app.py

from flask import Flask, request, jsonify
from flask_cors import CORS
from transformers import (
    MBartForConditionalGeneration, MBart50TokenizerFast, pipeline,
    MarianMTModel, MarianTokenizer
)
import torch

app = Flask(__name__)
CORS(app)

# 🧠 Load language detection model
lang_detector = pipeline("text-classification", model="papluca/xlm-roberta-base-language-detection")

# 🌐 Supported languages mapping for MBART
LANG_CODE_MAP = {
    "ar": "ar_AR", "en": "en_XX", "es": "es_XX", "fr": "fr_XX",
    "de": "de_DE", "it": "it_IT", "ru": "ru_RU", "zh": "zh_CN",
    "ja": "ja_XX", "ko": "ko_KR", "tr": "tr_TR", "pt": "pt_XX",
    # أضف أكثر لو حبيت
}

# Load MBART model (general case)
mbart_model_name = "facebook/mbart-large-50-many-to-one-mmt"
mbart_tokenizer = MBart50TokenizerFast.from_pretrained(mbart_model_name)
mbart_model = MBartForConditionalGeneration.from_pretrained(mbart_model_name)

# Load Arabic-specific translation model
helsinki_model_name = "Helsinki-NLP/opus-mt-ar-en"
helsinki_tokenizer = MarianTokenizer.from_pretrained(helsinki_model_name)
helsinki_model = MarianMTModel.from_pretrained(helsinki_model_name)

def detect_language(text: str):
    try:
        result = lang_detector(text)[0]
        lang = result["label"]
        return lang if lang in LANG_CODE_MAP else "en"
    except Exception:
        return "en"  # fallback

def translate_to_english(text: str):
    src_lang = detect_language(text)
    print(f"Detected language: {src_lang}")

    try:
        # ✨ Use Helsinki model for Arabic
        if src_lang == "ar":
            encoded = helsinki_tokenizer(text, return_tensors="pt", padding=True)
            translated = helsinki_model.generate(**encoded)
            return helsinki_tokenizer.decode(translated[0], skip_special_tokens=True)

        # ✨ Use MBART for all other languages
        mbart_tokenizer.src_lang = LANG_CODE_MAP.get(src_lang, "en_XX")
        encoded = mbart_tokenizer(text, return_tensors="pt")
        generated_tokens = mbart_model.generate(
            **encoded,
            forced_bos_token_id=mbart_tokenizer.lang_code_to_id["en_XX"]
        )
        return mbart_tokenizer.decode(generated_tokens[0], skip_special_tokens=True)

    except Exception as e:
        return f"❌ Translation Error: {str(e)}"

@app.route("/")
def home():
    return jsonify({"status": "Translation service is running!", "usage": "POST /translate with JSON {'text': 'your text here'}"})

@app.route("/translate", methods=["POST"])
def translate_text():
    data = request.get_json()
    if not data or 'text' not in data:
        return jsonify({"success": False, "error": "No text provided"}), 400

    translated = translate_to_english(data["text"])
    return jsonify({"success": True, "translatedText": translated})

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)