summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_unicodedata.py
blob: b604c282333684ef9338e89941280d7bb32a748c (plain)
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
""" Test script for the unicodedata module.

    Written by Marc-Andre Lemburg (mal@lemburg.com).

    (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.

"""#"
import sha

def test_methods():

    h = sha.sha()
    for i in range(65536):
        char = unichr(i)
        data = [
            
            # Predicates (single char)
            char.isalnum() and u'1' or u'0',
            char.isalpha() and u'1' or u'0',
            char.isdecimal() and u'1' or u'0',
            char.isdigit() and u'1' or u'0',
            char.islower() and u'1' or u'0',
            char.isnumeric() and u'1' or u'0',
            char.isspace() and u'1' or u'0',
            char.istitle() and u'1' or u'0',
            char.isupper() and u'1' or u'0',
            
            # Predicates (multiple chars)
            (char + u'abc').isalnum() and u'1' or u'0',
            (char + u'abc').isalpha() and u'1' or u'0',
            (char + u'123').isdecimal() and u'1' or u'0',
            (char + u'123').isdigit() and u'1' or u'0',
            (char + u'abc').islower() and u'1' or u'0',
            (char + u'123').isnumeric() and u'1' or u'0',
            (char + u' \t').isspace() and u'1' or u'0',
            (char + u'abc').istitle() and u'1' or u'0',
            (char + u'ABC').isupper() and u'1' or u'0',

            # Mappings (single char)
            char.lower(),
            char.upper(),
            char.title(),
            
            # Mappings (multiple chars)
            (char + u'abc').lower(),
            (char + u'ABC').upper(),
            (char + u'abc').title(),
            (char + u'ABC').title(),
            
            ]
        h.update(u''.join(data).encode('unicode-internal'))
    return h.hexdigest()

def test_unicodedata():

    h = sha.sha()
    for i in range(65536):
        char = unichr(i)
        data = [
            # Properties
            str(unicodedata.digit(char, -1)),
            str(unicodedata.numeric(char, -1)),
            str(unicodedata.decimal(char, -1)),
            unicodedata.category(char),
            unicodedata.bidirectional(char),
            unicodedata.decomposition(char),
            str(unicodedata.mirrored(char)),
            str(unicodedata.combining(char)),
            ] 
        h.update(''.join(data))
    return h.hexdigest()

### Run tests

print 'Testing Unicode Database...'
print 'Methods:',
print test_methods()

# In case unicodedata is not available, this will raise an ImportError,
# but still test the above cases...
import unicodedata
print 'Functions:',
print test_unicodedata()

# Some additional checks of the API:
print 'API:',

assert unicodedata.digit(u'A',None) is None
assert unicodedata.digit(u'9') == 9
assert unicodedata.digit(u'\u215b',None) is None
assert unicodedata.digit(u'\u2468') == 9

assert unicodedata.numeric(u'A',None) is None
assert unicodedata.numeric(u'9') == 9
assert unicodedata.numeric(u'\u215b') == 0.125
assert unicodedata.numeric(u'\u2468') == 9.0

assert unicodedata.decimal(u'A',None) is None
assert unicodedata.decimal(u'9') == 9
assert unicodedata.decimal(u'\u215b',None) is None
assert unicodedata.decimal(u'\u2468',None) is None

assert unicodedata.category(u'\uFFFE') == 'Cn'
assert unicodedata.category(u'a') == 'Ll'
assert unicodedata.category(u'A') == 'Lu'

assert unicodedata.bidirectional(u'\uFFFE') == ''
assert unicodedata.bidirectional(u' ') == 'WS'
assert unicodedata.bidirectional(u'A') == 'L'

assert unicodedata.decomposition(u'\uFFFE') == ''
assert unicodedata.decomposition(u'\u00bc') == '<fraction> 0031 2044 0034'

assert unicodedata.mirrored(u'\uFFFE') == 0
assert unicodedata.mirrored(u'a') == 0
assert unicodedata.mirrored(u'\u2201') == 1

assert unicodedata.combining(u'\uFFFE') == 0
assert unicodedata.combining(u'a') == 0
assert unicodedata.combining(u'\u20e1') == 230

print 'ok'