1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
1 |
# Copyright (C) 2006 by Canonical Ltd
|
2 |
# -*- coding: utf-8 -*-
|
|
1685.1.78
by Wouter van Heyst
more code cleanup |
3 |
#
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
4 |
# This program is free software; you can redistribute it and/or modify
|
5 |
# it under the terms of the GNU General Public License as published by
|
|
6 |
# the Free Software Foundation; either version 2 of the License, or
|
|
7 |
# (at your option) any later version.
|
|
1685.1.78
by Wouter van Heyst
more code cleanup |
8 |
#
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
9 |
# This program is distributed in the hope that it will be useful,
|
10 |
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
11 |
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
12 |
# GNU General Public License for more details.
|
|
1685.1.78
by Wouter van Heyst
more code cleanup |
13 |
#
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
14 |
# You should have received a copy of the GNU General Public License
|
15 |
# along with this program; if not, write to the Free Software
|
|
16 |
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
|
17 |
||
1685.1.76
by Wouter van Heyst
codecleanup |
18 |
"""Adapter for running test cases against multiple encodings."""
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
19 |
|
20 |
from copy import deepcopy |
|
21 |
||
22 |
from bzrlib.tests import TestSuite |
|
23 |
||
1685.1.76
by Wouter van Heyst
codecleanup |
24 |
|
1685.1.3
by John Arbash Meinel
Minor cleanups |
25 |
# prefix for micro (1/1000000)
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
26 |
_mu = u'\xb5' |
27 |
||
1711.4.7
by John Arbash Meinel
Adding cp437, which is my default encoding on windows |
28 |
# greek letter omega, not to be confused with
|
29 |
# the Ohm sign, u'\u2126'. Though they are probably identical
|
|
30 |
# cp437 can handle the first, but not the second
|
|
31 |
_omega = u'\u03a9' |
|
32 |
||
33 |
# smallest error possible, epsilon
|
|
34 |
# cp437 handles u03b5, but not u2208 the 'element of' operator
|
|
35 |
_epsilon = u'\u03b5' |
|
36 |
||
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
37 |
# Swedish?
|
38 |
_erik = u'Erik B\xe5gfors' |
|
39 |
||
40 |
# Swedish 'räksmörgås' means shrimp sandwich
|
|
41 |
_shrimp_sandwich = u'r\xe4ksm\xf6rg\xe5s' |
|
42 |
||
43 |
# Arabic, probably only Unicode encodings can handle this one
|
|
44 |
_juju = u'\u062c\u0648\u062c\u0648' |
|
45 |
||
46 |
# iso-8859-1 alternative for juju
|
|
47 |
_juju_alt = u'j\xfbj\xfa' |
|
48 |
||
49 |
# Russian, 'Alexander' in russian
|
|
50 |
_alexander = u'\u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440' |
|
1711.4.3
by John Arbash Meinel
Alexander recommended a better short russian string. |
51 |
# The word 'test' in Russian
|
52 |
_russian_test = u'\u0422\u0435\u0441\u0442' |
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
53 |
|
54 |
# Kanji
|
|
55 |
# It is a kanji sequence for nihonjin, or Japanese in English.
|
|
56 |
#
|
|
57 |
# '\u4eba' being person, 'u\65e5' sun and '\u672c' origin. Ie,
|
|
58 |
# sun-origin-person, 'native from the land where the sun rises'. Note, I'm
|
|
59 |
# not a fluent speaker, so this is just my crude breakdown.
|
|
60 |
#
|
|
61 |
# Wouter van Heyst
|
|
62 |
_nihonjin = u'\u65e5\u672c\u4eba' |
|
63 |
||
64 |
# Czech
|
|
65 |
# It's what is usually used for showing how fonts look, because it contains
|
|
66 |
# most accented characters, ie. in places where Englishman use 'Quick brown fox
|
|
67 |
# jumped over a lazy dog'. The literal translation of the Czech version would
|
|
68 |
# be something like 'Yellow horse groaned devilish codes'. Actually originally
|
|
69 |
# the last word used to be 'ódy' (odes). The 'k' was added as a pun when using
|
|
70 |
# the sentece to check whether one has properly set encoding.
|
|
71 |
_yellow_horse = (u'\u017dlu\u0165ou\u010dk\xfd k\u016f\u0148' |
|
72 |
u' \xfap\u011bl \u010f\xe1belsk\xe9 k\xf3dy') |
|
1185.85.72
by John Arbash Meinel
Fix some of the tests. |
73 |
_yellow = u'\u017dlu\u0165ou\u010dk\xfd' |
74 |
_someone = u'Some\u016f\u0148\u011b' |
|
75 |
_something = u'\u0165ou\u010dk\xfd' |
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
76 |
|
1185.85.79
by John Arbash Meinel
Adding Hebrew characters. |
77 |
# Hebrew
|
1185.85.82
by John Arbash Meinel
Fixing translation of Hebrew word. |
78 |
# Shalom -> 'hello' or 'peace', used as a common greeting
|
79 |
_shalom = u'\u05e9\u05dc\u05d5\u05dd' |
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
80 |
|
1685.1.3
by John Arbash Meinel
Minor cleanups |
81 |
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
82 |
class EncodingTestAdapter(object): |
83 |
"""A tool to generate a suite, testing multiple encodings for a single test.
