tedyu commented on a change in pull request #30984:
URL: https://github.com/apache/spark/pull/30984#discussion_r553712163
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
##########
@@ -737,6 +737,10 @@ abstract class PushableColumnBase {
}
case s: GetStructField if nestedPredicatePushdownEnabled =>
helper(s.child).map(_ :+ s.childSchema(s.ordinal).name)
+ case GetJsonObject(col, field) =>
+ val colName = col.toString.split("#")(0)
+ val fieldName = field.toString.split("\\.").last
+ Some(Seq("GetJsonObject(" + col + "," + field + ")"))
Review comment:
Running the above statement in a shell, I got the following:
```
scala> spark.sql("select * from t")
res2: org.apache.spark.sql.DataFrame = [id: int, phone: string]
org.apache.spark.sql.AnalysisException: cannot resolve
'`GetJsonObject(phone,'$.code')`' given input columns:
[spark_catalog.default.t.id, spark_catalog.default.t.phone]; line 1 pos 7;
'Project ['`GetJsonObject(phone,'$.code')`]
+- SubqueryAlias spark_catalog.default.t
+- HiveTableRelation [`default`.`t`,
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, Data Cols: [id#0, phone#1],
Partition Cols: []]
at
org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$$nestedInanonfun$checkAnalysis$1$2.applyOrElse(CheckAnalysis.scala:170)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$$nestedInanonfun$checkAnalysis$1$2.applyOrElse(CheckAnalysis.scala:167)
at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformUp$2(TreeNode.scala:341)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:73)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:341)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$transformExpressionsUp$1(QueryPlan.scala:104)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$1(QueryPlan.scala:116)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:73)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpression$1(QueryPlan.scala:116)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.recursiveTransform$1(QueryPlan.scala:127)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$3(QueryPlan.scala:132)
at
scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
at scala.collection.immutable.List.foreach(List.scala:392)
at scala.collection.TraversableLike.map(TraversableLike.scala:238)
at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
at scala.collection.immutable.List.map(List.scala:298)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.recursiveTransform$1(QueryPlan.scala:132)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.$anonfun$mapExpressions$4(QueryPlan.scala:137)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.mapExpressions(QueryPlan.scala:137)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:104)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis.$anonfun$checkAnalysis$1(CheckAnalysis.scala:167)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis.$anonfun$checkAnalysis$1$adapted(CheckAnalysis.scala:94)
at
org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:183)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis.checkAnalysis(CheckAnalysis.scala:94)
```
I don't think there is ambiguity.
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
