feat(deps): add lean setup.py for dependency splitting

- Create setup_lean.py with minimal core dependencies (pydantic, typing-extensions)
- Move heavy dependencies to optional extras (nlp, ocr, distributed, web, cli, crypto)
- Add Roadmap.md to .gitignore as working document
- Prepare for v4.1.0 lightweight architecture

Core install will be <2MB, heavy features available via pip install datafog[nlp,ocr,etc]

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

Co-Authored-By: Claude <noreply@anthropic.com>

Author: sidmohan0

.gitignore

@@ -63,4 +63,5 @@ docs/*
 
 # Keep all files but ignore their contents
 Claude.md
-notes/benchmarking_notes.md
+notes/benchmarking_notes.md
+Roadmap.md

setup_lean.py

@@ -0,0 +1,104 @@
+from setuptools import find_packages, setup
+
+# Read README for the long description
+with open("README.md", "r") as f:
+    long_description = f.read()
+
+# Use a single source of truth for the version
+__version__ = "4.1.0"
+
+project_urls = {
+    "Homepage": "https://datafog.ai",
+    "Documentation": "https://docs.datafog.ai",
+    "Discord": "https://discord.gg/bzDth394R4",
+    "Twitter": "https://twitter.com/datafoginc",
+    "GitHub": "https://github.com/datafog/datafog-python",
+}
+
+# Core lightweight dependencies only
+core_deps = [
+    "pydantic>=2.0,<3.0",
+    "typing-extensions>=4.0",
+]
+
+# Optional heavy dependencies
+extras_require = {
+    "nlp": [
+        "spacy>=3.7.0,<4.0",
+    ],
+    "ocr": [
+        "pytesseract>=0.3.0",
+        "Pillow>=10.0.0",
+        "sentencepiece>=0.2.0",
+        "protobuf>=4.0.0",
+    ],
+    "distributed": [
+        "pandas>=2.0.0",
+        "numpy>=1.24.0",
+    ],
+    "web": [
+        "fastapi>=0.100.0",
+        "aiohttp>=3.8.0",
+        "requests>=2.30.0",
+    ],
+    "cli": [
+        "typer>=0.12.0",
+    ],
+    "crypto": [
+        "cryptography>=40.0.0",
+    ],
+    "dev": [
+        "pytest>=7.0.0",
+        "pytest-asyncio>=0.21.0",
+        "pytest-cov>=4.0.0",
+        "sphinx>=7.0.0",
+    ],
+    # Convenience bundles
+    "all": [
+        "spacy>=3.7.0,<4.0",
+        "pytesseract>=0.3.0",
+        "Pillow>=10.0.0",
+        "sentencepiece>=0.2.0",
+        "protobuf>=4.0.0",
+        "pandas>=2.0.0",
+        "numpy>=1.24.0",
+        "fastapi>=0.100.0",
+        "aiohttp>=3.8.0",
+        "requests>=2.30.0",
+        "typer>=0.12.0",
+        "cryptography>=40.0.0",
+    ],
+}
+
+setup(
+    name="datafog",
+    version=__version__,
+    author="Sid Mohan",
+    author_email="sid@datafog.ai",
+    description="Lightning-fast PII detection and anonymization library with 190x performance advantage",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    packages=find_packages(),
+    install_requires=core_deps,
+    extras_require=extras_require,
+    python_requires=">=3.10,<3.13",
+    entry_points={
+        "console_scripts": [
+            "datafog=datafog.client:app [cli]",  # Requires cli extra
+        ],
+    },
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "License :: OSI Approved :: Apache Software License",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Topic :: Software Development :: Libraries :: Python Modules",
+        "Topic :: Text Processing",
+        "Topic :: Security",
+    ],
+    project_urls=project_urls,
+    keywords="pii detection anonymization privacy regex performance",
+)