aboutsummaryrefslogtreecommitdiffstats
path: root/library/python/strings/ut/test_strings.py
blob: dd0c694ee1df78fbfe269e13ffed1ec63cc63f8d (plain) (blame)
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
# coding=utf-8

import pytest
import six

import library.python.strings


class Convertible(object):
    text = u'текст'
    text_utf8 = text.encode('utf-8')

    def __unicode__(self):
        return self.text

    def __str__(self):
        return self.text_utf8


class ConvertibleToUnicodeOnly(Convertible):
    def __str__(self):
        return self.text.encode('ascii')


class ConvertibleToStrOnly(Convertible):
    def __unicode__(self):
        return self.text_utf8.decode('ascii')


class NonConvertible(ConvertibleToUnicodeOnly, ConvertibleToStrOnly):
    pass


def test_to_basestring():
    assert library.python.strings.to_basestring('str') == 'str'
    assert library.python.strings.to_basestring(u'юникод') == u'юникод'
    if six.PY2:  # __str__ should return str not bytes in Python3
        assert library.python.strings.to_basestring(Convertible()) == Convertible.text
        assert library.python.strings.to_basestring(ConvertibleToUnicodeOnly()) == Convertible.text
        assert library.python.strings.to_basestring(ConvertibleToStrOnly()) == Convertible.text_utf8
        assert library.python.strings.to_basestring(NonConvertible())


def test_to_unicode():
    assert library.python.strings.to_unicode(u'юникод') == u'юникод'
    assert library.python.strings.to_unicode('str') == u'str'
    assert library.python.strings.to_unicode(u'строка'.encode('utf-8')) == u'строка'
    assert library.python.strings.to_unicode(u'строка'.encode('cp1251'), 'cp1251') == u'строка'
    if six.PY2:  # __str__ should return str not bytes in Python3
        assert library.python.strings.to_unicode(Convertible()) == Convertible.text
        assert library.python.strings.to_unicode(ConvertibleToUnicodeOnly()) == Convertible.text
        with pytest.raises(UnicodeDecodeError):
            library.python.strings.to_unicode(ConvertibleToStrOnly())
        with pytest.raises(UnicodeDecodeError):
            library.python.strings.to_unicode(NonConvertible())


def test_to_unicode_errors_replace():
    assert library.python.strings.to_unicode(u'abcабв'.encode('utf-8'), 'ascii')
    assert library.python.strings.to_unicode(u'абв'.encode('utf-8'), 'ascii')


def test_to_str():
    assert library.python.strings.to_str('str') == 'str' if six.PY2 else b'str'
    assert library.python.strings.to_str(u'unicode') == 'unicode' if six.PY2 else b'unicode'
    assert library.python.strings.to_str(u'юникод') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод', 'cp1251') == u'юникод'.encode('cp1251')
    if six.PY2:
        assert library.python.strings.to_str(Convertible()) == Convertible.text_utf8
        with pytest.raises(UnicodeEncodeError):
            library.python.strings.to_str(ConvertibleToUnicodeOnly())
        assert library.python.strings.to_str(ConvertibleToStrOnly()) == Convertible.text_utf8
        with pytest.raises(UnicodeEncodeError):
            library.python.strings.to_str(NonConvertible())


def test_to_str_errors_replace():
    assert library.python.strings.to_str(u'abcабв', 'ascii')
    assert library.python.strings.to_str(u'абв', 'ascii')


def test_to_str_transcode():
    assert library.python.strings.to_str('str', from_enc='ascii') == 'str' if six.PY2 else b'str'
    assert library.python.strings.to_str('str', from_enc='utf-8') == 'str' if six.PY2 else b'str'

    assert library.python.strings.to_str(u'юникод'.encode('utf-8'), from_enc='utf-8') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод'.encode('utf-8'), to_enc='utf-8', from_enc='utf-8') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод'.encode('utf-8'), to_enc='cp1251', from_enc='utf-8') == u'юникод'.encode('cp1251')

