<!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>[51984] trunk: Permalinks: Sanitize non-visible characters inside `sanitize_title_with_dashes()`.</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/51984">51984</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/51984","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>johnjamesjacoby</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2021-11-02 18:46:36 +0000 (Tue, 02 Nov 2021)</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'>Permalinks: Sanitize non-visible characters inside `sanitize_title_with_dashes()`.
This change prevents non-visible characters in titles from creating encoded values in permalinks, opting instead for the following replacement strategy:
* Non-visible non-zero-width characters are replaced with hyphens
* Non-visible zero-width characters are removed entirely
Included with this change are 64 additional PHPUnit assertions to confirm that only the targeted non-visible characters are sanitized as intended.
Before this change, URLs would unintentionally contain encoded values where these non-visible characters were. After this change, URLs intentionally strip out or hyphenate these non-visible characters.
Props costdev, dhanendran, hellofromtonya, paaljoachim, peterwilsoncc, poena, sergeybiryukov.
Fixes <a href="https://core.trac.wordpress.org/ticket/47912">#47912</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludesformattingphp">trunk/src/wp-includes/formatting.php</a></li>
<li><a href="#trunktestsphpunittestsformattingsanitizeTitleWithDashesphp">trunk/tests/phpunit/tests/formatting/sanitizeTitleWithDashes.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludesformattingphp"></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/formatting.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/formatting.php 2021-11-02 18:32:24 UTC (rev 51983)
+++ trunk/src/wp-includes/formatting.php 2021-11-02 18:46:36 UTC (rev 51984)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -2288,11 +2288,45 @@
</span><span class="cx" style="display: block; padding: 0 10px"> '%cc%80',
</span><span class="cx" style="display: block; padding: 0 10px"> '%cc%84',
</span><span class="cx" style="display: block; padding: 0 10px"> '%cc%8c',
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ // Non-visible characters that display without a width.
+ '%e2%80%8b',
+ '%e2%80%8c',
+ '%e2%80%8d',
+ '%e2%80%8e',
+ '%e2%80%8f',
+ '%e2%80%aa',
+ '%e2%80%ab',
+ '%e2%80%ac',
+ '%e2%80%ad',
+ '%e2%80%ae',
+ '%ef%bb%bf',
</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"> $title
</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">+ // Convert non-visible characters that display with a width to hyphen.
+ $title = str_replace(
+ array(
+ '%e2%80%80',
+ '%e2%80%81',
+ '%e2%80%82',
+ '%e2%80%83',
+ '%e2%80%84',
+ '%e2%80%85',
+ '%e2%80%86',
+ '%e2%80%87',
+ '%e2%80%88',
+ '%e2%80%89',
+ '%e2%80%8a',
+ '%e2%80%a8',
+ '%e2%80%a9',
+ '%e2%80%af',
+ ),
+ '-',
+ $title
+ );
+
</ins><span class="cx" style="display: block; padding: 0 10px"> // Convert × to 'x'.
</span><span class="cx" style="display: block; padding: 0 10px"> $title = str_replace( '%c3%97', 'x', $title );
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre></div>
<a id="trunktestsphpunittestsformattingsanitizeTitleWithDashesphp"></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/formatting/sanitizeTitleWithDashes.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/formatting/sanitizeTitleWithDashes.php 2021-11-02 18:32:24 UTC (rev 51983)
+++ trunk/tests/phpunit/tests/formatting/sanitizeTitleWithDashes.php 2021-11-02 18:46:36 UTC (rev 51984)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -147,4 +147,214 @@
</span><span class="cx" style="display: block; padding: 0 10px"> $this->assertSame( 'aaaa', sanitize_title_with_dashes( 'ááa´aˊ', '', 'save' ) );
</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">+ /**
+ * @ticket 47912
+ * @dataProvider data_removes_non_visible_characters_without_width
+ *
+ * @param string $title The title to be sanitized.
+ * @param string $expected Expected sanitized title.
+ */
+ public function test_removes_non_visible_characters_without_width( $title, $expected = '' ) {
+ $this->assertSame( $expected, sanitize_title_with_dashes( $title, '', 'save' ) );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array
+ */
+ public function data_removes_non_visible_characters_without_width() {
+ return array(
+ // Only the non-visible characters.
+ 'only %e2%80%8b' => array( '%e2%80%8b' ),
+ 'only %e2%80%8c' => array( '%e2%80%8c' ),
+ 'only %e2%80%8d' => array( '%e2%80%8d' ),
+ 'only %e2%80%8e' => array( '%e2%80%8e' ),
+ 'only %e2%80%8f' => array( '%e2%80%8f' ),
+ 'only %e2%80%aa' => array( '%e2%80%aa' ),
+ 'only %e2%80%ab' => array( '%e2%80%ab' ),
+ 'only %e2%80%ac' => array( '%e2%80%ac' ),
+ 'only %e2%80%ad' => array( '%e2%80%ad' ),
+ 'only %e2%80%ae' => array( '%e2%80%ae' ),
+ 'only %ef%bb%bf' => array( '%ef%bb%bf' ),
+
+ // Non-visible characters within the title.
