Commit

src/utils/__init__.py

@@ -0,0 +1 @@
+# ...existing code...

src/utils/file_utils.py

@@ -0,0 +1,142 @@
+# --- Standard Library Imports ---
+import os
+import re
+
+# --- Module Constants ---
+
+# This will be populated at runtime by the main application,
+# but is defined here as it's conceptually related to file/folder naming.
+KNOWN_NAMES = []
+
+MAX_FILENAME_COMPONENT_LENGTH = 150
+
+# Sets of file extensions for quick type checking
+IMAGE_EXTENSIONS = {
+    '.jpg', '.jpeg', '.png', '.gif', '.bmp', '.tiff', '.tif', '.webp',
+    '.heic', '.heif', '.svg', '.ico', '.jfif', '.pjpeg', '.pjp', '.avif'
+}
+VIDEO_EXTENSIONS = {
+    '.mp4', '.mov', '.mkv', '.webm', '.avi', '.wmv', '.flv', '.mpeg',
+    '.mpg', '.m4v', '.3gp', '.ogv', '.ts', '.vob'
+}
+ARCHIVE_EXTENSIONS = {
+    '.zip', '.rar', '.7z', '.tar', '.gz', '.bz2'
+}
+AUDIO_EXTENSIONS = {
+    '.mp3', '.wav', '.aac', '.flac', '.ogg', '.wma', '.m4a', '.opus',
+    '.aiff', '.ape', '.mid', '.midi'
+}
+
+# Words to ignore when trying to generate a folder name from a title
+FOLDER_NAME_STOP_WORDS = {
+    "a", "alone", "am", "an", "and", "at", "be", "blues", "but", "by", "com",
+    "for", "grown", "hard", "he", "her", "his", "hitting", "i", "im", "in", "is", "it", "its",
+    "me", "much", "my", "net", "not", "of", "on", "or", "org", "our", "please",
+    "right", "s", "she", "so", "technically", "tell", "the", "their", "they", "this",
+    "to", "ve", "was", "we", "well", "were", "with", "www", "year", "you", "your",
+}
+
+# --- File and Folder Name Utilities ---
+
+def clean_folder_name(name):
+    """
+    Sanitizes a string to make it a valid folder name.
+    Removes invalid characters and trims whitespace.
+
+    Args:
+        name (str): The input string.
+
+    Returns:
+        str: A sanitized, valid folder name.
+    """
+    if not isinstance(name, str):
+        name = str(name)
+    
+    # Remove characters that are invalid in folder names on most OS
+    cleaned = re.sub(r'[<>:"/\\|?*]', '', name)
+    cleaned = cleaned.strip()
+    
+    # Replace multiple spaces with a single space
+    cleaned = re.sub(r'\s+', ' ', cleaned)
+
+    # If after cleaning the name is empty, provide a default
+    if not cleaned:
+        return "untitled_folder"
+
+    # Truncate to a reasonable length
+    if len(cleaned) > MAX_FILENAME_COMPONENT_LENGTH:
+        cleaned = cleaned[:MAX_FILENAME_COMPONENT_LENGTH]
+
+    # Remove trailing dots or spaces, which can be problematic
+    cleaned = cleaned.rstrip('. ')
+
+    return cleaned if cleaned else "untitled_folder"
+
+
+def clean_filename(name):
+    """
+    Sanitizes a string to make it a valid file name.
+
+    Args:
+        name (str): The input string.
+
+    Returns:
+        str: A sanitized, valid file name.
+    """
+    if not isinstance(name, str):
+        name = str(name)
+        
+    cleaned = re.sub(r'[<>:"/\\|?*]', '_', name)
+    cleaned = cleaned.strip()
+    
+    if not cleaned:
+        return "untitled_file"
+        
+    base_name, ext = os.path.splitext(cleaned)
+    max_base_len = MAX_FILENAME_COMPONENT_LENGTH - len(ext)
+
+    if len(base_name) > max_base_len:
+        if max_base_len > 0:
+            base_name = base_name[:max_base_len]
+        else:
+            # Handle cases where the extension itself is too long
+            return cleaned[:MAX_FILENAME_COMPONENT_LENGTH]
+    
+    return base_name + ext
+
+
+# --- File Type Identification Functions ---
+
+def is_image(filename):
+    """Checks if a filename has a common image extension."""
