panbingkun commented on code in PR #48594:
URL: https://github.com/apache/spark/pull/48594#discussion_r1860701665
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xmlExpressions.scala:
##########
@@ -192,26 +196,20 @@ case class SchemaOfXml(
}
}
- override def eval(v: InternalRow): Any = {
- val dataType = xmlInferSchema.infer(xml.toString).get match {
- case st: StructType =>
- xmlInferSchema.canonicalizeType(st).getOrElse(StructType(Nil))
- case at: ArrayType if at.elementType.isInstanceOf[StructType] =>
- xmlInferSchema
- .canonicalizeType(at.elementType)
- .map(ArrayType(_, containsNull = at.containsNull))
- .getOrElse(ArrayType(StructType(Nil), containsNull =
at.containsNull))
- case other: DataType =>
-
xmlInferSchema.canonicalizeType(other).getOrElse(SQLConf.get.defaultStringType)
- }
-
- UTF8String.fromString(dataType.sql)
- }
-
override def prettyName: String = "schema_of_xml"
override protected def withNewChildInternal(newChild: Expression):
SchemaOfXml =
copy(child = newChild)
+
+ @transient private lazy val xmlInferSchemaObjectType =
ObjectType(classOf[XmlInferSchema])
+
+ override def replacement: Expression = StaticInvoke(
+ XmlExpressionEvalUtils.getClass,
+ dataType,
+ "schemaOfXml",
+ Seq(Literal(xmlInferSchema, xmlInferSchemaObjectType), child),
+ Seq(xmlInferSchemaObjectType, child.dataType)
Review Comment:
Okay, I have fixed this issue with followup
https://github.com/apache/spark/pull/48987. I think `scheme_of_xml`,
`schema_of_csv` and `schema_of_json` has similar issues, so I will fix them all
at once.
Thanks!
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
