formatting_elements();
+                /*
+                 * @todo Adjust SVG attributes for the token. (This fixes the case of SVG attributes that are not all lowercase.)
+                 * @todo Adjust foreign attributes for the token. (This fixes the use of namespaced attributes, in particular XLink in SVG.)
+                 *
+                 * These ought to be handled in the attribute methods.
+                 */
+                $this->bail( 'Cannot process SVG element, opening foreign content.' );
+                break;
+            /*
+             * > A start tag whose tag name is one of: "caption", "col", "colgroup",
+             * > "frame", "head", "tbody", "td", "tfoot", "th", "thead", "tr"
+             */
+            case '+CAPTION':
+            case '+COL':
+            case '+COLGROUP':
+            case '+FRAME':
+            case '+HEAD':
+            case '+TBODY':
+            case '+TD':
+            case '+TFOOT':
+            case '+TH':
+            case '+THEAD':
+            case '+TR':
+                // Parse error. Ignore the token.
+                return $this->step();
+        }
 …
              */
             foreach ( $this->state->stack_of_open_elements->walk_up() as $node ) {
+                /*
+                 * @todo This needs to check if the element in scope is an HTML element, meaning that
+                 *       when SVG and MathML support is added, this needs to differentiate between an
+                 *       HTML element of the given name, such as `<object>`, and a foreign element of
+                 *       the same given name.
+                 */
                 if ( $token_name === $node->node_name ) {
                     break;

