1# Copyright (C) 2006 Canonical Ltd
2#
3# This program is free software; you can redistribute it and/or modify
4# it under the terms of the GNU General Public License as published by
5# the Free Software Foundation; either version 2 of the License, or
6# (at your option) any later version.
7#
8# This program is distributed in the hope that it will be useful,
9# but WITHOUT ANY WARRANTY; without even the implied warranty of
10# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
11# GNU General Public License for more details.
12#
13# You should have received a copy of the GNU General Public License
14# along with this program; if not, write to the Free Software
15# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
16
17"""Tests for utf8 caching."""
18
19from .. import (
20    cache_utf8,
21    )
22from . import TestCase
23
24
25class TestEncodeCache(TestCase):
26
27    def setUp(self):
28        super(TestEncodeCache, self).setUp()
29        cache_utf8.clear_encoding_cache()
30        self.addCleanup(cache_utf8.clear_encoding_cache)
31
32    def check_encode(self, rev_id):
33        rev_id_utf8 = rev_id.encode('utf-8')
34        self.assertFalse(rev_id in cache_utf8._unicode_to_utf8_map)
35        self.assertFalse(rev_id_utf8 in cache_utf8._utf8_to_unicode_map)
36
37        # After a single encode, the mapping should exist for
38        # both directions
39        self.assertEqual(rev_id_utf8, cache_utf8.encode(rev_id))
40        self.assertTrue(rev_id in cache_utf8._unicode_to_utf8_map)
41        self.assertTrue(rev_id_utf8 in cache_utf8._utf8_to_unicode_map)
42
43        self.assertEqual(rev_id, cache_utf8.decode(rev_id_utf8))
44
45        cache_utf8.clear_encoding_cache()
46        self.assertFalse(rev_id in cache_utf8._unicode_to_utf8_map)
47        self.assertFalse(rev_id_utf8 in cache_utf8._utf8_to_unicode_map)
48
49    def check_decode(self, rev_id):
50        rev_id_utf8 = rev_id.encode('utf-8')
51        self.assertFalse(rev_id in cache_utf8._unicode_to_utf8_map)
52        self.assertFalse(rev_id_utf8 in cache_utf8._utf8_to_unicode_map)
53
54        # After a single decode, the mapping should exist for
55        # both directions
56        self.assertEqual(rev_id, cache_utf8.decode(rev_id_utf8))
57        self.assertTrue(rev_id in cache_utf8._unicode_to_utf8_map)
58        self.assertTrue(rev_id_utf8 in cache_utf8._utf8_to_unicode_map)
59
60        self.assertEqual(rev_id_utf8, cache_utf8.encode(rev_id))
61        cache_utf8.clear_encoding_cache()
62
63        self.assertFalse(rev_id in cache_utf8._unicode_to_utf8_map)
64        self.assertFalse(rev_id_utf8 in cache_utf8._utf8_to_unicode_map)
65
66    def test_ascii(self):
67        self.check_decode(u'all_ascii_characters123123123')
68        self.check_encode(u'all_ascii_characters123123123')
69
70    def test_unicode(self):
71        self.check_encode(u'some_\xb5_unicode_\xe5_chars')
72        self.check_decode(u'some_\xb5_unicode_\xe5_chars')
73
74    def test_cached_unicode(self):
75        # Note that this is intentionally split, to prevent Python from
76        # assigning x and y to the same object
77        z = u'\xe5zz'
78        x = u'\xb5yy' + z
79        y = u'\xb5yy' + z
80        self.assertIsNot(x, y)
81        xp = cache_utf8.get_cached_unicode(x)
82        yp = cache_utf8.get_cached_unicode(y)
83
84        self.assertIs(xp, x)
85        self.assertIs(xp, yp)
86
87    def test_cached_utf8(self):
88        x = u'\xb5yy\xe5zz'.encode('utf8')
89        y = u'\xb5yy\xe5zz'.encode('utf8')
90        self.assertFalse(x is y)
91        xp = cache_utf8.get_cached_utf8(x)
92        yp = cache_utf8.get_cached_utf8(y)
93
94        self.assertIs(xp, x)
95        self.assertIs(xp, yp)
96
97    def test_cached_ascii(self):
98        x = b'%s %s' % (b'simple', b'text')
99        y = b'%s %s' % (b'simple', b'text')
100        self.assertIsNot(x, y)
101        xp = cache_utf8.get_cached_ascii(x)
102        yp = cache_utf8.get_cached_ascii(y)
103
104        self.assertIs(xp, x)
105        self.assertIs(xp, yp)
106
107        # after caching, encode and decode should also return the right
108        # objects.
109        uni_x = cache_utf8.decode(x)
110        self.assertEqual(u'simple text', uni_x)
111        self.assertIsInstance(uni_x, str)
112
113        utf8_x = cache_utf8.encode(uni_x)
114        self.assertIs(utf8_x, x)
115
116    def test_decode_with_None(self):
117        self.assertEqual(None, cache_utf8._utf8_decode_with_None(None))
118        self.assertEqual(u'foo', cache_utf8._utf8_decode_with_None(b'foo'))
119        self.assertEqual(u'f\xb5',
120                         cache_utf8._utf8_decode_with_None(b'f\xc2\xb5'))
121