<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" />
<title>[58806] trunk: HTML API: Add TABLE support in HTML Processor.</title>
</head>
<body>
<style type="text/css"><!--
#msg dl.meta { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dl.meta dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer, #logmsg { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre { white-space: pre-line; overflow: auto; background: #ffc; border: 1px #fa0 solid; padding: 6px; }
#logmsg { background: #ffc; border: 1px #fa0 solid; padding: 1em 1em 0 1em; }
#logmsg p, #logmsg pre, #logmsg blockquote { margin: 0 0 1em 0; }
#logmsg p, #logmsg li, #logmsg dt, #logmsg dd { line-height: 14pt; }
#logmsg h1, #logmsg h2, #logmsg h3, #logmsg h4, #logmsg h5, #logmsg h6 { margin: .5em 0; }
#logmsg h1:first-child, #logmsg h2:first-child, #logmsg h3:first-child, #logmsg h4:first-child, #logmsg h5:first-child, #logmsg h6:first-child { margin-top: 0; }
#logmsg ul, #logmsg ol { padding: 0; list-style-position: inside; margin: 0 0 0 1em; }
#logmsg ul { text-indent: -1em; padding-left: 1em; }#logmsg ol { text-indent: -1.5em; padding-left: 1.5em; }
#logmsg > ul, #logmsg > ol { margin: 0 0 1em 0; }
#logmsg pre { background: #eee; padding: 1em; }
#logmsg blockquote { border: 1px solid #fa0; border-left-width: 10px; padding: 1em 1em 0 1em; background: white;}
#logmsg dl { margin: 0; }
#logmsg dt { font-weight: bold; }
#logmsg dd { margin: 0; padding: 0 0 0.5em 0; }
#logmsg dd:before { content:'\00bb';}
#logmsg table { border-spacing: 0px; border-collapse: collapse; border-top: 4px solid #fa0; border-bottom: 1px solid #fa0; background: #fff; }
#logmsg table th { text-align: left; font-weight: normal; padding: 0.2em 0.5em; border-top: 1px dotted #fa0; }
#logmsg table td { text-align: right; border-top: 1px dotted #fa0; padding: 0.2em 0.5em; }
#logmsg table thead th { text-align: center; border-bottom: 1px solid #fa0; }
#logmsg table th.Corner { text-align: left; }
#logmsg hr { border: none 0; border-top: 2px dashed #fa0; height: 1px; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<div id="msg">
<dl class="meta" style="font-size: 105%">
<dt style="float: left; width: 6em; font-weight: bold">Revision</dt> <dd><a style="font-weight: bold" href="https://core.trac.wordpress.org/changeset/58806">58806</a><script type="application/ld+json">{"@context":"http://schema.org","@type":"EmailMessage","description":"Review this Commit","action":{"@type":"ViewAction","url":"https://core.trac.wordpress.org/changeset/58806","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>dmsnell</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2024-07-24 18:39:46 +0000 (Wed, 24 Jul 2024)</dd>
</dl>
<pre style='padding-left: 1em; margin: 2em 0; border-left: 2px solid #ccc; line-height: 1.25; font-size: 105%; font-family: sans-serif'>HTML API: Add TABLE support in HTML Processor.
As part of work to add more spec support to the HTML API, this patch adds
support for various table-related insertion modes. This includes support
for tables, table rows, table cells, table column groups, etc...
Developed in https://github.com/wordpress/wordpress-develop/pull/6040
Discussed in https://core.trac.wordpress.org/ticket/61576
Props: dmsnell, jonsurrell.
See <a href="https://core.trac.wordpress.org/ticket/61576">#61576</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludeshtmlapiclasswphtmlopenelementsphp">trunk/src/wp-includes/html-api/class-wp-html-open-elements.php</a></li>
<li><a href="#trunksrcwpincludeshtmlapiclasswphtmlprocessorphp">trunk/src/wp-includes/html-api/class-wp-html-processor.php</a></li>
<li><a href="#trunktestsphpunittestshtmlapiwpHtmlProcessorBreadcrumbsphp">trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php</a></li>
<li><a href="#trunktestsphpunittestshtmlapiwpHtmlProcessorSemanticRulesphp">trunk/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludeshtmlapiclasswphtmlopenelementsphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/src/wp-includes/html-api/class-wp-html-open-elements.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/html-api/class-wp-html-open-elements.php 2024-07-24 17:30:22 UTC (rev 58805)
+++ trunk/src/wp-includes/html-api/class-wp-html-open-elements.php 2024-07-24 18:39:46 UTC (rev 58806)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -721,6 +721,80 @@
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> /**
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * Clear the stack back to a table context.
+ *
+ * > When the steps above require the UA to clear the stack back to a table context, it means
+ * > that the UA must, while the current node is not a table, template, or html element, pop
+ * > elements from the stack of open elements.
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-stack-back-to-a-table-context
+ *
+ * @since 6.7.0
+ */
+ public function clear_to_table_context(): void {
+ foreach ( $this->walk_up() as $item ) {
+ if (
+ 'TABLE' === $item->node_name ||
+ 'TEMPLATE' === $item->node_name ||
+ 'HTML' === $item->node_name
+ ) {
+ break;
+ }
+ $this->pop();
+ }
+ }
+
+ /**
+ * Clear the stack back to a table body context.
+ *
+ * > When the steps above require the UA to clear the stack back to a table body context, it
+ * > means that the UA must, while the current node is not a tbody, tfoot, thead, template, or
+ * > html element, pop elements from the stack of open elements.
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-stack-back-to-a-table-body-context
+ *
+ * @since 6.7.0
+ */
+ public function clear_to_table_body_context(): void {
+ foreach ( $this->walk_up() as $item ) {
+ if (
+ 'TBODY' === $item->node_name ||
+ 'TFOOT' === $item->node_name ||
+ 'THEAD' === $item->node_name ||
+ 'TEMPLATE' === $item->node_name ||
+ 'HTML' === $item->node_name
+ ) {
+ break;
+ }
+ $this->pop();
+ }
+ }
+
+ /**
+ * Clear the stack back to a table row context.
+ *
+ * > When the steps above require the UA to clear the stack back to a table row context, it
+ * > means that the UA must, while the current node is not a tr, template, or html element, pop
+ * > elements from the stack of open elements.
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#clear-the-stack-back-to-a-table-row-context
+ *
+ * @since 6.7.0
+ */
+ public function clear_to_table_row_context(): void {
+ foreach ( $this->walk_up() as $item ) {
+ if (
+ 'TR' === $item->node_name ||
+ 'TEMPLATE' === $item->node_name ||
+ 'HTML' === $item->node_name
+ ) {
+ break;
+ }
+ $this->pop();
+ }
+ }
+
+ /**
</ins><span class="cx" style="display: block; padding: 0 10px"> * Wakeup magic method.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @since 6.6.0
</span></span></pre></div>
<a id="trunksrcwpincludeshtmlapiclasswphtmlprocessorphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/src/wp-includes/html-api/class-wp-html-processor.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/html-api/class-wp-html-processor.php 2024-07-24 17:30:22 UTC (rev 58805)
+++ trunk/src/wp-includes/html-api/class-wp-html-processor.php 2024-07-24 18:39:46 UTC (rev 58806)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1786,6 +1786,10 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * > A start tag whose tag name is "table"
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> case '+TABLE':
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ /*
+ * > If the Document is not set to quirks mode, and the stack of open elements
+ * > has a p element in button scope, then close a p element.
+ */
</ins><span class="cx" style="display: block; padding: 0 10px"> if (
</span><span class="cx" style="display: block; padding: 0 10px"> WP_HTML_Processor_State::QUIRKS_MODE !== $this->state->document_mode &&
</span><span class="cx" style="display: block; padding: 0 10px"> $this->state->stack_of_open_elements->has_p_in_button_scope()
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2117,7 +2121,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * This internal function performs the 'in table' insertion mode
</span><span class="cx" style="display: block; padding: 0 10px"> * logic for the generalized WP_HTML_Processor::step() function.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- * @since 6.7.0 Stub implementation.
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * @since 6.7.0
</ins><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2127,7 +2131,245 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * @return bool Whether an element was found.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> private function step_in_table(): bool {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE . ' state.' );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $token_name = $this->get_token_name();
+ $token_type = $this->get_token_type();
+ $op_sigil = '#tag' === $token_type ? ( parent::is_tag_closer() ? '-' : '+' ) : '';
+ $op = "{$op_sigil}{$token_name}";
+
+ switch ( $op ) {
+ /*
+ * > A character token, if the current node is table,
+ * > tbody, template, tfoot, thead, or tr element
+ */
+ case '#text':
+ $current_node = $this->state->stack_of_open_elements->current_node();
+ $current_node_name = $current_node ? $current_node->node_name : null;
+ if (
+ $current_node_name && (
+ 'TABLE' === $current_node_name ||
+ 'TBODY' === $current_node_name ||
+ 'TEMPLATE' === $current_node_name ||
+ 'TFOOT' === $current_node_name ||
+ 'THEAD' === $current_node_name ||
+ 'TR' === $current_node_name
+ )
+ ) {
+ $text = $this->get_modifiable_text();
+ /*
+ * If the text is empty after processing HTML entities and stripping
+ * U+0000 NULL bytes then ignore the token.
+ */
+ if ( '' === $text ) {
+ return $this->step();
+ }
+
+ /*
+ * This follows the rules for "in table text" insertion mode.
+ *
+ * Whitespace-only text nodes are inserted in-place. Otherwise
+ * foster parenting is enabled and the nodes would be
+ * inserted out-of-place.
+ *
+ * > If any of the tokens in the pending table character tokens
+ * > list are character tokens that are not ASCII whitespace,
+ * > then this is a parse error: reprocess the character tokens
+ * > in the pending table character tokens list using the rules
+ * > given in the "anything else" entry in the "in table"
+ * > insertion mode.
+ * >
+ * > Otherwise, insert the characters given by the pending table
+ * > character tokens list.
+ *
+ * @see https://html.spec.whatwg.org/#parsing-main-intabletext
+ */
+ if ( strlen( $text ) === strspn( $text, " \t\f\r\n" ) ) {
+ $this->insert_html_element( $this->state->current_token );
+ return true;
+ }
+
+ // Non-whitespace would trigger fostering, unsupported at this time.
+ $this->bail( 'Foster parenting is not supported.' );
+ break;
+ }
+ break;
+
+ /*
+ * > A comment token
+ */
+ case '#comment':
+ case '#funky-comment':
+ case '#presumptuous-tag':
+ $this->insert_html_element( $this->state->current_token );
+ return true;
+
+ /*
+ * > A DOCTYPE token
+ */
+ case 'html':
+ // Parse error: ignore the token.
+ return $this->step();
+
+ /*
+ * > A start tag whose tag name is "caption"
+ */
+ case '+CAPTION':
+ $this->state->stack_of_open_elements->clear_to_table_context();
+ $this->state->active_formatting_elements->insert_marker();
+ $this->insert_html_element( $this->state->current_token );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CAPTION;
+ return true;
+
+ /*
+ * > A start tag whose tag name is "colgroup"
+ */
+ case '+COLGROUP':
+ $this->state->stack_of_open_elements->clear_to_table_context();
+ $this->insert_html_element( $this->state->current_token );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
+ return true;
+
+ /*
+ * > A start tag whose tag name is "col"
+ */
+ case '+COL':
+ $this->state->stack_of_open_elements->clear_to_table_context();
+
+ /*
+ * > Insert an HTML element for a "colgroup" start tag token with no attributes,
+ * > then switch the insertion mode to "in column group".
+ */
+ $this->insert_virtual_node( 'COLGROUP' );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_COLUMN_GROUP;
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > A start tag whose tag name is one of: "tbody", "tfoot", "thead"
+ */
+ case '+TBODY':
+ case '+TFOOT':
+ case '+THEAD':
+ $this->state->stack_of_open_elements->clear_to_table_context();
+ $this->insert_html_element( $this->state->current_token );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
+ return true;
+
+ /*
+ * > A start tag whose tag name is one of: "td", "th", "tr"
+ */
+ case '+TD':
+ case '+TH':
+ case '+TR':
+ $this->state->stack_of_open_elements->clear_to_table_context();
+ /*
+ * > Insert an HTML element for a "tbody" start tag token with no attributes,
+ * > then switch the insertion mode to "in table body".
+ */
+ $this->insert_virtual_node( 'TBODY' );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > A start tag whose tag name is "table"
+ *
+ * This tag in the IN TABLE insertion mode is a parse error.
+ */
+ case '+TABLE':
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TABLE' ) ) {
+ return $this->step();
+ }
+
+ $this->state->stack_of_open_elements->pop_until( 'TABLE' );
+ $this->reset_insertion_mode();
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > An end tag whose tag name is "table"
+ */
+ case '-TABLE':
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TABLE' ) ) {
+ // @todo Indicate a parse error once it's possible.
+ return $this->step();
+ }
+
+ $this->state->stack_of_open_elements->pop_until( 'TABLE' );
+ $this->reset_insertion_mode();
+ return true;
+
+ /*
+ * > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr"
+ */
+ case '-BODY':
+ case '-CAPTION':
+ case '-COL':
+ case '-COLGROUP':
+ case '-HTML':
+ case '-TBODY':
+ case '-TD':
+ case '-TFOOT':
+ case '-TH':
+ case '-THEAD':
+ case '-TR':
+ // Parse error: ignore the token.
+ return $this->step();
+
+ /*
+ * > A start tag whose tag name is one of: "style", "script", "template"
+ * > An end tag whose tag name is "template"
+ */
+ case '+STYLE':
+ case '+SCRIPT':
+ case '+TEMPLATE':
+ case '-TEMPLATE':
+ /*
+ * > Process the token using the rules for the "in head" insertion mode.
+ */
+ return $this->step_in_head();
+
+ /*
+ * > A start tag whose tag name is "input"
+ *
+ * > If the token does not have an attribute with the name "type", or if it does, but
+ * > that attribute's value is not an ASCII case-insensitive match for the string
+ * > "hidden", then: act as described in the "anything else" entry below.
+ */
+ case '+INPUT':
+ $type_attribute = $this->get_attribute( 'type' );
+ if ( ! is_string( $type_attribute ) || 'hidden' !== strtolower( $type_attribute ) ) {
+ goto anything_else;
+ }
+ // @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 "form"
+ *
+ * This tag in the IN TABLE insertion mode is a parse error.
+ */
+ case '+FORM':
+ if (
+ $this->state->stack_of_open_elements->has_element_in_scope( 'TEMPLATE' ) ||
+ isset( $this->state->form_element )
+ ) {
+ return $this->step();
+ }
+
+ // This FORM is special because it immediately closes and cannot have other children.
+ $this->insert_html_element( $this->state->current_token );
+ $this->state->form_element = $this->state->current_token;
+ $this->state->stack_of_open_elements->pop();
+ return true;
+ }
+
+ /*
+ * > Anything else
+ * > Parse error. Enable foster parenting, process the token using the rules for the
+ * > "in body" insertion mode, and then disable foster parenting.
+ *
+ * @todo Indicate a parse error once it's possible.
+ */
+ anything_else:
+ $this->bail( 'Foster parenting is not supported.' );
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> /**
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2193,7 +2435,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * This internal function performs the 'in table body' insertion mode
</span><span class="cx" style="display: block; padding: 0 10px"> * logic for the generalized WP_HTML_Processor::step() function.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- * @since 6.7.0 Stub implementation.
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * @since 6.7.0
</ins><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2203,7 +2445,97 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * @return bool Whether an element was found.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> private function step_in_table_body(): bool {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY . ' state.' );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $tag_name = $this->get_tag();
+ $op_sigil = $this->is_tag_closer() ? '-' : '+';
+ $op = "{$op_sigil}{$tag_name}";
+
+ switch ( $op ) {
+ /*
+ * > A start tag whose tag name is "tr"
+ */
+ case '+TR':
+ $this->state->stack_of_open_elements->clear_to_table_body_context();
+ $this->insert_html_element( $this->state->current_token );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
+ return true;
+
+ /*
+ * > A start tag whose tag name is one of: "th", "td"
+ */
+ case '+TH':
+ case '+TD':
+ // @todo Indicate a parse error once it's possible.
+ $this->state->stack_of_open_elements->clear_to_table_body_context();
+ $this->insert_virtual_node( 'TR' );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > An end tag whose tag name is one of: "tbody", "tfoot", "thead"
+ */
+ case '-TBODY':
+ case '-TFOOT':
+ case '-THEAD':
+ /*
+ * @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.
+ */
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ $this->state->stack_of_open_elements->clear_to_table_body_context();
+ $this->state->stack_of_open_elements->pop();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
+ return true;
+
+ /*
+ * > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "tfoot", "thead"
+ * > An end tag whose tag name is "table"
+ */
+ case '+CAPTION':
+ case '+COL':
+ case '+COLGROUP':
+ case '+TBODY':
+ case '+TFOOT':
+ case '+THEAD':
+ case '-TABLE':
+ if (
+ ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TBODY' ) &&
+ ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'THEAD' ) &&
+ ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TFOOT' )
+ ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+ $this->state->stack_of_open_elements->clear_to_table_body_context();
+ $this->state->stack_of_open_elements->pop();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE;
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html", "td", "th", "tr"
+ */
+ case '-BODY':
+ case '-CAPTION':
+ case '-COL':
+ case '-COLGROUP':
+ case '-HTML':
+ case '-TD':
+ case '-TH':
+ case '-TR':
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ /*
+ * > Anything else
+ * > Process the token using the rules for the "in table" insertion mode.
+ */
+ return $this->step_in_table();
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> /**
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2212,7 +2544,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * This internal function performs the 'in row' insertion mode
</span><span class="cx" style="display: block; padding: 0 10px"> * logic for the generalized WP_HTML_Processor::step() function.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- * @since 6.7.0 Stub implementation.
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * @since 6.7.0
</ins><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2222,7 +2554,104 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * @return bool Whether an element was found.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> private function step_in_row(): bool {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_ROW . ' state.' );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $tag_name = $this->get_tag();
+ $op_sigil = $this->is_tag_closer() ? '-' : '+';
+ $op = "{$op_sigil}{$tag_name}";
+
+ switch ( $op ) {
+ /*
+ * > A start tag whose tag name is one of: "th", "td"
+ */
+ case '+TH':
+ case '+TD':
+ $this->state->stack_of_open_elements->clear_to_table_row_context();
+ $this->insert_html_element( $this->state->current_token );
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_CELL;
+ $this->state->active_formatting_elements->insert_marker();
+ return true;
+
+ /*
+ * > An end tag whose tag name is "tr"
+ */
+ case '-TR':
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TR' ) ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ $this->state->stack_of_open_elements->clear_to_table_row_context();
+ $this->state->stack_of_open_elements->pop();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
+ return true;
+
+ /*
+ * > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "tfoot", "thead", "tr"
+ * > An end tag whose tag name is "table"
+ */
+ case '+CAPTION':
+ case '+COL':
+ case '+COLGROUP':
+ case '+TBODY':
+ case '+TFOOT':
+ case '+THEAD':
+ case '+TR':
+ case '-TABLE':
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TR' ) ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ $this->state->stack_of_open_elements->clear_to_table_row_context();
+ $this->state->stack_of_open_elements->pop();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > An end tag whose tag name is one of: "tbody", "tfoot", "thead"
+ */
+ case '-TBODY':
+ case '-TFOOT':
+ case '-THEAD':
+ /*
+ * @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.
+ */
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( 'TR' ) ) {
+ // Ignore the token.
+ return $this->step();
+ }
+
+ $this->state->stack_of_open_elements->clear_to_table_row_context();
+ $this->state->stack_of_open_elements->pop();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_TABLE_BODY;
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html", "td", "th"
+ */
+ case '-BODY':
+ case '-CAPTION':
+ case '-COL':
+ case '-COLGROUP':
+ case '-HTML':
+ case '-TD':
+ case '-TH':
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ /*
+ * > Anything else
+ * > Process the token using the rules for the "in table" insertion mode.
+ */
+ return $this->step_in_table();
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> /**
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2231,7 +2660,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * This internal function performs the 'in cell' insertion mode
</span><span class="cx" style="display: block; padding: 0 10px"> * logic for the generalized WP_HTML_Processor::step() function.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- * @since 6.7.0 Stub implementation.
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * @since 6.7.0
</ins><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @throws WP_HTML_Unsupported_Exception When encountering unsupported HTML input.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2241,7 +2670,104 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * @return bool Whether an element was found.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> private function step_in_cell(): bool {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->bail( 'No support for parsing in the ' . WP_HTML_Processor_State::INSERTION_MODE_IN_CELL . ' state.' );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $tag_name = $this->get_tag();
+ $op_sigil = $this->is_tag_closer() ? '-' : '+';
+ $op = "{$op_sigil}{$tag_name}";
+
+ switch ( $op ) {
+ /*
+ * > An end tag whose tag name is one of: "td", "th"
+ */
+ case '-TD':
+ case '-TH':
+ /*
+ * @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.
+ */
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+
+ $this->generate_implied_end_tags();
+
+ /*
+ * @todo This needs to check if the current node 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.
+ */
+ if ( ! $this->state->stack_of_open_elements->current_node_is( $tag_name ) ) {
+ // @todo Indicate a parse error once it's possible.
+ }
+
+ $this->state->stack_of_open_elements->pop_until( $tag_name );
+ $this->state->active_formatting_elements->clear_up_to_last_marker();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
+ return true;
+
+ /*
+ * > A start tag whose tag name is one of: "caption", "col", "colgroup", "tbody", "td",
+ * > "tfoot", "th", "thead", "tr"
+ */
+ case '+CAPTION':
+ case '+COL':
+ case '+COLGROUP':
+ case '+TBODY':
+ case '+TD':
+ case '+TFOOT':
+ case '+TH':
+ case '+THEAD':
+ case '+TR':
+ /*
+ * > Assert: The stack of open elements has a td or th element in table scope.
+ *
+ * Nothing to do here, except to verify in tests that this never appears.
+ */
+
+ $this->close_cell();
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+
+ /*
+ * > An end tag whose tag name is one of: "body", "caption", "col", "colgroup", "html"
+ */
+ case '-BODY':
+ case '-CAPTION':
+ case '-COL':
+ case '-COLGROUP':
+ case '-HTML':
+ // Parse error: ignore the token.
+ return $this->step();
+
+ /*
+ * > An end tag whose tag name is one of: "table", "tbody", "tfoot", "thead", "tr"
+ */
+ case '-TABLE':
+ case '-TBODY':
+ case '-TFOOT':
+ case '-THEAD':
+ case '-TR':
+ /*
+ * @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.
+ */
+ if ( ! $this->state->stack_of_open_elements->has_element_in_table_scope( $tag_name ) ) {
+ // Parse error: ignore the token.
+ return $this->step();
+ }
+ $this->close_cell();
+ return $this->step( self::REPROCESS_CURRENT_NODE );
+ }
+
+ /*
+ * > Anything else
+ * > Process the token using the rules for the "in body" insertion mode.
+ */
+ return $this->step_in_body();
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> /**
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -3577,6 +4103,33 @@
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> /**
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * Runs the "close the cell" algorithm.
+ *
+ * > Where the steps above say to close the cell, they mean to run the following algorithm:
+ * > 1. Generate implied end tags.
+ * > 2. If the current node is not now a td element or a th element, then this is a parse error.
+ * > 3. Pop elements from the stack of open elements stack until a td element or a th element has been popped from the stack.
+ * > 4. Clear the list of active formatting elements up to the last marker.
+ * > 5. Switch the insertion mode to "in row".
+ *
+ * @see https://html.spec.whatwg.org/multipage/parsing.html#close-the-cell
+ *
+ * @since 6.7.0
+ */
+ private function close_cell(): void {
+ $this->generate_implied_end_tags();
+ // @todo Parse error if the current node is a "td" or "th" element.
+ foreach ( $this->state->stack_of_open_elements->walk_up() as $element ) {
+ $this->state->stack_of_open_elements->pop();
+ if ( 'TD' === $element->node_name || 'TH' === $element->node_name ) {
+ break;
+ }
+ }
+ $this->state->active_formatting_elements->clear_up_to_last_marker();
+ $this->state->insertion_mode = WP_HTML_Processor_State::INSERTION_MODE_IN_ROW;
+ }
+
+ /**
</ins><span class="cx" style="display: block; padding: 0 10px"> * Inserts an HTML element on the stack of open elements.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @since 6.4.0
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -3589,6 +4142,24 @@
</span><span class="cx" style="display: block; padding: 0 10px"> $this->state->stack_of_open_elements->push( $token );
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ /**
+ * Inserts a virtual element on the stack of open elements.
+ *
+ * @since 6.7.0
+ *
+ * @param string $token_name Name of token to create and insert into the stack of open elements.
+ * @param string|null $bookmark_name Optional. Name to give bookmark for created virtual node.
+ * Defaults to auto-creating a bookmark name.
+ */
+ private function insert_virtual_node( $token_name, $bookmark_name = null ): void {
+ $here = $this->bookmarks[ $this->state->current_token->bookmark_name ];
+ $name = $bookmark_name ?? $this->bookmark_token();
+
+ $this->bookmarks[ $name ] = new WP_HTML_Span( $here->start, 0 );
+
+ $this->insert_html_element( new WP_HTML_Token( $name, $token_name, false ) );
+ }
+
</ins><span class="cx" style="display: block; padding: 0 10px"> /*
</span><span class="cx" style="display: block; padding: 0 10px"> * HTML Specification Helpers
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span></span></pre></div>
<a id="trunktestsphpunittestshtmlapiwpHtmlProcessorBreadcrumbsphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php 2024-07-24 17:30:22 UTC (rev 58805)
+++ trunk/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php 2024-07-24 18:39:46 UTC (rev 58806)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -181,9 +181,6 @@
</span><span class="cx" style="display: block; padding: 0 10px"> 'BASE',
</span><span class="cx" style="display: block; padding: 0 10px"> 'BGSOUND', // Deprecated; self-closing if self-closing flag provided, otherwise normal.
</span><span class="cx" style="display: block; padding: 0 10px"> 'BODY',
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'CAPTION',
- 'COL',
- 'COLGROUP',
</del><span class="cx" style="display: block; padding: 0 10px"> 'FRAME',
</span><span class="cx" style="display: block; padding: 0 10px"> 'FRAMESET',
</span><span class="cx" style="display: block; padding: 0 10px"> 'HEAD',
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -198,15 +195,9 @@
</span><span class="cx" style="display: block; padding: 0 10px"> 'SCRIPT',
</span><span class="cx" style="display: block; padding: 0 10px"> 'STYLE',
</span><span class="cx" style="display: block; padding: 0 10px"> 'SVG',
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'TBODY',
- 'TD',
</del><span class="cx" style="display: block; padding: 0 10px"> 'TEMPLATE',
</span><span class="cx" style="display: block; padding: 0 10px"> 'TEXTAREA',
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'TFOOT',
- 'TH',
- 'THEAD',
</del><span class="cx" style="display: block; padding: 0 10px"> 'TITLE',
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'TR',
</del><span class="cx" style="display: block; padding: 0 10px"> 'XMP', // Deprecated, use PRE instead.
</span><span class="cx" style="display: block; padding: 0 10px"> );
</span><span class="cx" style="display: block; padding: 0 10px">
</span></span></pre></div>
<a id="trunktestsphpunittestshtmlapiwpHtmlProcessorSemanticRulesphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php 2024-07-24 17:30:22 UTC (rev 58805)
+++ trunk/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php 2024-07-24 18:39:46 UTC (rev 58806)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -424,4 +424,28 @@
</span><span class="cx" style="display: block; padding: 0 10px"> $this->assertFalse( $processor->is_tag_closer(), 'Should have treated the tag as an opening tag.' );
</span><span class="cx" style="display: block; padding: 0 10px"> $this->assertNull( $processor->get_attribute_names_with_prefix( '' ), 'Should have ignored any attributes on the tag.' );
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+
+ /*******************************************************************
+ * RULES FOR "IN TABLE" MODE
+ *******************************************************************/
+
+ /**
+ * Ensure that form elements in tables (but not cells) are immediately popped off the stack.
+ *
+ * @ticket 61576
+ */
+ public function test_table_form_element_immediately_popped() {
+ $processor = WP_HTML_Processor::create_fragment( '<table><form><!--comment-->' );
+
+ // There should be a FORM opener and a (virtual) FORM closer.
+ $this->assertTrue( $processor->next_tag( 'FORM' ) );
+ $this->assertTrue( $processor->next_token() );
+ $this->assertSame( 'FORM', $processor->get_token_name() );
+ $this->assertTrue( $processor->is_tag_closer() );
+
+ // Followed by the comment token.
+ $this->assertTrue( $processor->next_token() );
+ $this->assertSame( '#comment', $processor->get_token_name() );
+ $this->assertsame( array( 'HTML', 'BODY', 'TABLE', '#comment' ), $processor->get_breadcrumbs() );
+ }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>
</body>
</html>