import gradio as gr
from transformers import pipeline
import requests
import time  # For simulating intermediate steps

# Load the sentiment analysis model
classifier = pipeline('sentiment-analysis', model='krishnamishra8848/movie_sentiment_analysis')

# Language detection function
def detect_language(text):
    detect_url = "https://google-translator9.p.rapidapi.com/v2/detect"
    detect_payload = {"q": text}
    headers = {
        "x-rapidapi-key": "ef532cb7b6msh96f36c918327aacp171ce5jsn42c4de22fe5d",
        "x-rapidapi-host": "google-translator9.p.rapidapi.com",
        "Content-Type": "application/json"
    }

    response = requests.post(detect_url, json=detect_payload, headers=headers)
    if response.status_code == 200:
        detections = response.json().get('data', {}).get('detections', [[]])[0]
        if detections:
            return detections[0].get('language')
    return None

# Translation function
def translate_text(text, source_language, target_language="en"):
    translate_url = "https://google-translator9.p.rapidapi.com/v2"
    translate_payload = {
        "q": text,
        "source": source_language,
        "target": target_language,
        "format": "text"
    }
    headers = {
        "x-rapidapi-key": "ef532cb7b6msh96f36c918327aacp171ce5jsn42c4de22fe5d",
        "x-rapidapi-host": "google-translator9.p.rapidapi.com",
        "Content-Type": "application/json"
    }

    response = requests.post(translate_url, json=translate_payload, headers=headers)
    if response.status_code == 200:
        translations = response.json().get('data', {}).get('translations', [{}])
        if translations:
            return translations[0].get('translatedText')
    return None

# Main function for Gradio
def analyze_sentiment_with_steps(text):
    # Step 1: Detecting Language
    status = "Detecting Language..."
    yield status
    detected_language = detect_language(text)
    if not detected_language:
        yield "Error: Could not detect the language."
        return

    status = f"Language Detected: {detected_language.upper()}"
    yield status

    # Step 2: Translating if necessary
    if detected_language != "en":
        status += "\nTranslating text to English..."
        yield status
        text = translate_text(text, detected_language)
        if not text:
            yield "Error: Could not translate the input text."
            return

    # Step 3: Sending to model
    status += "\nSending to Model..."
    yield status
    time.sleep(1)  # Simulate processing time for better user experience

    # Step 4: Sentiment analysis
    result = classifier(text)
    label_mapping = {"LABEL_0": "negative", "LABEL_1": "positive"}
    sentiment = label_mapping[result[0]['label']]
    confidence = result[0]['score']
    status += f"\nPrediction: {sentiment.capitalize()} (Confidence: {confidence:.2f})"
    yield status

# Gradio interface
interface = gr.Interface(
    fn=analyze_sentiment_with_steps,
    inputs=gr.Textbox(
        label="Enter Movie Review",
        placeholder="Type your review in any language...",
        lines=3
    ),
    outputs=gr.Textbox(label="Prediction Steps"),
    live=True,
    title="Multilingual Movie Sentiment Analysis",
    description=(
        "This app analyzes movie reviews written in any language. "
        "It detects the language, translates it to English (if required), "
        "and predicts the sentiment (positive/negative)."
    )
)

# Launch Gradio app
interface.launch(share=True)