blob: 2c829508e589b3417e02d47d2f28bbf996e08c68 (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
package spark.api.python
import spark.Partitioner
import java.util.Arrays
/**
* A [[spark.Partitioner]] that performs handling of byte arrays, for use by the Python API.
*/
private[spark] class PythonPartitioner(override val numPartitions: Int) extends Partitioner {
override def getPartition(key: Any): Int = {
if (key == null) {
return 0
}
else {
val hashCode = {
if (key.isInstanceOf[Array[Byte]]) {
Arrays.hashCode(key.asInstanceOf[Array[Byte]])
}
else
key.hashCode()
}
val mod = hashCode % numPartitions
if (mod < 0) {
mod + numPartitions
} else {
mod // Guard against negative hash codes
}
}
}
override def equals(other: Any): Boolean = other match {
case h: PythonPartitioner =>
h.numPartitions == numPartitions
case _ =>
false
}
}
|