import os
import tempfile
import subprocess
from typing import Optional, Tuple, List
import pytube
from src.video_processing import extract_audio_from_video
from src.quiz_processing import analyze_document
import docx
import PyPDF2
import re


def parse_quiz_content(quiz_text):
    questions = []
    lines = quiz_text.split('\n')
    current_question = None
    
    for line in lines:
        line = line.strip()
        if not line:
            continue
            
        q_match = re.match(r'^(?:\d+\.|\[?Q\d+\]?\.?)\s+(.*)', line, re.IGNORECASE)
        if q_match:
            if current_question:
                questions.append(current_question)
            current_question = {"question": q_match.group(1), "answer": ""}
        elif current_question and line.lower().startswith(("answer:", "a:", "ans:")):
            answer_text = re.sub(r'^(?:answer:|a:|ans:)\s*', '', line, flags=re.IGNORECASE)
            current_question["answer"] = answer_text.strip()
    
    if current_question:
        questions.append(current_question)
        
    return {"questions": questions}