1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
|
# -*- coding: latin-1 -*-
__doc__ = br"""
>>> sa
'abc'
>>> ua
'abc'
>>> b
'123'
>>> c
'S\xf8k ik'
>>> d
'\xfc\xd6\xe4'
>>> e
'\x03g\xf8\uf8d2S\xf8k ik'
>>> f
'\xf8'
>>> add
'S\xf8k ik\xfc\xd6\xe4abc'
>>> null
'\x00'
""".decode("ASCII") + b"""
>>> len(sa)
3
>>> len(ua)
3
>>> len(b)
3
>>> len(c)
6
>>> len(d)
3
>>> len(e)
10
>>> len(f)
1
>>> len(add)
12
>>> len(null)
1
""".decode("ASCII") + u"""
>>> ua == 'abc'
True
>>> b == '123'
True
>>> c == 'Sk ik'
True
>>> d == ''
True
>>> e == '\x03\x67\xf8\uf8d2Sk ik' # unescaped by Cython
True
>>> e == '\\x03\\x67\\xf8\\uf8d2Sk ik' # unescaped by Python
True
>>> f == '\xf8' # unescaped by Cython
True
>>> f == '\\xf8' # unescaped by Python
True
>>> k == '' == '\\N{LATIN SMALL LETTER A WITH DIAERESIS}'
True
>>> add == 'Sk ik' + '' + 'abc'
True
>>> null == '\\x00' # unescaped by Python (required by doctest)
True
"""
sa = 'abc'
ua = u'abc'
b = u'123'
c = u'Sk ik'
d = u''
e = u'\x03\x67\xf8\uf8d2Sk ik'
f = u'\xf8'
k = u'\N{LATIN SMALL LETTER A WITH DIAERESIS}'
add = u'Sk ik' + u'' + u'abc'
null = u'\x00'
|
