Repository: spark Updated Branches: refs/heads/branch-2.4 144cb949d -> 3591bd229
[SQL][CATALYST][MINOR] update some error comments ## What changes were proposed in this pull request? this PR correct some comment error: 1. change from "as low a possible" to "as low as possible" in RewriteDistinctAggregates.scala 2. delete redundant word âwithâ in HiveTableScanExecâs doExecute() method ## How was this patch tested? Existing unit tests. Closes #22694 from CarolinePeng/update_comment. Authored-by: å½ç¿00244106 <00244106@zte.intra> Signed-off-by: hyukjinkwon <gurwls...@apache.org> (cherry picked from commit e9332f600eb4f275b3bff368863a68c2a4349182) Signed-off-by: hyukjinkwon <gurwls...@apache.org> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/3591bd22 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/3591bd22 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/3591bd22 Branch: refs/heads/branch-2.4 Commit: 3591bd2293f49ac8023166597704ad1bd21dabe9 Parents: 144cb94 Author: å½ç¿00244106 <00244106@zte.intra> Authored: Wed Oct 17 12:45:13 2018 +0800 Committer: hyukjinkwon <gurwls...@apache.org> Committed: Wed Oct 17 12:45:30 2018 +0800 ---------------------------------------------------------------------- .../spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala | 4 ++-- .../org/apache/spark/sql/hive/execution/HiveTableScanExec.scala | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/3591bd22/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala ---------------------------------------------------------------------- diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala index 4448ace..b946800 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDistinctAggregates.scala @@ -95,7 +95,7 @@ import org.apache.spark.sql.types.IntegerType * * This rule duplicates the input data by two or more times (# distinct groups + an optional * non-distinct group). This will put quite a bit of memory pressure of the used aggregate and - * exchange operators. Keeping the number of distinct groups as low a possible should be priority, + * exchange operators. Keeping the number of distinct groups as low as possible should be priority, * we could improve this in the current rule by applying more advanced expression canonicalization * techniques. */ @@ -241,7 +241,7 @@ object RewriteDistinctAggregates extends Rule[LogicalPlan] { groupByAttrs ++ distinctAggChildAttrs ++ Seq(gid) ++ regularAggChildAttrMap.map(_._2), a.child) - // Construct the first aggregate operator. This de-duplicates the all the children of + // Construct the first aggregate operator. This de-duplicates all the children of // distinct operators, and applies the regular aggregate operators. val firstAggregateGroupBy = groupByAttrs ++ distinctAggChildAttrs :+ gid val firstAggregate = Aggregate( http://git-wip-us.apache.org/repos/asf/spark/blob/3591bd22/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala index b3795b4..92c6632 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala @@ -182,7 +182,7 @@ case class HiveTableScanExec( protected override def doExecute(): RDD[InternalRow] = { // Using dummyCallSite, as getCallSite can turn out to be expensive with - // with multiple partitions. + // multiple partitions. val rdd = if (!relation.isPartitioned) { Utils.withDummyCallSite(sqlContext.sparkContext) { hadoopReader.makeRDDForTable(hiveQlTable) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org