fixSorting.py

import re
from typing import List, Tuple

def parse_line(line: str) -> Tuple[List[str], str]:
    line = line.strip()
    if not line or line.startswith('//'):
        return ([], line)
    
    domain = line.lstrip('!').lstrip('*.')
    
    labels = domain.split('.')
    labels.reverse()
    
    return (labels, line)

def should_sort(line: str) -> bool:
    line = line.strip()
    return line and not line.startswith('//')

def sort_block(block: List[str]) -> List[str]:
    sortable_lines = []
    non_sortable_indices = {}
    
    for i, line in enumerate(block):
        if should_sort(line):
            sortable_lines.append(line)
        else:
            non_sortable_indices[i] = line
    
    sorted_lines = sorted(sortable_lines, key=lambda x: parse_line(x)[0])
    
    result = []
    sortable_idx = 0
    
    for i in range(len(block)):
        if i in non_sortable_indices:
            result.append(non_sortable_indices[i])
        else:
            result.append(sorted_lines[sortable_idx])
            sortable_idx += 1
    
    return result

def process_file(input_path: str, output_path: str):
    try:
        with open(input_path, 'r', encoding='utf-8') as f:
            lines = f.readlines()
        
        lines = [line.rstrip() + '\n' for line in lines]
        
        blocks = []
        current_block = []
        
        for line in lines:
            if line.strip() and line.strip().startswith('//') and current_block:
                # Start of new block
                blocks.append(current_block)
                current_block = []
            current_block.append(line)
            
        if current_block:
            blocks.append(current_block)
        
        sorted_blocks = [sort_block(block) for block in blocks]
        
        with open(output_path, 'w', encoding='utf-8') as f:
            for block in sorted_blocks:
                f.writelines(block)
                
        print(f"Successfully processed {input_path} and wrote results to {output_path}")
        
    except Exception as e:
        print(f"Error processing file: {str(e)}")

if __name__ == "__main__":
    input_file = "public_suffix_list.dat"
    output_file = "public_suffix_list_sorted.dat"
    process_file(input_file, output_file)