Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/18704#discussion_r139364602
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/compression/compressionSchemes.scala
---
@@ -169,6 +267,125 @@ private[columnar] case object RunLengthEncoding
extends CompressionScheme {
}
override def hasNext: Boolean = valueCount < run || buffer.hasRemaining
+
+ override def decompress(columnVector: WritableColumnVector, capacity:
Int): Unit = {
+ val nullsBuffer = buffer.duplicate().order(ByteOrder.nativeOrder())
+ nullsBuffer.rewind()
+ val nullCount = ByteBufferHelper.getInt(nullsBuffer)
+ var nextNullIndex = if (nullCount > 0)
ByteBufferHelper.getInt(nullsBuffer) else -1
+ var pos = 0
+ var seenNulls = 0
+ var runLocal = 0
+ var valueCountLocal = 0
+ columnType.dataType match {
+ case _: BooleanType =>
--- End diff --
same here, can we reduce code duplication?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
