typespark 1.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- typespark-1.1.0/.gitignore +184 -0
- typespark-1.1.0/LICENSE +21 -0
- typespark-1.1.0/PKG-INFO +41 -0
- typespark-1.1.0/README.md +13 -0
- typespark-1.1.0/pyproject.toml +77 -0
- typespark-1.1.0/tests/__init__.py +0 -0
- typespark-1.1.0/tests/conftest.py +108 -0
- typespark-1.1.0/tests/test_array.py +252 -0
- typespark-1.1.0/tests/test_basic.py +345 -0
- typespark-1.1.0/tests/test_column.py +41 -0
- typespark-1.1.0/tests/test_create.py +183 -0
- typespark-1.1.0/tests/test_defaults.py +289 -0
- typespark-1.1.0/tests/test_functions_agg.py +415 -0
- typespark-1.1.0/tests/test_functions_array.py +463 -0
- typespark-1.1.0/tests/test_functions_date_time.py +628 -0
- typespark-1.1.0/tests/test_functions_higher_order.py +79 -0
- typespark-1.1.0/tests/test_functions_math.py +490 -0
- typespark-1.1.0/tests/test_functions_misc.py +403 -0
- typespark-1.1.0/tests/test_functions_string.py +640 -0
- typespark-1.1.0/tests/test_groups.py +127 -0
- typespark-1.1.0/tests/test_lazy.py +155 -0
- typespark-1.1.0/tests/test_literal_columns.py +222 -0
- typespark-1.1.0/tests/test_op_return_types.py +428 -0
- typespark-1.1.0/tests/test_operators.py +491 -0
- typespark-1.1.0/tests/test_primitive_init.py +282 -0
- typespark-1.1.0/tests/test_qualify.py +50 -0
- typespark-1.1.0/tests/test_schema.py +187 -0
- typespark-1.1.0/tests/test_struct.py +289 -0
- typespark-1.1.0/tests/test_subclassing.py +141 -0
- typespark-1.1.0/tests/test_typecheck.py +25 -0
- typespark-1.1.0/tests/test_window.py +116 -0
- typespark-1.1.0/tests/typecheck/enum_when_example.py +81 -0
- typespark-1.1.0/tests/typecheck/field_default_example.py +100 -0
- typespark-1.1.0/tests/typecheck/timestamp_ntz_example.py +32 -0
- typespark-1.1.0/tests/typecheck/window_example.py +46 -0
- typespark-1.1.0/tests/utils.py +22 -0
- typespark-1.1.0/typespark/__init__.py +80 -0
- typespark-1.1.0/typespark/_base.py +184 -0
- typespark-1.1.0/typespark/_default_types.py +45 -0
- typespark-1.1.0/typespark/_define.py +28 -0
- typespark-1.1.0/typespark/_exceptions.py +89 -0
- typespark-1.1.0/typespark/columns/__init__.py +43 -0
- typespark-1.1.0/typespark/columns/_generator.py +174 -0
- typespark-1.1.0/typespark/columns/_groups.py +106 -0
- typespark-1.1.0/typespark/columns/array.py +100 -0
- typespark-1.1.0/typespark/columns/columns.py +279 -0
- typespark-1.1.0/typespark/columns/primitives.py +512 -0
- typespark-1.1.0/typespark/columns/struct.py +66 -0
- typespark-1.1.0/typespark/columns/utils.py +16 -0
- typespark-1.1.0/typespark/data_contract/__init__.py +12 -0
- typespark-1.1.0/typespark/data_contract/cli.py +39 -0
- typespark-1.1.0/typespark/data_contract/generate.py +266 -0
- typespark-1.1.0/typespark/data_contract/mixins.py +15 -0
- typespark-1.1.0/typespark/data_contract/serialize.py +139 -0
- typespark-1.1.0/typespark/dataframe.py +659 -0
- typespark-1.1.0/typespark/field_transforms.py +229 -0
- typespark-1.1.0/typespark/functions/__init__.py +480 -0
- typespark-1.1.0/typespark/functions/_type_aliases.py +15 -0
- typespark-1.1.0/typespark/functions/aggregates.py +190 -0
- typespark-1.1.0/typespark/functions/array.py +355 -0
- typespark-1.1.0/typespark/functions/date_time.py +415 -0
- typespark-1.1.0/typespark/functions/higher_order.py +92 -0
- typespark-1.1.0/typespark/functions/math.py +461 -0
- typespark-1.1.0/typespark/functions/misc.py +358 -0
- typespark-1.1.0/typespark/functions/string.py +556 -0
- typespark-1.1.0/typespark/functions/window_functions.py +90 -0
- typespark-1.1.0/typespark/literals.py +20 -0
- typespark-1.1.0/typespark/metadata.py +636 -0
- typespark-1.1.0/typespark/py.typed +0 -0
- typespark-1.1.0/typespark/schema/__init__.py +3 -0
- typespark-1.1.0/typespark/schema/schema.py +144 -0
- typespark-1.1.0/typespark/utils.py +46 -0
- typespark-1.1.0/typespark/window.py +70 -0
|
@@ -0,0 +1,184 @@
|
|
|
1
|
+
# Byte-compiled / optimized / DLL files
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[cod]
