<!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>[48872] trunk: Sitemaps: Prevent incorrect redirection of paged sitemap requests.</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/48872">48872</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/48872","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>peterwilsoncc</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2020-08-27 01:28:24 +0000 (Thu, 27 Aug 2020)</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'>Sitemaps: Prevent incorrect redirection of paged sitemap requests.

Update `redirect_canonical()` to account for custom pagination and URL format used by sitemaps in order to follow standard practices.

Introduce the function `get_sitemap_url()` to simplify getting the index and provider URLs as needed.

Props jonathanstegall, pbiron, GamerZ, salvoaranzulla, peterwilsoncc.
Fixes <a href="https://core.trac.wordpress.org/ticket/50910">#50910</a>.</pre>

<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludescanonicalphp">trunk/src/wp-includes/canonical.php</a></li>
<li><a href="#trunksrcwpincludessitemapsphp">trunk/src/wp-includes/sitemaps.php</a></li>
<li><a href="#trunktestsphpunittestscanonicalsitemapsphp">trunk/tests/phpunit/tests/canonical/sitemaps.php</a></li>
<li><a href="#trunktestsphpunittestssitemapsfunctionsphp">trunk/tests/phpunit/tests/sitemaps/functions.php</a></li>
</ul>

</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludescanonicalphp"></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/canonical.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/canonical.php       2020-08-27 01:08:23 UTC (rev 48871)
+++ trunk/src/wp-includes/canonical.php 2020-08-27 01:28:24 UTC (rev 48872)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -410,8 +410,11 @@
</span><span class="cx" style="display: block; padding: 0 10px">                        $redirect['query'] = remove_query_arg( 'page', $redirect['query'] );
</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">-                // Paging and feeds.
-               if ( get_query_var( 'paged' ) || is_feed() || get_query_var( 'cpage' ) ) {
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+         if ( get_query_var( 'sitemap' ) ) {
+                       $redirect_url      = get_sitemap_url( get_query_var( 'sitemap' ), get_query_var( 'sitemap-subtype' ), get_query_var( 'paged' ) );
+                       $redirect['query'] = remove_query_arg( array( 'sitemap', 'sitemap-subtype', 'paged' ), $redirect['query'] );
+               } elseif ( get_query_var( 'paged' ) || is_feed() || get_query_var( 'cpage' ) ) {
+                       // Paging and feeds.
</ins><span class="cx" style="display: block; padding: 0 10px">                         $paged = get_query_var( 'paged' );
</span><span class="cx" style="display: block; padding: 0 10px">                        $feed  = get_query_var( 'feed' );
</span><span class="cx" style="display: block; padding: 0 10px">                        $cpage = get_query_var( 'cpage' );
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -508,11 +511,6 @@
</span><span class="cx" style="display: block; padding: 0 10px">                                $redirect['path'] = trailingslashit( $redirect['path'] ) . $addl_path;
</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">-                        // Remove trailing slash for sitemaps requests.
-                       if ( ! empty( get_query_var( 'sitemap' ) ) ) {
-                               $redirect['path'] = untrailingslashit( $redirect['path'] );
-                       }
-
</del><span class="cx" style="display: block; padding: 0 10px">                         $redirect_url = $redirect['scheme'] . '://' . $redirect['host'] . $redirect['path'];
</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="trunksrcwpincludessitemapsphp"></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/sitemaps.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/sitemaps.php        2020-08-27 01:08:23 UTC (rev 48871)
+++ trunk/src/wp-includes/sitemaps.php  2020-08-27 01:28:24 UTC (rev 48872)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -87,3 +87,39 @@
</span><span class="cx" style="display: block; padding: 0 10px">         */
</span><span class="cx" style="display: block; padding: 0 10px">        return apply_filters( 'wp_sitemaps_max_urls', 2000, $object_type );
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+
+/**
+ * Retrieves the full URL for a sitemap.
+ *
+ * @since 5.5.1
+ *
+ * @param string $name         The sitemap name.
+ * @param string $subtype_name The sitemap subtype name.  Default empty string.
+ * @param int    $page         The page of the sitemap.  Default 1.
+ * @return string|false The sitemap URL or false if the sitemap doesn't exist.
+ */
+function get_sitemap_url( $name, $subtype_name = '', $page = 1 ) {
+       $sitemaps = wp_sitemaps_get_server();
+       if ( ! $sitemaps ) {
+               return false;
+       }
+
+       if ( 'index' === $name ) {
