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 [37522] and [37523]. 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 #32105, #37522.

Fixes #36917.


Built from https://develop.svn.wordpress.org/trunk@37601

Author: pento

wp-includes/version.php

@@ -4,7 +4,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '4.6-alpha-37600';
+$wp_version = '4.6-alpha-37601';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.

wp-includes/wp-db.php

@@ -735,41 +735,62 @@ public function __unset( $name ) {
 	 */
 	public function init_charset() {
 		if ( function_exists('is_multisite') && is_multisite() ) {
-			$this->charset = 'utf8';
+			$charset = 'utf8';
 			if ( defined( 'DB_COLLATE' ) && DB_COLLATE ) {
-				$this->collate = DB_COLLATE;
+				$collate = DB_COLLATE;
 			} else {
-				$this->collate = 'utf8_general_ci';
+				$collate = 'utf8_general_ci';
 			}
 		} elseif ( defined( 'DB_COLLATE' ) ) {
-			$this->collate = DB_COLLATE;
+			$collate = DB_COLLATE;
 		}
 
 		if ( defined( 'DB_CHARSET' ) ) {
-			$this->charset = DB_CHARSET;
+			$charset = DB_CHARSET;
 		}
 
+		$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 ) {
 		if ( ( $this->use_mysqli && ! ( $this->dbh instanceof mysqli ) ) || empty( $this->dbh ) ) {
-			return;
+			return compact( 'charset', 'collate' );
 		}
 
-		if ( 'utf8' === $this->charset && $this->has_cap( 'utf8mb4' ) ) {
-			$this->charset = 'utf8mb4';
+		if ( 'utf8' === $charset && $this->has_cap( 'utf8mb4' ) ) {
+			$charset = 'utf8mb4';
 		}
 
-		if ( 'utf8mb4' === $this->charset ) {
+		if ( 'utf8mb4' === $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';
+			if ( ! $collate || 'utf8_general_ci' === $collate ) {
+				$collate = 'utf8mb4_unicode_ci';
 			} else {
-				$this->collate = str_replace( 'utf8_', 'utf8mb4_', $this->collate );
+				$collate = str_replace( 'utf8_', 'utf8mb4_', $collate );
 			}
 		}
 
 		// _unicode_520_ is a better collation, we should use that when it's available.
-		if ( $this->has_cap( 'utf8mb4_520' ) && 'utf8mb4_unicode_ci' === $this->collate ) {
-			$this->collate = 'utf8mb4_unicode_520_ci';
+		if ( $this->has_cap( 'utf8mb4_520' ) && 'utf8mb4_unicode_ci' === $collate ) {
+			$collate = 'utf8mb4_unicode_520_ci';
 		}
+
+		return compact( 'charset', 'collate' );
 	}
 
 	/**