|
|
4
|
+
*$py.class
|
|
5
|
+
|
|
6
|
+
# C extensions
|
|
7
|
+
*.so
|
|
8
|
+
|
|
9
|
+
# Distribution / packaging
|
|
10
|
+
.Python
|
|
11
|
+
build/
|
|
12
|
+
develop-eggs/
|
|
13
|
+
dist/
|
|
14
|
+
downloads/
|
|
15
|
+
eggs/
|
|
16
|
+
.eggs/
|
|
17
|
+
lib/
|
|
18
|
+
lib64/
|
|
19
|
+
parts/
|
|
20
|
+
sdist/
|
|
21
|
+
var/
|
|
22
|
+
wheels/
|
|
23
|
+
share/python-wheels/
|
|
24
|
+
*.egg-info/
|
|
25
|
+
.installed.cfg
|
|
26
|
+
*.egg
|
|
27
|
+
MANIFEST
|
|
28
|
+
|
|
29
|
+
# PyInstaller
|
|
30
|
+
# Usually these files are written by a python script from a template
|
|
31
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
32
|
+
*.manifest
|
|
33
|
+
*.spec
|
|
34
|
+
|
|
35
|
+
# Installer logs
|
|
36
|
+
pip-log.txt
|
|
37
|
+
pip-delete-this-directory.txt
|
|
38
|
+
|
|
39
|
+
# Unit test / coverage reports
|
|
40
|
+
htmlcov/
|
|
41
|
+
.tox/
|
|
42
|
+
.nox/
|
|
43
|
+
.coverage
|
|
44
|
+
.coverage.*
|
|
45
|
+
.cache
|
|
46
|
+
nosetests.xml
|
|
47
|
+
coverage.xml
|
|
48
|
+
*.cover
|
|
49
|
+
*.py,cover
|
|
50
|
+
.hypothesis/
|
|
51
|
+
.pytest_cache/
|
|
52
|
+
cover/
|
|
53
|
+
|
|
54
|
+
# Translations
|
|
55
|
+
*.mo
|
|
56
|
+
*.pot
|
|
57
|
+
|
|
58
|
+
# Django stuff:
|
|
59
|
+
*.log
|
|
60
|
+
local_settings.py
|
|
61
|
+
db.sqlite3
|
|
62
|
+
db.sqlite3-journal
|
|
63
|
+
|
|
64
|
+
# Flask stuff:
|
|
65
|
+
instance/
|
|
66
|
+
.webassets-cache
|
|
67
|
+
|
|
68
|
+
# Scrapy stuff:
|
|
69
|
+
.scrapy
|
|
70
|
+
|
|
71
|
+
# Sphinx documentation
|
|
72
|
+
docs/_build/
|
|
73
|
+
|
|
74
|
+
# PyBuilder
|
|
75
|
+
.pybuilder/
|
|
76
|
+
target/
|
|
77
|
+
|
|
78
|
+
# Jupyter Notebook
|
|
79
|
+
.ipynb_checkpoints
|
|
80
|
+
|
|
81
|
+
# IPython
|
|
82
|
+
profile_default/
|
|
83
|
+
ipython_config.py
|
|
84
|
+
|
|
85
|
+
# pyenv
|
|
86
|
+
# For a library or package, you might want to ignore these files since the code is
|
|
87
|
+
# intended to run in multiple environments; otherwise, check them in:
|
|
88
|
+
# .python-version
|
|
89
|
+
|
|
90
|
+
# pipenv
|
|
91
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
92
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
93
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
94
|
+
# install all needed dependencies.
|
|
95
|
+
#Pipfile.lock
|
|
96
|
+
|
|
97
|
+
# UV
|
|
98
|
+
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
|
99
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
100
|
+
# commonly ignored for libraries.
|
|
101
|
+
#uv.lock
|
|
102
|
+
|
|
103
|
+
# poetry
|
|
104
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
105
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
106
|
+
# commonly ignored for libraries.
|
|
107
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
108
|
+
#poetry.lock
|
|
109
|
+
|
|
110
|
+
# pdm
|
|
111
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
112
|
+
#pdm.lock
|
|
113
|
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
|
114
|
+
# in version control.
|
|
115
|
+
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
|
116
|
+
.pdm.toml
|
|
117
|
+
.pdm-python
