import os
import nltk
from fastapi import FastAPI, File, Request, UploadFile, Body, Depends, HTTPException
from fastapi.security.api_key import APIKeyHeader
from fastapi.middleware.cors import CORSMiddleware
from typing import Optional, Annotated
from fastapi.encoders import jsonable_encoder
from PIL import Image
from io import BytesIO
import pytesseract
from nltk.tokenize import sent_tokenize
from transformers import MarianMTModel, MarianTokenizer

API_KEY = os.environ.get("API_KEY")
VALID_IMAGE_EXTENSIONS = {"jpg", "jpeg", "png"}

app = FastAPI()
# CORS issue write below code
# origins = [
#     "http://localhost:3000",  # Update this with the actual origin of your frontend
# ]
# app.add_middleware(
#     CORSMiddleware,
#     allow_origins=origins,
#     allow_credentials=True,
#     allow_methods=["*"],
#     allow_headers=["*"],
# )
# ==========================
api_key_header = APIKeyHeader(name="api_key", auto_error=False)

def get_api_key(api_key: Optional[str] = Depends(api_key_header)):
    if api_key is None or api_key != API_KEY:
        raise HTTPException(status_code=401, detail="Unauthorized access")
    return api_key

@app.post("/api/ocr", response_model=dict)
async def ocr(
    api_key: str = Depends(get_api_key),
    image: UploadFile = File(...),
    # languages: list = Body(["eng"])
):
    try:
        
        # # Check if the file format is allowed
        file_extension = image.filename.split(".")[-1].lower()
        if file_extension not in VALID_IMAGE_EXTENSIONS:
            raise HTTPException(status_code=400, detail="Invalid file format. Only .jpg, .jpeg, and .png are allowed.")
            
        content = await image.read()
        image = Image.open(BytesIO(content))
        text = pytesseract.image_to_string(image, lang = 'eng')
        # text = pytesseract.image_to_string(image, lang="+".join(languages))
    except Exception as e:
        return {"error": str(e)}, 500

    return {"ImageText": text}

@app.post("/api/translate", response_model=dict)
async def translate(
    api_key: str = Depends(get_api_key),
    text: str = Body(...),
    src: str = "en",
    trg: str = "zh",
):

    tokenizer, model = get_model(src, trg)

    translated_text = ""
    for sentence in sent_tokenize(text):
        translated_sub = model.generate(**tokenizer(sentence, return_tensors="pt"))[0]
        translated_text += tokenizer.decode(translated_sub, skip_special_tokens=True) + "\n"

    return jsonable_encoder({"translated_text": translated_text})

def get_model(src: str, trg: str):
    model_name = f"Helsinki-NLP/opus-mt-{src}-{trg}"
    tokenizer = MarianTokenizer.from_pretrained(model_name)
    model = MarianMTModel.from_pretrained(model_name)
    return tokenizer, model