import os
import re
import streamlit as st
import google.generativeai as genai
from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
from db import get_entry_by_index

# Configure Gemini API key
GEMINI_API_KEY = os.getenv("gemini_api")
if GEMINI_API_KEY:
    genai.configure(api_key=GEMINI_API_KEY)
else:
    st.error("⚠️ Google API key is missing! Set it in Hugging Face Secrets.")

# Load pre-trained sentiment analysis model
MODEL_NAME = "cardiffnlp/twitter-roberta-base-sentiment"
try:
    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
    model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
    sentiment_pipeline = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
except Exception as e:
    st.error(f"❌ Error loading sentiment model: {e}")

# Load Topic Extraction Model
try:
    topic_pipeline = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
except Exception as e:
    st.error(f"❌ Error loading topic extraction model: {e}")

# Predefined topic labels for classification
TOPIC_LABELS = [
    "Technology", "Politics", "Business", "Sports", "Entertainment",
    "Health", "Science", "Education", "Finance", "Travel", "Food"
]

def analyze_sentiment(text):
    try:
        result = sentiment_pipeline(text)[0]
        label = result['label']
        score = result['score']
        sentiment_mapping = {
            "LABEL_0": "Negative",
            "LABEL_1": "Neutral",
            "LABEL_2": "Positive"
        }
        return sentiment_mapping.get(label, "Unknown"), score
    except Exception as e:
        return f"Error analyzing sentiment: {e}", None

def extract_topic(text):
    try:
        result = topic_pipeline(text, TOPIC_LABELS)
        top_topic = result["labels"][0]
        confidence = result["scores"][0]
        return top_topic, confidence
    except Exception as e:
        return f"Error extracting topic: {e}", None

# Helper function to parse a data entry index from the user's prompt.
# It looks for a pattern like "data entry 1" or "entry 1" (case insensitive).
def parse_entry_index(prompt):
    match = re.search(r'(?:data\s+entry|entry)\s+(\d+)', prompt, re.IGNORECASE)
    if match:
        try:
            # Convert to zero-based index.
            return int(match.group(1)) - 1
        except ValueError:
            return None
    return None

def chatbot_response(user_prompt):
    if not user_prompt:
        return None, None, None, None, None

    try:
        # Check if the prompt contains a specific data entry request.
        index = parse_entry_index(user_prompt)
        if index is not None:
            # Fetch the specified entry from MongoDB.
            entry = get_entry_by_index(index)
            if entry is None:
                return f"❌ No entry found for data entry {index+1}.", None, None, None, None
            entry_text = entry.get("text", "No text available.")
            # Construct a simple generative prompt.
            combined_prompt = f"Let's break down this tweet-like MongoDB entry:\n{entry_text}"
            # Analyze sentiment and topic on the entry's text.
            sentiment_label, sentiment_confidence = analyze_sentiment(entry_text)
            topic_label, topic_confidence = extract_topic(entry_text)
        else:
            # For any other prompt, use it as is.
            combined_prompt = user_prompt
            sentiment_label, sentiment_confidence = analyze_sentiment(user_prompt)
            topic_label, topic_confidence = extract_topic(user_prompt)
        
        # Generate AI response using Gemini with the constructed prompt.
        model_gen = genai.GenerativeModel("gemini-1.5-pro")
        ai_response = model_gen.generate_content(combined_prompt)

        # Return the generative response and the separately computed sentiment and category.
        return ai_response.text, sentiment_label, sentiment_confidence, topic_label, topic_confidence
    except Exception as e:
        return f"❌ Error: {e}", None, None, None, None