Adding tests for 4 byte unicode characters

* success on SQLite and Postgres
* failure on MySQL due to the limited charset that only supports up to 3 bytes

Add config option to update charset of mysql to utf8mb4

* fully optional
* requires additional options set in the database

only disable unicode test on mysql

Fixing ctor call

Adding docker based unit test execution for mysql utf8mb4

Add mysqlmb4 test configuration to Jenkinsfile

fix collation on utf8mb4

Properly setup charset and collation in the doctrine connection

Allow files containing 4-byte chars in case the database supports it

During setup of a mysql database we try to detect if charset 'utf8mb4' can be used

Fix mysql settings

Add console command to migrate the charset

Set ROW_FORMAT before setting collation to mb4

Also select tables with wrong collation

Faster MySQL docker

Signed-off-by: Morris Jobke <hey@morrisjobke.de>

1 files changed, 32 insertions, 6 deletions

diff --git a/lib/private/Repair/Collation.php b/lib/private/Repair/Collation.php
index 12e83c2b981..a01700e047e 100644
--- a/lib/private/Repair/Collation.php
+++ b/lib/private/Repair/Collation.php
@@ -88,6 +88,11 @@ class Collation implements IRepairStep {
 			}
 
 			$output->info("Change collation for $table ...");
+			if ($characterSet === 'utf8mb4') {
+				// need to set row compression first
+				$query = $this->connection->prepare('ALTER TABLE `' . $table . '` ROW_FORMAT=COMPRESSED;');
+				$query->execute();
+			}
 			$query = $this->connection->prepare('ALTER TABLE `' . $table . '` CONVERT TO CHARACTER SET ' . $characterSet . ' COLLATE ' . $characterSet . '_bin;');
 			try {
 				$query->execute();
@@ -99,16 +104,21 @@ class Collation implements IRepairStep {
 				}
 			}
 		}
+		if (empty($tables)) {
+			$output->info('All tables already have the correct collation -> nothing to do');
+		}
 	}
 
 	/**
-	 * @param \Doctrine\DBAL\Connection $connection
+	 * @param IDBConnection $connection
 	 * @return string[]
 	 */
-	protected function getAllNonUTF8BinTables($connection) {
+	protected function getAllNonUTF8BinTables(IDBConnection $connection) {
 		$dbName = $this->config->getSystemValue("dbname");
 		$characterSet = $this->config->getSystemValue('mysql.utf8mb4', false) ? 'utf8mb4' : 'utf8';
-		$rows = $connection->fetchAll(
+
+		// fetch tables by columns
+		$statement = $connection->executeQuery(
 			"SELECT DISTINCT(TABLE_NAME) AS `table`" .
 			"	FROM INFORMATION_SCHEMA . COLUMNS" .
 			"	WHERE TABLE_SCHEMA = ?" .
@@ -116,11 +126,27 @@ class Collation implements IRepairStep {
 			"	AND TABLE_NAME LIKE \"*PREFIX*%\"",
 			array($dbName)
 		);
-		$result = array();
+		$rows = $statement->fetchAll();
+		$result = [];
 		foreach ($rows as $row) {
-			$result[] = $row['table'];
+			$result[$row['table']] = true;
 		}
-		return $result;
+
+		// fetch tables by collation
+		$statement = $connection->executeQuery(
+			"SELECT DISTINCT(TABLE_NAME) AS `table`" .
+			"	FROM INFORMATION_SCHEMA . TABLES" .
+			"	WHERE TABLE_SCHEMA = ?" .
+			"	AND TABLE_COLLATION <> '" . $characterSet . "_bin'" .
+			"	AND TABLE_NAME LIKE \"*PREFIX*%\"",
+			[$dbName]
+		);
+		$rows = $statement->fetchAll();
+		foreach ($rows as $row) {
+			$result[$row['table']] = true;
+		}
+
+		return array_keys($result);
 	}
 }