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

-                      r58769
+                      r58779
  *     true === $processor->next_tag( 'DIV' );
+ *
  * #### Special elements
+ * #### Special self-contained elements
+ *
  * Some HTML elements are handled in a special way; their start and end tags
 …
     /**
+     * Whether the parser should skip over an immediately-following linefeed
+     * character, as is the case with LISTING, PRE, and TEXTAREA.
+     *
+     * > If the next token is a U+000A LINE FEED (LF) character token, then
+     * > ignore that token and move on to the next one. (Newlines at the start
+     * > of [these] elements are ignored as an authoring convenience.)
+     *
+     * @since 6.7.0
+     *
+     * @var int|null
+     */
+    private $skip_newline_at = null;
+    /**
      * Constructor.
+     *
 …
         /*
+         * For non-DATA sections which might contain text that looks like HTML tags but
+         * isn't, scan with the appropriate alternative mode. Looking at the first letter
+         * of the tag name as a pre-check avoids a string allocation when it's not needed.
+         */
+        $t = $this->html[ $this->tag_name_starts_at ];
+         * Certain tags require additional processing. The first-letter pre-check
+         * avoids unnecessary string allocation when comparing the tag names.
+         *
+         *  - IFRAME
+         *  - LISTING (deprecated)
+         *  - NOEMBED (deprecated)
+         *  - NOFRAMES (deprecated)
+         *  - PRE
+         *  - SCRIPT
+         *  - STYLE
+         *  - TEXTAREA
+         *  - TITLE
+         *  - XMP (deprecated)
+         */
         if (
             $this->is_closing_tag ||
+            ! (
+                'i' === $t || 'I' === $t ||
+                'n' === $t || 'N' === $t ||
+                's' === $t || 'S' === $t ||
+                't' === $t || 'T' === $t ||
+                'x' === $t || 'X' === $t
+            )
+!== strspn( $this->html, 'iIlLnNpPsStTxX', $this->tag_name_starts_at, 1 )
         ) {
             return true;
 …
         /*
+         * For LISTING, PRE, and TEXTAREA, the first linefeed of an immediately-following
+         * text node is ignored as an authoring convenience.
+         *
+         * @see static::skip_newline_at
+         */
+        if ( 'LISTING' === $tag_name || 'PRE' === $tag_name ) {
+            $this->skip_newline_at = $this->bytes_already_parsed;
+            return true;
+        }
+        /*
+         * There are certain elements whose children are not DATA but are instead
+         * RCDATA or RAWTEXT. These cannot contain other elements, and the contents
+         * are parsed as plaintext, with character references decoded in RCDATA but
+         * not in RAWTEXT.
+         *
+         * These elements are described here as "self-contained" or special atomic
+         * elements whose end tag is consumed with the opening tag, and they will
+         * contain modifiable text inside of them.
+         *
          * Preserve the opening tag pointers, as these will be overwritten
          * when finding the closing tag. They will be reset after finding
 …
+     *
      * @since 6.2.0
+     * @since 6.7.0 Reports all BR tags as opening tags.
+     *
      * @return bool Whether the current tag is a tag closer.
 …
         return (
             self::STATE_MATCHED_TAG === $this->parser_state &&
+            $this->is_closing_tag
+            $this->is_closing_tag &&
+            /*
+             * The BR tag can only exist as an opening tag. If something like `</br>`
+             * appears then the HTML parser will treat it as an opening tag with no
+             * attributes. The BR tag is unique in this way.
+             *
+             * @see https://html.spec.whatwg.org/#parsing-main-inbody
+             */
+            'BR' !== $this->get_tag()
         );
+    }
 …
      * have an empty string (e.g. a comment with no contents).
+     *
+     * Limitations:
+     *
+     *  - This function will not strip the leading newline appropriately
+     *    after seeking into a LISTING or PRE element. To ensure that the
+     *    newline is treated properly, seek to the LISTING or PRE opening
+     *    tag instead of to the first text node inside the element.
+     *
      * @since 6.5.0
+     * @since 6.7.0 Replaces NULL bytes (U+0000) and newlines appropriately.
+     *
      * @return string
      */
     public function get_modifiable_text(): string {
         if ( null === $this->text_starts_at ) {
+        if ( null === $this->text_starts_at || 0 === $this->text_length ) {
             return '';
+        }
         $text = substr( $this->html, $this->text_starts_at, $this->text_length );
+        /*
+         * Pre-processing the input stream would normally happen before
+         * any parsing is done, but deferring it means it's possible to
+         * skip in most cases. When getting the modifiable text, however
+         * it's important to apply the pre-processing steps, which is
+         * normalizing newlines.
+         *
+         * @see https://html.spec.whatwg.org/#preprocessing-the-input-stream
+         * @see https://infra.spec.whatwg.org/#normalize-newlines
+         */
+        $text = str_replace( "\r\n", "\n", $text );
+        $text = str_replace( "\r", "\n", $text );
         // Comment data is not decoded.
 …
             self::STATE_FUNKY_COMMENT === $this->parser_state
         ) {
             return $text;
+        }
         $tag_name = $this->get_tag();
+            return str_replace( "\x00", "\u{FFFD}", $text );
+        }
+        $tag_name = $this->get_token_name();
         if (
             // Script data is not decoded.
 …
             'XMP' === $tag_name
         ) {
             return $text;
+            return str_replace( "\x00", "\u{FFFD}", $text );
+        }
 …
         /*
+         * TEXTAREA skips a leading newline, but this newline may appear not only as the
+         * literal character `\n`, but also as a character reference, such as in the
+         * following markup: `<textarea>&#x0a;Content</textarea>`.
+         *
+         * For these cases it's important to first decode the text content before checking
+         * for a leading newline and removing it.
+         * Skip the first line feed after LISTING, PRE, and TEXTAREA opening tags.
+         *
+         * Note that this first newline may come in the form of a character
+         * reference, such as `&#x0a;`, and so it's important to perform
+         * this transformation only after decoding the raw text content.
          */
         if (
+            self::STATE_MATCHED_TAG === $this->parser_state &&
+            'TEXTAREA' === $tag_name &&
+            strlen( $decoded ) > 0 &&
+            "\n" === $decoded[0]
+            ( "\n" === ( $decoded[0] ?? '' ) ) &&
+            ( ( $this->skip_newline_at === $this->token_starts_at && '#text' === $tag_name ) || 'TEXTAREA' === $tag_name )
         ) {
+            return substr( $decoded, 1 );
+        }
+        return $decoded;
+            $decoded = substr( $decoded, 1 );
+        }
+        /*
+         * Only in normative text nodes does the NULL byte (U+0000) get removed.
+         * In all other contexts it's replaced by the replacement character (U+FFFD)
+         * for security reasons (to avoid joining together strings that were safe
+         * when separated, but not when joined).
+         */
+        return '#text' === $tag_name
+            ? str_replace( "\x00", '', $decoded )
+            : str_replace( "\x00", "\u{FFFD}", $decoded );
+    }

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

-                      r58769
+                      r58779
      * @since 6.4.0
+     *
+     * @param string        $bookmark_name         Name of bookmark corresponding to location in HTML where token is found.
+     * @param string|null   $bookmark_name         Name of bookmark corresponding to location in HTML where token is found,
+     *                                             or `null` for markers and nodes without a bookmark.
      * @param string        $node_name             Name of node token represents; if uppercase, an HTML element; if lowercase, a special value like "marker".
      * @param bool          $has_self_closing_flag Whether the source token contains the self-closing flag, regardless of whether it's valid.
      * @param callable|null $on_destroy            Optional. Function to call when destroying token, useful for releasing the bookmark.
      */
     public function __construct( string $bookmark_name, string $node_name, bool $has_self_closing_flag, ?callable $on_destroy = null ) {
+    public function __construct( ?string $bookmark_name, string $node_name, bool $has_self_closing_flag, ?callable $on_destroy = null ) {
         $this->bookmark_name         = $bookmark_name;
         $this->node_name             = $node_name;

