summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_unicodedata.py
blob: a3a5fbc97210abcc10cbd2c02c0a06a81871d87c (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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
""" Test script for the unicodedata module.

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

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

"""#"
import unittest, test.test_support
import sha

encoding = 'utf-8'


### Run tests

class UnicodeMethodsTest(unittest.TestCase):

    # update this, if the database changes
    expectedchecksum = 'a37276dc2c158bef6dfd908ad34525c97180fad9'

    def test_method_checksum(self):
        h = sha.sha()
        for i in range(65536):
            char = unichr(i)
            data = [
                # Predicates (single char)
                u"01"[char.isalnum()],
                u"01"[char.isalpha()],
                u"01"[char.isdecimal()],
                u"01"[char.isdigit()],
                u"01"[char.islower()],
                u"01"[char.isnumeric()],
                u"01"[char.isspace()],
                u"01"[char.istitle()],
                u"01"[char.isupper()],

                # Predicates (multiple chars)
                u"01"[(char + u'abc').isalnum()],
                u"01"[(char + u'abc').isalpha()],
                u"01"[(char + u'123').isdecimal()],
                u"01"[(char + u'123').isdigit()],
                u"01"[(char + u'abc').islower()],
                u"01"[(char + u'123').isnumeric()],
                u"01"[(char + u' \t').isspace()],
                u"01"[(char + u'abc').istitle()],
                u"01"[(char + u'ABC').isupper()],

                # 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(encoding))
        result = h.hexdigest()
        self.assertEqual(result, self.expectedchecksum)

class UnicodeDatabaseTest(unittest.TestCase):

    def setUp(self):
        # In case unicodedata is not available, this will raise an ImportError,
        # but the other test cases will still be run
        import unicodedata
        self.db = unicodedata

    def tearDown(self):
        del self.db

class UnicodeFunctionsTest(UnicodeDatabaseTest):

    # update this, if the database changes
    expectedchecksum = 'cfe20a967a450ebc82ca68c3e4eed344164e11af'

    def test_function_checksum(self):
        data = []
        h = sha.sha()

        for i in range(0x10000):
            char = unichr(i)
            data = [
                # Properties
                str(self.db.digit(char, -1)),
                str(self.db.numeric(char, -1)),
                str(self.db.decimal(char, -1)),
                self.db.category(char),
                self.db.bidirectional(char),
                self.db.decomposition(char),
                str(self.db.mirrored(char)),
                str(self.db.combining(char)),
            ]
            h.update(''.join(data))
        result = h.hexdigest()
        self.assertEqual(result, self.expectedchecksum)

    def test_digit(self):
        self.assertEqual(self.db.digit(u'A', None), None)
        self.assertEqual(self.db.digit(u'9'), 9)
        self.assertEqual(self.db.digit(u'\u215b', None), None)
        self.assertEqual(self.db.digit(u'\u2468'), 9)

        self.assertRaises(TypeError, self.db.digit)
        self.assertRaises(TypeError, self.db.digit, u'xx')
        self.assertRaises(ValueError, self.db.digit, u'x')

    def test_numeric(self):
        self.assertEqual(self.db.numeric(u'A',None), None)
        self.assertEqual(self.db.numeric(u'9'), 9)
        self.assertEqual(self.db.numeric(u'\u215b'), 0.125)
        self.assertEqual(self.db.numeric(u'\u2468'), 9.0)

        self.assertRaises(TypeError, self.db.numeric)
        self.assertRaises(TypeError, self.db.numeric, u'xx')
        self.assertRaises(ValueError, self.db.numeric, u'x')

    def test_decimal(self):
        self.assertEqual(self.db.decimal(u'A',None), None)
        self.assertEqual(self.db.decimal(u'9'), 9)
        self.assertEqual(self.db.decimal(u'\u215b', None), None)
        self.assertEqual(self.db.decimal(u'\u2468', None), None)

        self.assertRaises(TypeError, self.db.decimal)
        self.assertRaises(TypeError, self.db.decimal, u'xx')
        self.assertRaises(ValueError, self.db.decimal, u'x')

    def test_category(self):
        self.assertEqual(self.db.category(u'\uFFFE'), 'Cn')
        self.assertEqual(self.db.category(u'a'), 'Ll')
        self.assertEqual(self.db.category(u'A'), 'Lu')

        self.assertRaises(TypeError, self.db.category)
        self.assertRaises(TypeError, self.db.category, u'xx')

    def test_bidirectional(self):
        self.assertEqual(self.db.bidirectional(u'\uFFFE'), '')
        self.assertEqual(self.db.bidirectional(u' '), 'WS')
        self.assertEqual(self.db.bidirectional(u'A'), 'L')

        self.assertRaises(TypeError, self.db.bidirectional)
        self.assertRaises(TypeError, self.db.bidirectional, u'xx')

    def test_decomposition(self):
        self.assertEqual(self.db.decomposition(u'\uFFFE'),'')
        self.assertEqual(self.db.decomposition(u'\u00bc'), '<fraction> 0031 2044 0034')

        self.assertRaises(TypeError, self.db.decomposition)
        self.assertRaises(TypeError, self.db.decomposition, u'xx')

    def test_mirrored(self):
        self.assertEqual(self.db.mirrored(u'\uFFFE'), 0)
        self.assertEqual(self.db.mirrored(u'a'), 0)
        self.assertEqual(self.db.mirrored(u'\u2201'), 1)

        self.assertRaises(TypeError, self.db.mirrored)
        self.assertRaises(TypeError, self.db.mirrored, u'xx')

    def test_combining(self):
        self.assertEqual(self.db.combining(u'\uFFFE'), 0)
        self.assertEqual(self.db.combining(u'a'), 0)
        self.assertEqual(self.db.combining(u'\u20e1'), 230)

        self.assertRaises(TypeError, self.db.combining)
        self.assertRaises(TypeError, self.db.combining, u'xx')

    def test_normalize(self):
        self.assertRaises(TypeError, self.db.normalize)
        self.assertRaises(ValueError, self.db.normalize, 'unknown', u'xx')
        # The rest can be found in test_normalization.py
        # which requires an external file.


class UnicodeMiscTest(UnicodeDatabaseTest):

    def test_decimal_numeric_consistent(self):
        # Test that decimal and numeric are consistent,
        # i.e. if a character has a decimal value,
        # it's numeric value should be the same.
        count = 0
        for i in xrange(0x10000):
            c = unichr(i)
            dec = self.db.decimal(c, -1)
            if dec != -1:
                self.assertEqual(dec, self.db.numeric(c))
                count += 1
        self.assert_(count >= 10) # should have tested at least the ASCII digits

    def test_digit_numeric_consistent(self):
        # Test that digit and numeric are consistent,
        # i.e. if a character has a digit value,
        # it's numeric value should be the same.
        count = 0
        for i in xrange(0x10000):
            c = unichr(i)
            dec = self.db.digit(c, -1)
            if dec != -1:
                self.assertEqual(dec, self.db.numeric(c))
                count += 1
        self.assert_(count >= 10) # should have tested at least the ASCII digits

def test_main():
    suite = unittest.TestSuite()
    suite.addTest(unittest.makeSuite(UnicodeMiscTest))
    suite.addTest(unittest.makeSuite(UnicodeMethodsTest))
    suite.addTest(unittest.makeSuite(UnicodeFunctionsTest))
    test.test_support.run_suite(suite)

if __name__ == "__main__":
    test_main()