+    if not filename: return False
+    _, ext = os.path.splitext(filename)
+    return ext.lower() in IMAGE_EXTENSIONS
+
+def is_video(filename):
+    """Checks if a filename has a common video extension."""
+    if not filename: return False
+    _, ext = os.path.splitext(filename)
+    return ext.lower() in VIDEO_EXTENSIONS
+
+def is_zip(filename):
+    """Checks if a filename is a .zip file."""
+    if not filename: return False
+    return filename.lower().endswith('.zip')
+
+def is_rar(filename):
+    """Checks if a filename is a .rar file."""
+    if not filename: return False
+    return filename.lower().endswith('.rar')
+
+def is_archive(filename):
+    """Checks if a filename has a common archive extension."""
+    if not filename: return False
+    _, ext = os.path.splitext(filename)
+    return ext.lower() in ARCHIVE_EXTENSIONS
+
+def is_audio(filename):
+    """Checks if a filename has a common audio extension."""
+    if not filename: return False
+    _, ext = os.path.splitext(filename)
+    return ext.lower() in AUDIO_EXTENSIONS

src/utils/network_utils.py

@@ -0,0 +1,208 @@
+# --- Standard Library Imports ---
+import os
+import re
+from urllib.parse import urlparse
+
+# --- Third-Party Library Imports ---
+# This module might not require third-party libraries directly,
+# but 'requests' is a common dependency for network operations.
+# import requests
+
+
+def parse_cookie_string(cookie_string):
+    """
+    Parses a 'name=value; name2=value2' cookie string into a dictionary.
+
+    Args:
+        cookie_string (str): The cookie string from browser tools.
+
+    Returns:
+        dict or None: A dictionary of cookie names and values, or None if empty.
+    """
+    cookies = {}
+    if cookie_string:
+        for item in cookie_string.split(';'):
+            parts = item.split('=', 1)
+            if len(parts) == 2:
+                name = parts[0].strip()
+                value = parts[1].strip()
+                if name:
+                    cookies[name] = value
+    return cookies if cookies else None
+
+
+def load_cookies_from_netscape_file(filepath, logger_func, target_domain_filter=None):
+    """
+    Loads cookies from a Netscape-formatted cookies.txt file.
+
+    If a target_domain_filter is provided, only cookies for that domain
+    (or its subdomains) are returned.
+
+    Args:
+        filepath (str): The full path to the cookies.txt file.
+        logger_func (callable): Function to use for logging.
+        target_domain_filter (str, optional): The domain to filter cookies for.
+
+    Returns:
+        dict or None: A dictionary of cookie names and values, or None if none are loaded.
+    """
+    cookies = {}
+    try:
+        with open(filepath, 'r', encoding='utf-8') as f:
+            for line in f:
+                line = line.strip()
+                if not line or line.startswith('#'):
+                    continue
+                
+                parts = line.split('\t')
+                if len(parts) == 7:
+                    cookie_domain = parts[0]
+                    name = parts[5]
+                    value = parts[6]
+
+                    if not name:
+                        continue
+
+                    if target_domain_filter:
+                        # Match domain exactly or as a subdomain
+                        host_to_match = target_domain_filter.lower()
+                        cookie_domain_norm = cookie_domain.lower()
+                        if (cookie_domain_norm.startswith('.') and host_to_match.endswith(cookie_domain_norm)) or \
+                           (host_to_match == cookie_domain_norm):
+                            cookies[name] = value
+                    else:
+                        cookies[name] = value
+
+        logger_func(f"   🍪 Loaded {len(cookies)} cookies from '{os.path.basename(filepath)}' for domain '{target_domain_filter or 'any'}'.")
+        return cookies if cookies else None
+    except FileNotFoundError:
+        logger_func(f"   🍪 Cookie file '{os.path.basename(filepath)}' not found.")
