utils/utils.py

"""
Utility functions for the Logo Downloader application
"""
import os
import re
import json
import time
from pathlib import Path
from typing import List, Optional
from urllib.parse import urlparse
import logging

from services.appconfig import IMAGE_SIGNATURES, MIN_FILE_SIZE, MAX_FILE_SIZE

# Setup logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)


def create_safe_filename(name: str) -> str:
    """
    Create a safe filename from entity name
    
    Args:
        name (str): Entity name
        
    Returns:
        str: Safe filename
    """
    safe_name = re.sub(r'[^\w\s-]', '', name).strip()
    safe_name = re.sub(r'[-\s]+', '_', safe_name)
    return safe_name


def get_file_extension(url: str) -> str:
    """
    Extract file extension from URL
    
    Args:
        url (str): Image URL
        
    Returns:
        str: File extension
    """
    parsed_url = urlparse(url)
    extension = os.path.splitext(parsed_url.path)[1]
    
    if not extension or extension.lower() not in ['.png', '.jpg', '.jpeg', '.svg', '.webp']:
        extension = '.png'
    
    return extension


def is_valid_image_file(filepath: str) -> bool:
    """
    Validate if file is a proper image
    
    Args:
        filepath (str): Path to image file
        
    Returns:
        bool: True if valid image
    """
    try:
        # Check file exists and size
        if not os.path.exists(filepath):
            return False
            
        file_size = os.path.getsize(filepath)
        if file_size < MIN_FILE_SIZE or file_size > MAX_FILE_SIZE:
            logger.warning(f"Invalid file size: {file_size}")
            return False
        
        # Check image signature
        with open(filepath, 'rb') as f:
            header = f.read(12)
        
        for signature in IMAGE_SIGNATURES:
            if header.startswith(signature):
                return True
        
        return False
        
    except Exception as e:
        logger.error(f"Error validating image: {e}")
        return False


def create_directory(path: Path) -> bool:
    """
    Create directory if it doesn't exist
    
    Args:
        path (Path): Directory path
        
    Returns:
        bool: True if successful
    """
    try:
        path.mkdir(parents=True, exist_ok=True)
        return True
    except Exception as e:
        logger.error(f"Error creating directory {path}: {e}")
        return False


def clean_up_file(filepath: str) -> None:
    """
    Remove file if it exists
    
    Args:
        filepath (str): Path to file to remove
    """
    try:
        if os.path.exists(filepath):
            os.remove(filepath)
    except Exception as e:
        logger.error(f"Error removing file {filepath}: {e}")


def parse_json_safely(json_string: str) -> Optional[dict]:
    """
    Safely parse JSON string
    
    Args:
        json_string (str): JSON string to parse
        
    Returns:
        dict or None: Parsed JSON or None if failed
    """
    try:
        return json.loads(json_string)
    except json.JSONDecodeError:
        return None


def rate_limit_delay(delay: float = 1.0) -> None:
    """
    Add delay between requests to be respectful to servers
    
    Args:
        delay (float): Delay in seconds
    """
    time.sleep(delay)


def format_file_size(size_bytes: int) -> str:
    """
    Format file size in human readable format
    
    Args:
        size_bytes (int): Size in bytes
        
    Returns:
        str: Formatted size string
    """
    if size_bytes < 1024:
        return f"{size_bytes} B"
    elif size_bytes < 1024 * 1024:
        return f"{size_bytes / 1024:.1f} KB"
    else:
        return f"{size_bytes / (1024 * 1024):.1f} MB"


def truncate_text(text: str, max_length: int = 100) -> str:
    """
    Truncate text to specified length
    
    Args:
        text (str): Text to truncate
        max_length (int): Maximum length
        
    Returns:
        str: Truncated text
    """
    if len(text) <= max_length:
        return text
    return text[:max_length - 3] + "..."