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

-                      r58677
+                      r58779
      * @covers WP_HTML_Processor::is_void
+     *
      * @dataProvider data_void_tags
+     * @dataProvider data_void_tags_not_ignored_in_body
+     *
      * @param string $tag_name Name of void tag under test.
 …
         );
         foreach ( self::data_void_tags() as $tag_name => $_name ) {
+        foreach ( self::data_void_tags_not_ignored_in_body() as $tag_name => $_name ) {
             $self_contained_nodes[ "Void elements ({$tag_name})" ] = array( "<{$tag_name}>" );
+        }
 …
      * @ticket 60382
+     *
      * @dataProvider data_void_tags
+     * @dataProvider data_void_tags_not_ignored_in_body
+     *
      * @param string $tag_name Name of void tag under test.
 …
             $processor->get_breadcrumbs(),
             'Found incorrect nesting of first element.'
-        );
-        $this->assertTrue(
-            $processor->next_token(),
-            'Should have found the DIV as the second tag.'
-        );
-        $this->assertSame(
-            array( 'HTML', 'BODY', 'DIV' ),
-            $processor->get_breadcrumbs(),
-            "DIV should have been a sibling of the {$tag_name}."
         );
+    }
 …
     /**
+     * Data provider.
+     *
+     * @return array[]
+     */
+    public static function data_void_tags_not_ignored_in_body() {
+        $all_void_tags = self::data_void_tags();
+        unset( $all_void_tags['COL'] );
+        return $all_void_tags;
+    }
+    /**
      * Ensures that special handling of unsupported tags is cleaned up
      * as handling is implemented. Otherwise there's risk of leaving special
 …
     public static function data_unsupported_special_in_body_tags() {
         return array(
+            'APPLET'    => array( 'APPLET' ),
+            'BASE'      => array( 'BASE' ),
+            'BASEFONT'  => array( 'BASEFONT' ),
+            'BGSOUND'   => array( 'BGSOUND' ),
+            'BODY'      => array( 'BODY' ),
+            'CAPTION'   => array( 'CAPTION' ),
+            'COL'       => array( 'COL' ),
+            'COLGROUP'  => array( 'COLGROUP' ),
+            'FORM'      => array( 'FORM' ),
+            'FRAME'     => array( 'FRAME' ),
+            'FRAMESET'  => array( 'FRAMESET' ),
+            'HEAD'      => array( 'HEAD' ),
+            'HTML'      => array( 'HTML' ),
+            'IFRAME'    => array( 'IFRAME' ),
+            'LINK'      => array( 'LINK' ),
+            'MARQUEE'   => array( 'MARQUEE' ),
+            'MATH'      => array( 'MATH' ),
+            'META'      => array( 'META' ),
+            'NOBR'      => array( 'NOBR' ),
+            'NOEMBED'   => array( 'NOEMBED' ),
+            'NOFRAMES'  => array( 'NOFRAMES' ),
+            'NOSCRIPT'  => array( 'NOSCRIPT' ),
+            'OBJECT'    => array( 'OBJECT' ),
+            'PLAINTEXT' => array( 'PLAINTEXT' ),
+            'RB'        => array( 'RB' ),
+            'RP'        => array( 'RP' ),
+            'RT'        => array( 'RT' ),
+            'RTC'       => array( 'RTC' ),
+            'SARCASM'   => array( 'SARCASM' ),
+            'SCRIPT'    => array( 'SCRIPT' ),
+            'STYLE'     => array( 'STYLE' ),
+            'SVG'       => array( 'SVG' ),
+            'TABLE'     => array( 'TABLE' ),
+            'TBODY'     => array( 'TBODY' ),
+            'TD'        => array( 'TD' ),
+            'TEMPLATE'  => array( 'TEMPLATE' ),
+            'TEXTAREA'  => array( 'TEXTAREA' ),
+            'TFOOT'     => array( 'TFOOT' ),
+            'TH'        => array( 'TH' ),
+            'THEAD'     => array( 'THEAD' ),
+            'TITLE'     => array( 'TITLE' ),
+            'TR'        => array( 'TR' ),
+            'XMP'       => array( 'XMP' ),
+            'MATH' => array( 'MATH' ),
+            'SVG'  => array( 'SVG' ),
         );
+    }

