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>

src/ocr_sprint/schemas/extraction.py

@@ -0,0 +1,55 @@
+"""Top-level extraction result schemas."""
+
+from __future__ import annotations
+
+from datetime import date
+from enum import Enum
+
+from pydantic import BaseModel, Field
+
+from ocr_sprint.schemas.personnel import PersonnelEntry
+
+
+class ReviewFlag(str, Enum):
+    """Reasons a document was routed to human review."""
+
+    LOW_OCR_CONFIDENCE = "low_ocr_confidence"
+    MISSING_FIELD = "missing_field"
+    INVALID_NRP = "invalid_nrp"
+    UNKNOWN_PANGKAT = "unknown_pangkat"
+    PERSONNEL_COUNT_MISMATCH = "personnel_count_mismatch"
+    DATE_PARSE_FAILED = "date_parse_failed"
+
+
+class Signatory(BaseModel):
+    """The official signing the sprint (Penandatangan)."""
+
+    nama: str | None = None
+    pangkat: str | None = None
+    nrp: str | None = None
+    jabatan: str | None = None
+
+
+class HeaderFields(BaseModel):
+    """Header fields parsed from the top portion of a sprint."""
+
+    nomor_sprint: str | None = Field(None, description="e.g. Sprin/123/IV/2025/Reskrim.")
+    tanggal: date | None = Field(None, description="Date the sprint was issued.")
+    satuan_penerbit: str | None = Field(None, description="Issuing unit, e.g. 'Polres Bandung'.")
+    perihal: str | None = None
+    dasar: list[str] = Field(default_factory=list, description="List of legal/operational basis.")
+
+
+class ExtractionResult(BaseModel):
+    """Full structured payload extracted from a single sprint document."""
+
+    header: HeaderFields = Field(default_factory=HeaderFields)
+    personel: list[PersonnelEntry] = Field(default_factory=list)
+    untuk: list[str] = Field(
+        default_factory=list,
+        description="Bulleted task descriptions in the 'Untuk' / 'Dikerjakan' section.",
+    )
+    ttd: Signatory = Field(default_factory=Signatory)
+    raw_text: str = Field(default="", description="Concatenated OCR text for debugging.")
+    confidence: float = Field(0.0, ge=0.0, le=1.0)
+    review_flags: list[ReviewFlag] = Field(default_factory=list)