-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathpyproject.toml
162 lines (144 loc) · 3.7 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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
[build-system]
requires = ["hatchling", "hatch-vcs"]
build-backend = "hatchling.build"
[project]
name = "document-clustering"
version = "0.2.0"
description = 'Clustering documents according to document similarity, with a focus on scientific publications'
readme = "README.md"
requires-python = ">=3.9" # 3.9 Support wird für Neuron gebraucht
license = "MIT"
keywords = []
authors = [
{name = "Leona Gottfried", email = "[email protected]"},
{ name = "Center for Cognition and Computation (CCC) Frankfurt/Main" },
{ name = "Lehrstuhl für Angewandte Computerlinguistik (ACoLi) Augsburg" },
]
classifiers = [
"Development Status :: 4 - Beta",
"Programming Language :: Python",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
]
dependencies = [
"feedparser",
"matplotlib",
"numpy",
"pandas",
"scikit-learn",
"glassplitter @ git+https://github.com/glaserL/glassplitter.git#egg=glassplitter", # WIP
"python-poppler",
"rich",
]
[project.optional-dependencies]
tests = [
"nox",
"pytest",
"pytest-cov",
]
pdf = [
"python-poppler",
]
cli = [
"rich",
"tqdm",
]
[project.urls]
Documentation = "https://github.com/unknown/document-clustering#readme"
Issues = "https://github.com/unknown/document-clustering/issues"
Source = "https://github.com/unknown/document-clustering"
[tool.hatch.build.targets.sdist]
include = [
"src/",
"tests/",
"doc/"
]
[tool.hatch.build.targets.wheel]
packages = ["src/document_clustering"]
[tool.coverage.paths]
document_clustering = ["src/document_clustering", "*/document-clustering/src/document_clustering"]
tests = ["tests", "*/document-clustering/tests"]
[tool.coverage.report]
exclude_lines = [
"no cov",
"if __name__ == .__main__.:",
"if TYPE_CHECKING:",
]
[tool.coverage.run]
source_pkgs = ["document_clustering", "tests"]
branch = true
parallel = true
omit = [
"src/document_clustering/__about__.py",
"tests/*",
]
# [[tool.hatch.envs.all.matrix]]
# python = ["3.9", "3.10", "3.11", "3.12"]
[tool.hatch.envs.default]
dependencies = [
"coverage[toml]>=6.5",
"pytest",
]
[tool.hatch.envs.default.scripts]
test = "pytest {args:tests}"
test-cov = "coverage run -m pytest {args:tests}"
cov-report = [
"- coverage combine",
"coverage report",
]
cov = [
"test-cov",
"cov-report",
]
[tool.hatch.envs.types]
dependencies = [
"mypy>=1.0.0",
]
[tool.hatch.envs.types.scripts]
check = "mypy --install-types --non-interactive {args:src/document_clustering tests}"
[tool.hatch.metadata]
allow-direct-references = true # DEBUG
[tool.pytest.ini_options]
log_cli = true
log_cli_level = "INFO"
log_cli_format = "%(asctime)s [%(levelname)4s] %(message)s (%(filename)s:%(lineno)s)"
log_cli_date_format = "%H:%M:%S"
log_file = "pytest.log"
log_file_level = "DEBUG"
log_file_format = "%(asctime)s [%(levelname)8s] %(message)s (%(filename)s:%(lineno)s)"
log_file_date_format = "%Y-%m-%d %H:%M:%S"
[tool.ruff]
include = ["pyproject.toml", "src/**/*.py", "src/**/*.ipynb"]
[tool.ruff.format]
preview = true
[tool.ruff.lint]
preview = true
ignore = []
extend-select = [
"ARG",
"F",
"C901", # McCabe complexity
"TD",
"ANN",
"D",
"FIX",
]
extend-ignore = [
"EM101", # Fix upstream
"G004", # Logging-f-string
"S403", # While shelve may be insecure, we're not loading arbirtary files
"TRY003",
"D100",
"D104", "TD003", # TODO @leogott: These should be fixed eventually, but are low prio
"ANN202",
"ANN204",
"TCH002", "TCH003", # I don't understand the implications
"RET504",
"UP007", # slight disagree
]
[tool.ruff.lint.extend-per-file-ignores]
"*.ipynb" = ["T2", "ANN", "D"]
[tool.ruff.lint.pydocstyle]
convention = "numpy"