cnvkit/pyproject.toml at master · etal/cnvkit · 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
[project]
name = "CNVkit"
description = "Copy number variation toolkit for high-throughput sequencing."
readme = "README.rst"
#license = "Apache-2.0"
license = {"text" = "Apache-2.0"}
authors = [
  {name = "Eric Talevich", email = "me+code@etal.mozmail.com"}
]
maintainers = [
  {name = "Eric Talevich", email = "me+code@etal.mozmail.com"}
]
classifiers = [
  "Development Status :: 4 - Beta",
  "Environment :: Console",
  "Intended Audience :: Science/Research",
  "Intended Audience :: Healthcare Industry",
  "Operating System :: MacOS :: MacOS X",
  "Operating System :: POSIX",
  "Operating System :: POSIX :: Linux",
  "Operating System :: Unix",
  "Programming Language :: Python",
  "Programming Language :: Python :: 3",
  "Topic :: Scientific/Engineering",
  "Topic :: Scientific/Engineering :: Bio-Informatics",
  "Topic :: Scientific/Engineering :: Medical Science Apps.",
  "Topic :: Scientific/Engineering :: Visualization"
]
requires-python = ">=3.10"
dynamic = ["version", "dependencies", "optional-dependencies"]

[project.urls]
homepage = "https://github.com/etal/cnvkit"
documentation = "https://cnvkit.readthedocs.io"
repository = "https://github.com/etal/cnvkit"
changelog = "https://github.com/etal/cnvkit/releases"

[project.scripts]
"cnvkit.py" = "cnvlib.cnvkit:main"
"cnv_annotate.py" = "cnvlib.cli.cnv_annotate:main"
"cnv_expression_correlate.py" = "cnvlib.cli.cnv_expression_correlate:main"
"cnv_updater.py" = "cnvlib.cli.cnv_updater:main"
"genome_instability_index.py" = "cnvlib.cli.genome_instability_index:main"
"guess_baits.py" = "cnvlib.cli.guess_baits:main"
"reference2targets.py" = "cnvlib.cli.reference2targets:main"
"skg_convert.py" = "skgenome.cli.skg_convert:main"
# XXX TODO -- figure out whether this script should and could be included
# in the installation
#"snpfilter.sh" = "scripts/snpfilter.sh"

[build-system]
# Minimum requirements for the build system to execute (PEP 508)
requires = ["setuptools"]
build-backend = "setuptools.build_meta"

[tool.setuptools]
packages = ["cnvlib", "cnvlib.cli", "cnvlib.segmentation", "skgenome", "skgenome.cli", "skgenome.tabio"]

[tool.setuptools.dynamic]
version = {attr = "cnvlib._version.__version__"}
dependencies = {file = "requirements/core.txt"}
optional-dependencies = {test = {file = "requirements/tests.txt"}}

[tool.pytest.ini_options]
testpaths = ["test"]
markers = [
    "slow: tests that take >5 seconds (skip with -m 'not slow')",
    "hypothesis: property-based tests using Hypothesis (skip with -m 'not hypothesis')",
]
filterwarnings = [
    "error",
    # bioframe <=0.8.0 uses df.groupby(['col']).groups with a single-element
    # list, which pandas 3.0 deprecates via Pandas4Warning.
    "ignore:In a future version, the keys of:Warning",
    # Hypothesis internal warnings that would otherwise be promoted to errors
    "ignore::hypothesis.errors.NonInteractiveExampleWarning",
]

[tool.coverage.run]
branch = true
source = ["cnvlib", "skgenome"]

[tool.coverage.paths]
source = ["cnvlib", "skgenome"]

[tool.coverage.report]
precision = 2
show_missing = true
skip_covered = false
exclude_lines = [
    "pragma: no cover",
    "raise NotImplementedError",
    "if __name__ == .__main__.:",
    "if TYPE_CHECKING:",
    "@abstractmethod",
]

[tool.coverage.html]
directory = "htmlcov"

[tool.ruff]
target-version = "py310"
line-length = 88

[tool.ruff.lint]
select = [
    "E",  # pycodestyle errors
    "W",  # pycodestyle warnings
    "F",  # pyflakes
    "UP", # pyupgrade
    "B",  # flake8-bugbear
    "NPY", # numpy rules
    "PD", # pandas-vet
    "RUF", # ruff's extra rules
    "TC", # flake8-type-checking
    #"SIM", # flake8-simplify
    #"ANN", # flake8-annotations
]
ignore = [
    "E402",  # import not at top
    "E501",  # line too long
    "E731",  # inline lambda
    "F401",  # unused import
    "F841",  # unused variable
    "UP031", # % format
    "UP032", # format call vs. f-string
    "B007",  # loop variable not used in body
    "B023",  # def closing over loop variable
    "PD009", # use .iloc instead of .iat (iat is actually faster for scalar access)
    "PD901", # avoid generic variable name 'df' (acceptable in scientific code)
    "RUF100", # unneeded noqa
    #"SIM108", # ternary if-else
    #"SIM401", # use dict.get
]

[tool.ruff.format]
quote-style = "double"
indent-style = "space"

[tool.mypy]
python_version = "3.10"
packages = ["cnvlib", "skgenome"]
ignore_missing_imports = true
check_untyped_defs = true
warn_no_return = true
warn_return_any = true
warn_unused_configs = true
warn_unreachable = true
enable_error_code = ["ignore-without-code"]

[tool.bandit]
# Skip security rules inappropriate for bioinformatics toolkit that needs to call external tools
skips = [
    "B404",  # subprocess module - needed for calling bioinformatics tools like samtools, R
    "B603",  # subprocess without shell=True - this is actually good security practice
    "B607",  # partial executable path - standard practice for bioinformatics pipelines
]