Syncronize content of files across directories, keeping the most up-to-date edits

sync_lists_across_files.py

# Syncronize files across directories, keeping the most up-to-date edits

lists = [
    'directory_1/list_of_terms.yaml', 
    'directory_2/list_of_terms.txt'
]

list_items = {} # Form: [item] = [time(integer), keep(boolean)]                               

# Generate full list of single_listed items (stores all possible terms)                                    
for single_list in lists:
    with open(single_list, 'r') as f:
        for row in f:
            list_items[row.strip()] = [0, True]

# Sync lists, identifying whther to keep each item                                            
for single_list in lists:

    last_update  = os.stat(single_list).st_mtime # Last time file edited
    current_list = {} # Dictionary to keep track of last updated time

    # Generate dict from current list                                                         
    with open(single_list, 'r') as f:
        for row in f:
            current_list[row.strip()] = [last_update, True]

    # Iterate over all items to determine if we should utilize that                           
    for item in list_items:
        # Only keep the most recent updated item
        if last_update > list_items[item][0]:
            keep_item = True # Default, keep items                                             
            if item not in current_list:                                     
                keep_item = False # Mark for deletion 
            list_items[item] = [last_update, keep_item]

# Rewrite all the files to have the master list                                         
for single_list in lists:
    with open(single_list, 'w') as f:
        for item in list_items:                                         
            if list_items[item][1]: # Marked for saving the term
                f.write(item + "\n")