1
# Copyright (C) 2006 by Canonical Ltd
2
# -*- coding: utf-8 -*-
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.
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.
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
19
Adapter for running test cases against multiple encodings.
22
from copy import deepcopy
24
from bzrlib.tests import TestSuite
26
# prefix for micro (1/1000)
30
_erik = u'Erik B\xe5gfors'
32
# Swedish 'räksmörgås' means shrimp sandwich
33
_shrimp_sandwich = u'r\xe4ksm\xf6rg\xe5s'
35
# Arabic, probably only Unicode encodings can handle this one
36
_juju = u'\u062c\u0648\u062c\u0648'
38
# iso-8859-1 alternative for juju
39
_juju_alt = u'j\xfbj\xfa'
41
# Russian, 'Alexander' in russian
42
_alexander = u'\u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440'
43
# No idea if this means anything, but we need another string
44
_alex = u'\u0410\u043b\u0435\u043a'
47
# It is a kanji sequence for nihonjin, or Japanese in English.
49
# '\u4eba' being person, 'u\65e5' sun and '\u672c' origin. Ie,
50
# sun-origin-person, 'native from the land where the sun rises'. Note, I'm
51
# not a fluent speaker, so this is just my crude breakdown.
54
_nihonjin = u'\u65e5\u672c\u4eba'
57
# It's what is usually used for showing how fonts look, because it contains
58
# most accented characters, ie. in places where Englishman use 'Quick brown fox
59
# jumped over a lazy dog'. The literal translation of the Czech version would
60
# be something like 'Yellow horse groaned devilish codes'. Actually originally
61
# the last word used to be 'ódy' (odes). The 'k' was added as a pun when using
62
# the sentece to check whether one has properly set encoding.
63
_yellow_horse = (u'\u017dlu\u0165ou\u010dk\xfd k\u016f\u0148'
64
u' \xfap\u011bl \u010f\xe1belsk\xe9 k\xf3dy')
65
_yellow = u'\u017dlu\u0165ou\u010dk\xfd'
66
_someone = u'Some\u016f\u0148\u011b'
67
_something = u'\u0165ou\u010dk\xfd'
70
# Shalom -> 'hello' or 'peace', used as a common greeting
71
_shalom = u'\u05e9\u05dc\u05d5\u05dd'
73
class EncodingTestAdapter(object):
74
"""A tool to generate a suite, testing multiple encodings for a single test.
76
This is similar to bzrlib.transport.TransportTestProviderAdapter.
77
It is done by copying the test once for each encoding, and injecting
78
the encoding name, and the list of valid strings for that encoding.
79
Each copy is also given a new id() to make it easy to identify.
83
# Permutation 1 of utf-8
84
('utf-8', 1, {'committer':_erik
85
, 'message':_yellow_horse
86
, 'filename':_shrimp_sandwich
87
, 'directory':_nihonjin}),
88
# Permutation 2 of utf-8
89
('utf-8', 2, {'committer':_alexander
90
, 'message':u'Testing ' + _mu
92
, 'directory':_juju}),
93
('iso-8859-1', 0, {'committer':_erik
94
, 'message':u'Testing ' + _mu
95
, 'filename':_juju_alt
96
, 'directory':_shrimp_sandwich}),
97
('iso-8859-2', 0, {'committer':_someone
98
, 'message':_yellow_horse
100
, 'directory':_something}),
101
('cp1251', 0, {'committer':_alexander
102
, 'message':u'Testing ' + _mu
104
, 'directory':_alex + 'dir'}),
107
def adapt(self, test):
109
for encoding, count, info in self._encodings:
110
new_test = deepcopy(test)
111
new_test.encoding = encoding
113
def make_new_test_id():
115
new_id = "%s(%s,%s)" % (new_test.id(), encoding, count)
117
new_id = "%s(%s)" % (new_test.id(), encoding)
118
return lambda: new_id
119
new_test.id = make_new_test_id()
120
result.addTest(new_test)
added
removed
bzrlib/tests/EncodingAdapter.py
