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
|
/*
* 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
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.types.{StructField, StructType}
/**
* A set of classes that can be used to represent trees of relational expressions. A key goal of
* the expression library is to hide the details of naming and scoping from developers who want to
* manipulate trees of relational operators. As such, the library defines a special type of
* expression, a [[NamedExpression]] in addition to the standard collection of expressions.
*
* ==Standard Expressions==
* A library of standard expressions (e.g., [[Add]], [[EqualTo]]), aggregates (e.g., SUM, COUNT),
* and other computations (e.g. UDFs). Each expression type is capable of determining its output
* schema as a function of its children's output schema.
*
* ==Named Expressions==
* Some expression are named and thus can be referenced by later operators in the dataflow graph.
* The two types of named expressions are [[AttributeReference]]s and [[Alias]]es.
* [[AttributeReference]]s refer to attributes of the input tuple for a given operator and form
* the leaves of some expression trees. Aliases assign a name to intermediate computations.
* For example, in the SQL statement `SELECT a+b AS c FROM ...`, the expressions `a` and `b` would
* be represented by `AttributeReferences` and `c` would be represented by an `Alias`.
*
* During [[analysis]], all named expressions are assigned a globally unique expression id, which
* can be used for equality comparisons. While the original names are kept around for debugging
* purposes, they should never be used to check if two attributes refer to the same value, as
* plan transformations can result in the introduction of naming ambiguity. For example, consider
* a plan that contains subqueries, both of which are reading from the same table. If an
* optimization removes the subqueries, scoping information would be destroyed, eliminating the
* ability to reason about which subquery produced a given attribute.
*
* ==Evaluation==
* The result of expressions can be evaluated using the `Expression.apply(Row)` method.
*/
package object expressions {
/**
* Used as input into expressions whose output does not depend on any input value.
*/
val EmptyRow: InternalRow = null
/**
* Converts a [[InternalRow]] to another Row given a sequence of expression that define each
* column of the new row. If the schema of the input row is specified, then the given expression
* will be bound to that schema.
*/
abstract class Projection extends (InternalRow => InternalRow)
/**
* Converts a [[InternalRow]] to another Row given a sequence of expression that define each
* column of the new row. If the schema of the input row is specified, then the given expression
* will be bound to that schema.
*
* In contrast to a normal projection, a MutableProjection reuses the same underlying row object
* each time an input row is added. This significantly reduces the cost of calculating the
* projection, but means that it is not safe to hold on to a reference to a [[InternalRow]] after
* `next()` has been called on the [[Iterator]] that produced it. Instead, the user must call
* `InternalRow.copy()` and hold on to the returned [[InternalRow]] before calling `next()`.
*/
abstract class MutableProjection extends Projection {
def currentValue: InternalRow
/** Uses the given row to store the output of the projection. */
def target(row: MutableRow): MutableProjection
}
/**
* Helper functions for working with `Seq[Attribute]`.
*/
implicit class AttributeSeq(attrs: Seq[Attribute]) {
/** Creates a StructType with a schema matching this `Seq[Attribute]`. */
def toStructType: StructType = {
StructType(attrs.map(a => StructField(a.name, a.dataType, a.nullable)))
}
}
/**
* When an expression inherits this, meaning the expression is null intolerant (i.e. any null
* input will result in null output). We will use this information during constructing IsNotNull
* constraints.
*/
trait NullIntolerant
}
|