<!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>[55667] trunk: HTML API: Add support for a few invalid HTML comment forms.</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/55667">55667</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/55667","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>Bernhard Reiter</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2023-04-20 17:08:47 +0000 (Thu, 20 Apr 2023)</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 support for a few invalid HTML comment forms.
- Comments created by means of a tag closer with an invalid tag name, e.g. `</3>`.
- Comments closed with the invalid `--!>` closer. (Comments should be closed by `-->` but if the `!` appears it will also close it, in error.)
- Empty tag name elements, which are technically skipped over and aren't comments, e.g. `</>`.
Props dmsnell, costdev.
Fixes <a href="https://core.trac.wordpress.org/ticket/58007">#58007</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="#trunktestsphpunittestshtmlapiwpHtmlTagProcessorphp">trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor.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 2023-04-20 14:28:50 UTC (rev 55666)
+++ trunk/src/wp-includes/html-api/class-wp-html-tag-processor.php 2023-04-20 17:08:47 UTC (rev 55667)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -971,6 +971,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> * closing `>`; these are left for other methods.
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @since 6.2.0
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * @since 6.2.1 Support abruptly-closed comments, invalid-tag-closer-comments, and empty elements.
</ins><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @return bool Whether a tag was found before the end of the document.
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1039,13 +1040,42 @@
</span><span class="cx" style="display: block; padding: 0 10px"> '-' === $html[ $at + 2 ] &&
</span><span class="cx" style="display: block; padding: 0 10px"> '-' === $html[ $at + 3 ]
</span><span class="cx" style="display: block; padding: 0 10px"> ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $closer_at = strpos( $html, '-->', $at + 4 );
- if ( false === $closer_at ) {
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $closer_at = $at + 4;
+ // If it's not possible to close the comment then there is nothing more to scan.
+ if ( strlen( $html ) <= $closer_at ) {
</ins><span class="cx" style="display: block; padding: 0 10px"> return false;
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $at = $closer_at + 3;
- continue;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ // Abruptly-closed empty comments are a sequence of dashes followed by `>`.
+ $span_of_dashes = strspn( $html, '-', $closer_at );
+ if ( '>' === $html[ $closer_at + $span_of_dashes ] ) {
+ $at = $closer_at + $span_of_dashes + 1;
+ continue;
+ }
+
+ /*
+ * Comments may be closed by either a --> or an invalid --!>.
+ * The first occurrence closes the comment.
+ *
+ * See https://html.spec.whatwg.org/#parse-error-incorrectly-closed-comment
+ */
+ $closer_at--; // Pre-increment inside condition below reduces risk of accidental infinite looping.
+ while ( ++$closer_at < strlen( $html ) ) {
+ $closer_at = strpos( $html, '--', $closer_at );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ if ( $closer_at + 2 < strlen( $html ) && '>' === $html[ $closer_at + 2 ] ) {
+ $at = $closer_at + 3;
+ continue 2;
+ }
+
+ if ( $closer_at + 3 < strlen( $html ) && '!' === $html[ $closer_at + 2 ] && '>' === $html[ $closer_at + 3 ] ) {
+ $at = $closer_at + 4;
+ continue 2;
+ }
+ }
</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">@@ -1105,8 +1135,18 @@
</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">+ * </> is a missing end tag name, which is ignored.
+ *
+ * See https://html.spec.whatwg.org/#parse-error-missing-end-tag-name
+ */
+ if ( '>' === $html[ $at + 1 ] ) {
+ $at++;
+ continue;
+ }
+
+ /*
</ins><span class="cx" style="display: block; padding: 0 10px"> * <? transitions to a bogus comment state – skip to the nearest >
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- * https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ * See https://html.spec.whatwg.org/multipage/parsing.html#tag-open-state
</ins><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> if ( '?' === $html[ $at + 1 ] ) {
</span><span class="cx" style="display: block; padding: 0 10px"> $closer_at = strpos( $html, '>', $at + 2 );
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1118,6 +1158,22 @@
</span><span class="cx" style="display: block; padding: 0 10px"> continue;
</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">+ /*
+ * If a non-alpha starts the tag name in a tag closer it's a comment.
+ * Find the first `>`, which closes the comment.
+ *
+ * See https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
+ */
+ if ( $this->is_closing_tag ) {
+ $closer_at = strpos( $html, '>', $at + 3 );
+ if ( false === $closer_at ) {
+ return false;
+ }
+
+ $at = $closer_at + 1;
+ continue;
+ }
+
</ins><span class="cx" style="display: block; padding: 0 10px"> ++$at;
</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="trunktestsphpunittestshtmlapiwpHtmlTagProcessorphp"></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.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php 2023-04-20 14:28:50 UTC (rev 55666)
+++ trunk/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php 2023-04-20 17:08:47 UTC (rev 55667)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1733,6 +1733,47 @@
</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">+ * Invalid tag names are comments on tag closers.
+ *
+ * @ticket 58007
+ *
+ * @link https://html.spec.whatwg.org/#parse-error-invalid-first-character-of-tag-name
+ *
+ * @dataProvider data_next_tag_ignores_invalid_first_character_of_tag_name_comments
+ *
+ * @param string $html_with_markers HTML containing an invalid tag closer whose element before and
+ * element after contain the "start" and "end" CSS classes.
