opencode/backend/import_existing.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Импорт существующего output_123 в backend БД.

Использование:
    python import_existing.py
"""

import sys
import json
from pathlib import Path

# Добавить backend в path
sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))

from app.database import SessionLocal, Base, engine
from app import models, crud, schemas


def import_output_123():
    """Импорт существующего проекта output_123 в БД."""
    
    output_folder = Path("/Users/kirillblinov/development/opencode/OCR/opencode/output_123")
    if not output_folder.exists():
        print(f"[ERR] Не найден: {output_folder}")
        return
    
    db = SessionLocal()
    
    try:
        # Создать проект
        project = crud.create_project(
            db, 
            pdf_filename="123.pdf",
            name="Test Project 123"
        )
        print(f"[INFO] Создан проект: ID={project.id}")
        
        # Обновить статус
        crud.update_project_status(db, project.id, "completed", output_folder=str(output_folder))
        
        # Загрузить OCR
        ocr_path = output_folder / "full_ocr_results.json"
        if ocr_path.exists():
            ocr = json.loads(ocr_path.read_text(encoding="utf-8"))
            
            # Создать страницы
            for page_data in ocr.get("pages", []):
                page_num = page_data["page_number"]
                png_path = output_folder / f"page_{page_num:03d}.png"
                
                from PIL import Image
                width = height = None
                if png_path.exists():
                    with Image.open(png_path) as img:
                        width, height = img.size
                
                page = crud.create_page(
                    db,
                    project_id=project.id,
                    page_number=page_num,
                    png_path=str(png_path) if png_path.exists() else None,
                    ocr_data=page_data,
                    width=width,
                    height=height
                )
                print(f"  [OK] Страница {page_num}: {width}x{height}")
        
        # Загрузить QC issues
        qc_path = output_folder / "dimension_qc_report.json"
        if qc_path.exists():
            qc = json.loads(qc_path.read_text(encoding="utf-8"))
            
            total_imported = 0
            for severity in ["errors", "warnings", "infos"]:
                for item in qc.get(severity, []):
                    page_num = item["page"]
                    page = crud.get_page_by_number(db, project.id, page_num)
                    
                    # Извлечь bbox
                    bbox = item.get("bbox") or item.get("bbox1") or item.get("bbox_dim")
                    x1 = y1 = x2 = y2 = None
                    if bbox:
                        if isinstance(bbox[0], list):
                            xs = [p[0] for p in bbox]
                            ys = [p[1] for p in bbox]
                            x1, y1, x2, y2 = min(xs), min(ys), max(xs), max(ys)
                        else:
                            x1, y1, x2, y2 = bbox[0], bbox[1], bbox[2], bbox[3]
                    
                    crud.create_issue(
                        db,
                        project_id=project.id,
                        page_id=page.id if page else None,
                        issue_type=item["type"],
                        severity=item["severity"],
                        message=item["message"],
                        bbox_x1=x1, bbox_y1=y1, bbox_x2=x2, bbox_y2=y2,
                        dimension_text=item.get("text"),
                        confidence=item.get("confidence"),
                        extra_data={k: v for k, v in item.items() 
                                   if k not in ["type", "severity", "message", "page", "text", "confidence", "bbox", "bbox1", "bbox2", "bbox_dim"]}
                    )
                    total_imported += 1
            
            print(f"[OK] Импортировано замечаний: {total_imported}")
        
        # Загрузить VLM descriptions
        vlm_path = output_folder / "vlm_descriptions.json"
        if vlm_path.exists():
            vlm = json.loads(vlm_path.read_text(encoding="utf-8"))
            for page in project.pages:
                for item in vlm.get("descriptions", []):
                    if item.get("page") == page.page_number:
                        page.vlm_description = item.get("description")
                        db.commit()
                        break
            print(f"[OK] VLM описания загружены")
        
        print(f"\n[INFO] Проект #{project.id} готов!")
        print(f"      Dashboard: http://localhost:8001/")
        print(f"      Viewer: http://localhost:8001/viewer/{project.id}/5")
        print(f"      Review: http://localhost:8001/review.html?project={project.id}")
        
        return project.id
        
    except Exception as e:
        print(f"[ERR] {e}")
        import traceback
        traceback.print_exc()
    finally:
        db.close()


if __name__ == "__main__":
    import_output_123()