QuantEngineByItz/tools/refactor_database_structure.py

#!/usr/bin/env python3
"""
데이터베이스 구조 리팩토링

파편화된 DB 파일들을 정리하고 단일 위치(src/quant_engine/)로 통합
"""

import shutil
from pathlib import Path
from datetime import datetime

class DatabaseRefactorer:
    """데이터베이스 구조 리팩토링"""

    def __init__(self):
        self.root = Path(".")
        self.canonical_dir = Path("src/quant_engine")
        self.results = {
            "timestamp": datetime.now().isoformat(),
            "consolidated": [],
            "moved": [],
            "deleted": [],
            "errors": []
        }

    def get_canonical_location(self, db_name: str) -> Path:
        """DB의 정규 위치 반환"""
        canonical_map = {
            "kis_data_collection.db": self.canonical_dir / "kis_data_collection.db",
            "snapshot_admin.db": self.canonical_dir / "snapshot_admin.db",
        }
        return canonical_map.get(db_name)

    def find_scattered_dbs(self) -> dict:
        """파편화된 DB 파일 찾기"""
        scattered = {
            "outputs": [],
            "temp": [],
            "other": []
        }

        # outputs/ 검색
        outputs_dir = self.root / "outputs"
        if outputs_dir.exists():
            for db in outputs_dir.rglob("*.db"):
                scattered["outputs"].append(db)

        # Temp/ 검색
        temp_dir = self.root / "Temp"
        if temp_dir.exists():
            for db in temp_dir.glob("*_collection.db"):
                scattered["temp"].append(db)
            for db in temp_dir.glob("*_admin*.db"):
                scattered["temp"].append(db)

        return scattered

    def analyze(self) -> dict:
        """분석"""
        scattered = self.find_scattered_dbs()

        analysis = {
            "canonical_location": str(self.canonical_dir),
            "canonical_files": {
                "kis_data_collection.db": (self.canonical_dir / "kis_data_collection.db").exists(),
                "snapshot_admin.db": (self.canonical_dir / "snapshot_admin.db").exists(),
            },
            "scattered_files": {
                "outputs": [str(f.relative_to(self.root)) for f in scattered["outputs"]],
                "temp": [str(f.relative_to(self.root)) for f in scattered["temp"]],
            },
            "total_scattered": len(scattered["outputs"]) + len(scattered["temp"])
        }

        return analysis, scattered

    def consolidate(self, scattered: dict, dry_run: bool = True) -> dict:
        """통합"""
        action = "Would consolidate" if dry_run else "Consolidating"

        print(f"\n[Analysis]")
        analysis, _ = self.analyze()

        print(f"Canonical location: {analysis['canonical_location']}")
        print(f"  kis_data_collection.db: {'EXISTS' if analysis['canonical_files']['kis_data_collection.db'] else 'MISSING'}")
        print(f"  snapshot_admin.db: {'EXISTS' if analysis['canonical_files']['snapshot_admin.db'] else 'MISSING'}")

        print(f"\nScattered files found:")
        print(f"  outputs/: {len(analysis['scattered_files']['outputs'])} files")
        for f in analysis['scattered_files']['outputs'][:5]:
            print(f"    - {f}")
        print(f"  Temp/: {len(analysis['scattered_files']['temp'])} files")
        for f in analysis['scattered_files']['temp']:
            print(f"    - {f}")

        print(f"\n[Recommendation]")
        print(f"1. Keep canonical location: src/quant_engine/")
        print(f"   - kis_data_collection.db (KIS API 데이터)")
        print(f"   - snapshot_admin.db (성능/포지션)")
        print(f"")
        print(f"2. Archive old files: archive_db/ (2026-06-23)")
        print(f"   - outputs/kis_data_collection/*")
        print(f"   - outputs/snapshot_admin/smoke*.db")
        print(f"   - Temp/*_collection.db")
        print(f"   - Temp/*_admin*.db")
        print(f"")
        print(f"3. Delete: qualitative_sell_strategy.db (unrelated)")

        return analysis

    def create_consolidation_plan(self) -> str:
        """통합 계획서 작성"""
        analysis, _ = self.analyze()

        plan = f"""
# Database Consolidation Plan (2026-06-23)

## Current State: FRAGMENTED
- Canonical: src/quant_engine/ (2 files)
- Scattered: outputs/ ({len(analysis['scattered_files']['outputs'])}) + Temp/ ({len(analysis['scattered_files']['temp'])})
- Total: {analysis['total_scattered'] + 2} database files

## Issue
1. kis_data_collection.db in 3 locations:
   - src/quant_engine/ (CANONICAL)
   - outputs/kis_data_collection/
   - Temp/test_kis_data_collection.db

2. snapshot_admin.db in 4+ locations:
   - src/quant_engine/ (CANONICAL)
   - outputs/snapshot_admin/
   - Temp/snapshot_admin_*.db (multiple variants)
   - outputs/qualitative_sell_strategy/ (unrelated)

## Solution

### Step 1: Verify Canonical Copies (src/quant_engine/)
- kis_data_collection.db: 5 records [OK]
- snapshot_admin.db: 0 records (initialized) [OK]

### Step 2: Archive Scattered Files (archive_db/)
Create archive directory with timestamp:
```
archive_db/
├── 2026-06-23_outputs_kis_data_collection/
├── 2026-06-23_outputs_snapshot_admin/
├── 2026-06-23_temp_test_files/
└── manifest.json (record what was archived)
```

### Step 3: Clean Obsolete References
- Remove imports from "outputs/kis_data_collection/kis_data_collection.db"
- Remove imports from "outputs/snapshot_admin/*.db"
- Update any code expecting these paths

### Step 4: Update Documentation
- Update all references to use: src/quant_engine/
- Update deployment docs (Synology)
- Update CI/CD workflows

## Benefits
- Single source of truth
- Easier backup/recovery
- Clear separation: live vs. archived
- Faster data access
- Simplified deployment

## Files to Delete (After Archiving)
- outputs/kis_data_collection/ (entire dir)
- outputs/snapshot_admin/smoke*.db (old test files)
- outputs/qualitative_sell_strategy/qualitative_sell_strategy.db
- Temp/snapshot_admin_*.db
- Temp/test_kis_data_collection.db
"""
        return plan

def main():
    refactorer = DatabaseRefactorer()

    print("="*80)
    print("Database Structure Refactoring Analysis")
    print("="*80)

    analysis = refactorer.consolidate(None, dry_run=True)

    plan = refactorer.create_consolidation_plan()
    print(plan)

    # 계획서 저장
    plan_file = Path("docs/DATABASE_CONSOLIDATION_PLAN_2026_06_23.md")
    plan_file.parent.mkdir(parents=True, exist_ok=True)
    with open(plan_file, 'w', encoding='utf-8') as f:
        f.write(plan)

    print(f"\n[Saved] Consolidation plan: {plan_file}")

if __name__ == "__main__":
    main()