Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/6869#discussion_r32703247 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/InternalRow.scala --- @@ -19,39 +19,193 @@ package org.apache.spark.sql.catalyst import org.apache.spark.sql.Row import org.apache.spark.sql.catalyst.expressions.GenericRow +import org.apache.spark.sql.types.StructType +import org.apache.spark.unsafe.types.UTF8String /** * An abstract class for row used internal in Spark SQL, which only contain the columns as * internal types. + * + * The following is a mapping between Spark SQL types and types of objects in row: + * + * BooleanType -> java.lang.Boolean + * ByteType -> java.lang.Byte + * ShortType -> java.lang.Short + * IntegerType -> java.lang.Integer + * FloatType -> java.lang.Float + * DoubleType -> java.lang.Double + * StringType -> UTF8String + * DecimalType -> org.apache.spark.sql.types.Decimal + * + * DateType -> java.lang.Int + * TimestampType -> java.lang.Long + * + * BinaryType -> Array[Byte] + * ArrayType -> scala.collection.Seq + * MapType -> scala.collection.Map + * StructType -> InternalRow */ -abstract class InternalRow extends Row { - // A default implementation to change the return type - override def copy(): InternalRow = {this} -} +abstract class InternalRow extends Serializable { + /** Number of elements in the Row. */ + def size: Int = length --- End diff -- do we need size? maybe just keep one of length or size.
--- 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