Github user mbasmanova commented on a diff in the pull request: https://github.com/apache/spark/pull/18309#discussion_r122651779 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala --- @@ -128,6 +129,45 @@ 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) { + withTempPaths(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)) --- End diff -- This is how I wrote the test initially. In this case all partitions are located under the same top-level directory, but table-level location is somewhere else. I modified the test to use different paths for each partition as well as the table to address some of the earlier comments.
--- 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