streamflow-analytics/pyproject.toml at main · arthurmgraf/streamflow-analytics · 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
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[project]
name = "streamflow-analytics"
version = "0.1.0"
description = "Real-time streaming data platform for e-commerce fraud detection"
readme = "README.md"
requires-python = ">=3.11"
license = {text = "MIT"}
authors = [
    {name = "Arthur Maia Graf"}
]
keywords = ["streaming", "fraud-detection", "kafka", "flink", "data-engineering"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
]
dependencies = [
    "pydantic>=2.6.0",
    "pyyaml>=6.0",
    "psycopg2-binary>=2.9.9",
    "confluent-kafka>=2.3.0",
]

[project.optional-dependencies]
dev = [
    "pytest>=8.0.0",
    "pytest-cov>=4.0.0",
    "pytest-mock>=3.12.0",
    "ruff>=0.4.0",
    "mypy>=1.9.0",
    "pre-commit>=3.7.0",
    "types-PyYAML>=6.0",
    "types-psycopg2>=2.9",
]
ml = [
    "scikit-learn>=1.4.0",
    "joblib>=1.3.0",
    "numpy>=1.26.0",
]
flink = [
    "apache-flink>=1.20.0",
]
airflow = [
    "apache-airflow>=2.10.0",
    "apache-airflow-providers-postgres>=5.10.0",
    "astronomer-cosmos>=1.5.0",
]
dbt = [
    "dbt-core>=1.7.0",
    "dbt-postgres>=1.7.0",
]

[tool.hatch.build.targets.wheel]
packages = ["src"]

[tool.ruff]
target-version = "py311"
line-length = 100

[tool.ruff.lint]
select = ["E", "F", "I", "UP", "B", "SIM", "N", "RUF"]
ignore = ["E501"]

[tool.ruff.lint.isort]
known-first-party = ["src"]

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = ["test_*.py"]
python_functions = ["test_*"]
addopts = "-v --tb=short"
markers = [
    "e2e: end-to-end tests requiring running K3s cluster",
    "integration: cross-module integration tests (no external services)",
    "contract: schema contract tests (breaking = coordinated update needed)",
]
pythonpath = [".", "src"]

[tool.coverage.run]
source = ["src"]
branch = true
omit = [
    "tests/*",
    "src/dags/*",
    "src/flink_jobs/fraud_pipeline.py",
    "src/flink_jobs/transaction_processor.py",
    "src/generators/kafka_producer.py",
    "src/utils/db.py",
]

[tool.coverage.report]
show_missing = true
fail_under = 80
exclude_lines = [
    "pragma: no cover",
    "if TYPE_CHECKING:",
    "if __name__",
]

[tool.mypy]
python_version = "3.11"
strict = true
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
exclude = ["tests/", "src/dags/"]

[[tool.mypy.overrides]]
module = [
    "confluent_kafka.*",
    "pyflink.*",
    "airflow.*",
    "cosmos.*",
    "sklearn.*",
    "joblib.*",
    "numpy.*",
]
ignore_missing_imports = true