From 4422aac17cacaf5e99d8fa14ed8b06939cc53e52 Mon Sep 17 00:00:00 2001
From: pento <pento@602fd350-edb4-49c9-b593-d223f7449a82>
Date: Mon, 23 May 2016 05:53:02 +0000
Subject: [PATCH] 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.




git-svn-id: https://develop.svn.wordpress.org/trunk@37521 602fd350-edb4-49c9-b593-d223f7449a82
---
 src/wp-includes/wp-db.php  |  9 +++++++--
 tests/phpunit/tests/db.php | 21 +++++++++++++++++++++
 2 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/src/wp-includes/wp-db.php b/src/wp-includes/wp-db.php
index 6fcc31a7eb..8d9f84c63e 100644
--- a/src/wp-includes/wp-db.php
+++ b/src/wp-includes/wp-db.php
@@ -757,8 +757,13 @@ class wpdb {
 			$this->charset = 'utf8mb4';
 		}
 
-		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+			// _general_ is outdated, so we can upgrade it to _unicode_, instead.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 );
+			}
 		}
 	}
 
diff --git a/tests/phpunit/tests/db.php b/tests/phpunit/tests/db.php
index f49a3e07b6..20ed791b53 100644
--- a/tests/phpunit/tests/db.php
+++ b/tests/phpunit/tests/db.php
@@ -955,4 +955,25 @@ class Tests_DB extends WP_UnitTestCase {
 
 		$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 );
+	}
 }