# Aplicacion principal para cargar modelo, generar los prompts, y el la explicacion de los datos
import streamlit as st
import os
import re
import pandas as pd

from supabase import create_client, Client
from transformers import pipeline

# funcion para extraccion de codigo del modelo

def extract_code(llm_output):
        
        code_match = re.search(r"```python\n(.*?)\n```", llm_output, re.DOTALL)
        if code_match:
            return code_match.group(1)
        return None

# funcion para prompts y ejemplo basico

#prompt = "Generate a graph idea based on European fertility data."
#output = generator(prompt, max_length=50, num_return_sequences=1)[0]['generated_text']

# Aqui vamos a añadir los prompts, comparativa entre paises, lo ideal es mas de uno, pero podriamos iniciar en un 1v1 con la metrica 
# Vamos a generar un codigo para luego ejecutarlo con un exec() y poder imprimir en Streamlit st.pyplot()

def generate_graph_prompt(country1, country2, metric, start_year, end_year):
    
    prompt = f"""You have access to a database of European countries with data on {metric}, labor force participation, population, and their predictions for future years.
        Generate Python code using matplotlib to create a line graph showing the trend of {metric} for {country1} and {country2} from {start_year} to {end_year}.
        Also, provide a concise explanation of what this graph represents for an end user who might not be familiar with the data.
        """
    return prompt

# Ejemplo de como quedaria el prompt que recibiria el modelo
#prompt = generate_graph_prompt("Germany", "France", "fertility rate", 2020, 2030)


#Aqui van las credenciales, conectar las credenciales de Supabase en "Secrets"
# conexion a supabase

SUPABASE_URL = os.environ.get("SUPABASE_URL")
SUPABASE_KEY = os.environ.get("SUPABASE_KEY")
supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)

def load_data():
    
    """fertility, geo data, labor, population y predictions """
    try:
        response = supabase.from_("LabourForecast").select("*").execute()
        if response.error:
            st.error(f"Error fetching data: {response.error}")
            return pd.DataFrame()
        else:
            return pd.DataFrame(response.data)
    except Exception as e:
        st.error(f"An error occurred: {e}")
        return pd.DataFrame()



# Pendiente las Keys, dependiendo del modelo que escojamos

model_name = "google/flan-t5-small"  # Probando modelos
generator = pipeline("text-generation", model=model_name)

# Inicio de Streamlit (hice lo basico, podemos mejorarla)

st.title("_Europe GraphGen_  :blue[Graph generator] :flag-eu:")
user_input = st.text_input("What graphics do you have in mind")
generate_button = st.button("Generate")

if generate_button and user_input:
    
    if not SUPABASE_URL or not SUPABASE_KEY:
    print("Error: Supabase URL and/or Key not found in environment variables.")
    
    else:
        try:
            
            response = supabase.table("LabourForecast").select("*").limit(1).execute()
    
            if response.error:
                print(f"Supabase connection test failed with error: {response.error}")
            else:
                print("Supabase connection test successful!")
                print("First row from 'your_test_table':", response.data)
    
        except Exception as e:
            print(f"An unexpected error occurred during Supabase connection test: {e}")