Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/9016#discussion_r41679715
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/columnar/ColumnType.scala ---
@@ -449,124 +416,126 @@ private[sql] object LARGE_DECIMAL {
}
}
-private[sql] case class STRUCT(dataType: StructType)
- extends ByteArrayColumnType[InternalRow](20) {
+private[sql] case class STRUCT(dataType: StructType) extends
ColumnType[UnsafeRow] {
- private val projection: UnsafeProjection =
- UnsafeProjection.create(dataType)
private val numOfFields: Int = dataType.fields.size
- override def setField(row: MutableRow, ordinal: Int, value:
InternalRow): Unit = {
+ override def defaultSize: Int = 20
+
+ override def setField(row: MutableRow, ordinal: Int, value: UnsafeRow):
Unit = {
row.update(ordinal, value)
}
- override def getField(row: InternalRow, ordinal: Int): InternalRow = {
- row.getStruct(ordinal, numOfFields)
+ override def getField(row: InternalRow, ordinal: Int): UnsafeRow = {
+ row.getStruct(ordinal, numOfFields).asInstanceOf[UnsafeRow]
}
- override def serialize(value: InternalRow): Array[Byte] = {
- val unsafeRow = if (value.isInstanceOf[UnsafeRow]) {
- value.asInstanceOf[UnsafeRow]
- } else {
- projection(value)
- }
- unsafeRow.getBytes
+ override def actualSize(row: InternalRow, ordinal: Int): Int = {
+ 4 + getField(row, ordinal).getSizeInBytes
+ }
+
+ override def append(value: UnsafeRow, buffer: ByteBuffer): Unit = {
+ buffer.putInt(value.getSizeInBytes)
+ value.writeTo(buffer)
}
- override def deserialize(bytes: Array[Byte]): InternalRow = {
+ override def extract(buffer: ByteBuffer): UnsafeRow = {
+ val sizeInBytes = buffer.getInt()
+ assert(buffer.hasArray)
+ val base = buffer.array()
+ val offset = buffer.arrayOffset()
+ val cursor = buffer.position()
+ buffer.position(cursor + sizeInBytes)
val unsafeRow = new UnsafeRow
- unsafeRow.pointTo(bytes, numOfFields, bytes.length)
+ unsafeRow.pointTo(base, Platform.BYTE_ARRAY_OFFSET + offset + cursor,
numOfFields, sizeInBytes)
unsafeRow
}
- override def clone(v: InternalRow): InternalRow = v.copy()
+ override def clone(v: UnsafeRow): UnsafeRow = v.copy()
}
-private[sql] case class ARRAY(dataType: ArrayType)
- extends ByteArrayColumnType[ArrayData](16) {
+private[sql] case class ARRAY(dataType: ArrayType) extends
ColumnType[UnsafeArrayData] {
- private lazy val projection =
UnsafeProjection.create(Array[DataType](dataType))
- private val mutableRow = new GenericMutableRow(new Array[Any](1))
+ override def defaultSize: Int = 16
- override def setField(row: MutableRow, ordinal: Int, value: ArrayData):
Unit = {
+ override def setField(row: MutableRow, ordinal: Int, value:
UnsafeArrayData): Unit = {
row.update(ordinal, value)
}
- override def getField(row: InternalRow, ordinal: Int): ArrayData = {
- row.getArray(ordinal)
+ override def getField(row: InternalRow, ordinal: Int): UnsafeArrayData =
{
+ row.getArray(ordinal).asInstanceOf[UnsafeArrayData]
}
- override def serialize(value: ArrayData): Array[Byte] = {
- val unsafeArray = if (value.isInstanceOf[UnsafeArrayData]) {
- value.asInstanceOf[UnsafeArrayData]
- } else {
- mutableRow(0) = value
- projection(mutableRow).getArray(0)
- }
- val outputBuffer =
- ByteBuffer.allocate(4 +
unsafeArray.getSizeInBytes).order(ByteOrder.nativeOrder())
- outputBuffer.putInt(unsafeArray.numElements())
- val underlying = outputBuffer.array()
- unsafeArray.writeToMemory(underlying, Platform.BYTE_ARRAY_OFFSET + 4)
- underlying
+ override def actualSize(row: InternalRow, ordinal: Int): Int = {
+ val unsafeArray = getField(row, ordinal)
+ 4 + 4 + unsafeArray.getSizeInBytes
}
- override def deserialize(bytes: Array[Byte]): ArrayData = {
- val buffer = ByteBuffer.wrap(bytes).order(ByteOrder.nativeOrder())
+ override def append(value: UnsafeArrayData, buffer: ByteBuffer): Unit = {
+ buffer.putInt(value.numElements())
