Re: [PR] [SPARK-46679][SQL]: Handling of generic parameter with bounds while creating encoders [spark]

["hvanhovell (via GitHub)" <gi...@apache.org>]

hvanhovell commented on code in PR #48158:
URL: https://github.com/apache/spark/pull/48158#discussion_r1771680158


##########
sql/api/src/main/scala/org/apache/spark/sql/catalyst/JavaTypeInference.scala:
##########
@@ -66,37 +70,46 @@ object JavaTypeInference {
   private def encoderFor(
       t: Type,
       seenTypeSet: Set[Class[_]],
-      typeVariables: Map[TypeVariable[_], Type] = Map.empty): AgnosticEncoder[_] = t match {
-
-    case c: Class[_] if c == java.lang.Boolean.TYPE => PrimitiveBooleanEncoder
-    case c: Class[_] if c == java.lang.Byte.TYPE => PrimitiveByteEncoder
-    case c: Class[_] if c == java.lang.Short.TYPE => PrimitiveShortEncoder
-    case c: Class[_] if c == java.lang.Integer.TYPE => PrimitiveIntEncoder
-    case c: Class[_] if c == java.lang.Long.TYPE => PrimitiveLongEncoder
-    case c: Class[_] if c == java.lang.Float.TYPE => PrimitiveFloatEncoder
-    case c: Class[_] if c == java.lang.Double.TYPE => PrimitiveDoubleEncoder
-
-    case c: Class[_] if c == classOf[java.lang.Boolean] => BoxedBooleanEncoder
-    case c: Class[_] if c == classOf[java.lang.Byte] => BoxedByteEncoder
-    case c: Class[_] if c == classOf[java.lang.Short] => BoxedShortEncoder
-    case c: Class[_] if c == classOf[java.lang.Integer] => BoxedIntEncoder
-    case c: Class[_] if c == classOf[java.lang.Long] => BoxedLongEncoder
-    case c: Class[_] if c == classOf[java.lang.Float] => BoxedFloatEncoder
-    case c: Class[_] if c == classOf[java.lang.Double] => BoxedDoubleEncoder
-
-    case c: Class[_] if c == classOf[java.lang.String] => StringEncoder
-    case c: Class[_] if c == classOf[Array[Byte]] => BinaryEncoder
-    case c: Class[_] if c == classOf[java.math.BigDecimal] => DEFAULT_JAVA_DECIMAL_ENCODER
-    case c: Class[_] if c == classOf[java.math.BigInteger] => JavaBigIntEncoder
-    case c: Class[_] if c == classOf[java.time.LocalDate] => STRICT_LOCAL_DATE_ENCODER
-    case c: Class[_] if c == classOf[java.sql.Date] => STRICT_DATE_ENCODER
-    case c: Class[_] if c == classOf[java.time.Instant] => STRICT_INSTANT_ENCODER
-    case c: Class[_] if c == classOf[java.sql.Timestamp] => STRICT_TIMESTAMP_ENCODER
-    case c: Class[_] if c == classOf[java.time.LocalDateTime] => LocalDateTimeEncoder
-    case c: Class[_] if c == classOf[java.time.Duration] => DayTimeIntervalEncoder
-    case c: Class[_] if c == classOf[java.time.Period] => YearMonthIntervalEncoder
-
-    case c: Class[_] if c.isEnum => JavaEnumEncoder(ClassTag(c))
+      typeVariables: Map[TypeVariable[_], Type] = Map.empty,
+      forGenericBound: Boolean = false): AgnosticEncoder[_] = t match {
+
+    case c: Class[_] if !forGenericBound && c == java.lang.Boolean.TYPE => PrimitiveBooleanEncoder

Review Comment:
   For readability purposes I would create a branch at the beginning where you handle `case tv: TypeVariable[_] if forGenericBound =>` This way the rest of the code is less impacted.



-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


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