Phase 1 MVP: synchronous OCR + regex header extraction

Implements the foundation of the OCR Sprint service:
- FastAPI app with /api/v1/health and /api/v1/documents (sync upload)
- Pydantic v2 schemas for documents, extraction result, personnel
- Pipeline: PDF/image ingest (PyMuPDF), preprocessing (resize, deskew,
  denoise, optional adaptive threshold), PaddleOCR wrapper, regex-based
  header extraction (nomor sprint, tanggal, satuan, perihal, dasar),
  signatory NRP, master-pangkat validation, confidence scoring + routing.
- Tests: 61 unit tests covering regex rules, validators, preprocess,
  ingest, confidence, and API contract (PaddleOCR mocked).
- Tooling: pyproject (setuptools), ruff, mypy strict, pytest, pre-commit,
  Dockerfile, docker-compose, Makefile.
- Docs: README + docs/architecture.md (full hybrid stack rationale and
  6-phase roadmap).

Co-authored-by: adrian kuman firmansah <adriancuman@gmail.com>

pyproject.toml

@@ -0,0 +1,136 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ocr-sprint-service"
+version = "0.1.0"
+description = "OCR service for Indonesian police 'surat sprint' documents (FastAPI + PaddleOCR + hybrid extraction)"
+readme = "README.md"
+requires-python = ">=3.10,<3.13"
+license = { text = "Proprietary" }
+authors = [{ name = "Adrian Kuman Firmansah" }]
+
+dependencies = [
+    # Web framework
+    "fastapi>=0.115,<0.116",
+    "uvicorn[standard]>=0.30,<0.34",
+    "python-multipart>=0.0.9",
+    "pydantic>=2.7,<3",
+    "pydantic-settings>=2.4,<3",
+    # Image / PDF
+    "pillow>=10.4,<12",
+    "opencv-python-headless>=4.10,<5",
+    "numpy>=1.26,<2.2",
+    "PyMuPDF>=1.24,<2",
+    "python-magic>=0.4.27",
+    # OCR (CPU build of paddle; GPU users override via extra index)
+    "paddlepaddle==2.6.1",
+    "paddleocr>=2.7.5,<3",
+    # Logging / observability
+    "structlog>=24.1",
+    "prometheus-client>=0.20",
+    # Misc
+    "httpx>=0.27",
+    "tenacity>=8.5",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.2",
+    "pytest-asyncio>=0.23",
+    "pytest-cov>=5.0",
+    "ruff>=0.6.9",
+    "mypy>=1.11",
+    "types-Pillow",
+    "pre-commit>=3.7",
+]
+
+# Extraction layer (Phase 5) — kept optional so MVP install stays light
+llm = [
+    "ollama>=0.3",
+    "instructor>=1.4",
+]
+
+# Async pipeline (Phase 4)
+async-pipeline = [
+    "celery[redis]>=5.4",
+    "redis>=5.0",
+    "minio>=7.2",
+    "sqlalchemy>=2.0",
+    "psycopg[binary]>=3.2",
+    "alembic>=1.13",
+]
+
+[project.scripts]
+ocr-sprint-api = "ocr_sprint.main:run"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"ocr_sprint" = ["py.typed"]
+
+# ---------- Tooling ----------
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "E", "F", "W",       # pycodestyle / pyflakes
+    "I",                 # isort
+    "B",                 # bugbear
+    "UP",                # pyupgrade
+    "SIM",               # simplify
+    "RUF",               # ruff-specific
+    "C4",                # comprehensions
+    "PIE",
+    "PT",                # pytest style
+    "TID",               # tidy imports
+]
+ignore = [
+    "E501",  # line length handled by formatter
+    "B008",  # FastAPI Depends() pattern
+]
+
+[tool.ruff.format]
+quote-style = "double"
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+warn_unused_ignores = true
+warn_redundant_casts = true
+disallow_untyped_defs = true
+plugins = ["pydantic.mypy"]
+mypy_path = "src"
+namespace_packages = true
+explicit_package_bases = true
+
+[[tool.mypy.overrides]]
+module = ["paddleocr.*", "paddle.*", "cv2.*", "fitz.*", "magic.*"]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+minversion = "8.0"
+addopts = "-ra --strict-markers --strict-config"
+testpaths = ["tests"]
+asyncio_mode = "auto"
+filterwarnings = [
+    "ignore::DeprecationWarning:paddle.*",
+    "ignore::DeprecationWarning:paddleocr.*",
+]
+
+[tool.coverage.run]
+source = ["src/ocr_sprint"]
+branch = true
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "raise NotImplementedError",
+    "if TYPE_CHECKING:",
+]