|
|
84 |
|
|
85 |
This is similar to bzrlib.transport.TransportTestProviderAdapter.
|
|
86 |
It is done by copying the test once for each encoding, and injecting
|
|
87 |
the encoding name, and the list of valid strings for that encoding.
|
|
88 |
Each copy is also given a new id() to make it easy to identify.
|
|
89 |
"""
|
|
90 |
||
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
91 |
_encodings = [ |
92 |
# Permutation 1 of utf-8
|
|
1185.85.71
by John Arbash Meinel
list of encodings allows repeats |
93 |
('utf-8', 1, {'committer':_erik |
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
94 |
, 'message':_yellow_horse |
95 |
, 'filename':_shrimp_sandwich |
|
96 |
, 'directory':_nihonjin}), |
|
97 |
# Permutation 2 of utf-8
|
|
1185.85.71
by John Arbash Meinel
list of encodings allows repeats |
98 |
('utf-8', 2, {'committer':_alexander |
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
99 |
, 'message':u'Testing ' + _mu |
1185.85.82
by John Arbash Meinel
Fixing translation of Hebrew word. |
100 |
, 'filename':_shalom |
1185.85.79
by John Arbash Meinel
Adding Hebrew characters. |
101 |
, 'directory':_juju}), |
1185.85.71
by John Arbash Meinel
list of encodings allows repeats |
102 |
('iso-8859-1', 0, {'committer':_erik |
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
103 |
, 'message':u'Testing ' + _mu |
104 |
, 'filename':_juju_alt |
|
105 |
, 'directory':_shrimp_sandwich}), |
|
1185.85.72
by John Arbash Meinel
Fix some of the tests. |
106 |
('iso-8859-2', 0, {'committer':_someone |
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
107 |
, 'message':_yellow_horse |
1185.85.72
by John Arbash Meinel
Fix some of the tests. |
108 |
, 'filename':_yellow |
109 |
, 'directory':_something}), |
|
1185.85.71
by John Arbash Meinel
list of encodings allows repeats |
110 |
('cp1251', 0, {'committer':_alexander |
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
111 |
, 'message':u'Testing ' + _mu |
1711.4.3
by John Arbash Meinel
Alexander recommended a better short russian string. |
112 |
, 'filename':_russian_test |
113 |
, 'directory':_russian_test + 'dir'}), |
|
1711.4.12
by John Arbash Meinel
Remove cp437 from the set of encodings, it isn't strictly needed |
114 |
# The iso-8859-1 tests run on a default windows cp437 installation
|
115 |
# and it takes a long time to run an extra permutation of the tests
|
|
116 |
# But just in case we want to add this back in:
|
|
117 |
# ('cp437', 0, {'committer':_erik
|
|
118 |
# , 'message':u'Testing ' + _mu
|
|
119 |
# , 'filename':'file_' + _omega
|
|
120 |
# , 'directory':_epsilon + '_dir'}),
|
|
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
121 |
]
|
122 |
||
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
123 |
def adapt(self, test): |
124 |
result = TestSuite() |
|
1185.85.71
by John Arbash Meinel
list of encodings allows repeats |
125 |
for encoding, count, info in self._encodings: |
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
126 |
new_test = deepcopy(test) |
127 |
new_test.encoding = encoding |
|
128 |
new_test.info = info |
|
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
129 |
def make_new_test_id(): |
1185.85.71
by John Arbash Meinel
list of encodings allows repeats |
130 |
if count: |
131 |
new_id = "%s(%s,%s)" % (new_test.id(), encoding, count) |
|
132 |
else: |
|
133 |
new_id = "%s(%s)" % (new_test.id(), encoding) |
|
1185.85.70
by John Arbash Meinel
Hooked up EncodingAdapter, and updated test_non_ascii. |
134 |
return lambda: new_id |
135 |
new_test.id = make_new_test_id() |
|
1185.85.69
by John Arbash Meinel
New encoder with multiple strings. |
136 |
result.addTest(new_test) |
137 |
return result |
|
138 |
||
139 |