    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), from_enc='cp1251') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), to_enc='cp1251', from_enc='cp1251') == u'юникод'.encode('cp1251')
    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), to_enc='utf-8', from_enc='cp1251') == u'юникод'.encode('utf-8')

    assert library.python.strings.to_str(u'юникод'.encode('koi8-r'), from_enc='koi8-r') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод'.encode('koi8-r'), to_enc='koi8-r', from_enc='koi8-r') == u'юникод'.encode('koi8-r')
    assert library.python.strings.to_str(u'юникод'.encode('koi8-r'), to_enc='cp1251', from_enc='koi8-r') == u'юникод'.encode('cp1251')


def test_to_str_transcode_wrong():
    assert library.python.strings.to_str(u'юникод'.encode('utf-8'), from_enc='cp1251')
    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), from_enc='utf-8')


def test_to_str_transcode_disabled():
    # No transcoding enabled, set from_enc to enable
    assert library.python.strings.to_str(u'юникод'.encode('utf-8'), to_enc='utf-8') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод'.encode('utf-8'), to_enc='cp1251') == u'юникод'.encode('utf-8')
    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), to_enc='utf-8') == u'юникод'.encode('cp1251')
    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), to_enc='cp1251') == u'юникод'.encode('cp1251')
    assert library.python.strings.to_str(u'юникод'.encode('cp1251'), to_enc='koi8-r') == u'юникод'.encode('cp1251')
    assert library.python.strings.to_str(u'юникод'.encode('koi8-r'), to_enc='cp1251') == u'юникод'.encode('koi8-r')


def test_stringize_deep():
    assert library.python.strings.stringize_deep({
        'key 1': 'value 1',
        u'ключ 2': u'значение 2',
        'list': [u'ключ 2', 'key 1', (u'к', 2)]
    }) == {
        'key 1' if six.PY2 else b'key 1': 'value 1' if six.PY2 else b'value 1',
        u'ключ 2'.encode('utf-8'): u'значение 2'.encode('utf-8'),
        'list' if six.PY2 else b'list': [u'ключ 2'.encode('utf-8'), 'key 1' if six.PY2 else b'key 1', (u'к'.encode('utf-8'), 2)]
    }


def test_stringize_deep_doesnt_transcode():
    assert library.python.strings.stringize_deep({
        u'ключ 1'.encode('utf-8'): u'значение 1'.encode('utf-8'),
        u'ключ 2'.encode('cp1251'): u'значение 2'.encode('cp1251'),
    }) == {
        u'ключ 1'.encode('utf-8'): u'значение 1'.encode('utf-8'),
        u'ключ 2'.encode('cp1251'): u'значение 2'.encode('cp1251'),
    }


def test_stringize_deep_nested():
    assert library.python.strings.stringize_deep({
        'key 1': 'value 1',
        u'ключ 2': {
            'subkey 1': 'value 1',
            u'подключ 2': u'value 2',
        },
    }) == {
        'key 1' if six.PY2 else b'key 1': 'value 1' if six.PY2 else b'value 1',
        u'ключ 2'.encode('utf-8'): {
            'subkey 1' if six.PY2 else b'subkey 1': 'value 1' if six.PY2 else b'value 1',
            u'подключ 2'.encode('utf-8'): u'value 2'.encode('utf-8'),
        },
    }


def test_stringize_deep_plain():
    assert library.python.strings.stringize_deep('str') == 'str' if six.PY2 else b'str'
    assert library.python.strings.stringize_deep(u'юникод') == u'юникод'.encode('utf-8')
    assert library.python.strings.stringize_deep(u'юникод'.encode('utf-8')) == u'юникод'.encode('utf-8')


def test_stringize_deep_nonstr():
    with pytest.raises(TypeError):
        library.python.strings.stringize_deep(Convertible(), relaxed=False)
    x = Convertible()
    assert x == library.python.strings.stringize_deep(x)


def test_unicodize_deep():
    assert library.python.strings.unicodize_deep({
        'key 1': 'value 1',
        u'ключ 2': u'значение 2',
        u'ключ 3'.encode('utf-8'): u'значение 3'.encode('utf-8'),
    }) == {
        u'key 1': u'value 1',
        u'ключ 2': u'значение 2',
        u'ключ 3': u'значение 3',
    }


def test_unicodize_deep_nested():
    assert library.python.strings.unicodize_deep({
        'key 1': 'value 1',
        u'ключ 2': {
            'subkey 1': 'value 1',
            u'подключ 2': u'значение 2',
            u'подключ 3'.encode('utf-8'): u'значение 3'.encode('utf-8'),
        },
    }) == {
        u'key 1': u'value 1',
        u'ключ 2': {
            u'subkey 1': u'value 1',
            u'подключ 2': u'значение 2',
            u'подключ 3': u'значение 3',
        },
    }


def test_unicodize_deep_plain():
    assert library.python.strings.unicodize_deep('str') == u'str'
    assert library.python.strings.unicodize_deep(u'юникод') == u'юникод'
    assert library.python.strings.unicodize_deep(u'юникод'.encode('utf-8')) == u'юникод'


def test_unicodize_deep_nonstr():
    with pytest.raises(TypeError):
        library.python.strings.unicodize_deep(Convertible(), relaxed=False)
    x = Convertible()
    assert x == library.python.strings.stringize_deep(x)