pyproject.toml

# ============================================================================
# AUTOCSV PROFILER SUITE - PROJECT CONFIGURATION
# ============================================================================
# Multi-environment CSV data analysis orchestrator
#
# NOTE: This project is intentionally NON-PACKAGEABLE due to irreconcilable
# dependency conflicts between profiling libraries. See docs/ARCHITECTURE.md
# Dependencies are managed via conda environments in config/master_config.yml
# DISTRIBUTION: Source code and configuration only - users install dependencies

# ----------------------------------------------------------------------------
# Project Metadata
# ----------------------------------------------------------------------------

[project]
name = "autocsv-profiler-suite"
version = "2.0.0"
description = "Source code and configuration for multi-environment CSV data analysis"
authors = [{ name = "dhaneshbb", email = "dhaneshbb5@gmail.com" }]
license = { text = "MIT" }
# NOTE: Third-party conda dependencies have various licenses - see NOTICE file
readme = "README.md"
keywords = ["csv", "data-analysis", "profiling", "statistics", "pandas"]
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "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",
    "Programming Language :: Python :: 3.13",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Software Development :: Libraries :: Python Modules",
]
requires-python = ">=3.10"

# NOTE: Dependencies are managed via conda environments - see config/master_config.yml
# No dependencies declared here due to irreconcilable conflicts between profiling libraries
# Base environment dependencies: install requirements.txt for setup and optional requirements-dev.txt for development

# ----------------------------------------------------------------------------
# Project URLs
# ----------------------------------------------------------------------------

[project.urls]
Homepage = "https://github.com/dhaneshbb/autocsv-profiler-suite"
Documentation = "https://github.com/dhaneshbb/autocsv-profiler-suite/tree/main/docs"
Repository = "https://github.com/dhaneshbb/autocsv-profiler-suite.git"
Issues = "https://github.com/dhaneshbb/autocsv-profiler-suite/issues"

# ============================================================================
# TOOL CONFIGURATIONS
# ============================================================================

# ----------------------------------------------------------------------------
# Code Formatting
# ----------------------------------------------------------------------------

[tool.black]
line-length = 88
target-version = ["py310", "py311", "py312"]
include = "\\.pyi?$"
extend-exclude = '''
/(
    # directories
    \\.eggs
  | \\.git
  | \\.mypy_cache
  | \\.venv
  | \\.bkup
  | _build
  | build
  | dist
  | htmlcov
)/
'''

# ----------------------------------------------------------------------------
# Import Sorting
# ----------------------------------------------------------------------------

[tool.isort]
profile = "black"
line_length = 88
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true

# ----------------------------------------------------------------------------
# Type Checking
# ----------------------------------------------------------------------------
# MyPy configuration handled in environment-specific mypy_*.ini files
# This is required for multi-environment architecture where different
# conda environments have different packages available:
#   - mypy_main.ini: Main environment (Python 3.11)
#   - mypy_profiling.ini: Profiling environment (Python 3.10)
#   - mypy_dataprep.ini: DataPrep environment (Python 3.10)

# ----------------------------------------------------------------------------
# Testing Framework
# ----------------------------------------------------------------------------

[tool.pytest.ini_options]
# Test discovery
testpaths = ["tests"]
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]

# Output configuration
addopts = [
    "--verbose",
    "--tb=short",
    "--strict-markers",
    "--strict-config",
    "--disable-warnings",
    "--cov=autocsv_profiler",
    "--cov-report=term-missing",
    "--cov-report=html:htmlcov",
    "--cov-report=xml:coverage.xml",
    "--cov-fail-under=50",
    "-ra"
]

# Markers for test categorization
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "integration: marks tests as integration tests",
    "environment: marks tests that require specific conda environments",
    "performance: marks tests that check performance characteristics",
    "platform: marks tests for platform-specific functionality",
    "engines: marks tests related to profiling engines",
    "unit: marks tests as unit tests",
    "base_profiler: marks tests related to base profiler functionality",
    "visualization: marks tests related to plotting and visualization",
    "statistics: marks tests related to statistical analysis",
    "ui: marks tests related to user interface components",
    "plots: marks tests related to plotting functionality",
    "stats: marks tests related to statistics functionality",
    "components: marks tests related to UI components",
]

# Test filtering
filterwarnings = [
    "ignore::DeprecationWarning:pkg_resources.*",
    "ignore::DeprecationWarning:pandas.*",
    "ignore::DeprecationWarning:ydata_profiling.*",
    "ignore::PendingDeprecationWarning",
    "ignore::UserWarning:pandas.*",
    "ignore::RuntimeWarning:numpy.*",
]

# Minimum Python version
minversion = "3.10"

# ----------------------------------------------------------------------------
# Code Coverage
# ----------------------------------------------------------------------------

[tool.coverage.run]
source = ["autocsv_profiler"]
omit = [
    "*/tests/*",
    "*/test_*",
    "*/__pycache__/*",
    "*/.git/*",
    "*/.bkup/*",
    "setup.py",
    "*/venv/*",
    "*/.venv/*",
    "autocsv_profiler/ui/interactive.py",
    "autocsv_profiler/ui/interface.py",
    "autocsv_profiler/ui/components.py",
    "autocsv_profiler/plots.py",
    "autocsv_profiler/stats.py",
]
branch = true

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "if self.debug:",
    "if settings.DEBUG",
    "raise AssertionError",
    "raise NotImplementedError",
    "if 0:",
    "if __name__ == .__main__.:",
    "class .*\\bProtocol\\):",
    "@(abc\\.)?abstractmethod",
]
show_missing = true
skip_covered = false
fail_under = 50

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

# ----------------------------------------------------------------------------
# Linting
# ----------------------------------------------------------------------------
# Flake8 configuration in .flake8 file (flake8 doesn't natively support pyproject.toml)
# Future: Consider migrating to Ruff for full pyproject.toml support