66 lines
1.7 KiB
Python
66 lines
1.7 KiB
Python
# -*- encoding:utf-8 -*-
|
||
|
||
'''
|
||
@Author : dingjiawen
|
||
@Date : 2023/12/12 12:54
|
||
@Usage :
|
||
@Desc :
|
||
'''
|
||
|
||
# -*- coding: UTF-8 -*-
|
||
import numpy as np
|
||
import setting
|
||
|
||
|
||
def encode(text):
|
||
vector = np.zeros(setting.ALL_CHAR_SET_LEN * setting.MAX_CAPTCHA, dtype=float)
|
||
|
||
def char2pos(c):
|
||
if c == '_':
|
||
k = 62
|
||
return k
|
||
# ord()用来返回单个字符的ascii值(0-255)获取unicode值
|
||
# chr()用来返回一个【0-255】数值对应的ascii符号
|
||
# 48,65,97分别是0,A,a的ascii值
|
||
# 等价于ord(c)-ord(0)
|
||
k = ord(c) - 48
|
||
if k > 9:
|
||
# >9说明不是字母，+10是因为0-9位数字
|
||
k = ord(c) - 65 + 10
|
||
if k > 35:
|
||
# +26是因为大写字母有26位
|
||
k = ord(c) - 97 + 26 + 10
|
||
if k > 61:
|
||
raise ValueError('error')
|
||
return k
|
||
|
||
for i, c in enumerate(text):
|
||
idx = i * setting.ALL_CHAR_SET_LEN + char2pos(c)
|
||
vector[idx] = 1.0
|
||
return vector
|
||
|
||
|
||
def decode(vec):
|
||
char_pos = vec.nonzero()[0]
|
||
text = []
|
||
for i, c in enumerate(char_pos):
|
||
char_at_pos = i # c/63
|
||
char_idx = c % setting.ALL_CHAR_SET_LEN
|
||
if char_idx < 10:
|
||
char_code = char_idx + ord('0')
|
||
elif char_idx < 36:
|
||
char_code = char_idx - 10 + ord('A')
|
||
elif char_idx < 62:
|
||
char_code = char_idx - 36 + ord('a')
|
||
elif char_idx == 62:
|
||
char_code = ord('_')
|
||
else:
|
||
raise ValueError('error')
|
||
text.append(chr(char_code))
|
||
return "".join(text)
|
||
|
||
|
||
if __name__ == '__main__':
|
||
e = encode("BK7H")
|
||
print(decode(e))
|