Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/7955#discussion_r36301990
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/rows.scala
---
@@ -23,6 +23,130 @@ import org.apache.spark.sql.types._
import org.apache.spark.unsafe.types.{CalendarInterval, UTF8String}
/**
+ * An extended version of [[InternalRow]] that implements all special
getters, toString
+ * and equals/hashCode by `genericGet`.
+ */
+trait BaseGenericInternalRow extends InternalRow {
+
+ protected def genericGet(ordinal: Int): Any
+
+ // default implementation (slow)
+ private def getAs[T](ordinal: Int) = genericGet(ordinal).asInstanceOf[T]
+ override def isNullAt(ordinal: Int): Boolean = getAs[AnyRef](ordinal) eq
null
+ override def get(ordinal: Int, dataType: DataType): AnyRef =
getAs(ordinal)
+ override def getBoolean(ordinal: Int): Boolean = getAs(ordinal)
+ override def getByte(ordinal: Int): Byte = getAs(ordinal)
+ override def getShort(ordinal: Int): Short = getAs(ordinal)
+ override def getInt(ordinal: Int): Int = getAs(ordinal)
+ override def getLong(ordinal: Int): Long = getAs(ordinal)
+ override def getFloat(ordinal: Int): Float = getAs(ordinal)
+ override def getDouble(ordinal: Int): Double = getAs(ordinal)
+ override def getDecimal(ordinal: Int, precision: Int, scale: Int):
Decimal = getAs(ordinal)
+ override def getUTF8String(ordinal: Int): UTF8String = getAs(ordinal)
+ override def getBinary(ordinal: Int): Array[Byte] = getAs(ordinal)
+ override def getArray(ordinal: Int): ArrayData = getAs(ordinal)
+ override def getInterval(ordinal: Int): CalendarInterval = getAs(ordinal)
+ override def getMap(ordinal: Int): MapData = getAs(ordinal)
+ override def getStruct(ordinal: Int, numFields: Int): InternalRow =
getAs(ordinal)
+
+ override def toString(): String = {
+ if (numFields == 0) {
+ "[ empty row ]"
+ } else {
+ val sb = new StringBuilder
+ sb.append("[")
+ sb.append(genericGet(0))
+ val len = numFields
+ var i = 1
+ while (i < len) {
+ sb.append(",")
+ sb.append(genericGet(i))
+ i += 1
+ }
+ sb.append("]")
+ sb.toString()
+ }
+ }
+
+ override def equals(o: Any): Boolean = {
+ if (!o.isInstanceOf[BaseGenericInternalRow]) {
+ return false
+ }
+
+ val other = o.asInstanceOf[BaseGenericInternalRow]
+ if (other eq null) {
+ return false
+ }
+
+ val len = numFields
+ if (len != other.numFields) {
+ return false
+ }
+
+ var i = 0
+ while (i < len) {
+ if (isNullAt(i) != other.isNullAt(i)) {
+ return false
+ }
+ if (!isNullAt(i)) {
+ val o1 = genericGet(i)
+ val o2 = other.genericGet(i)
+ o1 match {
--- End diff --
It's the slow path anyway, we have optimized `equals` and `hashCode` at
codegen and unsafe versions.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
