aivanov_CIM/pyproject.toml

[build-system]
requires = ["setuptools>=68.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "pipeline-mco-pmsi-codage"
version = "0.1.0"
description = "Pipeline d'automatisation du codage médical PMSI avec architecture RAG"
readme = "README.md"
requires-python = ">=3.10"
license = {text = "MIT"}
authors = [
    {name = "DIM Team", email = "dim@hospital.fr"}
]
keywords = ["pmsi", "medical-coding", "rag", "llm", "healthcare"]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Healthcare Industry",
    "Topic :: Scientific/Engineering :: Medical Science Apps.",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
]

dependencies = [
    # Core dependencies
    "pydantic>=2.5.0",
    "pydantic-settings>=2.1.0",
    
    # Database
    "sqlalchemy>=2.0.0",
    "alembic>=1.13.0",
    "psycopg2-binary>=2.9.9",  # PostgreSQL driver
    
    # Property-based testing
    "hypothesis>=6.92.0",
    
    # LLM and embeddings
    "langchain>=0.1.0",
    "langchain-community>=0.0.10",
    "sentence-transformers>=2.2.0",
    "transformers>=4.36.0",
    "torch>=2.1.0",
    
    # Vector store and search
    "faiss-cpu>=1.7.4",  # or faiss-gpu for GPU support
    "qdrant-client>=1.7.0",
    
    # Text processing and NLP
    "spacy>=3.7.0",
    "nltk>=3.8.1",
    "regex>=2023.12.0",
    "edsnlp>=0.10.0",  # EDS-NLP for French clinical text processing
    
    # Search and indexing
    "rank-bm25>=0.2.2",
    "whoosh>=2.7.4",
    
    # PDF processing
    "pypdf>=3.17.0",
    "pdfplumber>=0.10.0",
    
    # Excel processing
    "openpyxl>=3.1.0",
    "xlrd>=2.0.0",
    
    # Data validation and serialization
    "python-dateutil>=2.8.2",
    "pytz>=2023.3",
    
    # Cryptography for exports
    "cryptography>=41.0.0",
    
    # Configuration
    "pyyaml>=6.0.1",
    "python-dotenv>=1.0.0",
    
    # Logging and monitoring
    "structlog>=23.2.0",
    "python-json-logger>=2.0.7",
    
    # HTTP client for potential API calls
    "httpx>=0.25.0",
    
    # API framework
    "fastapi>=0.109.0",
    "uvicorn[standard]>=0.27.0",
    "python-multipart>=0.0.6",
    
    # CLI interface
    "click>=8.1.7",
    "rich>=13.7.0",  # For beautiful CLI output
    
    # Utilities
    "tqdm>=4.66.0",
    "tenacity>=8.2.3",  # Retry logic
]

[project.optional-dependencies]
dev = [
    # Testing
    "pytest>=7.4.0",
    "pytest-cov>=4.1.0",
    "pytest-asyncio>=0.21.0",
    "pytest-mock>=3.12.0",
    "pytest-timeout>=2.2.0",
    
    # Code quality
    "black>=23.12.0",
    "isort>=5.13.0",
    "flake8>=7.0.0",
    "mypy>=1.8.0",
    "pylint>=3.0.0",
    
    # Documentation
    "sphinx>=7.2.0",
    "sphinx-rtd-theme>=2.0.0",
    
    # Development tools
    "ipython>=8.18.0",
    "ipdb>=0.13.13",
]

gpu = [
    "faiss-gpu>=1.7.4",
]

[project.scripts]
pipeline-mco = "pipeline_mco_pmsi.cli:main"

[tool.setuptools]
packages = ["pipeline_mco_pmsi"]
package-dir = {"" = "src"}

[tool.pytest.ini_options]
minversion = "7.0"
testpaths = ["tests"]
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
addopts = [
    "-v",
    "--strict-markers",
    "--tb=short",
    "--cov=pipeline_mco_pmsi",
    "--cov-report=term-missing",
    "--cov-report=html",
    "--cov-report=xml",
]
markers = [
    "unit: Unit tests",
    "integration: Integration tests",
    "property: Property-based tests",
    "slow: Slow tests",
    "gpu: Tests requiring GPU",
]
timeout = 300  # 5 minutes default timeout

[tool.coverage.run]
source = ["src"]
omit = [
    "*/tests/*",
    "*/test_*.py",
    "*/__pycache__/*",
    "*/site-packages/*",
]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "raise AssertionError",
    "raise NotImplementedError",
    "if __name__ == .__main__.:",
    "if TYPE_CHECKING:",
    "@abstractmethod",
]

[tool.black]
line-length = 100
target-version = ['py310', 'py311', 'py312']
include = '\.pyi?$'
extend-exclude = '''
/(
  # directories
  \.eggs
  | \.git
  | \.hg
  | \.mypy_cache
  | \.tox
  | \.venv
  | build
  | dist
)/
'''

[tool.isort]
profile = "black"
line_length = 100
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true

[tool.mypy]
python_version = "3.10"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = false
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
follow_imports = "normal"
ignore_missing_imports = true
strict_equality = true

[[tool.mypy.overrides]]
module = "tests.*"
disallow_untyped_defs = false

[tool.pylint.messages_control]
max-line-length = 100
disable = [
    "C0111",  # missing-docstring
    "C0103",  # invalid-name
    "R0903",  # too-few-public-methods
    "R0913",  # too-many-arguments
]

[tool.hypothesis]
# Configuration for Hypothesis property-based testing
max_examples = 100
deadline = 5000  # 5 seconds per test case
derandomize = false
print_blob = true