+ 'in middle of title' => array(
+ 'title' => 'Nonvisible %ef%bb%bfin middle of title',
+ 'expected' => 'nonvisible-in-middle-of-title',
+ ),
+ 'at start of title' => array(
+ 'title' => '%e2%80%8bNonvisible at start of title',
+ 'expected' => 'nonvisible-at-start-of-title',
+ ),
+ 'at end of title' => array(
+ 'title' => 'Nonvisible at end of title %e2%80%8b',
+ 'expected' => 'nonvisible-at-end-of-title',
+ ),
+ 'randomly in title' => array(
+ 'title' => 'Nonvisible%ef%bb%bf %e2%80%aerandomly %e2%80%8ein the %e2%80%8e title%e2%80%8e',
+ 'expected' => 'nonvisible-randomly-in-the-title',
+ ),
+ );
+ }
+
+ /**
+ * @ticket 47912
+ * @dataProvider data_non_visible_characters_without_width_when_not_save
+ *
+ * @param string $title The title to be sanitized.
+ * @param string $expected Expected sanitized title.
+ */
+ public function test_non_visible_characters_without_width_when_not_save( $title, $expected = '' ) {
+ $this->assertSame( $expected, sanitize_title_with_dashes( $title ) );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array
+ */
+ public function data_non_visible_characters_without_width_when_not_save() {
+ return array(
+ // Just the non-visible characters.
+ 'only %e2%80%8b' => array( '%e2%80%8b', '%e2%80%8b' ),
+ 'only %e2%80%8c' => array( '%e2%80%8c', '%e2%80%8c' ),
+ 'only %e2%80%8d' => array( '%e2%80%8d', '%e2%80%8d' ),
+ 'only %e2%80%8e' => array( '%e2%80%8e', '%e2%80%8e' ),
+ 'only %e2%80%8f' => array( '%e2%80%8f', '%e2%80%8f' ),
+ 'only %e2%80%aa' => array( '%e2%80%aa', '%e2%80%aa' ),
+ 'only %e2%80%ab' => array( '%e2%80%ab', '%e2%80%ab' ),
+ 'only %e2%80%ac' => array( '%e2%80%ac', '%e2%80%ac' ),
+ 'only %e2%80%ad' => array( '%e2%80%ad', '%e2%80%ad' ),
+ 'only %e2%80%ae' => array( '%e2%80%ae', '%e2%80%ae' ),
+ 'only %ef%bb%bf' => array( '%ef%bb%bf', '%ef%bb%bf' ),
+
+ // Non-visible characters within the title.
+ 'in middle of title' => array(
+ 'title' => 'Nonvisible %ef%bb%bfin middle of title',
+ 'expected' => 'nonvisible-%ef%bb%bfin-middle-of-title',
+ ),
+ 'at start of title' => array(
+ 'title' => '%e2%80%8bNonvisible at start of title',
+ 'expected' => '%e2%80%8bnonvisible-at-start-of-title',
+ ),
+ 'at end of title' => array(
+ 'title' => 'Nonvisible at end of title %e2%80%8b',
+ 'expected' => 'nonvisible-at-end-of-title-%e2%80%8b',
+ ),
+ 'randomly in title' => array(
+ 'title' => 'Nonvisible%ef%bb%bf %e2%80%aerandomly %e2%80%8ein the %e2%80%8e title%e2%80%8e',
+ 'expected' => 'nonvisible%ef%bb%bf-%e2%80%aerandomly-%e2%80%8ein-the-%e2%80%8e-title%e2%80%8e',
+ ),
+ );
+ }
+
+ /**
+ * @ticket 47912
+ * @dataProvider data_converts_non_visible_characters_with_width_to_hyphen
+ *
+ * @param string $title The title to be sanitized.
+ * @param string $expected Expected sanitized title.
+ */
+ public function test_converts_non_visible_characters_with_width_to_hyphen( $title, $expected = '' ) {
+ $this->assertSame( $expected, sanitize_title_with_dashes( $title, '', 'save' ) );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array
+ */
+ public function data_converts_non_visible_characters_with_width_to_hyphen() {
+ return array(
+ // Only the non-visible characters.