+        return None
+    except Exception as e:
+        logger_func(f"   🍪 Error parsing cookie file '{os.path.basename(filepath)}': {e}")
+        return None
+
+
+def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_cookie_file_path, app_base_dir, logger_func, target_domain=None):
+    """
+    Prepares a cookie dictionary from various sources based on user settings.
+    Priority:
+    1. UI-selected file path.
+    2. Domain-specific file in the app directory.
+    3. Default `cookies.txt` in the app directory.
+    4. Manually entered cookie text.
+
+    Args:
+        use_cookie_flag (bool): Whether cookies are enabled in the UI.
+        cookie_text_input (str): The raw text from the cookie input field.
+        selected_cookie_file_path (str): The path to a user-browsed cookie file.
+        app_base_dir (str): The base directory of the application.
+        logger_func (callable): Function for logging.
+        target_domain (str, optional): The domain for which cookies are needed.
+
+    Returns:
+        dict or None: A dictionary of cookies for the request, or None.
+    """
+    if not use_cookie_flag:
+        return None
+
+    # Priority 1: Use the specifically browsed file first
+    if selected_cookie_file_path and os.path.exists(selected_cookie_file_path):
+        cookies = load_cookies_from_netscape_file(selected_cookie_file_path, logger_func, target_domain)
+        if cookies:
+            return cookies
+
+    # Priority 2: Look for a domain-specific cookie file
+    if app_base_dir and target_domain:
+        domain_specific_path = os.path.join(app_base_dir, "data", f"{target_domain}_cookies.txt")
+        if os.path.exists(domain_specific_path):
+            cookies = load_cookies_from_netscape_file(domain_specific_path, logger_func, target_domain)
+            if cookies:
+                return cookies
+
+    # Priority 3: Look for a generic cookies.txt
+    if app_base_dir:
+        default_path = os.path.join(app_base_dir, "appdata", "cookies.txt")
+        if os.path.exists(default_path):
+            cookies = load_cookies_from_netscape_file(default_path, logger_func, target_domain)
+            if cookies:
+                return cookies
+
+    # Priority 4: Fall back to manually entered text
+    if cookie_text_input:
+        cookies = parse_cookie_string(cookie_text_input)
+        if cookies:
+            return cookies
+
+    logger_func(f"   🍪 Cookie usage enabled for '{target_domain or 'any'}', but no valid cookies found.")
+    return None
+
+
+def extract_post_info(url_string):
+    """
+    Parses a URL string to extract the service, user ID, and post ID.
+
+    Args:
+        url_string (str): The URL to parse.
+
+    Returns:
+        tuple: A tuple containing (service, user_id, post_id). Any can be None.
+    """
+    if not isinstance(url_string, str) or not url_string.strip():
+        return None, None, None
+    
+    try:
+        parsed_url = urlparse(url_string.strip())
+        path_parts = [part for part in parsed_url.path.strip('/').split('/') if part]
+        
+        # Standard format: /<service>/user/<user_id>/post/<post_id>
+        if len(path_parts) >= 3 and path_parts[1].lower() == 'user':
+            service = path_parts[0]
+            user_id = path_parts[2]
+            post_id = path_parts[4] if len(path_parts) >= 5 and path_parts[3].lower() == 'post' else None
+            return service, user_id, post_id
+            
+        # API format: /api/v1/<service>/user/<user_id>...
+        if len(path_parts) >= 5 and path_parts[0:2] == ['api', 'v1'] and path_parts[3].lower() == 'user':
+            service = path_parts[2]
+            user_id = path_parts[4]
+            post_id = path_parts[6] if len(path_parts) >= 7 and path_parts[5].lower() == 'post' else None
+            return service, user_id, post_id
+
+    except Exception as e:
+        print(f"Debug: Exception during URL parsing for '{url_string}': {e}")
+
+    return None, None, None
+
+
+def get_link_platform(url):
+    """
+    Identifies the platform of a given URL based on its domain.
+
+    Args:
+        url (str): The URL to identify.
+
+    Returns:
+        str: The name of the platform (e.g., 'mega', 'google drive') or 'external'.
