import os
import nltk
import csv
import logging
from tqdm import tqdm
import gradio as gr
from transformers import pipeline
from huggingface_hub import HfApi, upload_file, HfFolder
import time

# Setup Logging
logging.basicConfig(filename='app.log', level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Download All NLTK Data
nltk.download('all')

# Constants
HF_REPO = "katsukiai/DeepFocus-X3"
TOKENIZER = 'bert-base-uncased'
MODELS = ["bert-base-uncased", "gpt2", "roberta-base", "distilbert-base-uncased", "albert-v2"]  # Add more models as needed

# Initialize Models
models = {model: pipeline('feature-extraction', model=model) for model in MODELS}

# Functions
def process_text(text):
    tokens = nltk.word_tokenize(text)
    words = list(set(tokens))
    means = {}
    for word in tqdm(words, desc="Processing Words"):
        word_means = {}
        for model_name, model in models.items():
            try:
                output = model(word)
                word_means[model_name] = output[0].mean().item()
            except Exception as e:
                logging.error(f"Error processing word {word} with model {model_name}: {e}")
                word_means[model_name] = None
        means[word] = word_means
    return {"tokenizer": tokens, "words": words, "meaning": means}

def save_to_csv(data, filename="output.csv"):
    with open(filename, 'w', newline='', encoding='utf-8') as csvfile:
        writer = csv.DictWriter(csvfile, fieldnames=["word", "meanings"])
        writer.writeheader()
        for word in data['words']:
            writer.writerow({
                "word": word,
                "meanings": str(data['meaning'][word])
            })

def train_dataset():
    text = "Your long text goes here..."
    data = process_text(text)
    save_to_csv(data)
    logging.info("Dataset processed and saved to CSV.")

def generate_report():
    with open('app.log', 'r') as log_file:
        log_content = log_file.read()
    return log_content

def get_uptime():
    uptime = time.strftime('%H:%M:%S', time.gmtime(time.time() - start_time))
    return f"Uptime: {uptime}"

# Gradio Interface
def generate_all(text):
    data = process_text(text)
    save_to_csv(data)
    return "Processed data saved to output.csv"

# Custom CSS for Tailwind CSS
custom_css = """
<style>
@import url('https://cdn.jsdelivr.net/npm/tailwindcss@2.2.19/dist/tailwind.min.css');
body {
    font-family: 'Arial', sans-serif;
}
#title {
    text-align: center;
    margin-bottom: 20px;
}
#input_text, #output_text, #log_output {
    width: 100%;
    max-width: 600px;
    margin: 10px 0;
}
#generate_button, #report_button, #save_settings_button {
    width: 100%;
    max-width: 200px;
    margin: 10px 0;
}
#settings_container {
    margin-top: 20px;
}
</style>
"""

start_time = time.time()

with gr.Blocks(css=custom_css) as iface:
    gr.Markdown("# DeepFocus-X3", elem_id="title")
    
    with gr.Tab("Generate All"):
        with gr.Row():
            input_text = gr.Textbox(label="Input Text", placeholder="Enter your text here...", elem_id="input_text")
            output_text = gr.Textbox(label="Output", placeholder="Output will appear here...", elem_id="output_text")
            generate_button = gr.Button("Generate", elem_id="generate_button")
        generate_button.click(fn=generate_all, inputs=input_text, outputs=output_text)
        
    with gr.Tab("Logs"):
        with gr.Row():
            log_output = gr.Textbox(label="Logs", placeholder="Logs will appear here...", elem_id="log_output")
            report_button = gr.Button("Report using Logs", elem_id="report_button")
        report_button.click(fn=generate_report, outputs=log_output)
        
    with gr.Tab("Settings"):
        with gr.Row():
            commit_input = gr.Textbox(label="Commit", placeholder="Enter commit message", elem_id="commit_input")
            username_input = gr.Textbox(label="Username", placeholder="Enter your username", elem_id="username_input")
            metadata_input = gr.Textbox(label="Metadata", placeholder="Enter metadata", elem_id="metadata_input")
            uptime_text = gr.Textbox(label="Uptime", placeholder="Uptime will appear here...", elem_id="uptime_text", interactive=False)
            save_settings_button = gr.Button("Save Settings", elem_id="save_settings_button")
        
        save_settings_button.click(
            fn=lambda commit, username, metadata: f"Settings saved: {commit}, {username}, {metadata}",
            inputs=[commit_input, username_input, metadata_input],
            outputs=[uptime_text]  # Reusing uptime_text for output to show settings saved message
        )
        
        # Update uptime every 10 seconds
        iface.set_event_handler("load", lambda: uptime_text.update(get_uptime()), every=10)

# Run and Push to HuggingFace
def run_and_push():
    train_dataset()
    try:
        api = HfApi()
        api.create_repo(repo_id=HF_REPO, private=False, exist_ok=True)
        upload_file(
            path_or_fileobj="output.csv",
            path_in_repo="output.csv",
            repo_id=HF_REPO
        )
        logging.info("Dataset pushed to HuggingFace.")
    except Exception as e:
        logging.error(f"Error uploading to HuggingFace: {e}")
        try:
            # Log the error to a separate errors repo
            errors_repo = "katsukiai/errors"
            api.create_repo(repo_id=errors_repo, private=False, exist_ok=True)
            with open('upload_error.log', 'w') as error_file:
                error_file.write(f"Error uploading to HuggingFace: {e}\n")
            upload_file(
                path_or_fileobj="upload_error.log",
                path_in_repo="upload_error.log",
                repo_id=errors_repo
            )
            logging.info("Error log pushed to HuggingFace errors repo.")
        except Exception as e2:
            logging.error(f"Failed to log error to HuggingFace errors repo: {e2}")

if __name__ == "__main__":
    iface.launch()
    run_and_push()