+ buffer.putInt(value.getSizeInBytes)
+ value.writeTo(buffer)
+ }
+
+ override def extract(buffer: ByteBuffer): UnsafeArrayData = {
val numElements = buffer.getInt
+ val sizeInBytes = buffer.getInt
+ assert(buffer.hasArray)
+ val base = buffer.array()
+ val offset = buffer.arrayOffset()
+ val cursor = buffer.position()
+ buffer.position(cursor + sizeInBytes)
val array = new UnsafeArrayData
- array.pointTo(bytes, Platform.BYTE_ARRAY_OFFSET + 4, numElements,
bytes.length - 4)
+ array.pointTo(base, Platform.BYTE_ARRAY_OFFSET + offset + cursor,
numElements, sizeInBytes)
array
}
- override def clone(v: ArrayData): ArrayData = v.copy()
+ override def clone(v: UnsafeArrayData): UnsafeArrayData = v.copy()
}
-private[sql] case class MAP(dataType: MapType) extends
ByteArrayColumnType[MapData](32) {
+private[sql] case class MAP(dataType: MapType) extends
ColumnType[UnsafeMapData] {
- private lazy val projection: UnsafeProjection =
UnsafeProjection.create(Array[DataType](dataType))
- private val mutableRow = new GenericMutableRow(new Array[Any](1))
+ override def defaultSize: Int = 32
- override def setField(row: MutableRow, ordinal: Int, value: MapData):
Unit = {
+ override def setField(row: MutableRow, ordinal: Int, value:
UnsafeMapData): Unit = {
row.update(ordinal, value)
}
- override def getField(row: InternalRow, ordinal: Int): MapData = {
- row.getMap(ordinal)
+ override def getField(row: InternalRow, ordinal: Int): UnsafeMapData = {
+ row.getMap(ordinal).asInstanceOf[UnsafeMapData]
}
- override def serialize(value: MapData): Array[Byte] = {
- val unsafeMap = if (value.isInstanceOf[UnsafeMapData]) {
- value.asInstanceOf[UnsafeMapData]
- } else {
- mutableRow(0) = value
- projection(mutableRow).getMap(0)
- }
+ override def actualSize(row: InternalRow, ordinal: Int): Int = {
+ val unsafeMap = getField(row, ordinal)
+ 12 + unsafeMap.keyArray().getSizeInBytes +
unsafeMap.valueArray().getSizeInBytes
+ }
- val outputBuffer =
- ByteBuffer.allocate(8 +
unsafeMap.getSizeInBytes).order(ByteOrder.nativeOrder())
- outputBuffer.putInt(unsafeMap.numElements())
- val keyBytes = unsafeMap.keyArray().getSizeInBytes
- outputBuffer.putInt(keyBytes)
- val underlying = outputBuffer.array()
- unsafeMap.keyArray().writeToMemory(underlying,
Platform.BYTE_ARRAY_OFFSET + 8)
- unsafeMap.valueArray().writeToMemory(underlying,
Platform.BYTE_ARRAY_OFFSET + 8 + keyBytes)
- underlying
+ override def append(value: UnsafeMapData, buffer: ByteBuffer): Unit = {
+ buffer.putInt(value.numElements())
+ buffer.putInt(value.keyArray().getSizeInBytes)
+ buffer.putInt(value.valueArray().getSizeInBytes)
+ value.keyArray().writeTo(buffer)
+ value.valueArray().writeTo(buffer)
}
- override def deserialize(bytes: Array[Byte]): MapData = {
- val buffer = ByteBuffer.wrap(bytes).order(ByteOrder.nativeOrder())
+ override def extract(buffer: ByteBuffer): UnsafeMapData = {
val numElements = buffer.getInt
val keyArraySize = buffer.getInt
+ val valueArraySize = buffer.getInt
+ assert(buffer.hasArray)
+ val base = buffer.array()
+ val offset = buffer.arrayOffset()
+ val cursor = buffer.position()
val keyArray = new UnsafeArrayData
+ keyArray.pointTo(base, Platform.BYTE_ARRAY_OFFSET + offset + cursor,
numElements, keyArraySize)
val valueArray = new UnsafeArrayData
- keyArray.pointTo(bytes, Platform.BYTE_ARRAY_OFFSET + 8, numElements,
keyArraySize)
- valueArray.pointTo(bytes, Platform.BYTE_ARRAY_OFFSET + 8 +
keyArraySize, numElements,
- bytes.length - 8 - keyArraySize)
+ valueArray.pointTo(base, Platform.BYTE_ARRAY_OFFSET + offset + cursor
+ keyArraySize,
+ numElements, valueArraySize)
+ buffer.position(cursor + keyArraySize + valueArraySize)
new UnsafeMapData(keyArray, valueArray)
--- End diff --
I think we can use `UnsafeReaders.readMap` here.
Same to the array part.
---
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]
