sandip-db commented on code in PR #42462:
URL: https://github.com/apache/spark/pull/42462#discussion_r1300463633
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/DataFrameReader.scala:
##########
@@ -392,6 +392,46 @@ class DataFrameReader private[sql] (sparkSession:
SparkSession) extends Logging
def csv(csvDataset: Dataset[String]): DataFrame =
parse(csvDataset, ParseFormat.PARSE_FORMAT_CSV)
+ /**
+ * Loads a XML file and returns the result as a `DataFrame`. See the
documentation on the other
+ * overloaded `xml()` method for more details.
+ *
+ * @since 4.0.0
+ */
+ def xml(path: String): DataFrame = {
+ // This method ensures that calls that explicit need single argument
works, see SPARK-16009
+ xml(Seq(path): _*)
+ }
+
+ /**
+ * Loads XML files and returns the result as a `DataFrame`.
+ *
+ * This function will go through the input once to determine the input
schema if `inferSchema`
+ * is enabled. To avoid going through the entire data once, disable
`inferSchema` option or
+ * specify the schema explicitly using `schema`.
+ *
+ * You can find the XML-specific options for reading XML files in <a
+ *
href="https://spark.apache.org/docs/latest/sql-data-sources-xml.html#data-source-option";>
Review Comment:
yes. https://issues.apache.org/jira/browse/SPARK-44752
--
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]
