(spark) branch master updated: [SPARK-52670][SQL] Make HiveResult work with UserDefinedType#stringifyValue

[ya...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

yao pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/master by this push:
     new 3b15ee86bd29 [SPARK-52670][SQL] Make HiveResult work with UserDefinedType#stringifyValue
3b15ee86bd29 is described below

commit 3b15ee86bd2984cbf34bd509382440169b084ba4
Author: Kent Yao <ya...@apache.org>
AuthorDate: Fri Jul 4 10:03:20 2025 +0800

    [SPARK-52670][SQL] Make HiveResult work with UserDefinedType#stringifyValue
    
    ### What changes were proposed in this pull request?
    
    Make HiveResult work with UserDefinedType#stringifyValue
    
    ### Why are the changes needed?
    
    If the `toString` of the underlying class of a UDT is not well-defined, the JDBC/thrift side might not be able to get a meaningful value.
    
    ### Does this PR introduce _any_ user-facing change?
    No
    
    ### How was this patch tested?
    new tests
    
    ### Was this patch authored or co-authored using generative AI tooling?
    no
    
    Closes #51358 from yaooqinn/SPARK-52670.
    
    Authored-by: Kent Yao <ya...@apache.org>
    Signed-off-by: Kent Yao <ya...@apache.org>
---
 .../org/apache/spark/sql/execution/HiveResult.scala  |  2 +-
 .../apache/spark/sql/execution/HiveResultSuite.scala | 20 +++++++++++++++++---
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
index 21cf70dab59f..3a7b75a555af 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/HiveResult.scala
@@ -149,6 +149,6 @@ object HiveResult extends SQLConfHelper {
         startField,
         endField)
     case (v: VariantVal, VariantType) => v.toString
-    case (other, _: UserDefinedType[_]) => other.toString
+    case (other, u: UserDefinedType[_]) => u.stringifyValue(other)
   }
 }
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/HiveResultSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/HiveResultSuite.scala
index 13c246660e86..ae5b303116de 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/HiveResultSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/HiveResultSuite.scala
@@ -17,15 +17,15 @@
 
 package org.apache.spark.sql.execution
 
-import java.time.{Duration, Period}
+import java.time.{Duration, Period, Year}
 
+import org.apache.spark.sql.YearUDT
 import org.apache.spark.sql.catalyst.util.DateTimeTestUtils
 import org.apache.spark.sql.connector.catalog.InMemoryTableCatalog
 import org.apache.spark.sql.execution.HiveResult._
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.test.{ExamplePoint, ExamplePointUDT, SharedSparkSession}
-import org.apache.spark.sql.types.{YearMonthIntervalType => YM}
-import org.apache.spark.sql.types.YearMonthIntervalType
+import org.apache.spark.sql.types.{YearMonthIntervalType, YearMonthIntervalType => YM}
 
 
 class HiveResultSuite extends SharedSparkSession {
@@ -172,4 +172,18 @@ class HiveResultSuite extends SharedSparkSession {
     val plan2 = df.selectExpr("array(i)").queryExecution.executedPlan
     assert(hiveResultString(plan2) === Seq("[5 00:00:00.010000000]"))
   }
+
+  test("SPARK-52650: Use stringifyValue to get UDT string representation") {
+    val year = Year.of(18)
+    val tpe = new YearUDT()
+    assert(toHiveString((year, tpe),
+      nested = false, getTimeFormatters, getBinaryFormatter) === "18")
+    val tpe2 = new YearUDT() {
+      override def stringifyValue(obj: Any): String = {
+        f"${obj.asInstanceOf[Year].getValue}%04d"
+      }
+    }
+    assert(toHiveString((year, tpe2),
+      nested = false, getTimeFormatters, getBinaryFormatter) === "0018")
+  }
 }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org