|
|
118
|
+
.pdm-build/
|
|
119
|
+
|
|
120
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
121
|
+
__pypackages__/
|
|
122
|
+
|
|
123
|
+
# Celery stuff
|
|
124
|
+
celerybeat-schedule
|
|
125
|
+
celerybeat.pid
|
|
126
|
+
|
|
127
|
+
# SageMath parsed files
|
|
128
|
+
*.sage.py
|
|
129
|
+
|
|
130
|
+
# Environments
|
|
131
|
+
.env
|
|
132
|
+
.venv
|
|
133
|
+
env/
|
|
134
|
+
venv/
|
|
135
|
+
ENV/
|
|
136
|
+
env.bak/
|
|
137
|
+
venv.bak/
|
|
138
|
+
|
|
139
|
+
# Spyder project settings
|
|
140
|
+
.spyderproject
|
|
141
|
+
.spyproject
|
|
142
|
+
|
|
143
|
+
# Rope project settings
|
|
144
|
+
.ropeproject
|
|
145
|
+
|
|
146
|
+
# mkdocs documentation
|
|
147
|
+
/site
|
|
148
|
+
|
|
149
|
+
# mypy
|
|
150
|
+
.mypy_cache/
|
|
151
|
+
.dmypy.json
|
|
152
|
+
dmypy.json
|
|
153
|
+
|
|
154
|
+
# Pyre type checker
|
|
155
|
+
.pyre/
|
|
156
|
+
|
|
157
|
+
# pytype static type analyzer
|
|
158
|
+
.pytype/
|
|
159
|
+
|
|
160
|
+
# Cython debug symbols
|
|
161
|
+
cython_debug/
|
|
162
|
+
|
|
163
|
+
# PyCharm
|
|
164
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
165
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
166
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
167
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
168
|
+
#.idea/
|
|
169
|
+
|
|
170
|
+
# Ruff stuff:
|
|
171
|
+
.ruff_cache/
|
|
172
|
+
|
|
173
|
+
# PyPI configuration file
|
|
174
|
+
.pypirc
|
|
175
|
+
|
|
176
|
+
# Cursor
|
|
177
|
+
# Cursor is an AI-powered code editor.`.cursorignore` specifies files/directories to
|
|
178
|
+
# exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
|
|
179
|
+
# refer to https://docs.cursor.com/context/ignore-files
|
|
180
|
+
.cursorignore
|
|
181
|
+
.cursorindexingignore
|
|
182
|
+
# Project scratch
|
|
183
|
+
DONE.md
|
|
184
|
+
TODO.md
|
typespark-1.1.0/LICENSE
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
MIT License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2025 eageby
|
|
4
|
+
|
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
7
|
+
in the Software without restriction, including without limitation the rights
|
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
10
|
+
furnished to do so, subject to the following conditions:
|
|
11
|
+
|
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
|
13
|
+
copies or substantial portions of the Software.
|
|
14
|
+
|
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
21
|
+
SOFTWARE.
|
typespark-1.1.0/PKG-INFO
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
Metadata-Version: 2.5
|
|
2
|
+
Name: typespark
|
|
3
|
+
Version: 1.1.0
|
|
4
|
+
Summary: Static typing for PySpark DataFrames
|
|
5
|
+
Project-URL: Repository, https://github.com/eageby/typespark
|
|
6
|
+
Project-URL: Issues, https://github.com/eageby/typespark/issues
|
|
7
|
+
Author-email: Elias Ågeby <elias.ageby@gmail.com>
|
|
8
|
+
License-Expression: MIT
|
|
9
|
+
License-File: LICENSE
|
|
10
|
+
Keywords: dataframe,pyspark,schema,spark,type-safety,typing
|
|
11
|
+
Classifier: Development Status :: 5 - Production/Stable
