import gradio as gr
import requests
from fpdf import FPDF
import nltk
import os
import tempfile
from nltk.tokenize import sent_tokenize
import random

# Attempt to download punkt tokenizer
try:
    nltk.download("punkt")
except:
    print("NLTK punkt tokenizer download failed. Using custom tokenizer.")

def custom_sent_tokenize(text):
    return text.split(". ")

def transcribe(audio_path):
    with open(audio_path, "rb") as audio_file:
        audio_data = audio_file.read()

    groq_api_endpoint = "https://api.groq.com/openai/v1/audio/transcriptions"
    headers = {
        "Authorization": "Bearer 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",  # Replace with your actual API key
    }
    files = {
        'file': ('audio.wav', audio_data, 'audio/wav'),
    }
    data = {
        'model': 'whisper-large-v3-turbo',
        'response_format': 'json',
        'language': 'en',
    }

    response = requests.post(groq_api_endpoint, headers=headers, files=files, data=data)

    if response.status_code == 200:
        result = response.json()
        transcript = result.get("text", "No transcription available.")
        return generate_notes(transcript)
    else:
        error_msg = response.json().get("error", {}).get("message", "Unknown error.")
        print(f"API Error: {error_msg}")
        return create_error_pdf(f"API Error: {error_msg}")

def generate_notes(transcript):
    try:
        sentences = sent_tokenize(transcript)
    except LookupError:
        sentences = custom_sent_tokenize(transcript)

    # Generate long questions
    long_questions = [f"Explain the concept discussed in: '{sentence}'." for sentence in sentences[:5]]

    # Generate short questions
    short_questions = [f"What does '{sentence.split()[0]}' mean in the context of this text?" for sentence in sentences[:5]]

    # Generate MCQs with relevant distractors
    mcqs = []
    for sentence in sentences[:5]:
        if len(sentence.split()) > 1:  # Ensure there are enough words to create meaningful options
            key_word = sentence.split()[0]  # Use the first word as a key term
            distractors = ["Term A", "Term B", "Term C"]  # Replace with relevant terms if needed
            options = [key_word] + distractors
            random.shuffle(options)  # Shuffle options for randomness
            mcq = {
                "question": f"What is '{key_word}' based on the context?",
                "options": options,
                "answer": key_word
            }
            mcqs.append(mcq)

    # Generate and save a structured PDF
    pdf_path = create_pdf(transcript, long_questions, short_questions, mcqs)
    return pdf_path

def create_pdf(transcript, long_questions, short_questions, mcqs):
    pdf = FPDF()
    pdf.add_page()
    
    # Add title
    pdf.set_font("Arial", "B", 16)
    pdf.cell(200, 10, "Transcription Notes and Questions", ln=True, align="C")

    # Add transcription content
    pdf.set_font("Arial", "", 12)
    pdf.multi_cell(0, 10, f"Transcription:\n{transcript.encode('latin1', 'replace').decode('latin1')}\n\n")

    # Add long questions
    pdf.set_font("Arial", "B", 14)
    pdf.cell(200, 10, "Long Questions", ln=True)
    pdf.set_font("Arial", "", 12)
    for question in long_questions:
        pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")

    # Add short questions
    pdf.set_font("Arial", "B", 14)
    pdf.cell(200, 10, "Short Questions", ln=True)
    pdf.set_font("Arial", "", 12)
    for question in short_questions:
        pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")

    # Add MCQs
    pdf.set_font("Arial", "B", 14)
    pdf.cell(200, 10, "Multiple Choice Questions (MCQs)", ln=True)
    pdf.set_font("Arial", "", 12)
    for mcq in mcqs:
        pdf.multi_cell(0, 10, f"Q: {mcq['question'].encode('latin1', 'replace').decode('latin1')}")
        for option in mcq["options"]:
            pdf.multi_cell(0, 10, f"   - {option.encode('latin1', 'replace').decode('latin1')}")
        pdf.multi_cell(0, 10, f"Answer: {mcq['answer'].encode('latin1', 'replace').decode('latin1')}\n")

    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
        pdf.output(temp_pdf.name)
        pdf_path = temp_pdf.name
    
    return pdf_path

def create_error_pdf(message):
    pdf = FPDF()
    pdf.add_page()
    pdf.set_font("Arial", "B", 16)
    pdf.cell(200, 10, "Error Report", ln=True, align="C")
    pdf.set_font("Arial", "", 12)
    pdf.multi_cell(0, 10, message.encode('latin1', 'replace').decode('latin1'))
    
    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
        pdf.output(temp_pdf.name)
        error_pdf_path = temp_pdf.name
    
    return error_pdf_path

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(type="filepath"),
    outputs=gr.File(label="Download PDF with Notes or Error Report"),
    title="Voice to Text Converter and Notes Generator",
    description="This app converts audio to text and generates academic questions including long, short, and multiple-choice questions."
)

iface.launch()