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

-                      r58741
+                      r58779
             'ACRONYM', // Neutralized.
             'ADDRESS',
+            'APPLET', // Deprecated.
             'AREA',
             'ARTICLE',
 …
             'FIGURE',
             'FONT',
+            'FORM',
             'FOOTER',
             'H1',
 …
             'MAP',
             'MARK',
+            'MARQUEE', // Deprecated.
             'MENU',
             'METER',
 …
             'NAV',
             'NEXTID', // Deprecated.
+            'NOBR', // Neutralized.
+            'NOSCRIPT',
+            'OBJECT',
             'OL',
             'OUTPUT',
 …
             'PROGRESS',
             'Q',
+            'RB', // Neutralized.
+            'RP',
+            'RT',
+            'RTC', // Neutralized.
             'RUBY',
             'SAMP',
 …
             'SUMMARY',
             'SUP',
+            'TABLE',
             'TIME',
             'TT',
 …
     public static function data_unsupported_elements() {
         $unsupported_elements = array(
-            'APPLET', // Deprecated.
             'BASE',
             'BGSOUND', // Deprecated; self-closing if self-closing flag provided, otherwise normal.
 …
             'COL',
             'COLGROUP',
-            'FORM',
             'FRAME',
             'FRAMESET',
 …
             'IFRAME',
             'LINK',
-            'MARQUEE', // Deprecated.
             'MATH',
             'META',
-            'NOBR', // Neutralized.
             'NOEMBED', // Neutralized.
             'NOFRAMES', // Neutralized.
-            'NOSCRIPT',
-            'OBJECT',
             'PLAINTEXT', // Neutralized.
-            'RB', // Neutralized.
-            'RP',
-            'RT',
-            'RTC', // Neutralized.
             'SCRIPT',
             'STYLE',
             'SVG',
-            'TABLE',
             'TBODY',
             'TD',

trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

-                      r58742
+                      r58779
      */
     const SKIP_TESTS = array(
+        'adoption01/line0046'       => 'Unimplemented: Reconstruction of active formatting elements.',
+        'adoption01/line0159'       => 'Unimplemented: Reconstruction of active formatting elements.',
+        'adoption01/line0318'       => 'Unimplemented: Reconstruction of active formatting elements.',
+        'inbody01/line0001'         => 'Bug.',
+        'inbody01/line0014'         => 'Bug.',
+        'inbody01/line0029'         => 'Bug.',
+        'menuitem-element/line0012' => 'Bug.',
+        'tests1/line0342'           => "Closing P tag implicitly creates opener, which we don't visit.",
+        'tests1/line0720'           => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests15/line0001'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests15/line0022'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests2/line0650'           => 'Whitespace only test never enters "in body" parsing mode.',
+        'tests20/line0497'          => "Closing P tag implicitly creates opener, which we don't visit.",
+        'tests23/line0001'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0041'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0069'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0101'          => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests25/line0169'          => 'Bug.',
+        'tests26/line0263'          => 'Bug: An active formatting element should be created for a trailing text node.',
+        'adoption01/line0046' => 'Unimplemented: Reconstruction of active formatting elements.',
+        'adoption01/line0159' => 'Unimplemented: Reconstruction of active formatting elements.',
+        'adoption01/line0318' => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests1/line0720'     => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests15/line0001'    => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests15/line0022'    => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests15/line0068'    => 'Unimplemented: no support outside of IN BODY yet.',
+        'tests2/line0650'     => 'Whitespace only test never enters "in body" parsing mode.',
+        'tests19/line0965'    => 'Unimplemented: no support outside of IN BODY yet.',
+        'tests23/line0001'    => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0041'    => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0069'    => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests23/line0101'    => 'Unimplemented: Reconstruction of active formatting elements.',
+        'tests26/line0263'    => 'Bug: An active formatting element should be created for a trailing text node.',
+        'webkit01/line0231'   => 'Unimplemented: This parser does not add missing attributes to existing HTML or BODY tags.',
+        'webkit02/line0013'   => "Asserting behavior with scripting flag enabled, which this parser doesn't support.",
+        'webkit01/line0300'   => 'Unimplemented: no support outside of IN BODY yet.',
+        'webkit01/line0310'   => 'Unimplemented: no support outside of IN BODY yet.',
+        'webkit01/line0336'   => 'Unimplemented: no support outside of IN BODY yet.',
+        'webkit01/line0349'   => 'Unimplemented: no support outside of IN BODY yet.',
+        'webkit01/line0362'   => 'Unimplemented: no support outside of IN BODY yet.',
+        'webkit01/line0375'   => 'Unimplemented: no support outside of IN BODY yet.',
     );
 …
                             $output .= str_repeat( $indent, $tag_indent + 1 ) . "{$attribute_name}=\"{$val}\"\n";
+                        }
+                        // Self-contained tags contain their inner contents as modifiable text.
+                        $modifiable_text = $processor->get_modifiable_text();
+                        if ( '' !== $modifiable_text ) {
+                            $was_text = true;
+                            if ( '' === $text_node ) {
+                                $text_node = str_repeat( $indent, $indent_level ) . '"';
+                            }
+                            $text_node .= $modifiable_text;
+                            --$indent_level;
+                        }
+                    }
+                    // Self-contained tags contain their inner contents as modifiable text.
+                    $modifiable_text = $processor->get_modifiable_text();
+                    if ( '' !== $modifiable_text ) {
+                        $output .= str_repeat( $indent, $indent_level ) . "\"{$modifiable_text}\"\n";
+                    }
+                    if ( ! $processor->is_void( $tag_name ) && ! $processor->expects_closer() ) {
+                        --$indent_level;
+                    }
 …
                         case WP_HTML_Processor::COMMENT_AS_ABRUPTLY_CLOSED_COMMENT:
                         case WP_HTML_Processor::COMMENT_AS_HTML_COMMENT:
+                        case WP_HTML_Processor::COMMENT_AS_INVALID_HTML:
                             $comment_text_content = $processor->get_modifiable_text();
                             break;

