#!/usr/bin/python
# -*- coding: UTF-8 -*-

import sys

_char_array_1 = set()
_char_array_1 = set()
_char_array_1 = set()

char_file_1 = '../dict/universal_char_list_1_3500.txt'
char_file_2 = '../dict/universal_char_list_2_3000.txt'
char_file_3 = '../dict/universal_char_list_3_1605.txt'
_target_exclude_file = sys.argv[1]

with open(char_file_1, 'r', encoding='utf-8-sig') as f:
    for word in f.read().splitlines():
        _char_array_1 = word
        print(len(_char_array_1))
with open(char_file_2, 'r', encoding='utf-8-sig') as f:
    for word in f.read().splitlines():
        _char_array_2 = word
        print(len(_char_array_2))
with open(char_file_3, 'r', encoding='utf-8-sig') as f:
    for word in f.read().splitlines():
        _char_array_3 = word
        print(len(_char_array_3))


exclude_char_list_level1= ''
with open(_target_exclude_file, 'r', encoding='utf-8-sig') as f:
    for word in f.read().splitlines():
        exclude_char_list_level1 = exclude_char_list_level1+word
print(len(exclude_char_list_level1))

_level1_len = len(exclude_char_list_level1)


def check_word_not_include (char):
    not_include = True
    try:
        if  exclude_char_list_level1.index(char) > -1:
            return False
    except ValueError as err:
        not_include = True
    return not_include

_char_array_remain_1 = ''
_char_array_remain_2 = ''
_char_array_remain_3 = ''


for char in _char_array_1:
    if check_word_not_include(char):
        _char_array_remain_1 =_char_array_remain_1 +char
print(len(_char_array_remain_1))
print(_char_array_remain_1)