Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/14971#discussion_r117366221 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala --- @@ -414,6 +415,50 @@ private[hive] class HiveClientImpl( val properties = Option(h.getParameters).map(_.asScala.toMap).orNull + // Hive-generated Statistics are also recorded in ignoredProperties + val ignoredProperties = scala.collection.mutable.Map.empty[String, String] + for (key <- HiveStatisticsProperties; value <- properties.get(key)) { + ignoredProperties += key -> value + } + + val excludedTableProperties = HiveStatisticsProperties ++ Set( + // The property value of "comment" is moved to the dedicated field "comment" + "comment", + // For EXTERNAL_TABLE, the table properties has a particular field "EXTERNAL". This is added + // in the function toHiveTable. + "EXTERNAL" + ) + + val filteredProperties = properties.filterNot { + case (key, _) => excludedTableProperties.contains(key) + } + val comment = properties.get("comment") + + val totalSize = properties.get(StatsSetupConst.TOTAL_SIZE).map(BigInt(_)) + val rawDataSize = properties.get(StatsSetupConst.RAW_DATA_SIZE).map(BigInt(_)) + def rowCount = properties.get(StatsSetupConst.ROW_COUNT).map(BigInt(_)) match { --- End diff -- only used once. We also can use lazy val
--- 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