-
-
Notifications
You must be signed in to change notification settings - Fork 994
/
pyproject.toml
157 lines (138 loc) · 4.07 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
# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
[build-system]
requires = ["hatchling", "hatch-vcs"]
build-backend = "hatchling.build"
[project]
name = "ocrmypdf"
dynamic = ["version"]
description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
readme = "README.md"
license = { text = "MPL-2.0" }
requires-python = ">=3.10"
dependencies = [
"deprecation>=2.1.0",
"img2pdf>=0.5",
"packaging>=20",
"pdfminer.six>=20220319",
"pi-heif", # Heif image format - maintainers: if this is removed, it will NOT break
"pikepdf>=8.10.1",
"Pillow>=10.0.1",
"pluggy>=1",
"rich>=13",
]
authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]
classifiers = [
"Development Status :: 5 - Production/Stable",
"Environment :: Console",
"Intended Audience :: End Users/Desktop",
"Intended Audience :: Science/Research",
"Intended Audience :: System Administrators",
"License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
"Operating System :: MacOS",
"Operating System :: Microsoft :: Windows",
"Operating System :: POSIX",
"Operating System :: POSIX :: BSD",
"Operating System :: POSIX :: Linux",
"Programming Language :: Python :: 3",
"Topic :: Scientific/Engineering :: Image Recognition",
"Topic :: Text Processing :: Indexing",
"Topic :: Text Processing :: Linguistic",
]
keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
[project.urls]
Documentation = "https://ocrmypdf.readthedocs.io/"
Source = "https://github.com/ocrmypdf/OCRmyPDF"
Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
Changelog = "https://github.com/ocrmypdf/OCRmyPDF/docs/release_notes.rst"
[project.optional-dependencies]
docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
extended_test = ["PyMuPDF>=1.19.1"]
test = [
"coverage[toml]>=6.2",
"hypothesis>=6.36.0",
"pytest>=6.2.5",
"pytest-cov>=3.0.0",
"pytest-xdist>=2.5.0",
"python-xmp-toolkit==2.0.1", # also requires apt-get install libexempi3
"reportlab>=3.6.8",
"types-Pillow",
"types-humanfriendly",
]
watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
webservice = ["Flask>=2.0.1"]
[project.scripts]
ocrmypdf = "ocrmypdf.__main__:run"
[tool.hatch.version]
source = "vcs"
[tool.hatch.build.hooks.vcs]
version-file = "src/ocrmypdf/_version.py"
[tool.distutils.bdist_wheel]
python-tag = "py310"
[tool.coverage.run]
branch = true
parallel = true
concurrency = ["multiprocessing", "thread"]
sigterm = true
[tool.coverage.paths]
source = ["src/ocrmypdf"]
[tool.coverage.report]
# Regexes for lines to exclude from consideration
exclude_lines = [
# Have to re-enable the standard pragma
"pragma: no cover",
# Don't complain if tests don't hit defensive assertion code:
"raise AssertionError",
"raise NotImplementedError",
# Don't complain if non-runnable code isn't run:
"if 0:",
"if False:",
"if __name__ == .__main__.:",
"if TYPE_CHECKING:",
]
[tool.pytest.ini_options]
minversion = "6.0"
norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
testpaths = ["tests"]
addopts = "-n auto"
markers = ["slow"]
filterwarnings = [
"ignore:.*XMLParser.*:DeprecationWarning",
"ignore:.*ast.NameConstant.*:DeprecationWarning:reportlab",
"ignore:.*distutils.*:DeprecationWarning:libxmp",
]
[tool.mypy]
[[tool.mypy.overrides]]
module = [
'pluggy',
'tqdm',
'coloredlogs',
'img2pdf',
'pdfminer.*',
'reportlab.*',
'fitz',
'libxmp.utils',
]
ignore_missing_imports = true
[tool.ruff]
target-version = "py310"
[tool.ruff.lint]
"select" = [
"D", # pydocstyle
"E", # pycodestyle
"W", # pycodestyle
"F", # pyflakes
"I001", # isort
"UP", # pyupgrade
]
[tool.ruff.lint.isort]
known-first-party = ["ocrmypdf"]
[tool.ruff.lint.pydocstyle]
convention = "google"
[tool.ruff.lint.per-file-ignores]
"docs/conf.py" = ["D100", "D101", "D105"]
"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
"misc/*.py" = ["D103", "D101", "D102"]
"src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]
[tool.ruff.format]
quote-style = "preserve"