import os

import re

import time

def clean_filepaths(filepaths, retry_interval=1):

"""

Cleans a list of filepaths for manual execution, handling potential issues

like invalid characters and long paths.

Args:

filepaths (list): A list of filepaths to clean.

retry_interval (int): The number of seconds to wait before retrying

if a path cleaning fails.

Returns:

list: A list of cleaned filepaths. Returns the original filepath if cleaning fails after multiple attempts.

"""

cleaned_paths = []

for filepath in filepaths:

cleaned_path = filepath # Initialize with the original path

max_retries = 3 # Limit the number of retry attempts

for attempt in range(max_retries):

try:

# 1. Remove invalid characters

cleaned_path = re.sub(r'[\\/*?:"<>|]', '', cleaned_path)

# 2. Limit path length (Windows limit: 260 characters)

max_length = 260

if len(cleaned_path) > max_length:

# Find the last backslash and truncate

last_backslash = cleaned_path.rfind('\\')

if last_backslash != -1:

cleaned_path = cleaned_path[:last_backslash + 1] # include the backslash

else:

cleaned_path = cleaned_path[:max_length] #truncate if no backslashes

# 3. Normalize path (e.g., convert to forward slashes on Windows)

cleaned_path = cleaned_path.replace('\\', '/') #cross-platform

# Check if the path is valid (basic check - can be expanded)

if os.path.exists(cleaned_path):

break # Path is valid, exit retry loop

else:

print(f"Attempt {attempt + 1}/{max_retries}: Path '{filepath}' is invalid. Retrying...")

time.sleep(retry_interval)

except Exception as e:

print(f"Error cleaning path '{filepath}' (attempt {attempt + 1}/{max_retries}): {e}. Retrying...")

time.sleep(retry_interval)

cleaned_paths.append(cleaned_path) # Add the cleaned path to the list

return cleaned_paths