OCR/backend/app/main.py

"""
Tool_OCR - FastAPI Application Entry Point
Main application setup with CORS, routes, and startup/shutdown events
"""

from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from contextlib import asynccontextmanager
import logging
import asyncio
from pathlib import Path

from app.core.config import settings
from app.services.background_tasks import task_manager

# Ensure log directory exists before configuring logging
Path(settings.log_file).parent.mkdir(parents=True, exist_ok=True)

# Configure logging
logging.basicConfig(
    level=getattr(logging, settings.log_level),
    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
    handlers=[
        logging.FileHandler(settings.log_file),
        logging.StreamHandler(),
    ],
)
logger = logging.getLogger(__name__)


@asynccontextmanager
async def lifespan(app: FastAPI):
    """Application lifespan events"""
    # Startup
    logger.info("Starting Tool_OCR application...")

    # Ensure all directories exist
    settings.ensure_directories()
    logger.info("All directories created/verified")

    # Start cleanup scheduler as background task
    cleanup_task = asyncio.create_task(task_manager.start_cleanup_scheduler())
    logger.info("Started cleanup scheduler for expired files")

    # TODO: Initialize database connection pool
    # TODO: Load PaddleOCR models

    logger.info("Application startup complete")

    yield

    # Shutdown
    logger.info("Shutting down Tool_OCR application...")

    # Cancel cleanup task
    cleanup_task.cancel()
    try:
        await cleanup_task
    except asyncio.CancelledError:
        logger.info("Cleanup scheduler stopped")

    # TODO: Close database connections


# Create FastAPI application
app = FastAPI(
    title="Tool_OCR",
    description="OCR Batch Processing System with Structure Extraction",
    version="0.1.0",
    lifespan=lifespan,
)

# Configure CORS
app.add_middleware(
    CORSMiddleware,
    allow_origins=settings.cors_origins_list,
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)


# Health check endpoint
@app.get("/health")
async def health_check():
    """Health check endpoint with GPU status"""
    from app.services.ocr_service import OCRService

    response = {
        "status": "healthy",
        "service": "Tool_OCR",
        "version": "0.1.0",
    }

    # Add GPU status information
    try:
        # Create temporary OCRService instance to get GPU status
        # In production, this should be a singleton service
        ocr_service = OCRService()
        gpu_status = ocr_service.get_gpu_status()

        response["gpu"] = {
            "available": gpu_status.get("gpu_available", False),
            "enabled": gpu_status.get("gpu_enabled", False),
            "device_name": gpu_status.get("device_name", "N/A"),
            "device_count": gpu_status.get("device_count", 0),
            "compute_capability": gpu_status.get("compute_capability", "N/A"),
        }

        # Add memory info if available
        if gpu_status.get("memory_total_mb"):
            response["gpu"]["memory"] = {
                "total_mb": round(gpu_status.get("memory_total_mb", 0), 2),
                "allocated_mb": round(gpu_status.get("memory_allocated_mb", 0), 2),
                "utilization_percent": round(gpu_status.get("memory_utilization", 0), 2),
            }

        # Add reason if GPU is not available
        if not gpu_status.get("gpu_available") and gpu_status.get("reason"):
            response["gpu"]["reason"] = gpu_status.get("reason")

    except Exception as e:
        logger.warning(f"Failed to get GPU status: {e}")
        response["gpu"] = {
            "available": False,
            "error": str(e),
        }

    return response


# Root endpoint
@app.get("/")
async def root():
    """Root endpoint with API information"""
    return {
        "message": "Tool_OCR API",
        "version": "0.1.0",
        "docs_url": "/docs",
        "health_check": "/health",
    }


# Include API routers
from app.routers import auth, ocr, export, translation
# V2 routers with external authentication
from app.routers import auth_v2, tasks, admin

# Legacy V1 routers
app.include_router(auth.router)
app.include_router(ocr.router)
app.include_router(export.router)
app.include_router(translation.router)  # RESERVED for Phase 5

# New V2 routers with external authentication
app.include_router(auth_v2.router)
app.include_router(tasks.router)
app.include_router(admin.router)


if __name__ == "__main__":
    import uvicorn

    uvicorn.run(
        "app.main:app",
        host="0.0.0.0",
        port=settings.backend_port,
        reload=True,
        log_level=settings.log_level.lower(),
    )