+ */
+ public function test_next_tag_ignores_invalid_first_character_of_tag_name_comments( $html_with_markers ) {
+ $p = new WP_HTML_Tag_Processor( $html_with_markers );
+ $p->next_tag( array( 'class_name' => 'start' ) );
+ $p->next_tag();
+
+ $this->assertSame( 'end', $p->get_attribute( 'class' ) );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array[]
+ */
+ public function data_next_tag_ignores_invalid_first_character_of_tag_name_comments() {
+ return array(
+ 'Invalid tag openers as normal text' => array(
+ '<ul><li><div class=start>I <3 when outflow > inflow</div><img class=end></li></ul>',
+ ),
+
+ 'Invalid tag closers as comments' => array(
+ '<ul><li><div class=start>I </3 when <img> outflow <br class=end> inflow</div></li></ul>',
+ ),
+
+ 'Unexpected question mark instead of tag name' => array(
+ '<div class=start><?xml-stylesheet type="text/css" href="style.css"?><hr class=end>',
+ ),
+ );
+ }
+
+ /**
</ins><span class="cx" style="display: block; padding: 0 10px"> * @ticket 56299
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @covers WP_HTML_Tag_Processor::next_tag
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -1785,6 +1826,99 @@
</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 invalid comment closing syntax "--!>" properly closes a comment.
+ *
+ * @ticket 58007
+ *
+ * @covers WP_HTML_Tag_Processor::next_tag
+ *
+ */
+ public function test_allows_incorrectly_closed_comments() {
+ $p = new WP_HTML_Tag_Processor( '<img id=before><!-- <img id=inside> --!><img id=after>--><img id=final>' );
+
+ $p->next_tag();
+ $this->assertSame( 'before', $p->get_attribute( 'id' ), 'Did not find starting tag.' );
+
+ $p->next_tag();
+ $this->assertSame( 'after', $p->get_attribute( 'id' ), 'Did not properly close improperly-closed comment.' );
+
+ $p->next_tag();
+ $this->assertSame( 'final', $p->get_attribute( 'id' ), 'Did not skip over unopened comment-closer.' );
+ }
+
+ /**
+ * Ensures that unclosed and invalid comments don't trigger warnings or errors.
+ *
+ * @ticket 58007
+ *
+ * @covers WP_HTML_Tag_Processor::next_tag
+ *
+ * @dataProvider data_html_with_unclosed_comments
+ *
+ * @param string $html_ending_before_comment_close HTML with opened comments that aren't closed
+ */
+ public function test_documents_may_end_with_unclosed_comment( $html_ending_before_comment_close ) {
+ $p = new WP_HTML_Tag_Processor( $html_ending_before_comment_close );
+
+ $this->assertFalse( $p->next_tag() );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array[]
+ */
+ public function data_html_with_unclosed_comments() {
+ return array(
+ 'Shortest open valid comment' => array( '<!--' ),
+ 'Basic truncated comment' => array( '<!-- this ends --' ),
+ 'Comment with closer look-alike' => array( '<!-- this ends --x' ),
+ 'Comment with closer look-alike 2' => array( '<!-- this ends --!x' ),
+ 'Invalid tag-closer comment' => array( '</(when will this madness end?)' ),
+ 'Invalid tag-closer comment 2' => array( '</(when will this madness end?)--' ),
+ );
+ }
+
+ /**
+ * Ensures that abruptly-closed empty comments are properly closed.
+ *
+ * @ticket 58007
+ *
+ * @covers WP_HTML_Tag_Processor::next_tag
+ *
+ * @dataProvider data_abruptly_closed_empty_comments
+ *
+ * @param string $html_with_after_marker HTML to test with "id=after" on element immediately following an abruptly closed comment.
+ */
+ public function test_closes_abrupt_closing_of_empty_comment( $html_with_after_marker ) {
+ $p = new WP_HTML_Tag_Processor( $html_with_after_marker );
+ $p->next_tag();
+ $p->next_tag();
+
+ $this->assertSame( 'after', $p->get_attribute( 'id' ), 'Did not find tag after closing abruptly-closed comment' );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array[]
+ */
+ public function data_abruptly_closed_empty_comments() {
+ return array(
+ 'Empty comment with two dashes only' => array( '<hr><!--><hr id=after>' ),
+ 'Empty comment with two dashes only, improperly closed' => array( '<hr><!--!><hr id=inside>--><hr id=after>' ),
+ 'Comment with two dashes only, improperly closed twice' => array( '<hr><!--!><hr id=inside>--!><hr id=after>' ),
+ 'Empty comment with three dashes' => array( '<hr><!---><hr id=after>' ),
+ 'Empty comment with three dashes, improperly closed' => array( '<hr><!---!><hr id=inside>--><hr id=after>' ),
+ 'Comment with three dashes, improperly closed twice' => array( '<hr><!---!><hr id=inside>--!><hr id=after>' ),
+ 'Empty comment with four dashes' => array( '<hr><!----><hr id=after>' ),
+ 'Empty comment with four dashes, improperly closed' => array( '<hr><!----!><hr id=after>--><hr id=final>' ),
+ 'Comment with four dashes, improperly closed twice' => array( '<hr><!----!><hr id=after>--!><hr id=final>' ),
+ 'Comment with almost-closer inside' => array( '<hr><!-- ---!><hr id=after>--!><hr id=final>' ),
+ );
+ }
+
+ /**
</ins><span class="cx" style="display: block; padding: 0 10px"> * @ticket 56299
</span><span class="cx" style="display: block; padding: 0 10px"> *
</span><span class="cx" style="display: block; padding: 0 10px"> * @covers WP_HTML_Tag_Processor::next_tag
</span></span></pre>
</div>
</div>
</body>
</html>