mcp-legacy-files/pyproject.toml
Ryan Malloy 572379d9aa 🎉 Complete Phase 2: WordPerfect processor implementation
 WordPerfect Production Support:
- Comprehensive WordPerfect processor with 5-layer fallback chain
- Support for WP 4.2, 5.0-5.1, 6.0+ (.wpd, .wp, .wp5, .wp6)
- libwpd integration (wpd2text, wpd2html, wpd2raw)
- Binary strings extraction and emergency parsing
- Password detection and encoding intelligence
- Document structure analysis and integrity checking

🏗️ Infrastructure Enhancements:
- Created comprehensive CLAUDE.md development guide
- Updated implementation status documentation
- Added WordPerfect processor test suite
- Enhanced format detection with WP magic signatures
- Production-ready with graceful dependency handling

📊 Project Status:
- 2/4 core processors complete (dBASE + WordPerfect)
- 25+ legacy format detection engine operational
- Phase 2 complete: Ready for Lotus 1-2-3 implementation

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-08-18 02:03:44 -06:00

245 lines
6.2 KiB
TOML

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "mcp-legacy-files"
version = "0.1.0"
description = "The Ultimate Vintage Document Processing Powerhouse for AI - Transform 25+ legacy formats into modern intelligence"
authors = [
{name = "MCP Legacy Files Team", email = "legacy@mcp.dev"}
]
readme = "README.md"
license = {text = "MIT"}
keywords = [
"mcp", "legacy", "vintage", "documents", "dbase", "wordperfect",
"lotus123", "appleworks", "hypercard", "ai", "processing"
]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Intended Audience :: End Users/Desktop",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Office/Business",
"Topic :: Text Processing",
"Topic :: Database",
"Topic :: Scientific/Engineering :: Information Analysis",
]
requires-python = ">=3.11"
dependencies = [
# FastMCP framework
"fastmcp>=0.5.0",
# Core async libraries
"asyncio-throttle>=1.0.2",
"aiofiles>=23.2.0",
"aiohttp>=3.9.0",
# Data processing
"pandas>=2.1.0",
"numpy>=1.24.0",
# Legacy format processing - Core libraries
"dbfread>=2.0.7", # dBASE file reading
"simpledbf>=0.2.6", # Alternative dBASE reader
# Text processing and AI
"python-magic>=0.4.27", # File type detection
"chardet>=5.2.0", # Character encoding detection
"beautifulsoup4>=4.12.0", # Text cleaning
# Caching and performance
"diskcache>=5.6.3", # Intelligent disk caching
"python-dateutil>=2.8.2", # Date parsing for vintage files
# Logging and monitoring
"structlog>=23.2.0", # Structured logging
"rich>=13.7.0", # Rich terminal output
# Configuration and utilities
"pydantic>=2.5.0", # Data validation
"click>=8.1.7", # CLI interface
"typer>=0.9.0", # Modern CLI framework
]
[project.optional-dependencies]
# Legacy format processing libraries
legacy-full = [
# WordPerfect processing
"python-docx>=1.1.0", # For modern conversion fallbacks
# Spreadsheet processing
"openpyxl>=3.1.0", # Excel format fallbacks
"xlrd>=2.0.1", # Legacy Excel reading
# Archive processing
"py7zr>=0.21.0", # 7-Zip archives
"rarfile>=4.1", # RAR archives
# Mac format processing
"biplist>=1.0.3", # Binary plist processing
"macholib>=1.16.3", # Mac binary analysis
]
# AI and machine learning
ai-enhanced = [
"transformers>=4.36.0", # HuggingFace transformers
"torch>=2.1.0", # PyTorch for AI models
"scikit-learn>=1.3.0", # ML utilities
"spacy>=3.7.0", # NLP processing
]
# Development dependencies
dev = [
"pytest>=7.4.0",
"pytest-asyncio>=0.21.0",
"pytest-cov>=4.1.0",
"black>=23.12.0",
"ruff>=0.1.8",
"mypy>=1.8.0",
"pre-commit>=3.6.0",
]
# Enterprise features
enterprise = [
"prometheus-client>=0.19.0", # Metrics collection
"opentelemetry-api>=1.21.0", # Observability
"cryptography>=41.0.0", # Security features
"psutil>=5.9.0", # System monitoring
]
[project.urls]
Homepage = "https://github.com/MCP/mcp-legacy-files"
Documentation = "https://github.com/MCP/mcp-legacy-files/blob/main/README.md"
Repository = "https://github.com/MCP/mcp-legacy-files"
Issues = "https://github.com/MCP/mcp-legacy-files/issues"
Changelog = "https://github.com/MCP/mcp-legacy-files/blob/main/CHANGELOG.md"
[project.scripts]
mcp-legacy-files = "mcp_legacy_files.server:main"
legacy-files-cli = "mcp_legacy_files.cli:main"
[tool.setuptools.packages.find]
where = ["src"]
[tool.setuptools.package-data]
mcp_legacy_files = [
"data/*.json",
"data/signatures/*.dat",
"templates/*.json",
]
# Black code formatter
[tool.black]
line-length = 88
target-version = ['py311']
include = '\.pyi?$'
extend-exclude = '''
/(
# directories
\.eggs
| \.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| build
| dist
)/
'''
# Ruff linter
[tool.ruff]
target-version = "py311"
line-length = 88
select = [
"E", # pycodestyle errors
"W", # pycodestyle warnings
"F", # pyflakes
"I", # isort
"B", # flake8-bugbear
"C4", # flake8-comprehensions
"UP", # pyupgrade
]
ignore = [
"E501", # line too long, handled by black
"B008", # do not perform function calls in argument defaults
"C901", # too complex
]
[tool.ruff.per-file-ignores]
"__init__.py" = ["F401"]
# MyPy type checker
[tool.mypy]
python_version = "3.11"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
strict_equality = true
[[tool.mypy.overrides]]
module = [
"dbfread.*",
"simpledbf.*",
"python_magic.*",
"diskcache.*",
]
ignore_missing_imports = true
# Pytest configuration
[tool.pytest.ini_options]
minversion = "7.0"
addopts = [
"-ra",
"--strict-markers",
"--strict-config",
"--cov=mcp_legacy_files",
"--cov-report=term-missing",
"--cov-report=html",
"--cov-report=xml",
]
testpaths = ["tests"]
asyncio_mode = "auto"
markers = [
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
"integration: marks tests as integration tests",
"legacy_format: marks tests that require legacy format test files",
]
# Coverage configuration
[tool.coverage.run]
source = ["src"]
branch = true
omit = [
"*/tests/*",
"*/test_*.py",
"*/__init__.py",
]
[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",
]