FilesExpand file tree

 main

/

__init__.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

222 lines (197 loc) · 4.39 KB

 main

/

__init__.py

Copy path

Top

File metadata and controls

• Code
• Blame

222 lines (197 loc) · 4.39 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

# 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.

from abc import ABCMeta, abstractmethod

from typing import List

try:

import importlib.metadata as importlib_metadata

except ImportError:

import importlib_metadata

import pyarrow as pa

from ._internal import (

AggregateUDF,

Config,

DataFrame,

SessionContext,

SessionConfig,

RuntimeConfig,

ScalarUDF,

SQLOptions,

)

from .common import (

DFSchema,

)

from .expr import (

Alias,

Analyze,

Expr,

Filter,

Limit,

Like,

ILike,

Projection,

SimilarTo,

ScalarVariable,

Sort,

TableScan,

GetIndexedField,

Not,

IsNotNull,

IsTrue,

IsFalse,

IsUnknown,

IsNotTrue,

IsNotFalse,

IsNotUnknown,

Negative,

InList,

Exists,

Subquery,

InSubquery,

ScalarSubquery,

GroupingSet,

Placeholder,

Case,

Cast,

TryCast,

Between,

Explain,

CreateMemoryTable,

SubqueryAlias,

Extension,

CreateView,

Distinct,

DropTable,

Repartition,

Partitioning,

Window,

WindowFrame,

)

__version__ = importlib_metadata.version(__name__)

__all__ = [

"Config",

"DataFrame",

"SessionContext",

"SessionConfig",

"SQLOptions",

"RuntimeConfig",

"Expr",

"AggregateUDF",

"ScalarUDF",

"Window",

"WindowFrame",

"column",

"literal",

"TableScan",

"Projection",

"DFSchema",

"DFField",

"Analyze",

"Sort",

"Limit",

"Filter",

"Like",

"ILike",

"SimilarTo",

"ScalarVariable",

"Alias",

"GetIndexedField",

"Not",

"IsNotNull",

"IsTrue",

"IsFalse",

"IsUnknown",

"IsNotTrue",

"IsNotFalse",

"IsNotUnknown",

"Negative",

"ScalarFunction",

"BuiltinScalarFunction",

"InList",

"Exists",

"Subquery",

"InSubquery",

"ScalarSubquery",

"GroupingSet",

"Placeholder",

"Case",

"Cast",

"TryCast",

"Between",

"Explain",

"SubqueryAlias",

"Extension",

"CreateMemoryTable",

"CreateView",

"Distinct",

"DropTable",

"Repartition",

"Partitioning",

]

class Accumulator(metaclass=ABCMeta):

@abstractmethod

def state(self) -> List[pa.Scalar]:

pass

@abstractmethod

def update(self, values: pa.Array) -> None:

pass

@abstractmethod

def merge(self, states: pa.Array) -> None:

pass

@abstractmethod

def evaluate(self) -> pa.Scalar:

pass

def column(value):

return Expr.column(value)

col = column

def literal(value):

if not isinstance(value, pa.Scalar):

value = pa.scalar(value)

return Expr.literal(value)

lit = literal

def udf(func, input_types, return_type, volatility, name=None):

"""

Create a new User Defined Function

"""

if not callable(func):

raise TypeError("`func` argument must be callable")

if name is None:

name = func.__qualname__.lower()

return ScalarUDF(

name=name,

func=func,

input_types=input_types,

return_type=return_type,

volatility=volatility,

)

def udaf(accum, input_type, return_type, state_type, volatility, name=None):

"""

Create a new User Defined Aggregate Function

"""

if not issubclass(accum, Accumulator):

raise TypeError("`accum` must implement the abstract base class Accumulator")

if name is None:

name = accum.__qualname__.lower()

if isinstance(input_type, pa.lib.DataType):

input_type = [input_type]

return AggregateUDF(

name=name,

accumulator=accum,

input_type=input_type,

return_type=return_type,

state_type=state_type,

volatility=volatility,

)