Changeset 37521

Timestamp:

05/23/2016 05:53:02 AM (9 years ago)

Author:

pento

Message:

Database: Obey locale-specific utf8 collation settings.

Some sites prefer to use locale-specific location settings. For example, the Swedish WordPress package use utf8_swedish_ci, instead of utf8_unicode_ci. When upgrading the connection to utf8mb4, we were overriding this to be utf8mb4_unicode_ci, instead of maintaining the use of the _swedish_ci variant.

The locale-specific collations do have extra collation rules just for that language, so it's useful to maintain compatibility.

Fixes #32405.

Location:

trunk

Files:

• src/wp-includes/wp-db.php (modified) (1 diff)
• tests/phpunit/tests/db.php (modified) (1 diff)

trunk/src/wp-includes/wp-db.php

@@ -758 +758 @@
         }
 
-        if ( 'utf8mb4' === $this->charset && ( ! $this->collate || stripos( $this->collate, 'utf8_' ) === 0 ) ) {
-            $this->collate = 'utf8mb4_unicode_ci';
+        if ( 'utf8mb4' === $this->charset ) {
+            // _general_ is outdated, so we can upgrade it to _unicode_, instead.
+            if ( ! $this->collate || 'utf8_general_ci' === $this->collate ) {
+                $this->collate = 'utf8mb4_unicode_ci';
+            } else {
+                $this->collate = str_replace( 'utf8_', 'utf8mb4_', $this->collate );
+            }
         }
     }

trunk/tests/phpunit/tests/db.php

@@ -956 +956 @@
         $wpdb->check_connection();
     }
+
+    /**
+     * @ticket 32405
+     */
+    function test_non_unicode_collations() {
+        global $wpdb;
+
+        if ( ! $wpdb->has_cap( 'utf8mb4' ) ) {
+            $this->markTestSkipped( 'This test requires utf8mb4 support' );
+        }
+
+        $charset = $wpdb->charset;
+        $collate = $wpdb->collate;
+
+        $wpdb->init_charset( 'utf8', 'utf8_swedish_ci' );
+
+        $this->assertSame( 'utf8mb4', $wpdb->charset );
+        $this->assertSame( 'utf8mb4_swedish_ci', $wpdb->collate );
+
+        $wpdb->init_charset( $charset, $collate );
+    }
 }