|
|
12
|
+
Classifier: Intended Audience :: Developers
|
|
13
|
+
Classifier: Operating System :: OS Independent
|
|
14
|
+
Classifier: Programming Language :: Python :: 3
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
17
|
+
Classifier: Topic :: Database
|
|
18
|
+
Classifier: Topic :: Software Development :: Libraries
|
|
19
|
+
Classifier: Typing :: Typed
|
|
20
|
+
Requires-Python: <4,>=3.12
|
|
21
|
+
Requires-Dist: attrs<26,>=25.1.0
|
|
22
|
+
Requires-Dist: pyyaml<7,>=6.0.2
|
|
23
|
+
Requires-Dist: simple-parsing<0.2,>=0.1.7
|
|
24
|
+
Requires-Dist: typing-extensions>=4.15.0
|
|
25
|
+
Provides-Extra: pyspark
|
|
26
|
+
Requires-Dist: pyspark<4.1,>=3.5.2; extra == 'pyspark'
|
|
27
|
+
Description-Content-Type: text/markdown
|
|
28
|
+
|
|
29
|
+
# Functionality
|
|
30
|
+
|
|
31
|
+
## Statically typed DataFrames
|
|
32
|
+
|
|
33
|
+
## Aliasing
|
|
34
|
+
|
|
35
|
+
- Set alias for dataframe which is used to access the dataframe column
|
|
36
|
+
|
|
37
|
+
## Pyspark Schema generation
|
|
38
|
+
|
|
39
|
+
- provide arguments to data types
|
|
40
|
+
- generate structfields
|
|
41
|
+
- comments as metadata from attribute "docstring" or comment argument in field
|
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
# Functionality
|
|
2
|
+
|
|
3
|
+
## Statically typed DataFrames
|
|
4
|
+
|
|
5
|
+
## Aliasing
|
|
6
|
+
|
|
7
|
+
- Set alias for dataframe which is used to access the dataframe column
|
|
8
|
+
|
|
9
|
+
## Pyspark Schema generation
|
|
10
|
+
|
|
11
|
+
- provide arguments to data types
|
|
12
|
+
- generate structfields
|
|
13
|
+
- comments as metadata from attribute "docstring" or comment argument in field
|
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
[project]
|
|
2
|
+
name = "typespark"
|
|
3
|
+
dynamic = ["version"]
|
|
4
|
+
description = "Static typing for PySpark DataFrames"
|
|
5
|
+
authors = [{ name = "Elias Ågeby", email = "elias.ageby@gmail.com" }]
|
|
6
|
+
requires-python = ">=3.12,<4"
|
|
7
|
+
readme = "README.md"
|
|
8
|
+
license = "MIT"
|
|
9
|
+
license-files = ["LICENSE"]
|
|
10
|
+
keywords = ["pyspark", "spark", "dataframe", "typing", "type-safety", "schema"]
|
|
11
|
+
classifiers = [
|
|
12
|
+
"Development Status :: 5 - Production/Stable",
|
|
13
|
+
"Intended Audience :: Developers",
|
|
14
|
+
"Operating System :: OS Independent",
|
|
15
|
+
"Programming Language :: Python :: 3",
|
|
16
|
+
"Programming Language :: Python :: 3.12",
|
|
17
|
+
"Programming Language :: Python :: 3.13",
|
|
18
|
+
"Topic :: Database",
|
|
19
|
+
"Topic :: Software Development :: Libraries",
|
|
20
|
+
"Typing :: Typed",
|
|
21
|
+
]
|
|
22
|
+
dependencies = [
|
|
23
|
+
"attrs>=25.1.0,<26",
|
|
24
|
+
"pyyaml>=6.0.2,<7",
|
|
25
|
+
"simple-parsing>=0.1.7,<0.2",
|
|
26
|
+
"typing-extensions>=4.15.0",
|
|
27
|
+
]
|
|
28
|
+
|
|
29
|
+
[project.optional-dependencies]
|
|
30
|
+
pyspark = ["pyspark>=3.5.2,<4.1"]
|
|
31
|
+
|
|
32
|
+
[project.urls]
|
|
33
|
+
Repository = "https://github.com/eageby/typespark"
|
|
34
|
+
Issues = "https://github.com/eageby/typespark/issues"