+    """
+    try:
+        domain = urlparse(url).netloc.lower()
+        if 'drive.google.com' in domain: return 'google drive'
+        if 'mega.nz' in domain or 'mega.io' in domain: return 'mega'
+        if 'dropbox.com' in domain: return 'dropbox'
+        if 'patreon.com' in domain: return 'patreon'
+        if 'gofile.io' in domain: return 'gofile'
+        if 'instagram.com' in domain: return 'instagram'
+        if 'twitter.com' in domain or 'x.com' in domain: return 'twitter/x'
+        if 'discord.gg' in domain or 'discord.com/invite' in domain: return 'discord invite'
+        if 'pixiv.net' in domain: return 'pixiv'
+        if 'kemono.su' in domain or 'kemono.party' in domain: return 'kemono'
+        if 'coomer.su' in domain or 'coomer.party' in domain: return 'coomer'
+        
+        # Fallback to a generic name for other domains
+        parts = domain.split('.')
+        if len(parts) >= 2:
+            return parts[-2]
+        return 'external'
+    except Exception:
+        return 'unknown'

src/utils/text_utils.py

@@ -0,0 +1,207 @@
+# --- Standard Library Imports ---
+import re
+import html
+
+# --- Local Application Imports ---
+# Import from file_utils within the same package
+from .file_utils import clean_folder_name, FOLDER_NAME_STOP_WORDS
+
+# --- Module Constants ---
+
+# Regular expression patterns for cleaning up titles before matching against Known.txt
+KNOWN_TXT_MATCH_CLEANUP_PATTERNS = [
+    r'\bcum\b',
+    r'\bnsfw\b',
+    r'\bsfw\b',
+    r'\bweb\b',
+    r'\bhd\b',
+    r'\bhi\s*res\b',
+    r'\bhigh\s*res\b',
+    r'\b\d+p\b',
+    r'\b\d+k\b',
+    r'\[OC\]',
+    r'\[Request(?:s)?\]',
+    r'\bCommission\b',
+    r'\bComm\b',
+    r'\bPreview\b',
+]
+
+# --- Text Matching and Manipulation Utilities ---
+
+def is_title_match_for_character(post_title, character_name_filter):
+    """
+    Checks if a post title contains a specific character name as a whole word.
+    Case-insensitive.
+
+    Args:
+        post_title (str): The title of the post.
+        character_name_filter (str): The character name to search for.
+
+    Returns:
+        bool: True if the name is found as a whole word, False otherwise.
+    """
+    if not post_title or not character_name_filter:
+        return False
+        
+    # Use word boundaries (\b) to match whole words only
+    pattern = r"(?i)\b" + re.escape(str(character_name_filter).strip()) + r"\b"
+    return bool(re.search(pattern, post_title))
+
+
+def is_filename_match_for_character(filename, character_name_filter):
+    """
+    Checks if a filename contains a character name. This is a simple substring check.
+    Case-insensitive.
+
+    Args:
+        filename (str): The name of the file.
+        character_name_filter (str): The character name to search for.
+
+    Returns:
+        bool: True if the substring is found, False otherwise.
+    """
+    if not filename or not character_name_filter:
+        return False
+        
+    return str(character_name_filter).strip().lower() in filename.lower()
+
+
+def strip_html_tags(html_text):
+    """
+    Removes HTML tags from a string and cleans up resulting whitespace.
+
+    Args:
+        html_text (str): The input string containing HTML.
+
+    Returns:
+        str: The text with HTML tags removed.
+    """
+    if not html_text:
+        return ""
+    # First, unescape HTML entities like & -> &
+    text = html.unescape(str(html_text))
+    # Remove all tags
+    text_after_tag_removal = re.sub(r'<[^>]+>', ' ', text)
+    # Replace multiple whitespace characters with a single space
+    cleaned_text = re.sub(r'\s+', ' ', text_after_tag_removal).strip()
+    return cleaned_text
+
+
+def extract_folder_name_from_title(title, unwanted_keywords):
+    """
+    Extracts a plausible folder name from a post title by finding the first
+    significant word that isn't a stop-word.
+
+    Args:
+        title (str): The post title.
+        unwanted_keywords (set): A set of words to ignore.
+
+    Returns:
+        str: The extracted folder name, or 'Uncategorized'.
