xiaonanyang-db commented on code in PR #50300:
URL: https://github.com/apache/spark/pull/50300#discussion_r2034175548
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xml/XmlExpressionEvalUtils.scala:
##########
@@ -119,3 +122,49 @@ case class XPathListEvaluator(path: UTF8String) extends
XPathEvaluator {
}
}
}
+
+case class XmlToStructsEvaluator(
+ options: Map[String, String],
+ nullableSchema: DataType,
+ nameOfCorruptRecord: String,
+ timeZoneId: Option[String],
+ child: Expression
+) {
+ @transient lazy val parsedOptions = new XmlOptions(options, timeZoneId.get,
nameOfCorruptRecord)
+
+ // This converts parsed rows to the desired output by the given schema.
+ @transient
+ private lazy val converter =
+ (rows: Iterator[InternalRow]) => if (rows.hasNext) rows.next() else null
+
+ // Parser that parse XML strings as internal rows
+ @transient
+ private lazy val parser = {
+ val parsedOptions = new XmlOptions(options, timeZoneId.get,
nameOfCorruptRecord)
Review Comment:
oh yeah, we should definitely do that
--
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: reviews-unsubscr...@spark.apache.org
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
