Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/18309#discussion_r123163221
--- Diff:
sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala ---
@@ -128,6 +129,93 @@ class StatisticsSuite extends
StatisticsCollectionTestBase with TestHiveSingleto
TableIdentifier("tempTable"), ignoreIfNotExists = true, purge =
false)
}
+ test("SPARK-21079 - analyze table with location different than that of
individual partitions") {
+ def queryTotalSize(tableName: String): BigInt =
+
spark.table(tableName).queryExecution.analyzed.stats(conf).sizeInBytes
+
+ val tableName = "analyzeTable_part"
+ withTable(tableName) {
+ // Create 4 paths: one to use as table location and one for each of
the 3 partitions
+ withTempPaths(numPaths = 4) {
+ case tablePath :: partitionPaths =>
+ sql(
+ s"""
+ |CREATE TABLE ${tableName} (key STRING, value STRING)
PARTITIONED BY (ds STRING)
+ |LOCATION '${tablePath}'
+ """.stripMargin).collect()
+
+ val partitionDates = List("2010-01-01", "2010-01-02",
"2010-01-03")
+ partitionDates.zip(partitionPaths).foreach {
+ case (ds, path) =>
+ sql(
+ s"""
+ |ALTER TABLE ${tableName} ADD PARTITION (ds='${ds}')
+ |LOCATION '${path.toString}'
+ """.stripMargin).collect()
+ sql(
+ s"""
+ |INSERT INTO TABLE ${tableName} PARTITION (ds='${ds}')
+ |SELECT * FROM src
+ """.stripMargin).collect()
+ }
+
+ sql(s"ANALYZE TABLE ${tableName} COMPUTE STATISTICS noscan")
+
+ assert(queryTotalSize(tableName) === BigInt(17436))
+ }
+ }
+ }
+
+ test("SPARK-21079 - analyze partitioned table with only a subset of
partitions visible") {
+ def queryTotalSize(tableName: String): BigInt =
+
spark.table(tableName).queryExecution.analyzed.stats(conf).sizeInBytes
+
+ val sourceTableName = "analyzeTable_part"
+ val tableName = "analyzeTable_part_vis"
+ withTable(sourceTableName, tableName) {
+ withTempPath {
+ path =>
+ // Create a table with 3 partitions all located under a single
top-level directory 'path'
+ sql(
+ s"""
+ |CREATE TABLE ${sourceTableName} (key STRING, value STRING)
+ |PARTITIONED BY (ds STRING)
+ |LOCATION '${path}'
+ """.stripMargin).collect()
+
+ val partitionDates = List("2010-01-01", "2010-01-02",
"2010-01-03")
+ partitionDates.foreach {
+ ds =>
+ sql(
+ s"""
+ |INSERT INTO TABLE ${sourceTableName} PARTITION
(ds='${ds}')
+ |SELECT * FROM src
+ """.stripMargin).collect()
--- End diff --
No need to call `collect()`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
