utf8mb4.patch

diff --git a/includes/database/mysql/database.inc b/includes/database/mysql/database.inc
index a96b053..4e59d77 100644
--- a/includes/database/mysql/database.inc
+++ b/includes/database/mysql/database.inc
@@ -28,6 +28,9 @@ class DatabaseConnection_mysql extends DatabaseConnection {
 
     $this->connectionOptions = $connection_options;
 
+    // Allow the charset to be overridden to utf8mb4 in settings.php.
+    $charset = $this->utf8mb4IsEnabled() && !(isset($this->connectionOptions['_dsn_utf8_fallback']) && $this->connectionOptions['_dsn_utf8_fallback'] === TRUE) ? 'utf8mb4' : 'utf8';
+
     // The DSN should use either a socket or a host/port.
     if (isset($connection_options['unix_socket'])) {
       $dsn = 'mysql:unix_socket=' . $connection_options['unix_socket'];
@@ -39,7 +42,7 @@ class DatabaseConnection_mysql extends DatabaseConnection {
     // Character set is added to dsn to ensure PDO uses the proper character
     // set when escaping. This has security implications. See
     // https://www.drupal.org/node/1201452 for further discussion.
-    $dsn .= ';charset=utf8';
+    $dsn .= ';charset=' . $charset;
     $dsn .= ';dbname=' . $connection_options['database'];
     // Allow PDO options to be overridden.
     $connection_options += array(
@@ -63,10 +66,10 @@ class DatabaseConnection_mysql extends DatabaseConnection {
     // certain one has been set; otherwise, MySQL defaults to 'utf8_general_ci'
     // for UTF-8.
     if (!empty($connection_options['collation'])) {
-      $this->exec('SET NAMES utf8 COLLATE ' . $connection_options['collation']);
+      $this->exec('SET NAMES ' . $charset . ' COLLATE ' . $connection_options['collation']);
     }
     else {
-      $this->exec('SET NAMES utf8');
+      $this->exec('SET NAMES ' . $charset);
     }
 
     // Set MySQL init_commands if not already defined.  Default Drupal's MySQL
@@ -206,6 +209,48 @@ class DatabaseConnection_mysql extends DatabaseConnection {
       }
     }
   }
+
+  /**
+   * Checks whether utf8mb4 support is enabled in settings.php.
+   *
+   * @return bool
+   */
+  public function utf8mb4IsEnabled() {
+    return isset($this->connectionOptions['charset']) && $this->connectionOptions['charset'] === 'utf8mb4';
+  }
+
+  /**
+   * Checks whether utf8mb4 support is available on the current system.
+   *
+   * @return bool
+   */
+  public function utf8mb4IsSupported() {
+    // Ensure that the MySQL driver supports utf8mb4 encoding.
+    $version = $this->getAttribute(\PDO::ATTR_CLIENT_VERSION);
+    if (FALSE !== strpos($version, 'mysqlnd')) {
+      // The mysqlnd driver supports utf8mb4 starting at version 5.0.9.
+      $version = preg_replace('/^\D+([\d.]+).*/', '$1', $version);
+      if (version_compare($version, '5.0.9', '<')) {
+        return FALSE;
+      }
+    }
+    else {
+      // The libmysqlclient driver supports utf8mb4 starting at version 5.5.3.
+      if (version_compare($version, '5.5.3', '<')) {
+        return FALSE;
+      }
+    }
+
+    // Ensure that the MySQL server supports large prefixes and utf8mb4.
+    try {
+      $this->query("CREATE TABLE {drupal_utf8mb4_test} (id VARCHAR(255), PRIMARY KEY(id(255))) CHARACTER SET utf8mb4 COLLATE utf8mb4_general_ci ROW_FORMAT=DYNAMIC");
+    }
+    catch (\Exception $e) {
+      return FALSE;
+    }
+    $this->query("DROP TABLE {drupal_utf8mb4_test}");
+    return TRUE;
+  }
 }
 
 
diff --git a/includes/database/mysql/schema.inc b/includes/database/mysql/schema.inc
index 2a2722e..f8fea1a 100644
--- a/includes/database/mysql/schema.inc
+++ b/includes/database/mysql/schema.inc
@@ -81,7 +81,8 @@ class DatabaseSchema_mysql extends DatabaseSchema {
     // Provide defaults if needed.
     $table += array(
       'mysql_engine' => 'InnoDB',
-      'mysql_character_set' => 'utf8',
+      // Allow the default charset to be overridden in settings.php.
+      'mysql_character_set' => $this->connection->utf8mb4IsEnabled() ? 'utf8mb4' : 'utf8',
     );
 
