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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
|
/*
* 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.expressions
import org.apache.spark.annotation.Experimental
import org.apache.spark.sql.{Column, Row}
import org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression, Complete}
import org.apache.spark.sql.execution.aggregate.ScalaUDAF
import org.apache.spark.sql.types._
/**
* :: Experimental ::
* The base class for implementing user-defined aggregate functions (UDAF).
*/
@Experimental
abstract class UserDefinedAggregateFunction extends Serializable {
/**
* A [[StructType]] represents data types of input arguments of this aggregate function.
* For example, if a [[UserDefinedAggregateFunction]] expects two input arguments
* with type of [[DoubleType]] and [[LongType]], the returned [[StructType]] will look like
*
* ```
* new StructType()
* .add("doubleInput", DoubleType)
* .add("longInput", LongType)
* ```
*
* The name of a field of this [[StructType]] is only used to identify the corresponding
* input argument. Users can choose names to identify the input arguments.
*/
def inputSchema: StructType
/**
* A [[StructType]] represents data types of values in the aggregation buffer.
* For example, if a [[UserDefinedAggregateFunction]]'s buffer has two values
* (i.e. two intermediate values) with type of [[DoubleType]] and [[LongType]],
* the returned [[StructType]] will look like
*
* ```
* new StructType()
* .add("doubleInput", DoubleType)
* .add("longInput", LongType)
* ```
*
* The name of a field of this [[StructType]] is only used to identify the corresponding
* buffer value. Users can choose names to identify the input arguments.
*/
def bufferSchema: StructType
/**
* The [[DataType]] of the returned value of this [[UserDefinedAggregateFunction]].
*/
def dataType: DataType
/**
* Returns true iff this function is deterministic, i.e. given the same input,
* always return the same output.
*/
def deterministic: Boolean
/**
* Initializes the given aggregation buffer, i.e. the zero value of the aggregation buffer.
*
* The contract should be that applying the merge function on two initial buffers should just
* return the initial buffer itself, i.e.
* `merge(initialBuffer, initialBuffer)` should equal `initialBuffer`.
*/
def initialize(buffer: MutableAggregationBuffer): Unit
/**
* Updates the given aggregation buffer `buffer` with new input data from `input`.
*
* This is called once per input row.
*/
def update(buffer: MutableAggregationBuffer, input: Row): Unit
/**
* Merges two aggregation buffers and stores the updated buffer values back to `buffer1`.
*
* This is called when we merge two partially aggregated data together.
*/
def merge(buffer1: MutableAggregationBuffer, buffer2: Row): Unit
/**
* Calculates the final result of this [[UserDefinedAggregateFunction]] based on the given
* aggregation buffer.
*/
def evaluate(buffer: Row): Any
/**
* Creates a [[Column]] for this UDAF using given [[Column]]s as input arguments.
*/
@_root_.scala.annotation.varargs
def apply(exprs: Column*): Column = {
val aggregateExpression =
AggregateExpression(
ScalaUDAF(exprs.map(_.expr), this),
Complete,
isDistinct = false)
Column(aggregateExpression)
}
/**
* Creates a [[Column]] for this UDAF using the distinct values of the given
* [[Column]]s as input arguments.
*/
@_root_.scala.annotation.varargs
def distinct(exprs: Column*): Column = {
val aggregateExpression =
AggregateExpression(
ScalaUDAF(exprs.map(_.expr), this),
Complete,
isDistinct = true)
Column(aggregateExpression)
}
}
/**
* :: Experimental ::
* A [[Row]] representing an mutable aggregation buffer.
*
* This is not meant to be extended outside of Spark.
*/
@Experimental
abstract class MutableAggregationBuffer extends Row {
/** Update the ith value of this buffer. */
def update(i: Int, value: Any): Unit
}
|
