maropu commented on a change in pull request #24715: [SPARK-25474][SQL] Data
source tables support fallback to HDFS for size estimation
URL: https://github.com/apache/spark/pull/24715#discussion_r314586339
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
##########
@@ -650,4 +650,44 @@ class StatisticsCollectionSuite extends
StatisticsCollectionTestBase with Shared
}
}
}
+
+ test("Data source tables support fallback to HDFS for size estimation") {
+ // Non-partitioned table
+ withTempDir { dir =>
+ Seq(false, true).foreach { fallBackToHDFSForStats =>
+ withSQLConf(SQLConf.ENABLE_FALL_BACK_TO_HDFS_FOR_STATS.key ->
s"$fallBackToHDFSForStats") {
+ withTable("spark_25474") {
+ sql(s"CREATE TABLE spark_25474 (c1 BIGINT) USING PARQUET LOCATION
'${dir.toURI}'")
+
spark.range(5).write.mode(SaveMode.Overwrite).parquet(dir.getCanonicalPath)
+
+ assert(getCatalogTable("spark_25474").stats.isEmpty)
+ val relation =
spark.table("spark_25474").queryExecution.analyzed.children.head
+ assert(relation.stats.sizeInBytes === getDataSize(dir))
+ }
+ }
+ }
+ }
+
+ // Partitioned table
+ Seq(false, true).foreach { fallBackToHDFSForStats =>
+ withSQLConf(SQLConf.ENABLE_FALL_BACK_TO_HDFS_FOR_STATS.key ->
s"$fallBackToHDFSForStats") {
+ withTable("spark_25474") {
+ withTempDir { dir =>
+ spark.sql("CREATE TABLE spark_25474(a int, b int) USING parquet " +
Review comment:
nit: don't need `spark.`
----------------------------------------------------------------
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]
