import os
import streamlit as st
import google.generativeai as genai
from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer
from db import get_dataset_summary, 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:
        sentiment_result = sentiment_pipeline(text)[0]
        label = sentiment_result['label']
        score = sentiment_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:
        topic_result = topic_pipeline(text, TOPIC_LABELS)
        top_topic = topic_result["labels"][0]
        confidence = topic_result["scores"][0]
        return top_topic, confidence
    except Exception as e:
        return f"Error extracting topic: {e}", None

def is_dataset_query(prompt):
    keywords = ["dataset", "data", "csv", "mongodb", "historical"]
    return any(keyword in prompt.lower() for keyword in keywords)

def extract_entry_index(prompt):
    # Map ordinal words to indices (0-indexed)
    ordinals = {
        "first": 0,
        "1st": 0,
        "second": 1,
        "2nd": 1,
        "third": 2,
        "3rd": 2,
        "fourth": 3,
        "4th": 3,
        "fifth": 4,
        "5th": 4,
    }
    for word, index in ordinals.items():
        if word in prompt.lower():
            return index
    return None

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

    # Check if the query is about a specific dataset entry.
    entry_index = extract_entry_index(user_prompt)
    if entry_index is not None:
        entry_text = get_entry_by_index(entry_index)
        if entry_text:
            # Create a combined prompt for Gemini to generate detailed insights.
            combined_prompt = (
                f"Analyze the following dataset entry from MongoDB:\n\n{entry_text}\n\n"
                "Provide detailed insights, including sentiment analysis and category extraction."
            )
            model_gen = genai.GenerativeModel("gemini-1.5-pro")
            ai_response = model_gen.generate_content(combined_prompt)
            # Analyze the entry text.
            sentiment_label, sentiment_confidence = analyze_sentiment(entry_text)
            topic_label, topic_confidence = extract_topic(entry_text)
            return ai_response.text, sentiment_label, sentiment_confidence, topic_label, topic_confidence
        else:
            return f"❌ No entry found for index {entry_index+1}.", None, None, None, None

    # Otherwise, if the query is about the dataset in general.
    if is_dataset_query(user_prompt):
        dataset_insights = get_dataset_summary()
        combined_prompt = (
            f"{user_prompt}\n\nDataset Insights:\n{dataset_insights}\n\n"
            "Provide a detailed answer that incorporates these dataset insights."
        )
    else:
        combined_prompt = user_prompt

    model_gen = genai.GenerativeModel("gemini-1.5-pro")
    ai_response = model_gen.generate_content(combined_prompt)

    # Run sentiment analysis and topic extraction on the original user prompt.
    sentiment_label, sentiment_confidence = analyze_sentiment(user_prompt)
    topic_label, topic_confidence = extract_topic(user_prompt)

    return ai_response.text, sentiment_label, sentiment_confidence, topic_label, topic_confidence