excel-parser/pyproject.toml at main · knowledgestack/excel-parser · 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
[build-system]
requires = ["setuptools>=68.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "ks-xlsx-parser"
version = "0.2.1"
description = "Production-grade Excel Workflow Parser for RAG + auditability systems"
readme = "README.md"
license = {text = "MIT"}
requires-python = ">=3.10"
authors = [
    {name = "XLSX Parser Contributors"}
]
keywords = [
    "excel",
    "xlsx",
    "parser",
    "rag",
    "workbook",
    "spreadsheet",
    "extraction",
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Office/Business :: Financial :: Spreadsheet",
]
dependencies = [
    "openpyxl>=3.1.0",
    "pydantic>=2.0",
    "lxml>=4.9.0",
    "xxhash>=3.0.0",
    "tiktoken>=0.5.0",
]

[project.urls]
Homepage = "https://github.com/knowledgestack/ks-xlsx-parser"
Repository = "https://github.com/knowledgestack/ks-xlsx-parser"
Documentation = "https://github.com/knowledgestack/ks-xlsx-parser#readme"

[project.scripts]
xlsx-parser-api = "ks_xlsx_parser.api:main"

[project.optional-dependencies]
api = [
    "fastapi>=0.100.0",
    "uvicorn[standard]>=0.20.0",
    "python-multipart>=0.0.6",
]
dev = [
    "pytest>=7.0",
    "pytest-cov>=4.0",
    "pytest-xdist>=3.0",
    "pytest-timeout>=2.2.0",
    "python-calamine>=0.2.0",
    "requests>=2.28.0",
    "ruff>=0.6.0",
    "mypy>=1.0",
]
# Retrieval-recall benchmark (scripts/eval_retrieval.py). Heavy — only the
# benchmark Docker image and `make bench-retrieval` need these.
bench = [
    "sentence-transformers>=2.2.0",
    "numpy>=1.24.0",
]

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
markers = [
    "crossval: cross-validation tests against calamine",
    "invariant: structural invariant tests",
    "corpus: external corpus tests (skipped by default)",
    "slow: tests taking >10 seconds",
]
addopts = "-m 'not corpus'"

[tool.setuptools.packages.find]
where = ["src"]
include = ["ks_xlsx_parser*"]

[tool.setuptools.package-data]
ks_xlsx_parser = ["py.typed"]

[tool.ruff]
line-length = 110
target-version = "py310"
extend-exclude = ["examples/stress_test", "dist", "build"]

[tool.ruff.lint]
select = [
    "E",   # pycodestyle errors
    "F",   # pyflakes
    "I",   # isort
    "B",   # flake8-bugbear
    "UP",  # pyupgrade
    "SIM", # flake8-simplify
]
ignore = [
    "E501",   # line length handled by formatter
    "B008",   # function call in default arg (FastAPI pattern)
    "SIM105", # try/except/pass — often clearer than contextlib.suppress at call sites
    "B007",   # unused loop control variable (fine in generators)
]

[tool.ruff.lint.per-file-ignores]
"tests/**" = ["B011", "B017"]
"scripts/**" = ["B008"]