bzr branch
http://gegoxaren.bato24.eu/bzr/brz/remove-bazaar
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
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
|
|
|
4183.7.1
by Sabin Iacob
update FSF mailing address |
15 |
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
16 |
|
17 |
"""Tests for utf8 caching."""
|
|
18 |
||
|
6624
by Jelmer Vernooij
Merge Python3 porting work ('py3 pokes') |
19 |
from .. import ( |
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
20 |
cache_utf8, |
21 |
)
|
|
|
6624
by Jelmer Vernooij
Merge Python3 porting work ('py3 pokes') |
22 |
from . import TestCase |
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
23 |
|
24 |
||
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
25 |
class TestEncodeCache(TestCase): |
|
3943.8.1
by Marius Kruger
remove all trailing whitespace from bzr source |
26 |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
27 |
def setUp(self): |
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
28 |
super(TestEncodeCache, self).setUp() |
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
29 |
cache_utf8.clear_encoding_cache() |
30 |
self.addCleanup(cache_utf8.clear_encoding_cache) |
|
31 |
||
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
32 |
def check_encode(self, rev_id): |
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
33 |
rev_id_utf8 = rev_id.encode('utf-8') |
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
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) |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
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)) |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
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) |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
42 |
|
43 |
self.assertEqual(rev_id, cache_utf8.decode(rev_id_utf8)) |
|
44 |
||
45 |
cache_utf8.clear_encoding_cache() |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
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) |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
48 |
|
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
49 |
def check_decode(self, rev_id): |
50 |
rev_id_utf8 = rev_id.encode('utf-8') |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
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) |
|
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
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)) |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
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) |
|
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
59 |
|
60 |
self.assertEqual(rev_id_utf8, cache_utf8.encode(rev_id)) |
|
61 |
cache_utf8.clear_encoding_cache() |
|
62 |
||
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
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) |
|
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
65 |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
66 |
def test_ascii(self): |
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
67 |
self.check_decode(u'all_ascii_characters123123123') |
68 |
self.check_encode(u'all_ascii_characters123123123') |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
69 |
|
70 |
def test_unicode(self): |
|
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
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 |
x = u'\xb5yy' + u'\xe5zz' |
|
76 |
y = u'\xb5yy' + u'\xe5zz' |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
77 |
self.assertFalse(x is y) |
|
1911.2.5
by John Arbash Meinel
Update cache tests, add a function to do something like intern() only for unicode objects |
78 |
xp = cache_utf8.get_cached_unicode(x) |
79 |
yp = cache_utf8.get_cached_unicode(y) |
|
80 |
||
|
2249.5.3
by John Arbash Meinel
Add get_cached_ascii for dealing with how cElementTree handles ascii strings |
81 |
self.assertIs(xp, x) |
82 |
self.assertIs(xp, yp) |
|
|
1911.2.3
by John Arbash Meinel
Moving everything into a new location so that we can cache more than just revision ids |
83 |
|
|
2249.5.2
by John Arbash Meinel
Add a get_cached_utf8, which will ensure it is really utf8, and cache the strings |
84 |
def test_cached_utf8(self): |
85 |
x = u'\xb5yy\xe5zz'.encode('utf8') |
|
86 |
y = u'\xb5yy\xe5zz'.encode('utf8') |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
87 |
self.assertFalse(x is y) |
|
2249.5.2
by John Arbash Meinel
Add a get_cached_utf8, which will ensure it is really utf8, and cache the strings |
88 |
xp = cache_utf8.get_cached_utf8(x) |
89 |
yp = cache_utf8.get_cached_utf8(y) |
|
90 |
||
|
2249.5.3
by John Arbash Meinel
Add get_cached_ascii for dealing with how cElementTree handles ascii strings |
91 |
self.assertIs(xp, x) |
92 |
self.assertIs(xp, yp) |
|
93 |
||
94 |
def test_cached_ascii(self): |
|
95 |
x = '%s %s' % ('simple', 'text') |
|
96 |
y = '%s %s' % ('simple', 'text') |
|
|
5784.1.1
by Martin Pool
Stop using failIf, failUnless, etc |
97 |
self.assertFalse(x is y) |
|
2249.5.3
by John Arbash Meinel
Add get_cached_ascii for dealing with how cElementTree handles ascii strings |
98 |
xp = cache_utf8.get_cached_ascii(x) |
99 |
yp = cache_utf8.get_cached_ascii(y) |
|
100 |
||
101 |
self.assertIs(xp, x) |
|
102 |
self.assertIs(xp, yp) |
|
103 |
||
104 |
# after caching, encode and decode should also return the right
|
|
105 |
# objects.
|
|
106 |
uni_x = cache_utf8.decode(x) |
|
107 |
self.assertEqual(u'simple text', uni_x) |
|
108 |
self.assertIsInstance(uni_x, unicode) |
|
109 |
||
110 |
utf8_x = cache_utf8.encode(uni_x) |
|
111 |
self.assertIs(utf8_x, x) |
|
|
2255.7.95
by Robert Collins
Add convenience utf8 decode routine for handling strings that might be None |
112 |
|
113 |
def test_decode_with_None(self): |
|
|
2360.1.6
by John Arbash Meinel
Change utf8_decode_with_None to return what we care about. |
114 |
self.assertEqual(None, cache_utf8._utf8_decode_with_None(None)) |
115 |
self.assertEqual(u'foo', cache_utf8._utf8_decode_with_None('foo')) |
|
116 |
self.assertEqual(u'f\xb5', |
|
117 |
cache_utf8._utf8_decode_with_None('f\xc2\xb5')) |