Github user chenghao-intel commented on a diff in the pull request:
https://github.com/apache/spark/pull/2762#discussion_r19389129
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala ---
@@ -123,43 +93,88 @@ private[hive] trait HiveInspectors {
case pi: PrimitiveObjectInspector => pi.getPrimitiveJavaObject(data)
case li: ListObjectInspector =>
Option(li.getList(data))
- .map(_.map(unwrapData(_, li.getListElementObjectInspector)).toSeq)
+ .map(_.map(unwrap(_, li.getListElementObjectInspector)).toSeq)
.orNull
case mi: MapObjectInspector =>
Option(mi.getMap(data)).map(
_.map {
case (k,v) =>
- (unwrapData(k, mi.getMapKeyObjectInspector),
- unwrapData(v, mi.getMapValueObjectInspector))
+ (unwrap(k, mi.getMapKeyObjectInspector),
+ unwrap(v, mi.getMapValueObjectInspector))
}.toMap).orNull
case si: StructObjectInspector =>
val allRefs = si.getAllStructFieldRefs
new GenericRow(
allRefs.map(r =>
- unwrapData(si.getStructFieldData(data,r),
r.getFieldObjectInspector)).toArray)
+ unwrap(si.getStructFieldData(data,r),
r.getFieldObjectInspector)).toArray)
}
- /** Converts native catalyst types to the types expected by Hive */
- def wrap(a: Any): AnyRef = a match {
- case s: String => s: java.lang.String
- case i: Int => i: java.lang.Integer
- case b: Boolean => b: java.lang.Boolean
- case f: Float => f: java.lang.Float
- case d: Double => d: java.lang.Double
- case l: Long => l: java.lang.Long
- case l: Short => l: java.lang.Short
- case l: Byte => l: java.lang.Byte
- case b: BigDecimal => new HiveDecimal(b.underlying())
- case b: Array[Byte] => b
- case d: java.sql.Date => d
- case t: java.sql.Timestamp => t
- case s: Seq[_] => seqAsJavaList(s.map(wrap))
- case m: Map[_,_] =>
- // Some UDFs seem to assume we pass in a HashMap.
- val hashMap = new java.util.HashMap[AnyRef, AnyRef]()
- hashMap.putAll(m.map { case (k, v) => wrap(k) -> wrap(v) })
- hashMap
- case null => null
+ /**
+ * Converts native catalyst types to the types expected by Hive
+ * @param a the value to be wrapped
+ * @param oi wrapped object used by this ObjectInspector, which supposed
to be
+ * the ObjectInspector enumerated in functions:
+ * def toInspector(dataType: DataType)
+ * def toInspector(expr: Expression)
+ */
+ def wrap(a: Any, oi: ObjectInspector): AnyRef = if (a == null) {
+ null
+ } else {
+ oi match {
+ case x: ConstantObjectInspector => x.getWritableConstantValue
+ case x: PrimitiveObjectInspector => a match {
+ // TODO what if x.preferWritable() == true?
--- End diff --
Currently the `ObjectInspector` passed should not be `preferWriteable`,
because the function `def toInspector(DataType)` will never returns that. I
would like to keep it for further improvement
(https://issues.apache.org/jira/browse/SPARK-4093), which probably pass in the
`WritableObjectInspector`.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