     $sql = "CREATE TABLE {" . $name . "} (\n";
@@ -109,6 +110,13 @@ class DatabaseSchema_mysql extends DatabaseSchema {
       $sql .= ' COLLATE ' . $info['collation'];
     }
 
+    // The row format needs to be either DYNAMIC or COMPRESSED in order to allow
+    // for the innodb_large_prefix setting to take effect, see
+    // https://dev.mysql.com/doc/refman/5.6/en/create-table.html
+    if ($this->connection->utf8mb4IsEnabled()) {
+      $sql .= ' ROW_FORMAT=DYNAMIC';
+    }
+
     // Add table comment.
     if (!empty($table['description'])) {
       $sql .= ' COMMENT ' . $this->prepareComment($table['description'], self::COMMENT_MAX_TABLE);
diff --git a/includes/install.inc b/includes/install.inc
index 5e1d3c6..2e9bb06 100644
--- a/includes/install.inc
+++ b/includes/install.inc
@@ -433,7 +433,35 @@ abstract class DatabaseTasks {
       // This doesn't actually test the connection.
       db_set_active();
       // Now actually do a check.
-      Database::getConnection();
+      try {
+        Database::getConnection();
+      }
+      catch  (\Exception $e) {
+        // Detect utf8mb4 incompability.
+        // Error code for "Can't initialize character set" error.
+        if ($e->getCode() == 2019) {
+          $this->fail(t('Your MySQL server and PHP MySQL driver must support utf8mb4 character encoding. Make sure to use a database system that supports this (such as MySQL/MariaDB/Percona 5.5.3 and up), and that the utf8mb4 character set is compiled in. See the <a href="@documentation" target="_blank">MySQL documentation</a> for more information.', array('@documentation' => 'https://dev.mysql.com/doc/refman/5.0/en/cannot-initialize-character-set.html')));
+          $info = Database::getConnectionInfo();
+          $info_copy = $info;
+          // Set a flag to fall back to utf8. Note: this flag should only be
+          // used here and is for internal use only.
+          $info_copy['default']['_dsn_utf8_fallback'] = TRUE;
+          // In order to change the Database::$databaseInfo array, we need to
+          // remove the active connection, then re-add it with the new info.
+          Database::removeConnection('default');
+          Database::addConnectionInfo('default', 'default', $info_copy['default']);
+          // Connect with the new database info, using the utf8 character set so
+          // that we can run the checkEngineVersion test.
+          Database::getConnection();
+          // Revert to the old settings.
+          Database::removeConnection('default');
+          Database::addConnectionInfo('default', 'default', $info['default']);
+        }
+        else {
+          // Rethrow the exception.
+          throw $e;
+        }
+      }
       $this->pass('Drupal can CONNECT to the database ok.');
     }
     catch (Exception $e) {
diff --git a/modules/system/system.install b/modules/system/system.install
index 323b7b3..b1282cf 100644
--- a/modules/system/system.install
+++ b/modules/system/system.install
@@ -196,6 +196,12 @@ function system_requirements($phase) {
     );
   }
 
+  // Test database-specific multi-byte UTF-8 related requirements.
+  $charset_requirements = _system_check_db_utf8mb4_requirements();
+  if (!empty($charset_requirements)) {
+    $requirements['database_charset'] = $charset_requirements;
+  }
+
   // Test PHP memory_limit
   $memory_limit = ini_get('memory_limit');
   $requirements['php_memory_limit'] = array(
@@ -518,6 +524,56 @@ function system_requirements($phase) {
 }
 
