cloud-fan commented on code in PR #44190:
URL: https://github.com/apache/spark/pull/44190#discussion_r1423115936
##########
sql/core/src/test/scala/org/apache/spark/sql/connector/DataSourceV2Suite.scala:
##########
@@ -723,6 +724,158 @@ class DataSourceV2Suite extends QueryTest with
SharedSparkSession with AdaptiveS
}
}
}
+
+ test("SPARK-46272: create table as select") {
+ val cls = classOf[SupportsExternalMetadataDataSource]
+ withTable("test") {
+ sql(
+ s"""
+ |CREATE TABLE test USING ${cls.getName}
+ |AS VALUES (0, 1), (1, 2)
+ |""".stripMargin)
+ checkAnswer(sql("SELECT * FROM test"), Seq(Row(0, 1), Row(1, 2)))
+ sql(
+ s"""
+ |CREATE OR REPLACE TABLE test USING ${cls.getName}
+ |AS VALUES (2, 3), (4, 5)
+ |""".stripMargin)
+ checkAnswer(sql("SELECT * FROM test"), Seq(Row(2, 3), Row(4, 5)))
+ sql(
+ s"""
+ |CREATE TABLE IF NOT EXISTS test USING ${cls.getName}
+ |AS VALUES (3, 4), (4, 5)
+ |""".stripMargin)
+ checkAnswer(sql("SELECT * FROM test"), Seq(Row(2, 3), Row(4, 5)))
+ }
+ }
+
+ test("SPARK-46272: create table as select - error cases") {
+ val cls = classOf[SupportsExternalMetadataDataSource]
+ // CTAS with too many columns
+ withTable("test") {
+ checkError(
+ exception = intercept[AnalysisException] {
+ sql(
+ s"""
+ |CREATE TABLE test USING ${cls.getName}
+ |AS VALUES (0, 1, 2), (1, 2, 3)
+ |""".stripMargin)
+ },
+ errorClass = "INSERT_COLUMN_ARITY_MISMATCH.TOO_MANY_DATA_COLUMNS",
Review Comment:
I think we should enforce something here. When calling
`TableProvider.getTable` with user-specified schema, we should make sure the
returned table reports the same schema as the user-specified schema (probably
ignore nullability). It's actually a documented requirement
```
* Return a {@link Table} instance with the specified table schema,
partitioning and properties
* to do read/write. The returned table should report the same schema and
partitioning with the
* specified ones, or Spark may fail the operation.
```
--
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]