|
|
35
|
+
|
|
36
|
+
[project.scripts]
|
|
37
|
+
typespark = "typespark.data_contract.cli:main"
|
|
38
|
+
|
|
39
|
+
[dependency-groups]
|
|
40
|
+
dev = [
|
|
41
|
+
"mypy>=1.15.0,<2",
|
|
42
|
+
"pytest>=8.3.4,<9",
|
|
43
|
+
"pandas>=2.2.3,<3",
|
|
44
|
+
"pyarrow>=19.0.0,<20",
|
|
45
|
+
"prettyprinter>=0.18.0,<0.19",
|
|
46
|
+
"devtools>=0.12.2,<0.13",
|
|
47
|
+
"pyspark>=3.5.2,<4.1",
|
|
48
|
+
"pyright>=1.1.414",
|
|
49
|
+
]
|
|
50
|
+
datacontract = [
|
|
51
|
+
"black>=25.1.0,<26",
|
|
52
|
+
"simple-parsing>=0.1.7,<0.2",
|
|
53
|
+
"datacontract-specification>=1.2.0,<2",
|
|
54
|
+
"click>=8.2.1,<9",
|
|
55
|
+
]
|
|
56
|
+
|
|
57
|
+
[tool.uv]
|
|
58
|
+
default-groups = [
|
|
59
|
+
"dev",
|
|
60
|
+
"datacontract",
|
|
61
|
+
]
|
|
62
|
+
|
|
63
|
+
[build-system]
|
|
64
|
+
requires = ["hatchling", "hatch-vcs"]
|
|
65
|
+
build-backend = "hatchling.build"
|
|
66
|
+
|
|
67
|
+
[tool.hatch.version]
|
|
68
|
+
source = "vcs"
|
|
69
|
+
|
|
70
|
+
[tool.hatch.build.targets.sdist]
|
|
71
|
+
include = ["typespark", "tests", "README.md", "LICENSE"]
|
|
72
|
+
|
|
73
|
+
[tool.hatch.build.targets.wheel]
|
|
74
|
+
packages = ["typespark"]
|
|
75
|
+
|
|
76
|
+
[tool.pytest.ini_options]
|
|
77
|
+
testpaths = ["tests"]
|
|
File without changes
|
|
@@ -0,0 +1,108 @@
|
|
|
1
|
+
import pytest
|
|
2
|
+
from pyspark.sql import DataFrame, Row, SparkSession, types
|
|
3
|
+
|
|
4
|
+
from typespark import Int, String
|
|
5
|
+
from typespark.dataframe import BaseDataFrame
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
@pytest.fixture(scope="module")
|
|
9
|
+
def spark():
|
|
10
|
+
"""Creates a single Spark session for all tests."""
|
|
11
|
+
session = (
|
|
12
|
+
SparkSession.Builder().master("local").appName("pytest-pyspark").getOrCreate()
|
|
13
|
+
)
|
|
14
|
+
|
|
15
|
+
yield session # Provide the session to tests
|
|
16
|
+
|
|
17
|
+
session.stop() # Cleanup after tests
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
@pytest.fixture(scope="function")
|
|
21
|
+
def dataframe(spark):
|
|
22
|
+
"""Creates a default dataframe."""
|
|
23
|
+
data = [Row(name="Alice", age=30), Row(name="Bob", age=25)]
|
|
24
|
+
|
|
25
|
+
yield spark.createDataFrame(data)
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
@pytest.fixture(scope="function")
|
|
29
|
+
def struct_dataframe(spark):
|
|
30
|
+
"""Creates a default dataframe."""
|
|
31
|
+
data = [
|
|
32
|
+
Row(struct={"name": "Alice", "age": 30}),
|
|
33
|
+
Row(struct={"name": "Bob", "age": 25}),
|
|
34
|
+
]
|
|
35
|
+
|
|
36
|
+
yield spark.createDataFrame(data)
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
@pytest.fixture(scope="function")
|
|
40
|
+
def array_dataframe(spark):
|
|
41
|
+
"""Creates a default dataframe."""
|
|
42
|
+
data = [
|
|
43
|
+
Row(elements=[1, 2]),
|
|
44
|
+
Row(elements=[3, 4]),
|
|
45
|
+
]
|
|
46
|
+
|
|
47
|
+
yield spark.createDataFrame(data)
|
|
48
|
+
|
|
49
|
+
|
|
50
|
+
@pytest.fixture(scope="function")
|
|
51
|
+
def array_struct_dataframe(spark):
|
|
52
|
+
"""Creates a default dataframe."""