+ 'only %e2%80%80' => array( '%e2%80%80' ),
+ 'only %e2%80%81' => array( '%e2%80%81' ),
+ 'only %e2%80%82' => array( '%e2%80%82' ),
+ 'only %e2%80%83' => array( '%e2%80%83' ),
+ 'only %e2%80%84' => array( '%e2%80%84' ),
+ 'only %e2%80%85' => array( '%e2%80%85' ),
+ 'only %e2%80%86' => array( '%e2%80%86' ),
+ 'only %e2%80%87' => array( '%e2%80%87' ),
+ 'only %e2%80%88' => array( '%e2%80%88' ),
+ 'only %e2%80%89' => array( '%e2%80%89' ),
+ 'only %e2%80%8a' => array( '%e2%80%8a' ),
+ 'only %e2%80%a8' => array( '%e2%80%a8' ),
+ 'only %e2%80%a9' => array( '%e2%80%a9' ),
+ 'only %e2%80%af' => array( '%e2%80%af' ),
+
+ // Non-visible characters within the title.
+ 'in middle of title' => array(
+ 'title' => 'Nonvisible %e2%80%82 in middle of title',
+ 'expected' => 'nonvisible-in-middle-of-title',
+ ),
+ 'at start of title' => array(
+ 'title' => '%e2%80%83Nonvisible at start of title',
+ 'expected' => 'nonvisible-at-start-of-title',
+ ),
+ 'at end of title' => array(
+ 'title' => 'Nonvisible at end of title %e2%80%81',
+ 'expected' => 'nonvisible-at-end-of-title',
+ ),
+ 'two end of title' => array(
+ 'title' => 'Nonvisible at end of title %e2%80%81 %e2%80%af',
+ 'expected' => 'nonvisible-at-end-of-title',
+ ),
+ 'randomly in title' => array(
+ 'title' => 'Nonvisible%e2%80%80 %e2%80%a9randomly %e2%80%87in the %e2%80%a8 title%e2%80%af',
+ 'expected' => 'nonvisible-randomly-in-the-title',
+ ),
+ );
+ }
+
+ /**
+ * @ticket 47912
+ * @dataProvider data_non_visible_characters_with_width_to_hyphen_when_not_save
+ *
+ * @param string $title The title to be sanitized.
+ * @param string $expected Expected sanitized title.
+ */
+ public function test_non_visible_characters_with_width_to_hyphen_when_not_save( $title, $expected = '' ) {
+ $this->assertSame( $expected, sanitize_title_with_dashes( $title ) );
+ }
+
+ /**
+ * Data provider.
+ *
+ * @return array
+ */
+ public function data_non_visible_characters_with_width_to_hyphen_when_not_save() {
+ return array(
+ // Just the non-visible characters.
+ 'only %e2%80%8b' => array( '%e2%80%8b', '%e2%80%8b' ),
+ 'only %e2%80%8c' => array( '%e2%80%8c', '%e2%80%8c' ),
+ 'only %e2%80%8d' => array( '%e2%80%8d', '%e2%80%8d' ),
+ 'only %e2%80%8e' => array( '%e2%80%8e', '%e2%80%8e' ),
+ 'only %e2%80%8f' => array( '%e2%80%8f', '%e2%80%8f' ),
+ 'only %e2%80%aa' => array( '%e2%80%aa', '%e2%80%aa' ),
+ 'only %e2%80%ab' => array( '%e2%80%ab', '%e2%80%ab' ),
+ 'only %e2%80%ac' => array( '%e2%80%ac', '%e2%80%ac' ),
+ 'only %e2%80%ad' => array( '%e2%80%ad', '%e2%80%ad' ),
+ 'only %e2%80%ae' => array( '%e2%80%ae', '%e2%80%ae' ),
+ 'only %ef%bb%bf' => array( '%ef%bb%bf', '%ef%bb%bf' ),
+
+ // Non-visible characters within the title.
+ 'in middle of title' => array(
+ 'title' => 'Nonvisible %e2%80%82 in middle of title',
+ 'expected' => 'nonvisible-%e2%80%82-in-middle-of-title',
+ ),
+ 'at start of title' => array(
+ 'title' => '%e2%80%83Nonvisible at start of title',
+ 'expected' => '%e2%80%83nonvisible-at-start-of-title',
+ ),
+ 'at end of title' => array(
+ 'title' => 'Nonvisible at end of title %e2%80%81',
+ 'expected' => 'nonvisible-at-end-of-title-%e2%80%81',
+ ),
+ 'randomly in title' => array(
+ 'title' => 'Nonvisible%e2%80%80 %e2%80%aerandomly %e2%80%87in the %e2%80%a8 title%e2%80%af',
+ 'expected' => 'nonvisible%e2%80%80-%e2%80%aerandomly-%e2%80%87in-the-%e2%80%a8-title%e2%80%af',
+ ),
+ );
+ }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>
</body>
</html>