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

-                      r58713
+                      r58779
     /**
+     * Ensures that support isn't accidentally partially added for the closing BR tag `</br>`.
+     *
+     * This tag closer has special rules and support shouldn't be added without implementing full support.
+     * Ensures that closing `</br>` tags are appropriately treated as opening tags with no attributes.
+     *
      * > An end tag whose tag name is "br"
 …
      * >   tag token that it actually is.
+     *
-     * When this handling is implemented, this test should be removed. It's not incorporated
-     * into the existing unsupported tag behavior test because the opening tag is supported;
-     * only the closing tag isn't.
+     *
      * @covers WP_HTML_Processor::step_in_body
+     *
 …
      */
     public function test_br_end_tag_unsupported() {
+        $processor = WP_HTML_Processor::create_fragment( '</br>' );
+        $this->assertFalse( $processor->next_tag(), 'Found a BR tag that should not be handled.' );
+        $this->assertSame( WP_HTML_Processor::ERROR_UNSUPPORTED, $processor->get_last_error() );
+        $processor = WP_HTML_Processor::create_fragment( '</br id="an-opener" html>' );
+        $this->assertTrue( $processor->next_tag(), 'Failed to find the expected opening BR tag.' );
+        $this->assertFalse( $processor->is_tag_closer(), 'Should have treated the tag as an opening tag.' );
+        $this->assertNull( $processor->get_attribute_names_with_prefix( '' ), 'Should have ignored any attributes on the tag.' );
+    }
+}

