viirya commented on a change in pull request #30705:
URL: https://github.com/apache/spark/pull/30705#discussion_r540702506
##########
File path:
sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
##########
@@ -2872,4 +2845,103 @@ class HiveDDLSuite
assert(sql("SELECT * FROM t2 WHERE c = 'A'").collect().isEmpty)
}
}
+
+ test("SPARK-33546: CREATE TABLE LIKE should validate row format & file
format") {
+ val catalog = spark.sessionState.catalog
+ withTable("sourceHiveTable", "sourceDsTable") {
+ sql("CREATE TABLE sourceHiveTable(a INT, b INT) STORED AS PARQUET")
+ sql("CREATE TABLE sourceDsTable(a INT, b INT) USING PARQUET")
+
+ // ROW FORMAT SERDE ... STORED AS [SEQUENCEFILE | RCFILE | TEXTFILE]
+ val allowSerdeFileFormats = Seq("TEXTFILE", "SEQUENCEFILE", "RCFILE")
+ Seq("sourceHiveTable", "sourceDsTable").foreach { sourceTable =>
+ allowSerdeFileFormats.foreach { format =>
+ withTable("targetTable") {
+ spark.sql(
+ s"""
+ |CREATE TABLE targetTable LIKE $sourceTable
+ |ROW FORMAT SERDE
'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
+ |STORED AS $format
+ """.stripMargin)
+
+ val expectedSerde = HiveSerDe.sourceToSerDe(format)
+ val table =
catalog.getTableMetadata(TableIdentifier("targetTable", Some("default")))
+ assert(table.provider === Some("hive"))
+ assert(table.storage.inputFormat ===
Some(expectedSerde.get.inputFormat.get))
+ assert(table.storage.outputFormat ===
Some(expectedSerde.get.outputFormat.get))
+ assert(table.storage.serde ===
+ Some("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"))
+ }
+ }
+
+ // negative case
+ hiveFormats.filterNot(allowSerdeFileFormats.contains(_)).foreach {
format =>
+ withTable("targetTable") {
+ val ex = intercept[AnalysisException] {
+ spark.sql(
+ s"""
+ |CREATE TABLE targetTable LIKE $sourceTable
+ |ROW FORMAT SERDE
'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
+ |STORED AS $format
+ """.stripMargin)
+ }.getMessage
+ assert(ex.contains(
+ s"ROW FORMAT SERDE is incompatible with format
'${format.toLowerCase(Locale.ROOT)}'"))
+ }
+ }
+ }
+
+ // ROW FORMAT DELIMITED ... STORED AS TEXTFILE
+ Seq("sourceHiveTable", "sourceDsTable").foreach { sourceTable =>
+ withTable("targetTable", "failedTable") {
Review comment:
`failedTable` is not used.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
