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
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.sql.catalyst.expressions
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.types._
/**
* An interpreted row ordering comparator.
*/
class InterpretedOrdering(ordering: Seq[SortOrder]) extends Ordering[InternalRow] {
def this(ordering: Seq[SortOrder], inputSchema: Seq[Attribute]) =
this(ordering.map(BindReferences.bindReference(_, inputSchema)))
def compare(a: InternalRow, b: InternalRow): Int = {
var i = 0
val size = ordering.size
while (i < size) {
val order = ordering(i)
val left = order.child.eval(a)
val right = order.child.eval(b)
if (left == null && right == null) {
// Both null, continue looking.
} else if (left == null) {
return if (order.nullOrdering == NullsFirst) -1 else 1
} else if (right == null) {
return if (order.nullOrdering == NullsFirst) 1 else -1
} else {
val comparison = order.dataType match {
case dt: AtomicType if order.direction == Ascending =>
dt.ordering.asInstanceOf[Ordering[Any]].compare(left, right)
case dt: AtomicType if order.direction == Descending =>
dt.ordering.asInstanceOf[Ordering[Any]].reverse.compare(left, right)
case a: ArrayType if order.direction == Ascending =>
a.interpretedOrdering.asInstanceOf[Ordering[Any]].compare(left, right)
case a: ArrayType if order.direction == Descending =>
a.interpretedOrdering.asInstanceOf[Ordering[Any]].reverse.compare(left, right)
case s: StructType if order.direction == Ascending =>
s.interpretedOrdering.asInstanceOf[Ordering[Any]].compare(left, right)
case s: StructType if order.direction == Descending =>
s.interpretedOrdering.asInstanceOf[Ordering[Any]].reverse.compare(left, right)
case other =>
throw new IllegalArgumentException(s"Type $other does not support ordered operations")
}
if (comparison != 0) {
return comparison
}
}
i += 1
}
return 0
}
}
object InterpretedOrdering {
/**
* Creates a [[InterpretedOrdering]] for the given schema, in natural ascending order.
*/
def forSchema(dataTypes: Seq[DataType]): InterpretedOrdering = {
new InterpretedOrdering(dataTypes.zipWithIndex.map {
case (dt, index) => SortOrder(BoundReference(index, dt, nullable = true), Ascending)
})
}
}
object RowOrdering {
/**
* Returns true iff the data type can be ordered (i.e. can be sorted).
*/
def isOrderable(dataType: DataType): Boolean = dataType match {
case NullType => true
case dt: AtomicType => true
case struct: StructType => struct.fields.forall(f => isOrderable(f.dataType))
case array: ArrayType => isOrderable(array.elementType)
case udt: UserDefinedType[_] => isOrderable(udt.sqlType)
case _ => false
}
/**
* Returns true iff outputs from the expressions can be ordered.
*/
def isOrderable(exprs: Seq[Expression]): Boolean = exprs.forall(e => isOrderable(e.dataType))
}
|
