wangyum commented on a change in pull request #25584: [SPARK-28876][SQL]
fallBackToHdfs should not support Hive partitioned table
URL: https://github.com/apache/spark/pull/25584#discussion_r317948185
##########
File path:
sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
##########
@@ -1484,4 +1484,41 @@ class StatisticsSuite extends
StatisticsCollectionTestBase with TestHiveSingleto
}
}
}
+
+ test("fallBackToHdfs should not support Hive partitioned table") {
+ Seq(true, false).foreach { fallBackToHdfs =>
+ withSQLConf(SQLConf.ENABLE_FALL_BACK_TO_HDFS_FOR_STATS.key ->
s"$fallBackToHdfs",
+ HiveUtils.CONVERT_METASTORE_PARQUET.key -> "false") {
+ withTempDir { tableDir =>
+ withTable("spark_28876") {
+ sql(
+ s"""
+ |CREATE TABLE spark_28876(id bigint)
+ |PARTITIONED BY (ds STRING)
+ |STORED AS PARQUET
+ |LOCATION '${tableDir.toURI}'
+ """.stripMargin)
+ withTempDir { partitionDir =>
+
spark.range(5).write.mode(SaveMode.Overwrite).parquet(partitionDir.getCanonicalPath)
+ sql(s"ALTER TABLE spark_28876 ADD PARTITION (ds='p1') LOCATION
'$partitionDir'")
+
+ val table = getCatalogTable("spark_28876")
+ assert(table.stats.isEmpty)
+ val partitions =
spark.sessionState.catalog.listPartitions(table.identifier)
+ assert(partitions.size === 1)
+ partitions.foreach { p =>
+ // Partition directory is outside of the table directory
Review comment:
Done
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