|
|
53
|
+
data = [
|
|
54
|
+
Row(
|
|
55
|
+
elements=[
|
|
56
|
+
{"name": "Alice", "age": 30},
|
|
57
|
+
{"name": "Bob", "age": 25},
|
|
58
|
+
]
|
|
59
|
+
)
|
|
60
|
+
]
|
|
61
|
+
|
|
62
|
+
yield spark.createDataFrame(
|
|
63
|
+
data,
|
|
64
|
+
schema=types.StructType(
|
|
65
|
+
[
|
|
66
|
+
types.StructField(
|
|
67
|
+
"elements",
|
|
68
|
+
types.ArrayType(
|
|
69
|
+
types.StructType(
|
|
70
|
+
[
|
|
71
|
+
types.StructField("name", types.StringType()),
|
|
72
|
+
types.StructField("age", types.IntegerType()),
|
|
73
|
+
]
|
|
74
|
+
)
|
|
75
|
+
),
|
|
76
|
+
)
|
|
77
|
+
],
|
|
78
|
+
),
|
|
79
|
+
)
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
class Person(BaseDataFrame):
|
|
83
|
+
name: String
|
|
84
|
+
age: Int
|
|
85
|
+
|
|
86
|
+
|
|
87
|
+
@pytest.fixture(scope="function")
|
|
88
|
+
def person(dataframe: DataFrame):
|
|
89
|
+
yield Person.from_df(dataframe)
|
|
90
|
+
|
|
91
|
+
|
|
92
|
+
class Id(BaseDataFrame):
|
|
93
|
+
value: Int
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
class Range(BaseDataFrame):
|
|
97
|
+
id: Int
|
|
98
|
+
|
|
99
|
+
|
|
100
|
+
@pytest.fixture(scope="function")
|
|
101
|
+
def id(spark: SparkSession):
|
|
102
|
+
yield Id.from_df(spark.createDataFrame([1, 2, 3, 3, 4], "int"))
|
|
103
|
+
|
|
104
|
+
|
|
105
|
+
@pytest.fixture(scope="function")
|
|
106
|
+
def small_range(spark: SparkSession):
|
|
107
|
+
rf = spark.range(3)
|
|
108
|
+
yield Range.from_df(rf.withColumn("id", rf["id"].cast(types.IntegerType())))
|
|
@@ -0,0 +1,252 @@
|
|
|
1
|
+
import warnings
|
|
2
|
+
|
|
3
|
+
import pytest
|
|
4
|
+
from pyspark.sql import Row, functions as F
|
|
5
|
+
from pyspark.sql import types
|
|
6
|
+
from pyspark.sql.types import StringType
|
|
7
|
+
|
|
8
|
+
from tests.utils import collect_values
|
|
9
|
+
from typespark import Integer, String
|
|
10
|
+
from typespark.columns.array import TypedArrayType
|
|
11
|
+
from typespark.columns.struct import Struct
|
|
12
|
+
from typespark.dataframe import BaseDataFrame
|
|
13
|
+
from typespark.metadata import field
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def test_array(array_dataframe):
|
|
17
|
+
class DataClass(BaseDataFrame):
|
|
18
|
+
elements: TypedArrayType[Integer]
|
|
19
|
+
|
|
20
|
+
df = DataClass.from_df(array_dataframe)
|
|
21
|
+
|
|
22
|
+
array_values = collect_values(df.select(df.elements))
|
|
23
|
+
|
|
24
|
+
assert len(array_values) == 2
|
|
25
|
+
assert array_values[0]["elements"] == [1, 2]
|
|
26
|
+
assert array_values[1]["elements"] == [3, 4]
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
def test_array_explode(array_dataframe):
|
|
30
|
+
class DataClass(BaseDataFrame):
|
|
31
|
+
elements: TypedArrayType[Integer]
|
|
32
|
+
|
|
33
|
+
df = DataClass.from_df(array_dataframe)
|
|
34
|
+
|
|
35
|
+
result = df.select(df.elements.explode())
|
|
36
|
+
result_values = collect_values(result)
|
|
37
|
+
|
|
38
|
+
assert len(result_values) == 4
|
|
39
|
+
assert result_values[0]["elements"] == 1
|
|
40
|
+
assert result_values[1]["elements"] == 2
|
|
41
|
+
assert result_values[2]["elements"] == 3
|
|
42
|
+
assert result_values[3]["elements"] == 4
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
def test_array_struct(array_struct_dataframe):
|
|
46
|
+
class Nested(Struct):
|
|
47
|
+
name_: String = field(df_alias="name")
|
|
48
|
+
age: Integer
|
|
49
|
+
|
|
50
|
+
class DataClass(BaseDataFrame):
|
|
51
|
+
elements: TypedArrayType[Nested]
|
|
52
|
+
|
|
53
|
+
df = DataClass.from_df(array_struct_dataframe)
|
|
54
|
+
|
|
55
|
+
structs = df.elements.explode()
|
|
56
|
+
|
|
57
|
+
struct_values = collect_values(df.select(structs.age))
|
|
58
|
+
|
|
59
|
+
assert struct_values[0]["elements.age"] == 30
|
|
60
|
+
assert struct_values[1]["elements.age"] == 25
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
def test_array_struct_multiple(array_struct_dataframe):
