Github user wzhfy commented on a diff in the pull request: https://github.com/apache/spark/pull/18205#discussion_r121263828 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/PruneFileSourcePartitionsSuite.scala --- @@ -66,4 +67,35 @@ class PruneFileSourcePartitionsSuite extends QueryTest with SQLTestUtils with Te } } } + + test("SPARK-20986 Reset table's statistics after PruneFileSourcePartitions rule") { + withTempView("tempTbl") { + withTable("partTbl") { + spark.range(1000).selectExpr("id").createOrReplaceTempView("tempTbl") + sql("CREATE TABLE partTbl (id INT) PARTITIONED BY (part INT) STORED AS parquet") + for (part <- Seq(1, 2, 3)) { + sql( + s""" + |INSERT OVERWRITE TABLE partTbl PARTITION (part='$part') + |select id from tempTbl + """.stripMargin) + } + + withSQLConf(SQLConf.ENABLE_FALL_BACK_TO_HDFS_FOR_STATS.key -> "true") { + val df = sql("SELECT * FROM partTbl where part = 1") + val query = df.queryExecution.analyzed.analyze + val sizes1 = query.collect { + case relation: LogicalRelation => relation.computeStats(conf).sizeInBytes + } + assert(sizes1.size === 1, s"Size wrong for:\n ${df.queryExecution}") + assert(sizes1(0) > 5000, s"expected > 5000 for test table 'src', got: ${sizes1(0)}") + val sizes2 = Optimize.execute(query).collect { + case relation: LogicalRelation => relation.computeStats(conf).sizeInBytes + } + assert(sizes2.size === 1, s"Size wrong for:\n ${df.queryExecution}") --- End diff -- assert the new size in catalog stats is larger than the previous one, and equal to `computeStats(conf).sizeInBytes`?
--- 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