[SPARK-48296][SQL] Codegen Support for to_xml

### What changes were proposed in this pull request?
The PR adds `Codegen Support` for `to_xml`.

### Why are the changes needed?
Improve codegen coverage.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
- Add new UT & existed UT.
- Pass GA.

### Was this patch authored or co-authored using generative AI tooling?
No.

Closes #46591 from panbingkun/minor_to_xml.

Lead-authored-by: panbingkun <panbingkun@baidu.com>
Co-authored-by: panbingkun <pbk1982@gmail.com>
Signed-off-by: Kent Yao <yao@apache.org>

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xmlExpressions.scala

@@ -21,7 +21,7 @@ import java.io.CharArrayWriter
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{DataTypeMismatch, TypeCheckSuccess}
-import org.apache.spark.sql.catalyst.expressions.codegen.CodegenFallback
+import org.apache.spark.sql.catalyst.expressions.codegen.{CodegenContext, CodegenFallback, ExprCode}
 import org.apache.spark.sql.catalyst.util.{ArrayData, DropMalformedMode, FailFastMode, FailureSafeParser, GenericArrayData, PermissiveMode}
 import org.apache.spark.sql.catalyst.util.TypeUtils._
 import org.apache.spark.sql.catalyst.xml.{StaxXmlGenerator, StaxXmlParser, ValidatorUtil, XmlInferSchema, XmlOptions}
@@ -186,9 +186,6 @@ case class SchemaOfXml(
   @transient
   private lazy val xmlOptions = new XmlOptions(options, "UTC")
 
-  @transient
-  private lazy val xmlFactory = xmlOptions.buildXmlFactory()
-
   @transient
   private lazy val xmlInferSchema = {
     if (xmlOptions.parseMode == DropMalformedMode) {
@@ -266,7 +263,6 @@ case class StructsToXml(
     timeZoneId: Option[String] = None)
   extends UnaryExpression
   with TimeZoneAwareExpression
-  with CodegenFallback
   with ExpectsInputTypes
   with NullIntolerant {
   override def nullable: Boolean = true
@@ -328,6 +324,11 @@ case class StructsToXml(
 
   override def nullSafeEval(value: Any): Any = converter(value)
 
+  override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+    val expr = ctx.addReferenceObj("this", this)
+    defineCodeGen(ctx, ev, input => s"(UTF8String) $expr.nullSafeEval($input)")
+  }
+
   override def inputTypes: Seq[AbstractDataType] = StructType :: Nil
 
   override def prettyName: String = "to_xml"

sql/core/src/test/scala/org/apache/spark/sql/XmlFunctionsSuite.scala

@@ -22,6 +22,7 @@ import java.util.Locale
 
 import scala.jdk.CollectionConverters._
 
+import org.apache.spark.sql.execution.WholeStageCodegenExec
 import org.apache.spark.sql.functions._
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.test.SharedSparkSession
@@ -55,7 +56,7 @@ class XmlFunctionsSuite extends QueryTest with SharedSparkSession {
     val options = Map("rowTag" -> "foo").asJava
 
     checkAnswer(
-      df.select(from_xml($"value", schema)),
+      df.select(from_xml($"value", schema, options)),
       Row(Row(1)) :: Nil)
   }
 
@@ -383,6 +384,22 @@ class XmlFunctionsSuite extends QueryTest with SharedSparkSession {
     }
   }
 
+  test("SPARK-48296: to_xml - Codegen Support") {
+    withTempView("StructsToXmlTable") {
+      val schema = StructType(StructField("a", IntegerType, nullable = false) :: Nil)
+      val dataDF = spark.createDataFrame(Seq(Row(1)).asJava, schema).withColumn("a", struct($"a"))
+      dataDF.createOrReplaceTempView("StructsToXmlTable")
+      val df = sql("SELECT to_xml(a) FROM StructsToXmlTable")
+      val plan = df.queryExecution.executedPlan
+      assert(plan.isInstanceOf[WholeStageCodegenExec])
+      val expected =
+        s"""|<ROW>
+            |    <a>1</a>
+            |</ROW>""".stripMargin
+      checkAnswer(df, Seq(Row(expected)))
+    }
+  }
+
   test("corrupt record column in the middle") {
     val schema = new StructType()
       .add("a", IntegerType)