valentine/pyproject.toml at master · delftdata/valentine · GitHub

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
[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"

[project]
name = "valentine"
version = "1.0.0.dev0"
description = "Valentine: find relationships between columns of different tabular datasets"
readme = "README.md"
authors = [
    { name = "Delft Data", email = "delftdatasystems@gmail.com" }
]
maintainers = [
    { name = "Delft Data", email = "delftdatasystems@gmail.com" }
]
license = { file = "LICENSE" }
keywords = ["matching", "valentine", "schema matching", "dataset discovery", "coma", "cupid", "similarity flooding"]

classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "License :: OSI Approved :: Apache Software License",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3.14",
    "Operating System :: POSIX",
    "Operating System :: MacOS :: MacOS X",
    "Operating System :: Microsoft :: Windows",
]

requires-python = ">=3.10,<3.15"
dependencies = [
    "numpy>=2.0,<3.0",
    "pandas>=2.0,<4.0",
    "nltk>=3.9.4,<4.0",
    "anytree>=2.9,<3.0",
    "networkx>=2.8,<4.0",
    "chardet>=7.0,<8.0",
    "rapidfuzz>=3.0,<4.0",
    "PuLP>=2.5,<4.0",
    "POT>=0.9.5,<1.0",
    "scipy>=1.12,<2.0",
    "python-dateutil>=2.8,<3.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=9.0,<10.0",
    "coverage>=7.0,<8.0",
    "ruff>=0.15,<1.0",
]
polars = [
    "polars>=1.0,<2.0",
]
docs = [
    # Pinned intentionally: Zensical is pre-1.0 and moves fast. Bump
    # deliberately rather than relying on a range, so a bad release
    # can't silently break the docs build.
    "zensical==0.0.37",
]

[project.urls]
Homepage = "https://delftdata.github.io/valentine/"
Documentation = "https://delftdata.github.io/valentine/"
Source = "https://github.com/delftdata/valentine"
Issues = "https://github.com/delftdata/valentine/issues"
Changelog = "https://github.com/delftdata/valentine/releases"

[tool.setuptools]
packages = { find = { include = ["valentine*"], exclude = ["tests*", "examples*", "docs*", "experiments*"] } }
include-package-data = true
license-files = ["LICENSE"]


[tool.ruff]
target-version = "py310"
line-length = 100
indent-width = 4

exclude = [
    ".git",
    ".venv",
    "build",
    "dist",
    "__pycache__",
    "docs",
    "site",
]

[tool.ruff.lint]
select = [
    # Core
    "E", "W", "F",

    # Imports
    "I",

    # Bug detection
    "B",        # bugbear
    "RUF",      # Ruff-native

    # Code quality
    "C4",       # comprehensions
    "SIM",      # simplifications
    "RET",      # returns
    "ARG",      # unused args

    # Modern Python
    "UP",

    # Pathlib over os
    "PTH",

    # Pylint-like (strictness boost)
    "PL",

    # Exception handling
    "TRY",

    # Performance
    "PERF",

    #Numpy
    "NPY",

    # dateutil
    "DTZ",
]


ignore = [
    # Style tradeoffs
    "E501",    # line length handled by formatter
    "SIM108",  # ternary suggestions can hurt readability

    # Practicality for algorithms / research code
    "PLR0913", # too many arguments (common in matching algorithms)
    "PLR2004", # magic values (similarity thresholds, etc.)
    "PLR0915", # too many statements (complex pipelines)

    # Readability tradeoffs
    "RET504",  # unnecessary assignment before return
    "RET505",  # else-after-return (sometimes clearer)

    # Allow flexible exception patterns
    "TRY003",  # long exception messages
]

dummy-variable-rgx = "^_.*"

[tool.ruff.lint.per-file-ignores]
"tests/*" = [
    "ARG",      # unused fixtures
    "S101",     # asserts
    "PLR2004",  # magic values
    "PLR0913",  # many args
]

"__init__.py" = [
    "F401",     # re-exports
]

[tool.ruff.lint.isort]
known-first-party = ["valentine"]
combine-as-imports = true

[tool.ruff.format]
quote-style = "double"
indent-style = "space"
line-ending = "auto"
docstring-code-format = true