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

-                      r58677
+                      r58779
-<?php
-/**
- * Unit tests for the HTML API indicating that changes are needed to the
- * WP_HTML_Processor class before specific features are added to the API.
+ *
- * Note! Duplication of test cases and the helper function in this file are intentional.
- * This test file exists to warn developers of related areas of code that need to update
- * together when adding support for new elements to the HTML Processor. For example,
- * when adding support for the LI element it's necessary to update the function which
- * generates implied end tags. This is because each element might bring with it semantic
- * rules that impact the way the document should be parsed.
+ *
- * Without these tests a developer needs to investigate all possible places they
- * might need to update when adding support for more elements and risks overlooking
- * important parts that, in the absence of the related support, will lead to errors.
+ *
- * @package WordPress
- * @subpackage HTML-API
+ *
- * @since 6.4.0
+ *
- * @group html-api
+ *
- * @coversDefaultClass WP_HTML_Processor
- */
-class Tests_HtmlApi_WpHtmlSupportRequiredHtmlProcessor extends WP_UnitTestCase {
-    /**
-     * Fails to assert if the HTML Processor handles the given tag.
+     *
-     * This test helper is used throughout this test file for one purpose only: to
-     * fail a test if the HTML Processor handles the given tag. In other words, it
-     * ensures that the HTML Processor aborts when encountering the given tag.
+     *
-     * This is used to ensure that when support for a new tag is added to the
-     * HTML Processor it receives full support and not partial support, which
-     * could lead to a variety of issues.
+     *
-     * Do not remove this helper function as it provides semantic meaning to the
-     * assertions in the tests in this file and its behavior is incredibly specific
-     * and limited and doesn't warrant adding a new abstraction into WP_UnitTestCase.
+     *
-     * @param string $tag_name the HTML Processor should abort when encountering this tag, e.g. "BUTTON".
-     */
-    private function ensure_support_is_added_everywhere( $tag_name ) {
-        $processor = WP_HTML_Processor::create_fragment( "<$tag_name>" );
-        $this->assertFalse( $processor->step(), "Must support terminating elements in specific scope check before adding support for the {$tag_name} element." );
+    }
-    /**
-     * Generating implied end tags walks up the stack of open elements
-     * as long as any of the following missing elements is the current node.
+     *
-     * @since 6.4.0
+     *
-     * @ticket 58907
+     *
-     * @covers WP_HTML_Processor::generate_implied_end_tags
-     */
-    public function test_generate_implied_end_tags_needs_support() {
-        $this->ensure_support_is_added_everywhere( 'RB' );
-        $this->ensure_support_is_added_everywhere( 'RP' );
-        $this->ensure_support_is_added_everywhere( 'RT' );
-        $this->ensure_support_is_added_everywhere( 'RTC' );
+    }
-    /**
-     * Generating implied end tags thoroughly walks up the stack of open elements
-     * as long as any of the following missing elements is the current node.
+     *
-     * @since 6.4.0
+     *
-     * @ticket 58907
+     *
-     * @covers WP_HTML_Processor::generate_implied_end_tags_thoroughly
-     */
-    public function test_generate_implied_end_tags_thoroughly_needs_support() {
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'COLGROUP' );
-        $this->ensure_support_is_added_everywhere( 'RB' );
-        $this->ensure_support_is_added_everywhere( 'RP' );
-        $this->ensure_support_is_added_everywhere( 'RT' );
-        $this->ensure_support_is_added_everywhere( 'RTC' );
-        $this->ensure_support_is_added_everywhere( 'TBODY' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TFOOT' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'HEAD' );
-        $this->ensure_support_is_added_everywhere( 'TR' );
+    }
+}