|
|
64
|
+
class Nested(Struct):
|
|
65
|
+
name_: String = field(df_alias="name")
|
|
66
|
+
age: Integer
|
|
67
|
+
|
|
68
|
+
class DataClass(BaseDataFrame):
|
|
69
|
+
elements: TypedArrayType[Nested]
|
|
70
|
+
|
|
71
|
+
df = DataClass.from_df(array_struct_dataframe)
|
|
72
|
+
|
|
73
|
+
nested = df.elements.explode()
|
|
74
|
+
struct_values = collect_values(df.select(nested.age, nested.name_))
|
|
75
|
+
|
|
76
|
+
assert struct_values[0]["elements.age"] == 30
|
|
77
|
+
assert struct_values[0]["elements.name"] == "Alice"
|
|
78
|
+
assert struct_values[1]["elements.age"] == 25
|
|
79
|
+
assert struct_values[1]["elements.name"] == "Bob"
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
def test_array_struct_to_new(array_struct_dataframe):
|
|
83
|
+
class Nested(Struct):
|
|
84
|
+
name_: String = field(df_alias="name")
|
|
85
|
+
age: Integer
|
|
86
|
+
|
|
87
|
+
class New(BaseDataFrame):
|
|
88
|
+
n: String = field(df_alias="name")
|
|
89
|
+
age: Integer
|
|
90
|
+
|
|
91
|
+
class DataClass(BaseDataFrame):
|
|
92
|
+
elements: TypedArrayType[Nested]
|
|
93
|
+
|
|
94
|
+
df = DataClass.from_df(array_struct_dataframe)
|
|
95
|
+
|
|
96
|
+
nested = df.elements.explode()
|
|
97
|
+
|
|
98
|
+
result = New(df, n=nested.name_, age=nested.age)
|
|
99
|
+
result_values = collect_values(result)
|
|
100
|
+
|
|
101
|
+
assert result_values[0]["name"] == "Alice"
|
|
102
|
+
assert result_values[0]["age"] == 30
|
|
103
|
+
assert result_values[1]["name"] == "Bob"
|
|
104
|
+
assert result_values[1]["age"] == 25
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
def test_array_struct_to_new_with_cast(array_struct_dataframe):
|
|
108
|
+
class Nested(Struct):
|
|
109
|
+
name_: String = field(df_alias="name")
|
|
110
|
+
age: Integer
|
|
111
|
+
|
|
112
|
+
class New(BaseDataFrame):
|
|
113
|
+
n: String = field(df_alias="name")
|
|
114
|
+
age: String
|
|
115
|
+
|
|
116
|
+
class DataClass(BaseDataFrame):
|
|
117
|
+
elements: TypedArrayType[Nested]
|
|
118
|
+
|
|
119
|
+
df = DataClass.from_df(array_struct_dataframe)
|
|
120
|
+
|
|
121
|
+
nested = df.elements.explode()
|
|
122
|
+
|
|
123
|
+
result = New(df, n=nested.name_, age=nested.age.cast(StringType()))
|
|
124
|
+
|
|
125
|
+
result_values = collect_values(result)
|
|
126
|
+
|
|
127
|
+
assert result_values[0]["name"] == "Alice"
|
|
128
|
+
assert result_values[0]["age"] == "30" # After casting
|
|
129
|
+
assert result_values[1]["name"] == "Bob"
|
|
130
|
+
assert result_values[1]["age"] == "25" # After casting
|
|
131
|
+
|
|
132
|
+
|
|
133
|
+
@pytest.fixture(scope="function")
|
|
134
|
+
def id_array_struct_dataframe(spark):
|
|
135
|
+
"""A scalar column alongside an array of structs, for mixed selects."""
|
|
136
|
+
schema = types.StructType(
|
|
137
|
+
[
|
|
138
|
+
types.StructField("id", types.IntegerType()),
|
|
139
|
+
types.StructField(
|
|
140
|
+
"elements",
|
|
141
|
+
types.ArrayType(
|
|
142
|
+
types.StructType(
|
|
143
|
+
[
|
|
144
|
+
types.StructField("name", types.StringType()),
|
|
145
|
+
types.StructField("age", types.IntegerType()),
|
|
146
|
+
]
|
|
147
|
+
)
|
|
148
|
+
),
|
|
149
|
+
),
|
|
150
|
+
]
|
|
151
|
+
)
|
|
152
|
+
|
|
153
|
+
data = [
|
|
154
|
+
Row(
|
|
155
|
+
id=1,
|
|
156
|
+
elements=[
|
|
157
|
+
{"name": "Alice", "age": 30},
|
|
158
|
+
{"name": "Bob", "age": 25},
|
|
159
|
+
],
|
|
160
|
+
)
|
|
161
|
+
]
|
|
162
|
+
|
|
163
|
+
yield spark.createDataFrame(data, schema=schema)
|
|
164
|
+
|
|
165
|
+
|
|
166
|
+
class _Nested(Struct):
|
|
167
|
+
name: String
|
|
168
|
+
age: Integer
|
|
169
|
+
|
|
170
|
+
|
|
171
|
+
class _IdArray(BaseDataFrame):
|
|
172
|
+
id: Integer
|
|
173
|
+
elements: TypedArrayType[_Nested]
|
|
174
|
+
|
|
175
|
+
|
|
176
|
+
def test_generator_with_plain_column(id_array_struct_dataframe):
|
|
177
|
+
"""Generator column selected alongside an ordinary typed column."""
