LuciferYang commented on code in PR #52810:
URL: https://github.com/apache/spark/pull/52810#discussion_r2485417898
##########
sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectStatement.scala:
##########
@@ -49,33 +51,51 @@ class SparkConnectStatement(conn: SparkConnectConnection)
extends Statement {
}
override def executeQuery(sql: String): ResultSet = {
- checkOpen()
-
- val df = conn.spark.sql(sql)
- val sparkResult = df.collectResult()
- operationId = sparkResult.operationId
- resultSet = new SparkConnectResultSet(sparkResult, this)
- resultSet
+ val hasResultSet = execute(sql)
+ if (hasResultSet) {
+ assert(resultSet != null)
+ resultSet
+ } else {
+ throw new SQLException("The query does not produce a ResultSet.")
+ }
}
override def executeUpdate(sql: String): Int = {
- checkOpen()
-
- val df = conn.spark.sql(sql)
- val sparkResult = df.collectResult()
- operationId = sparkResult.operationId
- resultSet = null
+ val hasResultSet = execute(sql)
+ if (hasResultSet) {
+ // user are not expected to access the result set in this case,
+ // we must close it to avoid memory leak.
+ resultSet.close()
+ throw new SQLException("The query produces a ResultSet.")
Review Comment:
show we reset `resultSet` to `null` after `close`
##########
sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectStatement.scala:
##########
@@ -49,33 +51,51 @@ class SparkConnectStatement(conn: SparkConnectConnection)
extends Statement {
}
override def executeQuery(sql: String): ResultSet = {
- checkOpen()
-
- val df = conn.spark.sql(sql)
- val sparkResult = df.collectResult()
- operationId = sparkResult.operationId
- resultSet = new SparkConnectResultSet(sparkResult, this)
- resultSet
+ val hasResultSet = execute(sql)
+ if (hasResultSet) {
+ assert(resultSet != null)
+ resultSet
+ } else {
+ throw new SQLException("The query does not produce a ResultSet.")
+ }
}
override def executeUpdate(sql: String): Int = {
- checkOpen()
-
- val df = conn.spark.sql(sql)
- val sparkResult = df.collectResult()
- operationId = sparkResult.operationId
- resultSet = null
+ val hasResultSet = execute(sql)
+ if (hasResultSet) {
+ // user are not expected to access the result set in this case,
+ // we must close it to avoid memory leak.
+ resultSet.close()
+ throw new SQLException("The query produces a ResultSet.")
+ } else {
+ assert(resultSet == null)
+ getUpdateCount
+ }
+ }
- // always return 0 because affected rows is not supported yet
- 0
+ private def hasResultSet(sparkResult: SparkResult[_]): Boolean = {
+ // suppose this works in most cases
+ sparkResult.schema.length > 0
}
override def execute(sql: String): Boolean = {
checkOpen()
- // always perform executeQuery and reture a ResultSet
- executeQuery(sql)
- true
+ // stmt can be reused to exeute more than one queries,
Review Comment:
typo: `exeute` -> `execute`
##########
sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectStatement.scala:
##########
@@ -49,33 +51,51 @@ class SparkConnectStatement(conn: SparkConnectConnection)
extends Statement {
}
override def executeQuery(sql: String): ResultSet = {
- checkOpen()
-
- val df = conn.spark.sql(sql)
- val sparkResult = df.collectResult()
- operationId = sparkResult.operationId
- resultSet = new SparkConnectResultSet(sparkResult, this)
- resultSet
+ val hasResultSet = execute(sql)
+ if (hasResultSet) {
+ assert(resultSet != null)
+ resultSet
+ } else {
+ throw new SQLException("The query does not produce a ResultSet.")
+ }
}
override def executeUpdate(sql: String): Int = {
- checkOpen()
-
- val df = conn.spark.sql(sql)
- val sparkResult = df.collectResult()
- operationId = sparkResult.operationId
- resultSet = null
+ val hasResultSet = execute(sql)
+ if (hasResultSet) {
+ // user are not expected to access the result set in this case,
+ // we must close it to avoid memory leak.
+ resultSet.close()
+ throw new SQLException("The query produces a ResultSet.")
+ } else {
+ assert(resultSet == null)
+ getUpdateCount
+ }
+ }
- // always return 0 because affected rows is not supported yet
- 0
+ private def hasResultSet(sparkResult: SparkResult[_]): Boolean = {
+ // suppose this works in most cases
+ sparkResult.schema.length > 0
}
override def execute(sql: String): Boolean = {
checkOpen()
- // always perform executeQuery and reture a ResultSet
- executeQuery(sql)
- true
+ // stmt can be reused to exeute more than one queries,
+ // reset before executinng new query
Review Comment:
typo: `executinng` -> `executing`
##########
sql/connect/client/jdbc/src/test/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectStatementSuite.scala:
##########
@@ -0,0 +1,77 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.connect.client.jdbc
+
+import java.sql.{Array => _, _}
+
+import scala.util.Using
+
+import org.apache.spark.sql.connect.client.jdbc.test.JdbcHelper
+import org.apache.spark.sql.connect.test.{ConnectFunSuite, RemoteSparkSession,
SQLHelper}
+
+class SparkConnectStatementSuite extends ConnectFunSuite with
RemoteSparkSession
+ with JdbcHelper with SQLHelper {
+
+ override def jdbcUrl: String = s"jdbc:sc://localhost:$serverPort"
+
+ test("returned result set and update count of execute* methods") {
+ withTable("t1", "t2", "t3") {
+ withStatement { stmt =>
+ // CREATE TABLE
+ assert(!stmt.execute("CREATE TABLE t1 (id INT) USING Parquet"))
+ assert(stmt.getUpdateCount === 0)
+ assert(stmt.getResultSet === null)
+
+ intercept[SQLException] {
+ stmt.executeQuery("CREATE TABLE t2 (id INT) USING Parquet")
+ }
+
+ assert(stmt.executeUpdate("CREATE TABLE t3 (id INT) USING Parquet")
=== 0)
+ assert(stmt.getResultSet === null)
+
+ // INSERT INTO
+ assert(!stmt.execute("INSERT INTO t1 VALUES (1)"))
+ assert(stmt.getUpdateCount === 0)
+ assert(stmt.getResultSet === null)
+
+ intercept[SQLException] {
+ stmt.executeQuery("INSERT INTO t1 VALUES (1)")
+ }
+
+ assert(stmt.executeUpdate("INSERT INTO t1 VALUES (1)") === 0)
+ assert(stmt.getResultSet === null)
+
+ // SELECT
+ assert(stmt.execute("SELECT id FROM t1"))
+ assert(stmt.getUpdateCount === -1)
+ Using.resource(stmt.getResultSet) { rs =>
+ assert(rs !== null)
+ }
+
+ Using.resource(stmt.executeQuery("SELECT id FROM t1")) { rs =>
+ assert(stmt.getUpdateCount === -1)
+ assert(rs !== null)
+ }
+
+ intercept[SQLException] {
Review Comment:
Let's add an assertion for the error message.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
