cloud-fan commented on a change in pull request #32863: URL: https://github.com/apache/spark/pull/32863#discussion_r649707269
########## File path: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala ########## @@ -1161,6 +1161,28 @@ class Dataset[T] private[sql]( throw new AnalysisException("Invalid join type in joinWith: " + joined.joinType.sql) } + // If auto self join alias is enable + if (sqlContext.conf.dataFrameSelfJoinAutoResolveAmbiguity) { Review comment: is this code repeated somewhere? and can we move it to a function to share code? ########## File path: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala ########## @@ -1088,26 +1112,9 @@ class Dataset[T] private[sql]( // Otherwise, find the trivially true predicates and automatically resolves them to both sides. // By the time we get here, since we have already run analysis, all attributes should've been // resolved and become AttributeReference. - val resolver = sparkSession.sessionState.analyzer.resolver Review comment: we don't look at the `dataFrameSelfJoinAutoResolveAmbiguity` config here. Why do we check the config in `joinWith`? ########## File path: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala ########## @@ -1034,6 +1034,31 @@ class Dataset[T] private[sql]( */ def join(right: Dataset[_], joinExprs: Column): DataFrame = join(right, joinExprs, "inner") + /** + * find the trivially true predicates and automatically resolves them to both sides. + */ + Review comment: nit: remove the blank line here -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org