Github user mbasmanova commented on a diff in the pull request: https://github.com/apache/spark/pull/18309#discussion_r122224357 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala --- @@ -128,6 +128,40 @@ 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 + + sql( + """ + |CREATE TABLE analyzeTable_part (key STRING, value STRING) PARTITIONED BY (ds STRING) + """.stripMargin).collect() + sql( + """ + |INSERT INTO TABLE analyzeTable_part PARTITION (ds='2010-01-01') + |SELECT * FROM src + """.stripMargin).collect() + sql( + """ + |INSERT INTO TABLE analyzeTable_part PARTITION (ds='2010-01-02') + |SELECT * FROM src + """.stripMargin).collect() + sql( --- End diff -- This is a fine suggestion, but I feel it falls outside of the scope of this change. This particular fix concerns only the case when table-level location is not a parent directory of a partition-level location.
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org