|
#!/usr/bin/python
|
# -*- coding: UTF-8 -*-
|
|
import sys
|
|
'''
|
检查汉字表中，每个字的一二三级字的分类， 输出123和空； 如：
|
原始汉字是：炯炯有神， 其中 输出结果为：“囧”属于三级字表，“有”属于一级字，“神”属于一级字
|
|
炯3炯3有1神1
|
|
|
'''
|
|
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'
|
|
_file_qianziwen = sys.argv[1]
|
_file_qianziwen_result = sys.argv[2]
|
|
_char_array_1 = []
|
_char_array_2= []
|
_char_array_3= []
|
_char_array_None= []
|
|
|
|
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))
|
|
with open(_file_qianziwen_result, 'w', encoding='utf-8') as result_f:
|
with open(_file_qianziwen, 'r', encoding='utf-8-sig') as f:
|
for word in f.read().splitlines():
|
write_words = ''
|
for char in word:
|
not_in_level_1_2_3 = True
|
try:
|
if _char_array_1.index(char) > -1:
|
write_words=write_words+char+'1'
|
not_in_level_1_2_3 = False
|
except ValueError as err:
|
print()
|
try:
|
if _char_array_2.index(char) > -1:
|
write_words=write_words+char+'2'
|
not_in_level_1_2_3 = False
|
except ValueError as err:
|
print()
|
try:
|
if _char_array_3.index(char) > -1:
|
write_words=write_words+char+'3'
|
not_in_level_1_2_3 = False
|
except ValueError as err:
|
print()
|
if not_in_level_1_2_3 :
|
write_words=write_words+char
|
|
result_f.write(write_words+';')
|