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

-                      r58677
+                      r58779
      */
     public function test_has_element_in_scope_needs_support() {
-        // These elements impact all scopes.
-        $this->ensure_support_is_added_everywhere( 'APPLET' );
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'HTML' );
-        $this->ensure_support_is_added_everywhere( 'TABLE' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
-        $this->ensure_support_is_added_everywhere( 'OBJECT' );
-        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
         // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
         $this->ensure_support_is_added_everywhere( 'MATH' );
 …
      */
     public function test_has_element_in_list_item_scope_needs_support() {
-        // These elements impact all scopes.
-        $this->ensure_support_is_added_everywhere( 'APPLET' );
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'HTML' );
-        $this->ensure_support_is_added_everywhere( 'TABLE' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
-        $this->ensure_support_is_added_everywhere( 'OBJECT' );
-        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
         // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
         $this->ensure_support_is_added_everywhere( 'MATH' );
 …
      */
     public function test_has_element_in_button_scope_needs_support() {
-        // These elements impact all scopes.
-        $this->ensure_support_is_added_everywhere( 'APPLET' );
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'HTML' );
-        $this->ensure_support_is_added_everywhere( 'TABLE' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
-        $this->ensure_support_is_added_everywhere( 'OBJECT' );
-        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
         // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
         $this->ensure_support_is_added_everywhere( 'MATH' );
 …
      */
     public function test_after_element_pop_must_maintain_p_in_button_scope_flag() {
-        // These elements impact all scopes.
-        $this->ensure_support_is_added_everywhere( 'APPLET' );
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'HTML' );
-        $this->ensure_support_is_added_everywhere( 'TABLE' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
-        $this->ensure_support_is_added_everywhere( 'OBJECT' );
-        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
         // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
         $this->ensure_support_is_added_everywhere( 'MATH' );
 …
      */
     public function test_after_element_push_must_maintain_p_in_button_scope_flag() {
-        // These elements impact all scopes.
-        $this->ensure_support_is_added_everywhere( 'APPLET' );
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'HTML' );
-        $this->ensure_support_is_added_everywhere( 'TABLE' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
-        $this->ensure_support_is_added_everywhere( 'OBJECT' );
-        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
         // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
         $this->ensure_support_is_added_everywhere( 'MATH' );
 …
      */
     public function test_has_element_in_table_scope_needs_support() {
+        // These elements impact all scopes.
+        $this->ensure_support_is_added_everywhere( 'APPLET' );
+        $this->ensure_support_is_added_everywhere( 'CAPTION' );
+        $this->ensure_support_is_added_everywhere( 'HTML' );
+        $this->ensure_support_is_added_everywhere( 'TABLE' );
+        $this->ensure_support_is_added_everywhere( 'TD' );
+        $this->ensure_support_is_added_everywhere( 'TH' );
+        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
+        $this->ensure_support_is_added_everywhere( 'OBJECT' );
+        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
+        // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
+        $this->ensure_support_is_added_everywhere( 'MATH' );
+        /*
+         * SVG elements: note that TITLE is both an HTML element and an SVG element
+         * so care must be taken when adding support for either one.
+         *
+         * FOREIGNOBJECT, DESC, TITLE.
+         */
+        $this->ensure_support_is_added_everywhere( 'SVG' );
+        // These elements are specific to TABLE scope.
+        $this->ensure_support_is_added_everywhere( 'HTML' );
+        $this->ensure_support_is_added_everywhere( 'TABLE' );
+        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
+        // These elements depend on table scope.
+        $this->ensure_support_is_added_everywhere( 'CAPTION' );
+        $this->ensure_support_is_added_everywhere( 'COL' );
+        $this->ensure_support_is_added_everywhere( 'COLGROUP' );
+        $this->ensure_support_is_added_everywhere( 'TBODY' );
+        $this->ensure_support_is_added_everywhere( 'TD' );
+        $this->ensure_support_is_added_everywhere( 'TFOOT' );
+        $this->ensure_support_is_added_everywhere( 'TH' );
+        $this->ensure_support_is_added_everywhere( 'THEAD' );
+        $this->ensure_support_is_added_everywhere( 'TR' );
+        // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
+        $this->ensure_support_is_added_everywhere( 'MATH' );
+        /*
+         * SVG elements: note that TITLE is both an HTML element and an SVG element
+         * so care must be taken when adding support for either one.
+         *
+         * FOREIGNOBJECT, DESC, TITLE.
+         */
+        $this->ensure_support_is_added_everywhere( 'SVG' );
+    }
 …
      */
     public function test_has_element_in_select_scope_needs_support() {
-        // These elements impact all scopes.
-        $this->ensure_support_is_added_everywhere( 'APPLET' );
-        $this->ensure_support_is_added_everywhere( 'CAPTION' );
-        $this->ensure_support_is_added_everywhere( 'HTML' );
-        $this->ensure_support_is_added_everywhere( 'TABLE' );
-        $this->ensure_support_is_added_everywhere( 'TD' );
-        $this->ensure_support_is_added_everywhere( 'TH' );
-        $this->ensure_support_is_added_everywhere( 'MARQUEE' );
-        $this->ensure_support_is_added_everywhere( 'OBJECT' );
-        $this->ensure_support_is_added_everywhere( 'TEMPLATE' );
         // MathML Elements: MI, MO, MN, MS, MTEXT, ANNOTATION-XML.
         $this->ensure_support_is_added_everywhere( 'MATH' );