 /**
+ * Checks whether the requirements for multi-byte UTF-8 support are met.
+ *
+ * @return array
+ *   A requirements array with the result of the charset check.
+ */
+function _system_check_db_utf8mb4_requirements() {
+  global $install_state;
+  $connection = Database::getConnection();
+  // Skip the requirements check if we're in the initial step of the installer
+  // where the settings have not yet been verified, or if using
+  // a database driver that does not have any special UTF-8-related requirements
+  // (such as PostgreSQL or SQLite).
+  if ($install_state['settings_verified'] === FALSE || !method_exists($connection, 'utf8mb4IsEnabled') || !method_exists($connection, 'utf8mb4IsSupported')) {
+    return array();
+  }
+  $t = get_t();
+  $requirements['title'] = $t('Database multi-byte UTF-8 support');
+
+  $utf8mb4_enabled = $connection->utf8mb4IsEnabled();
+  $utf8mb4_supported = $connection->utf8mb4IsSupported();
+  $driver = $connection->driver();
+
+  if ($utf8mb4_enabled) {
+    if ($utf8mb4_supported) {
+      $requirements['value'] = $t('Enabled');
+      $requirements['description'] = $t('Multi-byte UTF-8 for @driver is enabled.', array('@driver' => $driver));
+      $requirements['severity'] = REQUIREMENT_OK;
+    }
+    else {
+      $requirements['value'] = $t('Not supported');
+      $requirements['description'] = $t('Multi-byte UTF-8 for @driver is activated in settings.php, but not supported on your system. Please turn this off in settings.php, or ensure that all requirements are met. See <a href="https://www.drupal.org/node/2754539">https://www.drupal.org/node/2754539</a> for more information.', array('@driver' => $driver));
+      $requirements['severity'] = REQUIREMENT_ERROR;
+    }
+  }
+  else {
+    if ($utf8mb4_supported) {
+      $requirements['value'] = $t('Not enabled');
+      $requirements['description'] = $t('Multi-byte UTF-8 for @driver is activated in settings.php, but not supported on your system. Please turn this off in settings.php, or ensure that all requirements are met. See <a href="https://www.drupal.org/node/2754539">https://www.drupal.org/node/2754539</a> for more information.', array('@driver' => $driver));
+      $requirements['severity'] = REQUIREMENT_WARNING;
+    }
+    else {
+      $requirements['value'] = $t('Disabled');
+      $requirements['description'] = $t('Multi-byte UTF-8 for @driver is disabled.', array('@driver' => $driver));
+      $requirements['severity'] = REQUIREMENT_INFO;
+    }
+  }
+  return $requirements;
+}
+
+/**
  * Implements hook_install().
  */
 function system_install() {
diff --git a/sites/default/default.settings.php b/sites/default/default.settings.php
index 7e36a4a..47cde4f 100644
--- a/sites/default/default.settings.php
+++ b/sites/default/default.settings.php
@@ -126,6 +126,30 @@
  * );
  * @endcode
  *
+ * For handling full UTF-8 in MySQL, including multi-byte characters such as
+ * emojis, asian symbols, and mathematical symbols, you may set the collation
+ * and charset to "utf8mb4":
+ * @code
+ * $databases['default']['default']['charset'] = 'utf8mb4';
+ * $databases['default']['default']['collation'] = 'utf8mb4_general_ci';
+ * @endcode
+ * When using this setting on an existing installation, ensure that
+ * all existing tables have been converted to the utf8mb4 charset,
+ * for example by using the utf8mb4_convert contrib module, so as to prevent
+ * mixing data with different charsets.
+ * Note this should only be used when all of the following conditions are met:
+ * - In order to allow for large indexes, MySQL must be set up with the
+ *   following my.cnf settings:
+ *     [mysqld]
+ *     innodb_large_prefix=0
+ *     innodb_file_format=barracuda
+ *     innodb_file_per_table=true
+ *   These settings are available as of MySQL 5.5.14, and are defaults in
+ *   MySQL 5.7.7 and up.
+ * - The PHP MySQL driver must support the utf8mb4 charset (libmysqlclient
+     5.5.3 and up, as well as mysqlnd 5.0.9 and up).
+ * - The MySQL server must support the utf8mb4 charset (5.5.3 and up).
+ *
  * You can optionally set prefixes for some or all database table names
  * by using the 'prefix' setting. If a prefix is specified, the table
  * name will be prepended with its value. Be sure to use valid database