-
Notifications
You must be signed in to change notification settings - Fork 167
/
Copy pathpyproject.toml
143 lines (127 loc) · 3.4 KB
/
pyproject.toml
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
[tool.poetry]
name = "splink"
version = "3.9.9"
description = "Fast probabilistic data linkage at scale"
authors = ["Robin Linacre <[email protected]>", "Sam Lindsay", "Theodore Manassis", "Tom Hepworth", "Andy Bond", "Ross Kennedy"]
license = "MIT"
homepage = "https://github.com/moj-analytical-services/splink"
repository = "https://github.com/moj-analytical-services/splink"
readme = "README.md"
[tool.poetry.dependencies]
python = ">=3.7.1,<4.0.0"
jsonschema = ">=3.2,<5.0"
# 1.3.5 is the last version supporting py 3.7.1
pandas = ">1.3.0"
duckdb = ">=0.8.0"
sqlglot = ">=13.0.0, <19.0.0"
altair = "^5.0.1"
Jinja2 = ">=3.0.3"
phonetics = "^1.0.5"
# Optional installs
pyspark = {version="^3.2.1", optional=true}
awswrangler = [
{version = "2.18.0,<3.0.0", python = ">=3.7.1,<3.8", optional=true},
{version=">=3.0.0,<4.0.0", python = "^3.8", optional=true}
]
# sqlalchemy >= 2.0.0 not working well with older pandas
sqlalchemy = {version=">=1.4.0,<2.0.0", optional=true}
psycopg2-binary = {version=">=2.8.0", optional=true}
[tool.poetry.group.dev]
[tool.poetry.group.dev.dependencies]
tabulate = "0.8.9"
pyspark = "^3.2.1"
# sqlalchemy >= 2.0.0 not working well with older pandas
sqlalchemy = ">=1.4.0,<2.0.0"
# temporarily use binary version, to avoid issues with pg_config path
psycopg2-binary = ">=2.8.0"
[tool.poetry.group.linting]
[tool.poetry.group.linting.dependencies]
black = "22.6.0"
ruff = "0.0.257"
[tool.poetry.group.testing]
[tool.poetry.group.testing.dependencies]
# pin to reduce dependencies
pytest = "7.3"
pyarrow = ">=7.0.0"
networkx = "2.5.1"
rapidfuzz = "^2.0.3"
[tool.poetry.group.benchmarking]
optional = true
[tool.poetry.group.benchmarking.dependencies]
pytest-benchmark = "^4"
lzstring = "1.0.4"
[tool.poetry.group.typechecking]
optional = true
[tool.poetry.group.typechecking.dependencies]
mypy = "1.7.0"
[tool.poetry.group.demos]
[tool.poetry.group.demos.dependencies]
importlib-resources = "5.4.0"
jupyterlab = "3.6.1"
pyarrow = ">=7.0.0"
ipywidgets = "8.0.4"
nbmake = "1.3.4"
pytest = "^7.0"
pyspark = "^3.2.1"
[tool.poetry.extras]
pyspark = ["pyspark"]
spark = ["pyspark"]
athena = ["awswrangler"]
postgres = ["sqlalchemy", "psycopg2-binary"]
[build-system]
requires = ["poetry-core>=1.0.8"]
build-backend = "poetry.core.masonry.api"
[tool.isort]
profile = "black"
[tool.ruff]
line-length = 88
select = [
# Pyflakes
"F",
# Pycodestyle
"E",
"W",
# isort
"I001",
# bugbear
"B",
# flake8-print
"T20"
]
ignore = [
"B905", # `zip()` without an explicit `strict=` parameter
"B006", # Do not use mutable data structures for argument defaults"
]
[tool.pytest.ini_options]
addopts = ["-m default"]
markers = [
# only tests where backend is irrelevant:
"core",
# see tests/decorator.py::dialect_groups for group details:
"default",
"all",
# backend-specific sets
"duckdb",
"duckdb_only",
"spark",
"spark_only",
"sqlite",
"sqlite_only",
]
[tool.mypy]
packages = "splink"
# temporary exclusions
exclude = [
# modules getting substantial rewrites:
'.*comparison_imports\.py$',
'.*comparison.*library\.py',
'comparison_level_composition',
# modules with large number of errors
'.*linker\.py',
]
# for now at least allow implicit optionals
# to cut down on noise. Easy to fix.
implicit_optional = true
# for now, ignore missing imports
# can remove later and install stubs, where existent
ignore_missing_imports = true