|
|
178
|
+
df = _IdArray.from_df(id_array_struct_dataframe)
|
|
179
|
+
nested = df.elements.explode()
|
|
180
|
+
|
|
181
|
+
values = collect_values(df.select(nested.age, df.id))
|
|
182
|
+
|
|
183
|
+
assert [v["elements.age"] for v in values] == [30, 25]
|
|
184
|
+
assert [v["id"] for v in values] == [1, 1]
|
|
185
|
+
|
|
186
|
+
|
|
187
|
+
def test_generator_with_calculated_column(id_array_struct_dataframe):
|
|
188
|
+
"""Generator column alongside an aliased calculated column."""
|
|
189
|
+
df = _IdArray.from_df(id_array_struct_dataframe)
|
|
190
|
+
nested = df.elements.explode()
|
|
191
|
+
|
|
192
|
+
values = collect_values(df.select(nested.age, (df.id + 1).alias("id_plus")))
|
|
193
|
+
|
|
194
|
+
assert [v["elements.age"] for v in values] == [30, 25]
|
|
195
|
+
assert [v["id_plus"] for v in values] == [2, 2]
|
|
196
|
+
|
|
197
|
+
|
|
198
|
+
def test_generator_with_unaliased_calculated_column(id_array_struct_dataframe):
|
|
199
|
+
"""Generator column alongside a calculated column with no explicit alias."""
|
|
200
|
+
df = _IdArray.from_df(id_array_struct_dataframe)
|
|
201
|
+
nested = df.elements.explode()
|
|
202
|
+
|
|
203
|
+
result = df.select(nested.age, df.id + 1)
|
|
204
|
+
values = collect_values(result)
|
|
205
|
+
|
|
206
|
+
assert [v["elements.age"] for v in values] == [30, 25]
|
|
207
|
+
calc_name = [c for c in result.to_spark().columns if c != "elements.age"][0]
|
|
208
|
+
assert [v[calc_name] for v in values] == [2, 2]
|
|
209
|
+
|
|
210
|
+
|
|
211
|
+
def test_calculation_on_generator_column(id_array_struct_dataframe):
|
|
212
|
+
"""Arithmetic applied to the generator-derived column itself."""
|
|
213
|
+
df = _IdArray.from_df(id_array_struct_dataframe)
|
|
214
|
+
nested = df.elements.explode()
|
|
215
|
+
|
|
216
|
+
values = collect_values(df.select((nested.age + 1).alias("age_plus")))
|
|
217
|
+
|
|
218
|
+
assert [v["age_plus"] for v in values] == [31, 26]
|
|
219
|
+
|
|
220
|
+
|
|
221
|
+
def test_bare_generator_with_plain_column(id_array_struct_dataframe):
|
|
222
|
+
"""Bare generator (no DeferredColumn access) alongside another column."""
|
|
223
|
+
df = _IdArray.from_df(id_array_struct_dataframe)
|
|
224
|
+
|
|
225
|
+
values = collect_values(df.select(df.elements.explode(), df.id))
|
|
226
|
+
|
|
227
|
+
assert [v["elements"] for v in values] == [
|
|
228
|
+
Row(name="Alice", age=30),
|
|
229
|
+
Row(name="Bob", age=25),
|
|
230
|
+
]
|
|
231
|
+
assert [v["id"] for v in values] == [1, 1]
|
|
232
|
+
|
|
233
|
+
|
|
234
|
+
def test_generator_column_comparison(id_array_struct_dataframe):
|
|
235
|
+
"""Comparison on a generator column yields a usable boolean projection."""
|
|
236
|
+
df = _IdArray.from_df(id_array_struct_dataframe)
|
|
237
|
+
nested = df.elements.explode()
|
|
238
|
+
|
|
239
|
+
values = collect_values(df.select((nested.age > 26).alias("is_older")))
|
|
240
|
+
|
|
241
|
+
assert [v["is_older"] for v in values] == [True, False]
|
|
242
|
+
|
|
243
|
+
|
|
244
|
+
def test_bare_typed_array_type_no_error(spark):
|
|
245
|
+
"""Regression: bare TypedArrayType(col) must not raise AttributeError."""
|
|
246
|
+
col = F.array(F.lit(1), F.lit(2))
|
|
247
|
+
with warnings.catch_warnings(record=True) as w:
|
|
248
|
+
warnings.simplefilter("always")
|
|
249
|
+
instance = TypedArrayType(col)
|
|
250
|
+
assert instance is not None
|
|
251
|
+
assert any(issubclass(warning.category, UserWarning) for warning in w), \
|
|
252
|
+
"Expected a UserWarning when constructing bare TypedArrayType"
|