<!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>[37601] trunk: Database: Split the logic of `wpdb::init_charset()` into a separate method.</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 { 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/37601">37601</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/37601","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>pento</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2016-06-01 02:37:20 +0000 (Wed, 01 Jun 2016)</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'>Database: Split the logic of `wpdb::init_charset()` into a separate method.
The logic for determining the appropriate character set and collation to use is becoming more complex, particularly with the recent additions of <a href="https://core.trac.wordpress.org/changeset/37522">[37522]</a> and <a href="https://core.trac.wordpress.org/changeset/37523">[37523]</a>. As `init_charset()` has side effects, and makes use of constants instead of parameters, it's not possible to unit test this logic.
This commit splits the logic part of `init_charset()` out into a new method, `wpdb::determine_charset()`, along with appropriate unit tests.
See <a href="https://core.trac.wordpress.org/ticket/32105">#32105</a>, <a href="https://core.trac.wordpress.org/ticket/37522">#37522</a>.
Fixes <a href="https://core.trac.wordpress.org/ticket/36917">#36917</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludeswpdbphp">trunk/src/wp-includes/wp-db.php</a></li>
<li><a href="#trunktestsphpunittestsdbphp">trunk/tests/phpunit/tests/db.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludeswpdbphp"></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/wp-db.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/wp-includes/wp-db.php 2016-05-31 19:28:46 UTC (rev 37600)
+++ trunk/src/wp-includes/wp-db.php 2016-06-01 02:37:20 UTC (rev 37601)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -735,41 +735,62 @@
</span><span class="cx" style="display: block; padding: 0 10px"> */
</span><span class="cx" style="display: block; padding: 0 10px"> public function init_charset() {
</span><span class="cx" style="display: block; padding: 0 10px"> if ( function_exists('is_multisite') && is_multisite() ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->charset = 'utf8';
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $charset = 'utf8';
</ins><span class="cx" style="display: block; padding: 0 10px"> if ( defined( 'DB_COLLATE' ) && DB_COLLATE ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->collate = DB_COLLATE;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $collate = DB_COLLATE;
</ins><span class="cx" style="display: block; padding: 0 10px"> } else {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->collate = 'utf8_general_ci';
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $collate = 'utf8_general_ci';
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px"> } elseif ( defined( 'DB_COLLATE' ) ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->collate = DB_COLLATE;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $collate = DB_COLLATE;
</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"> if ( defined( 'DB_CHARSET' ) ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->charset = DB_CHARSET;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $charset = DB_CHARSET;
</ins><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">+ $charset_collate = $this->determine_charset( $charset, $collate );
+
+ $this->charset = $charset_collate['charset'];
+ $this->collate = $charset_collate['collate'];
+ }
+
+ /**
+ * Given a charset and collation, determine the best charset and collation to use.
+ *
+ * For example, when able, utf8mb4 should be used instead of utf8.
+ *
+ * @since 4.6.0
+ *
+ * @param string $charset The character set to check.
+ * @param string $collate The collation to check.
+ *
+ * @return array The most appropriate character set and collation to use.
+ */
+ public function determine_charset( $charset, $collate ) {
</ins><span class="cx" style="display: block; padding: 0 10px"> if ( ( $this->use_mysqli && ! ( $this->dbh instanceof mysqli ) ) || empty( $this->dbh ) ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- return;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ return compact( 'charset', 'collate' );
</ins><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">- if ( 'utf8' === $this->charset && $this->has_cap( 'utf8mb4' ) ) {
- $this->charset = 'utf8mb4';
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ if ( 'utf8' === $charset && $this->has_cap( 'utf8mb4' ) ) {
+ $charset = 'utf8mb4';
</ins><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">- if ( 'utf8mb4' === $this->charset ) {
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ if ( 'utf8mb4' === $charset ) {
</ins><span class="cx" style="display: block; padding: 0 10px"> // _general_ is outdated, so we can upgrade it to _unicode_, instead.
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- if ( ! $this->collate || 'utf8_general_ci' === $this->collate ) {
- $this->collate = 'utf8mb4_unicode_ci';
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ if ( ! $collate || 'utf8_general_ci' === $collate ) {
+ $collate = 'utf8mb4_unicode_ci';
</ins><span class="cx" style="display: block; padding: 0 10px"> } else {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $this->collate = str_replace( 'utf8_', 'utf8mb4_', $this->collate );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $collate = str_replace( 'utf8_', 'utf8mb4_', $collate );
</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="cx" style="display: block; padding: 0 10px"> // _unicode_520_ is a better collation, we should use that when it's available.
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- if ( $this->has_cap( 'utf8mb4_520' ) && 'utf8mb4_unicode_ci' === $this->collate ) {
- $this->collate = 'utf8mb4_unicode_520_ci';
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ if ( $this->has_cap( 'utf8mb4_520' ) && 'utf8mb4_unicode_ci' === $collate ) {
+ $collate = 'utf8mb4_unicode_520_ci';
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+
+ return compact( 'charset', 'collate' );
</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="trunktestsphpunittestsdbphp"></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/db.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/tests/db.php 2016-05-31 19:28:46 UTC (rev 37600)
+++ trunk/tests/phpunit/tests/db.php 2016-06-01 02:37:20 UTC (rev 37601)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -955,4 +955,78 @@
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> $wpdb->check_connection();
</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 36917
+ */
+ function test_charset_not_determined_when_disconnected() {
+ global $wpdb;
+
+ $charset = 'utf8';
+ $collate = 'this_isnt_a_collation';
+
+ $wpdb->close();
+
+ $result = $wpdb->determine_charset( $charset, $collate );
+
+ $this->assertSame( compact( 'charset', 'collate' ), $result );
+
+ $wpdb->check_connection();
+ }
+
+ /**
+ * @ticket 36917
+ */
+ function test_charset_switched_to_utf8mb4() {
+ global $wpdb;
+
+ if ( ! $wpdb->has_cap( 'utf8mb4' ) ) {
+ $this->markTestSkipped( 'This test requires utf8mb4 support.' );
+ }
+
+ $charset = 'utf8';
+ $collate = 'utf8_general_ci';
+
+ $result = $wpdb->determine_charset( $charset, $collate );
+
+ $this->assertSame( 'utf8mb4', $result['charset'] );
+ }
+
+ /**
+ * @ticket 32105
+ * @ticket 36917
+ */
+ function test_collate_switched_to_utf8mb4_520() {
+ global $wpdb;
+
+ if ( ! $wpdb->has_cap( 'utf8mb4_520' ) ) {
+ $this->markTestSkipped( 'This test requires utf8mb4_520 support.' );
+ }
+
+ $charset = 'utf8';
+ $collate = 'utf8_general_ci';
+
+ $result = $wpdb->determine_charset( $charset, $collate );
+
+ $this->assertSame( 'utf8mb4_unicode_520_ci', $result['collate'] );
+ }
+
+ /**
+ * @ticket 36917
+ * @ticket 37522
+ */
+ function test_non_unicode_collations() {
+ global $wpdb;
+
+ if ( ! $wpdb->has_cap( 'utf8mb4' ) ) {
+ $this->markTestSkipped( 'This test requires utf8mb4 support.' );
+ }
+
+ $charset = 'utf8';
+ $collate = 'utf8_swedish_ci';
+
+ $result = $wpdb->determine_charset( $charset, $collate );
+
+ $this->assertSame( 'utf8mb4_swedish_ci', $result['collate'] );
+ }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>
</body>
</html>