# main.py

import shutil
import os
import uuid
from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.responses import JSONResponse
from fastapi.middleware.cors import CORSMiddleware
from predict import predict_image

app = FastAPI(
    title="Medical Image Classification API",
    description="AI-powered medical image classification service",
    version="1.0.0"
)

# Add CORS middleware for Flutter integration
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

# Create uploads directory in tmp (writable in containers)
import tempfile
UPLOAD_DIR = tempfile.mkdtemp()
os.makedirs(UPLOAD_DIR, exist_ok=True)

@app.get("/health")
async def health_check():
    return {"status": "healthy", "service": "gp-tea-skin-analysis"}

@app.post("/analyze_image")
async def analyze_image(file: UploadFile = File(...)):
    """Analyze skin image for medical conditions"""
    try:
        if not file.content_type or not file.content_type.startswith('image/'):
            raise HTTPException(status_code=400, detail="File must be an image")
        
        unique_filename = f"{uuid.uuid4().hex}_{file.filename}"
        file_path = os.path.join(UPLOAD_DIR, unique_filename)
        
        with open(file_path, "wb") as buffer:
            shutil.copyfileobj(file.file, buffer)
        
        label, confidence, all_predictions = predict_image(file_path)
        os.remove(file_path)
        
        formatted_predictions = []
        for pred in all_predictions:
            formatted_predictions.append({
                "label": pred["label"],
                "confidence": float(pred["confidence"]),
                "confidence_percent": f"{pred['confidence'] * 100:.2f}%"
            })
        
        return JSONResponse(
            status_code=200,
            content={
                "success": True,
                "prediction": {
                    "top_prediction": {
                        "label": label,
                        "confidence": float(confidence),
                        "confidence_percent": f"{confidence * 100:.2f}%"
                    },
                    "all_predictions": formatted_predictions
                }
            }
        )
        
    except Exception as e:
        if 'file_path' in locals() and os.path.exists(file_path):
            os.remove(file_path)
        raise HTTPException(status_code=500, detail=f"Classification failed: {str(e)}")