|
#!/usr/bin/python
|
# -*- coding: UTF-8 -*-
|
|
import sys
|
|
|
'''
|
在第一个文件的基础上，添加后续的全部不重复的2字词语。 再加一个限定条件，即新加的2个字全部都属于一级字表。
|
|
'''
|
|
_list_unique = set()
|
_list_temp = set()
|
|
base_txt_file = sys.argv[1]
|
new_added_txt_file =sys.argv[2]
|
base_txt_file_with_added = sys.argv[3]
|
|
level1_words_file = 'universal_char_list_1_3500.txt'
|
|
level1_words = ''
|
with open(level1_words_file, 'r', encoding='utf-8-sig') as f:
|
level1_words = f.read().splitlines()
|
|
with open(base_txt_file, 'r', encoding='utf-8-sig') as f:
|
for word in f.read().splitlines():
|
_list_unique.add(word[0])
|
_list_unique.add(word[1])
|
_list_unique.add(word[2])
|
_list_unique.add(word[3])
|
|
def if_all_level_one(word):
|
for char in word:
|
try:
|
_index = level1_words[0].index(char)
|
except:
|
return False
|
return True
|
|
|
print(len(_list_unique))
|
with open(base_txt_file_with_added, 'w', encoding='utf-8') as final_f:
|
with open(new_added_txt_file, 'r', encoding='utf-8-sig') as f:
|
for word in f.read().splitlines():
|
#print(word)
|
if len(word) == 2:
|
|
_list_temp = _list_unique.copy()
|
_list_temp.add(word[0])
|
_list_temp.add(word[1])
|
|
if len(_list_temp) - len(_list_unique) == 2:
|
if if_all_level_one(word):
|
_list_unique.add(word[0])
|
_list_unique.add(word[1])
|
final_f.write(word)
|
final_f.write('\n')
|
else:
|
print(word)
|
print(len(word))
|
