HyukjinKwon commented on code in PR #43319:
URL: https://github.com/apache/spark/pull/43319#discussion_r1353981938
##########
sql/core/src/test/resources/test-data/xml-resources/root-level-value.xml:
##########
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<ROWSET>
+ <ROW>value1</ROW>
+ <ROW attr="attr1">value2</ROW>
+ <ROW>
+ value3
+ <!-- this is a comment-->
+ </ROW>
+</ROWSET>
Review Comment:
If possible, I would prefer put this XML into a string variable within
`XmlSuite.scala` to make the test easier to read, and self-contained.
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -1645,4 +1645,43 @@ class XmlSuite extends QueryTest with SharedSparkSession
{
.xml(getTestResourcePath(resDir + "fias_house.xml"))
assert(df.collect().length === 37)
}
+
+ test("root-level value tag for attributes-only object") {
+
+ val schema = buildSchema(field("_attr"), field("_VALUE"))
+ val results = Seq(
+ // user specified schema
+ spark.read
+ .schema(schema)
+ .xml(getTestResourcePath(resDir + "root-level-value.xml")).collect(),
+ // schema inference
+ spark.read
+ .xml(getTestResourcePath(resDir + "root-level-value.xml")).collect())
+ results.foreach { result =>
+ assert(result.length === 3)
+ assert(result(0).getAs[String]("_VALUE") == "value1")
+ assert(result(1).getAs[String]("_attr") == "attr1"
+ && result(1).getAs[String]("_VALUE") == "value2")
+ // comments aren't included in valueTag
+ assert(result(2).getAs[String]("_VALUE") == "\n value3\n ")
+ }
+ }
+
+ test("root-level value tag for attributes-only object - from xml") {
+ val xmlData =
+ s"""
Review Comment:
```suggestion
"""
```
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -1645,4 +1645,43 @@ class XmlSuite extends QueryTest with SharedSparkSession
{
.xml(getTestResourcePath(resDir + "fias_house.xml"))
assert(df.collect().length === 37)
}
+
+ test("root-level value tag for attributes-only object") {
+
+ val schema = buildSchema(field("_attr"), field("_VALUE"))
+ val results = Seq(
+ // user specified schema
+ spark.read
+ .schema(schema)
+ .xml(getTestResourcePath(resDir + "root-level-value.xml")).collect(),
+ // schema inference
+ spark.read
+ .xml(getTestResourcePath(resDir + "root-level-value.xml")).collect())
+ results.foreach { result =>
+ assert(result.length === 3)
+ assert(result(0).getAs[String]("_VALUE") == "value1")
+ assert(result(1).getAs[String]("_attr") == "attr1"
+ && result(1).getAs[String]("_VALUE") == "value2")
+ // comments aren't included in valueTag
+ assert(result(2).getAs[String]("_VALUE") == "\n value3\n ")
+ }
+ }
+
+ test("root-level value tag for attributes-only object - from xml") {
Review Comment:
```suggestion
test("SPARK-45488: root-level value tag for attributes-only object - from
xml") {
```
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala:
##########
@@ -1645,4 +1645,43 @@ class XmlSuite extends QueryTest with SharedSparkSession
{
.xml(getTestResourcePath(resDir + "fias_house.xml"))
assert(df.collect().length === 37)
}
+
+ test("root-level value tag for attributes-only object") {
Review Comment:
```suggestion
test("SPARK-45488: root-level value tag for attributes-only object") {
```
--
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]
