This is an automated email from the ASF dual-hosted git repository.
yangjie01 pushed a commit to branch branch-4.1
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.1 by this push:
new a88b15c98dd5 [SPARK-54111][CONNECT] Support getCatalogs for
SparkConnectDatabaseMetaData
a88b15c98dd5 is described below
commit a88b15c98dd56ca3b44ed5edb7188448a0db319c
Author: Cheng Pan <[email protected]>
AuthorDate: Mon Nov 3 14:34:56 2025 +0800
[SPARK-54111][CONNECT] Support getCatalogs for SparkConnectDatabaseMetaData
### What changes were proposed in this pull request?
Implement `getCatalogs` defined in `java.sql.DatabaseMetaData` for
`SparkConnectDatabaseMetaData`.
```java
/**
* Retrieves the catalog names available in this database. The results
* are ordered by catalog name.
*
* <P>The catalog column is:
* <OL>
* <LI><B>TABLE_CAT</B> String {code =>} catalog name
* </OL>
*
* return a {code ResultSet} object in which each row has a
* single {code String} column that is a catalog name
* throws SQLException if a database access error occurs
*/
ResultSet getCatalogs() throws SQLException;
```
### Why are the changes needed?
Enhance API coverage of the Connect JDBC driver, for example,
`get[Catalogs|Schemas|Tables|...]` APIs are used by SQL GUI tools such as
DBeaver for displaying the tree category.
### Does this PR introduce _any_ user-facing change?
No, the Connect JDBC driver is a new feature under development.
### How was this patch tested?
New UT is added.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #52815 from pan3793/SPARK-54111.
Authored-by: Cheng Pan <[email protected]>
Signed-off-by: yangjie01 <[email protected]>
(cherry picked from commit 2be1eb72e1ca27a9b882dec7dfea726c437821fa)
Signed-off-by: yangjie01 <[email protected]>
---
.../client/jdbc/SparkConnectDatabaseMetaData.scala | 12 +++++--
.../jdbc/SparkConnectDatabaseMetaDataSuite.scala | 40 ++++++++++++++++++++--
2 files changed, 48 insertions(+), 4 deletions(-)
diff --git
a/sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala
b/sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala
index a16cba5e3da4..215c8256acbc 100644
---
a/sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala
+++
b/sql/connect/client/jdbc/src/main/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaData.scala
@@ -25,6 +25,8 @@ import org.apache.spark.util.VersionUtils
class SparkConnectDatabaseMetaData(conn: SparkConnectConnection) extends
DatabaseMetaData {
+ import conn.spark.implicits._
+
override def allProceduresAreCallable: Boolean = false
override def allTablesAreSelectable: Boolean = false
@@ -288,8 +290,14 @@ class SparkConnectDatabaseMetaData(conn:
SparkConnectConnection) extends Databas
columnNamePattern: String): ResultSet =
throw new SQLFeatureNotSupportedException
- override def getCatalogs: ResultSet =
- throw new SQLFeatureNotSupportedException
+ override def getCatalogs: ResultSet = {
+ conn.checkOpen()
+
+ val df = conn.spark.sql("SHOW CATALOGS")
+ .select($"catalog".as("TABLE_CAT"))
+ .orderBy("TABLE_CAT")
+ new SparkConnectResultSet(df.collectResult())
+ }
override def getSchemas: ResultSet =
throw new SQLFeatureNotSupportedException
diff --git
a/sql/connect/client/jdbc/src/test/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaDataSuite.scala
b/sql/connect/client/jdbc/src/test/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaDataSuite.scala
index b2ecc163b2b8..42596b56f4c5 100644
---
a/sql/connect/client/jdbc/src/test/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaDataSuite.scala
+++
b/sql/connect/client/jdbc/src/test/scala/org/apache/spark/sql/connect/client/jdbc/SparkConnectDatabaseMetaDataSuite.scala
@@ -19,16 +19,27 @@ package org.apache.spark.sql.connect.client.jdbc
import java.sql.{Array => _, _}
+import scala.util.Using
+
import org.apache.spark.SparkBuildInfo.{spark_version => SPARK_VERSION}
+import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.connect.client.jdbc.test.JdbcHelper
-import org.apache.spark.sql.connect.test.{ConnectFunSuite, RemoteSparkSession}
+import org.apache.spark.sql.connect.test.{ConnectFunSuite, RemoteSparkSession,
SQLHelper}
import org.apache.spark.util.VersionUtils
class SparkConnectDatabaseMetaDataSuite extends ConnectFunSuite with
RemoteSparkSession
- with JdbcHelper {
+ with JdbcHelper with SQLHelper {
def jdbcUrl: String = s"jdbc:sc://localhost:$serverPort"
+ // catalyst test jar is inaccessible here, but presents at the testing
connect server classpath
+ private val TEST_IN_MEMORY_CATALOG =
"org.apache.spark.sql.connector.catalog.InMemoryCatalog"
+
+ private def registerCatalog(
+ name: String, className: String)(implicit spark: SparkSession): Unit = {
+ spark.conf.set(s"spark.sql.catalog.$name", className)
+ }
+
test("SparkConnectDatabaseMetaData simple methods") {
withConnection { conn =>
val spark = conn.asInstanceOf[SparkConnectConnection].spark
@@ -199,4 +210,29 @@ class SparkConnectDatabaseMetaDataSuite extends
ConnectFunSuite with RemoteSpark
// scalastyle:on line.size.limit
}
}
+
+ test("SparkConnectDatabaseMetaData getCatalogs") {
+ withConnection { conn =>
+ implicit val spark: SparkSession =
conn.asInstanceOf[SparkConnectConnection].spark
+
+ registerCatalog("testcat", TEST_IN_MEMORY_CATALOG)
+ registerCatalog("testcat2", TEST_IN_MEMORY_CATALOG)
+
+ // forcibly initialize the registered catalogs because SHOW CATALOGS only
+ // returns the initialized catalogs.
+ spark.sql("USE testcat")
+ spark.sql("USE testcat2")
+ spark.sql("USE spark_catalog")
+
+ val metadata = conn.getMetaData
+ Using.resource(metadata.getCatalogs) { rs =>
+ val catalogs = new Iterator[String] {
+ def hasNext: Boolean = rs.next()
+ def next(): String = rs.getString("TABLE_CAT")
+ }.toSeq
+ // results are ordered by TABLE_CAT
+ assert(catalogs === Seq("spark_catalog", "testcat", "testcat2"))
+ }
+ }
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