+               return $sitemaps->index->get_index_url();
+       }
+
+       $provider = $sitemaps->registry->get_provider( $name );
+       if ( ! $provider ) {
+               return false;
+       }
+
+       if ( $subtype_name && ! in_array( $subtype_name, array_keys( $provider->get_object_subtypes() ), true ) ) {
+               return false;
+       }
+
+       $page = absint( $page );
+       if ( 0 >= $page ) {
+               $page = 1;
+       }
+       return $provider->get_sitemap_url( $subtype_name, $page );
+}
</ins></span></pre></div>
<a id="trunktestsphpunittestscanonicalsitemapsphp"></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/canonical/sitemaps.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/canonical/sitemaps.php  2020-08-27 01:08:23 UTC (rev 48871)
+++ trunk/tests/phpunit/tests/canonical/sitemaps.php    2020-08-27 01:28:24 UTC (rev 48872)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -40,4 +40,75 @@
</span><span class="cx" style="display: block; padding: 0 10px">                $this->assertCanonical( '/wp-sitemap.xsl/', '/wp-sitemap.xsl' );
</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">+        /**
+        * Ensure sitemaps redirects work as expected with pretty permalinks.
+        *
+        * @dataProvider data_sitemaps_canonical_pretty_redirects
+        * @ticket 50910
+        */
+       public function test_sitemaps_canonical_pretty_redirects( $test_url, $expected ) {
+               $this->set_permalink_structure( '/%postname%/' );
+               $this->assertCanonical( $test_url, $expected, 50910 );
+       }
+
+       /**
+        * Data provider for test_sitemaps_canonical_pretty_redirects.
+        *
+        * @return array[] {
+        *     Data to test with.
+        *
+        *     @type string $0 The test URL.
+        *     @type string $1 The expected canonical URL.
+        * }
+        */
+       public function data_sitemaps_canonical_pretty_redirects() {
+               return array(
+                       // Ugly/incorrect versions redirect correctly.
+                       array( '/?sitemap=index', '/wp-sitemap.xml' ),
+                       array( '/wp-sitemap.xml/', '/wp-sitemap.xml' ),
+                       array( '/?sitemap=posts&sitemap-subtype=post', '/wp-sitemap-posts-post-1.xml' ),
+                       array( '/?sitemap=posts&sitemap-subtype=post&paged=2', '/wp-sitemap-posts-post-2.xml' ),
+                       array( '/?sitemap=taxonomies&sitemap-subtype=category', '/wp-sitemap-taxonomies-category-1.xml' ),
+                       array( '/?sitemap=taxonomies&sitemap-subtype=category&paged=2', '/wp-sitemap-taxonomies-category-2.xml' ),
+
+                       // Pretty versions don't redirect incorrectly.
+                       array( '/wp-sitemap.xml', '/wp-sitemap.xml' ),
+                       array( '/wp-sitemap-posts-post-1.xml', '/wp-sitemap-posts-post-1.xml' ),
+                       array( '/wp-sitemap-posts-post-2.xml', '/wp-sitemap-posts-post-2.xml' ),
+                       array( '/wp-sitemap-taxonomies-category-1.xml', '/wp-sitemap-taxonomies-category-1.xml' ),
+                       array( '/wp-sitemap-taxonomies-category-2.xml', '/wp-sitemap-taxonomies-category-2.xml' ),
+               );
+       }
+
+       /**
+        * Ensure sitemaps redirects work as expected with ugly permalinks.
+        *
+        * @dataProvider data_sitemaps_canonical_ugly_redirects
+        * @ticket 50910
+        */
+       public function test_sitemaps_canonical_ugly_redirects( $test_url, $expected ) {
+               $this->set_permalink_structure( '' );
+               $this->assertCanonical( $test_url, $expected, 50910 );
+       }
+
+       /**
+        * Data provider for test_sitemaps_canonical_ugly_redirects.
+        *
+        * @return array[] {
+        *     Data to test with.
+        *
+        *     @type string $0 The test URL.
+        *     @type string $1 The expected canonical URL.
+        * }
+        */
+       public function data_sitemaps_canonical_ugly_redirects() {
+               return array(
+                       // Ugly permalinks remain ugly.
+                       array( '/?sitemap=index', '/?sitemap=index' ),
+                       array( '/?sitemap=posts&sitemap-subtype=post', '/?sitemap=posts&sitemap-subtype=post' ),
+                       array( '/?sitemap=posts&sitemap-subtype=post&paged=2', '/?sitemap=posts&sitemap-subtype=post&paged=2' ),
+                       array( '/?sitemap=taxonomies&sitemap-subtype=category', '/?sitemap=taxonomies&sitemap-subtype=category' ),
+                       array( '/?sitemap=taxonomies&sitemap-subtype=category&paged=2', '/?sitemap=taxonomies&sitemap-subtype=category&paged=2' ),
+               );
+       }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre></div>
<a id="trunktestsphpunittestssitemapsfunctionsphp"></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/sitemaps/functions.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/sitemaps/functions.php  2020-08-27 01:08:23 UTC (rev 48871)
