<!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>[57527] trunk: HTML API: Reset parser state after seeking to bookmark.</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/57527">57527</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/57527","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>2024-02-02 22:55:27 +0000 (Fri, 02 Feb 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: Reset parser state after seeking to bookmark.
When parser states were introduced, nothing in the `seek()` method reset the
parser state. This is problematic because it could leave the parser in the
wrong state.
In this patch the parser state is reset so that it's properly adjusted on
the successive call to `next_token()`.
Developed in https://github.com/WordPress/wordpress-develop/pull/6021
Discussed in https://core.trac.wordpress.org/ticket/60428
Follow-up to <a href="https://core.trac.wordpress.org/changeset/57211">[57211]</a>
Props dmsnell, kevin940726
Fixes <a href="https://core.trac.wordpress.org/ticket/60428">#60428</a></pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludeshtmlapiclasswphtmltagprocessorphp">trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php</a></li>
<li><a href="#trunktestsphpunittestshtmlapiwpHtmlTagProcessorbookmarkphp">trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor-bookmark.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludeshtmlapiclasswphtmltagprocessorphp"></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-tag-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-tag-processor.php 2024-02-02 20:22:11 UTC (rev 57526)
+++ trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php 2024-02-02 22:55:27 UTC (rev 57527)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2335,6 +2335,7 @@
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> // Point this tag processor before the sought tag opener and consume it.
</span><span class="cx" style="display: block; padding: 0 10px"> $this->bytes_already_parsed = $this->bookmarks[ $bookmark_name ]->start;
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $this->parser_state = self::STATE_READY;
</ins><span class="cx" style="display: block; padding: 0 10px"> return $this->next_token();
</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="trunktestsphpunittestshtmlapiwpHtmlTagProcessorbookmarkphp"></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/wpHtmlTagProcessor-bookmark.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor-bookmark.php 2024-02-02 20:22:11 UTC (rev 57526)
+++ trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor-bookmark.php 2024-02-02 22:55:27 UTC (rev 57527)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -435,4 +435,49 @@
</span><span class="cx" style="display: block; padding: 0 10px"> $this->setExpectedIncorrectUsage( 'WP_HTML_Tag_Processor::seek' );
</span><span class="cx" style="display: block; padding: 0 10px"> $this->assertFalse( $processor->seek( 'bookmark' ), "$i-th seek() to the bookmark succeeded, even though it should exceed the allowed limit" );
</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 it's possible to seek to an earlier location in a document even
+ * after reaching the end of a document, when most functionality shuts down.
+ *
+ * @ticket 60428
+ *
+ * @dataProvider data_incomplete_html_with_target_nodes_for_seeking
+ *
+ * @param string $html_with_target_element HTML string containing a tag with a `target` attribute.
+ */
+ public function test_can_seek_after_document_ends( $html_with_target_element ) {
+ $processor = new WP_HTML_Tag_Processor( $html_with_target_element );
+
+ $sought_tag_name = null;
+ while ( $processor->next_tag() ) {
+ if ( null !== $processor->get_attribute( 'target' ) ) {
+ $processor->set_bookmark( 'target' );
+ $sought_tag_name = $processor->get_tag();
+ }
+ }
+
+ $this->assertTrue(
+ $processor->seek( 'target' ),
+ 'Should have been able to seek to the target bookmark after reaching the end of the document.'
+ );
+
+ $this->assertSame(
+ $sought_tag_name,
+ $processor->get_tag(),
+ "Should have found original target node instead of {$processor->get_tag()}."
+ );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array[].
+ */
+ public static function data_incomplete_html_with_target_nodes_for_seeking() {
+ return array(
+ 'Compete document' => array( '<div><img target></div>' ),
+ 'Incomplete document' => array( '<div><img target></div' ),
+ );
+ }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>
</body>
</html>