core/utils.py

"""
Utility functions for the AI Study Assistant
"""

import re
import os
from typing import List, Dict, Tuple
import json
from datetime import datetime


def create_directory(path: str) -> None:
    """Create a directory if it doesn't exist."""
    if not os.path.exists(path):
        os.makedirs(path)
        print(f"✓ Created directory: {path}")


def read_file(filepath: str) -> str:
    """Read and return file contents."""
    try:
        with open(filepath, 'r', encoding='utf-8') as f:
            return f.read()
    except FileNotFoundError:
        raise FileNotFoundError(f"File not found: {filepath}")
    except Exception as e:
        raise Exception(f"Error reading file {filepath}: {str(e)}")


def write_file(filepath: str, content: str) -> None:
    """Write content to a file."""
    try:
        os.makedirs(os.path.dirname(filepath) or '.', exist_ok=True)
        with open(filepath, 'w', encoding='utf-8') as f:
            f.write(content)
    except Exception as e:
        raise Exception(f"Error writing to file {filepath}: {str(e)}")


def load_prompt_template(prompt_name: str, mode: str = "normal") -> str:
    """
    Load a prompt template from file.
    
    Args:
        prompt_name: Name of the prompt (e.g., 'summary', 'quiz')
        mode: Mode for the prompt (e.g., 'normal', 'detailed')
    
    Returns:
        The prompt template content
    """
    from config import PROMPTS_DIR, MODES_DIR
    
    # Try mode-specific prompt first
    mode_path = os.path.join(MODES_DIR, f"{mode}.txt")
    base_path = os.path.join(PROMPTS_DIR, f"{prompt_name}_prompt.txt")
    
    try:
        return read_file(base_path)
    except FileNotFoundError:
        raise FileNotFoundError(
            f"Prompt template not found: {prompt_name}_prompt.txt\n"
            f"Expected at: {base_path}"
        )


def extract_text_from_pdf(pdf_path: str) -> str:
    """
    Extract text from a PDF file.
    
    Args:
        pdf_path: Path to the PDF file
    
    Returns:
        Extracted text content
    """
    try:
        from PyPDF2 import PdfReader
        
        text = []
        with open(pdf_path, 'rb') as file:
            pdf_reader = PdfReader(file)
            for page_num, page in enumerate(pdf_reader.pages):
                page_text = page.extract_text()
                if page_text:
                    text.append(page_text)
        
        return '\n'.join(text)
    
    except ImportError:
        raise ImportError("PyPDF2 not installed. Install with: pip install PyPDF2")
    except Exception as e:
        raise Exception(f"Error extracting PDF: {str(e)}")


def extract_text_from_file(file_path: str) -> str:
    """
    Extract text from various file types.
    
    Args:
        file_path: Path to the file
    
    Returns:
        Extracted text content
    """
    file_ext = os.path.splitext(file_path)[1].lower()
    
    if file_ext == '.pdf':
        return extract_text_from_pdf(file_path)
    elif file_ext in ['.txt', '.md']:
        return read_file(file_path)
    else:
        raise ValueError(f"Unsupported file type: {file_ext}")


def truncate_text(text: str, max_length: int) -> str:
    """
    Truncate text to maximum length while preserving words.
    
    Args:
        text: The text to truncate
        max_length: Maximum number of characters
    
    Returns:
        Truncated text
    """
    if len(text) <= max_length:
        return text
    
    # Truncate at word boundary
    truncated = text[:max_length].rsplit(' ', 1)[0]
    return truncated + "..."


def clean_text(text: str) -> str:
    """
    Clean and normalize text.
    
    Args:
        text: Text to clean
    
    Returns:
        Cleaned text
    """
    # Remove excess whitespace
    text = re.sub(r'\s+', ' ', text)
    # Remove special characters but keep punctuation
    text = re.sub(r'[^\w\s.,!?;:\-\'"()]', '', text)
    return text.strip()


def extract_json_from_text(text: str) -> Dict:
    """
    Extract JSON object from text response.
    
    Args:
        text: Text potentially containing JSON
    
    Returns:
        Parsed JSON object or empty dict if not found
    """
    try:
        # Look for JSON-like patterns
        json_match = re.search(r'\{.*\}', text, re.DOTALL)
        if json_match:
            json_str = json_match.group(0)
            return json.loads(json_str)
    except json.JSONDecodeError:
        pass
    
    return {}


def format_quiz_response(quiz_text: str) -> List[Dict]:
    """
    Parse and format quiz response into structured questions.
    
    Args:
        quiz_text: Raw quiz text from LLM
    
    Returns:
        List of question dictionaries
    """
    questions = []
    
    # Split by question markers
    q_pattern = r'(?:Q\d+\.|Question \d+:|^\d+\.)'
    
    raw_questions = re.split(q_pattern, quiz_text)[1:]  # Skip first empty part
    
    for idx, q_text in enumerate(raw_questions, 1):
        questions.append({
            'id': idx,
            'question': q_text.strip()[:200],  # First 200 chars
            'raw_text': q_text.strip()
        })
    
    return questions[:5]  # Return max 5 questions


def format_summary(text: str) -> str:
    """
    Format summary response for better readability.
    
    Args:
        text: Raw summary text
    
    Returns:
        Formatted summary
    """
    # Add line breaks between paragraphs
    paragraphs = text.split('\n\n')
    formatted = '\n\n'.join(p.strip() for p in paragraphs if p.strip())
    return formatted


def log_event(event_type: str, details: str) -> None:
    """
    Log events for debugging and monitoring.
    
    Args:
        event_type: Type of event (e.g., 'API_CALL', 'ERROR', 'VALIDATION')
        details: Event details
    """
    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    log_message = f"[{timestamp}] {event_type}: {details}"
    print(log_message)
    
    # Optionally save to log file
    try:
        with open("app.log", "a", encoding='utf-8') as log_file:
            log_file.write(log_message + "\n")
    except:
        pass


def validate_api_response(response: str, min_length: int = 10) -> Tuple[bool, str]:
    """
    Validate API response quality.
    
    Args:
        response: The response to validate
        min_length: Minimum acceptable length
    
    Returns:
        Tuple of (is_valid, message)
    """
    if not response:
        return False, "Empty response from API"
    
    if len(response.strip()) < min_length:
        return False, f"Response too short (minimum {min_length} characters)"
    
    if response.lower().startswith("error"):
        return False, "API returned an error"
    
    return True, "Valid response"


def format_error_message(error: Exception) -> str:
    """
    Format error messages for display to user.
    
    Args:
        error: The exception
    
    Returns:
        User-friendly error message
    """
    error_str = str(error)
    
    if "API" in error_str:
        return f"🔴 API Error: {error_str}\n\nPlease check your API key in config.py"
    elif "file" in error_str.lower():
        return f"🔴 File Error: {error_str}\n\nEnsure the file exists and is readable"
    else:
        return f"🔴 Error: {error_str}"