dongjoon-hyun commented on a change in pull request #29587:
URL: https://github.com/apache/spark/pull/29587#discussion_r487643038
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveUnion.scala
##########
@@ -17,29 +17,107 @@
package org.apache.spark.sql.catalyst.analysis
+import scala.collection.mutable
+
import org.apache.spark.sql.AnalysisException
-import org.apache.spark.sql.catalyst.expressions.{Alias, Literal}
+import org.apache.spark.sql.catalyst.expressions.{Alias, Attribute,
Expression, Literal, NamedExpression, WithFields}
import org.apache.spark.sql.catalyst.optimizer.CombineUnions
import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, Project,
Union}
import org.apache.spark.sql.catalyst.rules.Rule
import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types._
import org.apache.spark.sql.util.SchemaUtils
/**
* Resolves different children of Union to a common set of columns.
*/
object ResolveUnion extends Rule[LogicalPlan] {
- private def unionTwoSides(
+ /**
+ * Adds missing fields recursively into given `col` expression, based on the
target `StructType`.
+ * For example, given `col` as "a struct<a:int, b:int>, b int" and `target`
as
+ * "a struct<a:int, b:int, c:long>, b int, c string", this method should add
`a.c` and `c` to
+ * `col` expression.
+ */
+ private def addFields(col: NamedExpression, target: StructType):
Option[Expression] = {
+ assert(col.dataType.isInstanceOf[StructType], "Only support StructType.")
+
+ val resolver = SQLConf.get.resolver
+ val missingFields =
+ StructType.findMissingFields(col.dataType.asInstanceOf[StructType],
target, resolver)
+ if (missingFields.isEmpty) {
+ None
+ } else {
+ missingFields.map(s => addFieldsInto(col, "", s.fields))
+ }
+ }
+
+ /**
+ * Adds missing fields recursively into given `col` expression. The missing
fields are given
+ * in `fields`. For example, given `col` as "a struct<a:int, b:int>, b int",
and `fields` is
+ * "a struct<c:long>, c string". This method will add a nested `a.c` field
and a top-level
Review comment:
Do we have a test case for `sortOutputColumns`? And, shall we have `z
struct<z: int, y:int>, x int` and `z struct<w: long>, w string` if it gives
more clear sense on what is happening 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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
