HyukjinKwon commented on code in PR #42462:
URL: https://github.com/apache/spark/pull/42462#discussion_r1300848391
##########
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 = {
Review Comment:
ditto for https://github.com/apache/spark/pull/42462/files#r1300848164
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/DataFrameWriter.scala:
##########
@@ -470,6 +470,34 @@ final class DataFrameWriter[T] private[sql] (ds:
Dataset[T]) {
format("csv").save(path)
}
+ /**
+ * Saves the content of the `DataFrame` in XML format at the specified path.
This is equivalent
+ * to:
+ * {{{
+ * format("xml").save(path)
+ * }}}
+ *
+ * Note that writing a XML file from `DataFrame` having a field `ArrayType`
with its element as
+ * `ArrayType` would have an additional nested field for the element. For
example, the
+ * `DataFrame` having a field below,
+ *
+ * {@code fieldA [[data1], [data2]]}
+ *
+ * would produce a XML file below. { @code <fieldA> <item>data1</item>
</fieldA> <fieldA>
+ * <item>data2</item> </fieldA>}
+ *
+ * Namely, roundtrip in writing and reading can end up in different schema
structure.
+ *
+ * You can find the XML-specific options for writing XML files in <a
+ *
href="https://spark.apache.org/docs/latest/sql-data-sources-xml.html#data-source-option";>
+ * Data Source Option</a> in the version you use.
+ *
+ * @since 4.0.0
+ */
+ def xml(path: String): Unit = {
Review Comment:
ditto for https://github.com/apache/spark/pull/42462/files#r1300848164
--
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]