+++ trunk/tests/phpunit/tests/sitemaps/functions.php    2020-08-27 01:28:24 UTC (rev 48872)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -58,4 +58,92 @@
</span><span class="cx" style="display: block; padding: 0 10px">                        $this->assertTrue( is_a( $sitemaps[ $name ], $provider ), "Default $name sitemap is not a $provider object." );
</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">+
+       /**
+        * Test get_sitemap_url() with ugly permalinks.
+        *
+        * @dataProvider ugly_permalinks_provider
+        */
+       public function test_get_sitemap_url_ugly_permalinks( $name, $subtype_name, $page, $expected ) {
+               $actual = get_sitemap_url( $name, $subtype_name, $page );
+
+               $this->assertSame( $expected, $actual );
+       }
+
+       /**
+        * Test get_sitemap_url() with pretty permalinks.
+        *
+        * @dataProvider pretty_permalinks_provider
+        */
+       public function test_get_sitemap_url_pretty_permalinks( $name, $subtype_name, $page, $expected ) {
+               $this->set_permalink_structure( '/%postname%/' );
+
+               $actual = get_sitemap_url( $name, $subtype_name, $page );
+
+               $this->assertSame( $expected, $actual );
+       }
+
+       /**
+        * Data provider for test_get_sitemap_url_ugly_permalinks.
+        *
+        * @return array[] {
+        *     Data to test with.
+        *
+        *     @type string       $0 Sitemap name.
+        *     @type string       $1 Sitemap subtype name.
+        *     @type int          $3 Sitemap page.
+        *     @type string|false $4 Sitemap URL.
+        * }
+        */
+       function ugly_permalinks_provider() {
+               return array(
+                       array( 'posts', 'post', 1, home_url( '/?sitemap=posts&sitemap-subtype=post&paged=1' ) ),
+                       array( 'posts', 'post', 0, home_url( '/?sitemap=posts&sitemap-subtype=post&paged=1' ) ),
+                       array( 'posts', 'page', 1, home_url( '/?sitemap=posts&sitemap-subtype=page&paged=1' ) ),
+                       array( 'posts', 'page', 5, home_url( '/?sitemap=posts&sitemap-subtype=page&paged=5' ) ),
+                       // post_type doesn't exist.
+                       array( 'posts', 'foo', 5, false ),
+                       array( 'taxonomies', 'category', 1, home_url( '/?sitemap=taxonomies&sitemap-subtype=category&paged=1' ) ),
+                       array( 'taxonomies', 'post_tag', 1, home_url( '/?sitemap=taxonomies&sitemap-subtype=post_tag&paged=1' ) ),
+                       array( 'taxonomies', 'post_tag', -1, home_url( '/?sitemap=taxonomies&sitemap-subtype=post_tag&paged=1' ) ),
+                       // negative paged, gets converted to it's absolute value.
+                       array( 'users', '', 4, home_url( '/?sitemap=users&paged=4' ) ),
+                       // users provider doesn't allow subtypes.
+                       array( 'users', 'foo', 4, false ),
+                       // provider doesn't exist.
+                       array( 'foo', '', 4, false ),
+               );
+       }
+
+       /**
+        * Data provider for test_get_sitemap_url_pretty_permalinks
+        *
+        * @return array[] {
+        *     Data to test with.
+        *
+        *     @type string       $0 Sitemap name.
+        *     @type string       $1 Sitemap subtype name.
+        *     @type int          $3 Sitemap page.
+        *     @type string|false $4 Sitemap URL.
+        * }
+        */
+       function pretty_permalinks_provider() {
+               return array(
+                       array( 'posts', 'post', 1, home_url( '/wp-sitemap-posts-post-1.xml' ) ),
+                       array( 'posts', 'post', 0, home_url( '/wp-sitemap-posts-post-1.xml' ) ),
+                       array( 'posts', 'page', 1, home_url( '/wp-sitemap-posts-page-1.xml' ) ),
+                       array( 'posts', 'page', 5, home_url( '/wp-sitemap-posts-page-5.xml' ) ),
+                       // post_type doesn't exist.
+                       array( 'posts', 'foo', 5, false ),
+                       array( 'taxonomies', 'category', 1, home_url( '/wp-sitemap-taxonomies-category-1.xml' ) ),
+                       array( 'taxonomies', 'post_tag', 1, home_url( '/wp-sitemap-taxonomies-post_tag-1.xml' ) ),
+                       // negative paged, gets converted to it's absolute value.
+                       array( 'taxonomies', 'post_tag', -1, home_url( '/wp-sitemap-taxonomies-post_tag-1.xml' ) ),
+                       array( 'users', '', 4, home_url( '/wp-sitemap-users-4.xml' ) ),
+                       // users provider doesn't allow subtypes.
+                       array( 'users', 'foo', 4, false ),
+                       // provider doesn't exist.
+                       array( 'foo', '', 4, false ),
+               );
+       }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>

</body>
</html>