+    """
+    if not title:
+        return 'Uncategorized'
+        
+    title_lower = title.lower()
+    # Find all whole words in the title
+    tokens = re.findall(r'\b[\w\-]+\b', title_lower)
+    
+    for token in tokens:
+        clean_token = clean_folder_name(token)
+        if clean_token and clean_token.lower() not in unwanted_keywords:
+            return clean_token
+            
+    # Fallback to cleaning the full title if no single significant word is found
+    cleaned_full_title = clean_folder_name(title)
+    return cleaned_full_title if cleaned_full_title else 'Uncategorized'
+
+
+def match_folders_from_title(title, names_to_match, unwanted_keywords):
+    """
+    Matches folder names from a title based on a list of known name objects.
+    Each name object is a dict: {'name': 'PrimaryName', 'aliases': ['alias1', ...]}
+
+    Args:
+        title (str): The post title to check.
+        names_to_match (list): A list of known name dictionaries.
+        unwanted_keywords (set): A set of folder names to ignore.
+
+    Returns:
+        list: A sorted list of matched primary folder names.
+    """
+    if not title or not names_to_match:
+        return []
+
+    # Clean the title by removing common tags like [OC], [HD], etc.
+    cleaned_title = title
+    for pat_str in KNOWN_TXT_MATCH_CLEANUP_PATTERNS:
+        cleaned_title = re.sub(pat_str, ' ', cleaned_title, flags=re.IGNORECASE)
+    cleaned_title = re.sub(r'\s+', ' ', cleaned_title).strip()
+    title_lower = cleaned_title.lower()
+
+    matched_cleaned_names = set()
+    
+    # Sort by name length descending to match longer names first (e.g., "Cloud Strife" before "Cloud")
+    sorted_name_objects = sorted(names_to_match, key=lambda x: len(x.get("name", "")), reverse=True)
+
+    for name_obj in sorted_name_objects:
+        primary_folder_name = name_obj.get("name")
+        aliases = name_obj.get("aliases", [])
+        if not primary_folder_name or not aliases:
+            continue
+            
+        for alias in aliases:
+            alias_lower = alias.lower()
+            if not alias_lower: continue
+            
+            # Use word boundaries for accurate matching
+            pattern = r'\b' + re.escape(alias_lower) + r'\b'
+            if re.search(pattern, title_lower):
+                cleaned_primary_name = clean_folder_name(primary_folder_name)
+                if cleaned_primary_name.lower() not in unwanted_keywords:
+                    matched_cleaned_names.add(cleaned_primary_name)
+                    break # Move to the next name object once a match is found for this one
+                    
+    return sorted(list(matched_cleaned_names))
+
+
+def match_folders_from_filename_enhanced(filename, names_to_match, unwanted_keywords):
+    """
+    Matches folder names from a filename, prioritizing longer and more specific aliases.
+
+    Args:
+        filename (str): The filename to check.
+        names_to_match (list): A list of known name dictionaries.
+        unwanted_keywords (set): A set of folder names to ignore.
+
+    Returns:
+        list: A sorted list of matched primary folder names.
+    """
+    if not filename or not names_to_match:
+        return []
+
+    filename_lower = filename.lower()
+    matched_primary_names = set()
+
+    # Create a flat list of (alias, primary_name) tuples to sort by alias length
+    alias_map_to_primary = []
+    for name_obj in names_to_match:
+        primary_name = name_obj.get("name")
+        if not primary_name: continue
+        
+        cleaned_primary_name = clean_folder_name(primary_name)
+        if not cleaned_primary_name or cleaned_primary_name.lower() in unwanted_keywords:
+            continue
+
+        for alias in name_obj.get("aliases", []):
+            if alias.lower():
+                alias_map_to_primary.append((alias.lower(), cleaned_primary_name))
+    
+    # Sort by alias length, descending, to match longer aliases first
+    alias_map_to_primary.sort(key=lambda x: len(x[0]), reverse=True)
+
+    for alias_lower, primary_name_for_alias in alias_map_to_primary:
+        if filename_lower.startswith(alias_lower):
+            matched_primary_names.add(primary_name_for_alias)
+
+    return sorted(list(matched_primary_names))