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

-                      r58040
+                      r58779
     /**
+     * Ensures that `get_modifiable_text()` properly transforms text content.
+     *
+     * The newline and NULL byte (U+0000) behaviors can be complicated since they depend
+     * on where the bytes were found and whether they were raw bytes in the input stream
+     * or decoded from character references.
+     *
+     * @ticket 61576
+     *
+     * @dataProvider data_modifiable_text_needing_transformation
+     *
+     * @param string $html_with_target_node    HTML with node containing `target` or `target-next` attribute.
+     * @param string $expected_modifiable_text Expected modifiable text from target node or following node.
+     */
+    public function test_modifiable_text_proper_transforms( string $html_with_target_node, string $expected_modifiable_text ) {
+        $processor = new WP_HTML_Tag_Processor( $html_with_target_node );
+        // Find the expected target node.
+        while ( $processor->next_token() ) {
+            $target = $processor->get_attribute( 'target' );
+            if ( true === $target ) {
+                break;
+            }
+            if ( is_numeric( $target ) ) {
+                for ( $i = (int) $target; $i > 0; $i-- ) {
+                    $processor->next_token();
+                }
+                break;
+            }
+        }
+        $this->assertSame(
+            $expected_modifiable_text,
+            $processor->get_modifiable_text(),
+            "Should have properly decoded and transformed modifiable text, but didn't."
+        );
+    }
+    /**
+     * Data provider.
+     *
+     * @return array[].
+     */
+    public static function data_modifiable_text_needing_transformation() {
+        return array(
+            'Text node + NULL byte'      => array( "<span target=1>NULL byte in \x00 text nodes disappears.", 'NULL byte in  text nodes disappears.' ),
+            'LISTING + newline'          => array( "<listing target=1>\nNo newline</listing>", 'No newline' ),
+            'LISTING + CR + LF'          => array( "<listing target=1>\r\nNo newline</listing>", 'No newline' ),
+            'LISTING + Encoded LF'       => array( '<listing target=1>&#x0a;No newline</listing>', 'No newline' ),
+            'LISTING + Encoded CR'       => array( '<listing target=1>&#x0d;Newline</listing>', "\rNewline" ),
+            'LISTING + Encoded CR + LF'  => array( '<listing target=1>&#x0d;&#x0a;Newline</listing>', "\r\nNewline" ),
+            'PRE + newline'              => array( "<pre target=1>\nNo newline</pre>", 'No newline' ),
+            'PRE + CR + LF'              => array( "<pre target=1>\r\nNo newline</pre>", 'No newline' ),
+            'PRE + Encoded LF'           => array( '<pre target=1>&#x0a;No newline</pre>', 'No newline' ),
+            'PRE + Encoded CR'           => array( '<pre target=1>&#x0d;Newline</pre>', "\rNewline" ),
+            'PRE + Encoded CR + LF'      => array( '<pre target=1>&#x0d;&#x0a;Newline</pre>', "\r\nNewline" ),
+            'TEXTAREA + newline'         => array( "<textarea target>\nNo newline</textarea>", 'No newline' ),
+            'TEXTAREA + CR + LF'         => array( "<textarea target>\r\nNo newline</textarea>", 'No newline' ),
+            'TEXTAREA + Encoded LF'      => array( '<textarea target>&#x0a;No newline</textarea>', 'No newline' ),
+            'TEXTAREA + Encoded CR'      => array( '<textarea target>&#x0d;Newline</textarea>', "\rNewline" ),
+            'TEXTAREA + Encoded CR + LF' => array( '<textarea target>&#x0d;&#x0a;Newline</textarea>', "\r\nNewline" ),
+            'TEXTAREA + Comment-like'    => array( "<textarea target><!-- comment -->\nNo newline</textarea>", "<!-- comment -->\nNo newline" ),
+            'PRE + Comment'              => array( "<pre target=2><!-- comment -->\nNo newline</pre>", "\nNo newline" ),
+            'PRE + CDATA-like'           => array( "<pre target=2><![CDATA[test]]>\nNo newline</pre>", "\nNo newline" ),
+            'LISTING + NULL byte'        => array( "<listing target=1>\x00 is missing</listing>", ' is missing' ),
+            'PRE + NULL byte'            => array( "<pre target=1>\x00 is missing</pre>", ' is missing' ),
+            'TEXTAREA + NULL byte'       => array( "<textarea target>\x00 is U+FFFD</textarea>", "\u{FFFD} is U+FFFD" ),
+            'SCRIPT + NULL byte'         => array( "<script target>\x00 is U+FFFD</script>", "\u{FFFD} is U+FFFD" ),
+            'esc(SCRIPT) + NULL byte'    => array( "<script target><!-- <script> \x00 </script> --> is U+FFFD</script>", "<!-- <script> \u{FFFD} </script> --> is U+FFFD" ),
+            'STYLE + NULL byte'          => array( "<style target>\x00 is U+FFFD</style>", "\u{FFFD} is U+FFFD" ),
+            'XMP + NULL byte'            => array( "<xmp target>\x00 is U+FFFD</xmp>", "\u{FFFD} is U+FFFD" ),
+            'CDATA-like + NULL byte'     => array( "<span target=1><![CDATA[just a \x00comment]]>", "just a \u{FFFD}comment" ),
+            'Funky comment + NULL byte'  => array( "<span target=1></%just a \x00comment>", "%just a \u{FFFD}comment" ),
+        );
+    }
+    /**
      * Ensures that normative Elements are properly parsed.
+     *

Make WordPress Core

Context Navigation

Legend:

trunk/src/wp-includes/html-api/class-wp-html-active-formatting-elements.php

trunk/src/wp-includes/html-api/class-wp-html-open-elements.php

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

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

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

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

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

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

trunk/tests/phpunit/tests/html-api/wpHtmlProcessorHtml5lib.php

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

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

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

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

Download in other formats: