<!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>[60502] trunk: HTML API: Simplify META tag processing.</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/60502">60502</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/60502","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>jonsurrell</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2025-07-24 06:47:41 +0000 (Thu, 24 Jul 2025)</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: Simplify META tag processing.
META tag processing can be simplified in most cases. Add an early check and return to avoid additional processing.
Developed in https://github.com/WordPress/wordpress-develop/pull/9231.
Props jonsurrell, dmsnell.
See <a href="https://core.trac.wordpress.org/ticket/63738">#63738</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludeshtmlapiclasswphtmlprocessorphp">trunk/src/wp-includes/html-api/class-wp-html-processor.php</a></li>
</ul>
<h3>Added Paths</h3>
<ul>
<li><a href="#trunktestsphpunittestshtmlapiwpHtmlProcessorMetaTagphp">trunk/tests/phpunit/tests/html-api/wpHtmlProcessorMetaTag.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<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 2025-07-24 06:11:38 UTC (rev 60501)
+++ trunk/src/wp-includes/html-api/class-wp-html-processor.php 2025-07-24 06:47:41 UTC (rev 60502)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1760,6 +1760,11 @@
</span><span class="cx" style="display: block; padding: 0 10px"> case '+META':
</span><span class="cx" style="display: block; padding: 0 10px"> $this->insert_html_element( $this->state->current_token );
</span><span class="cx" style="display: block; padding: 0 10px">
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ // All following conditions depend on "tentative" encoding confidence.
+ if ( 'tentative' !== $this->state->encoding_confidence ) {
+ return true;
+ }
+
</ins><span class="cx" style="display: block; padding: 0 10px"> /*
</span><span class="cx" style="display: block; padding: 0 10px"> * > If the active speculative HTML parser is null, then:
</span><span class="cx" style="display: block; padding: 0 10px"> * > - If the element has a charset attribute, and getting an encoding from
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1767,7 +1772,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * > tentative, then change the encoding to the resulting encoding.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> $charset = $this->get_attribute( 'charset' );
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- if ( is_string( $charset ) && 'tentative' === $this->state->encoding_confidence ) {
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ if ( is_string( $charset ) ) {
</ins><span class="cx" style="display: block; padding: 0 10px"> $this->bail( 'Cannot yet process META tags with charset to determine encoding.' );
</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">@@ -1784,8 +1789,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> if (
</span><span class="cx" style="display: block; padding: 0 10px"> is_string( $http_equiv ) &&
</span><span class="cx" style="display: block; padding: 0 10px"> is_string( $content ) &&
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 0 === strcasecmp( $http_equiv, 'Content-Type' ) &&
- 'tentative' === $this->state->encoding_confidence
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ 0 === strcasecmp( $http_equiv, 'Content-Type' )
</ins><span class="cx" style="display: block; padding: 0 10px"> ) {
</span><span class="cx" style="display: block; padding: 0 10px"> $this->bail( 'Cannot yet process META tags with http-equiv Content-Type to determine encoding.' );
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre></div>
<a id="trunktestsphpunittestshtmlapiwpHtmlProcessorMetaTagphp"></a>
<div class="addfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Added: trunk/tests/phpunit/tests/html-api/wpHtmlProcessorMetaTag.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/html-api/wpHtmlProcessorMetaTag.php (rev 0)
+++ trunk/tests/phpunit/tests/html-api/wpHtmlProcessorMetaTag.php 2025-07-24 06:47:41 UTC (rev 60502)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -0,0 +1,77 @@
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+<?php
+/**
+ * Unit tests covering WP_HTML_Processor META tag handling.
+ *
+ * @package WordPress
+ * @subpackage HTML-API
+ *
+ * @since 6.9
+ *
+ * @group html-api
+ *
+ * @coversDefaultClass WP_HTML_Processor
+ */
+class Tests_HtmlApi_WpHtmlProcessorMetaTag extends WP_UnitTestCase {
+ /**
+ * Data provider.
+ */
+ public static function data_supported_meta_tags(): array {
+ return array(
+ 'No attributes' => array( '<meta>' ),
+ 'Unrelated attributes' => array( '<meta not-charset="OK">' ),
+ 'Boolean charset' => array( '<meta charset>' ),
+ 'HTTP Equiv: accept' => array( '<meta http-equiv="accept" content="">' ),
+ 'HTTP Equiv: content-type, no content' => array( '<meta http-equiv="content-type">' ),
+ 'Boolean HTTP Equiv' => array( '<meta http-equiv content="">' ),
+ );
+ }
+
+ /**
+ * Ensures that META tags correctly handle encoding confidence.
+ *
+ * @ticket 63738
+ *
+ * @dataProvider data_supported_meta_tags
+ */
+ public function test_supported_meta_tag( string $html ) {
+ $html = '<!DOCTYPE html>' . $html;
+ $processor = new class($html) extends WP_HTML_Processor {
+ public function __construct( $html ) {
+ parent::__construct( $html, parent::CONSTRUCTOR_UNLOCK_CODE );
+ }
+ };
+
+ $this->assertTrue( $processor->next_tag( 'META' ) );
+ }
+
+ /**
+ * Data provider.
+ */
+ public function data_unsupported_meta_tags(): array {
+ return array(
+ 'With charset' => array( '<meta charset="utf8">', 'Cannot yet process META tags with charset to determine encoding.' ),
+ 'With CHARSET' => array( '<meta CHARSET="utf8">', 'Cannot yet process META tags with charset to determine encoding.' ),
+ 'With http-equiv' => array( '<meta http-equiv="content-type" content="">', 'Cannot yet process META tags with http-equiv Content-Type to determine encoding.' ),
+ 'With http-equiv and content' => array( '<meta http-equiv="Content-Type" content="UTF-8">', 'Cannot yet process META tags with http-equiv Content-Type to determine encoding.' ),
+ );
+ }
+
+ /**
+ * Ensures that unsupported encoding META tags bail.
+ *
+ * @ticket 63738
+ *
+ * @dataProvider data_unsupported_meta_tags
+ */
+ public function test_unsupported_meta_tags( string $html, string $unsupported_message ) {
+ $html = '<!DOCTYPE html>' . $html;
+ $processor = new class($html) extends WP_HTML_Processor {
+ public function __construct( $html ) {
+ parent::__construct( $html, parent::CONSTRUCTOR_UNLOCK_CODE );
+ }
+ };
+
+ $this->assertFalse( $processor->next_tag( 'META' ) );
+ $this->assertInstanceOf( WP_HTML_Unsupported_Exception::class, $processor->get_unsupported_exception() );
+ }
+}
</ins></span></pre>
</div>
</div>
</body>
</html>