<!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>[59014] trunk: HTML API: Make WP_HTML_Processor::get_tag() namespace aware.</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/59014">59014</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/59014","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>2024-09-11 16:11:32 +0000 (Wed, 11 Sep 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: Make WP_HTML_Processor::get_tag() namespace aware.
The HTML specification indicates that an HTML tag with the name "IMAGE"
should be renamed as "IMG" and handled as if it were an "IMG", but this
only applies to elements in the HTML namespace.
In this patch the HTML Processor is updated to ensure that it doesn't
remap the tag name when processing foreign content, such as SVG and
MathML markup.
Developed in https://github.com/wordpress/wordpress-develop/7330
Discussed in https://core.trac.wordpress.org/ticket/61656
Props dmsnell, jonsurrell.
See <a href="https://core.trac.wordpress.org/ticket/61576">#61576</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludeshtmlapiclasswphtmlprocessorphp">trunk/src/wp-includes/html-api/class-wp-html-processor.php</a></li>
<li><a href="#trunktestsphpunittestshtmlapiwpHtmlProcessorphp">trunk/tests/phpunit/tests/html-api/wpHtmlProcessor.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 2024-09-11 15:42:34 UTC (rev 59013)
+++ trunk/src/wp-includes/html-api/class-wp-html-processor.php 2024-09-11 16:11:32 UTC (rev 59014)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -4727,17 +4727,13 @@
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> $tag_name = parent::get_tag();
</span><span class="cx" style="display: block; padding: 0 10px">
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- switch ( $tag_name ) {
- case 'IMAGE':
- /*
- * > A start tag whose tag name is "image"
- * > Change the token's tag name to "img" and reprocess it. (Don't ask.)
- */
- return 'IMG';
-
- default:
- return $tag_name;
- }
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ /*
+ * > A start tag whose tag name is "image"
+ * > Change the token's tag name to "img" and reprocess it. (Don't ask.)
+ */
+ return ( 'IMAGE' === $tag_name && 'html' === $this->get_namespace() )
+ ? 'IMG'
+ : $tag_name;
</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></pre></div>
<a id="trunktestsphpunittestshtmlapiwpHtmlProcessorphp"></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/wpHtmlProcessor.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/html-api/wpHtmlProcessor.php 2024-09-11 15:42:34 UTC (rev 59013)
+++ trunk/tests/phpunit/tests/html-api/wpHtmlProcessor.php 2024-09-11 16:11:32 UTC (rev 59014)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -55,6 +55,57 @@
</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">+ * Ensures that the proper tag-name remapping happens for the `IMAGE` tag.
+ *
+ * An HTML parser should treat an IMAGE tag as if it were an IMG tag, but
+ * only when found in the HTML namespace. As part of this rule, IMAGE tags
+ * in the HTML namespace are also void elements, while those in foreign
+ * content are not, making the self-closing flag significant.
+ *
+ * Example:
+ *
+ * // This input...
+ * <image/><svg><image/></svg>
+ *
+ * // ...is equivalent to this normative HTML.
+ * <img><svg><image/></svg>
+ *
+ * @ticket 61576
+ *
+ * @covers WP_HTML_Processor::get_tag
+ */
+ public function test_get_tag_replaces_image_with_namespace_awareness() {
+ $processor = WP_HTML_Processor::create_fragment( '<image/><svg><image/></svg>' );
+
+ $this->assertTrue(
+ $processor->next_tag(),
+ 'Could not find initial "<image/>" tag: check test setup.'
+ );
+
+ $this->assertSame(
+ 'IMG',
+ $processor->get_tag(),
+ 'HTML tags with the name "IMAGE" should be remapped to "IMG"'
+ );
+
+ $this->assertTrue(
+ $processor->next_tag(),
+ 'Could not find "<svg>" tag: check test setup.'
+ );
+
+ $this->assertTrue(
+ $processor->next_tag(),
+ 'Could not find SVG "<image/>" tag: check test setup.'
+ );
+
+ $this->assertSame(
+ 'IMAGE',
+ $processor->get_tag(),
+ 'Should not remap "IMAGE" to "IMG" for foreign elements.'
+ );
+ }
+
+ /**
</ins><span class="cx" style="display: block; padding: 0 10px"> * Ensures that the HTML Processor maintains its internal state through seek calls.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * Because the HTML Processor must track a stack of open elements and active formatting
</span></span></pre>
</div>
</div>
</body>
</html>