1
# Copyright (C) 2006, 2009, 2010 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
18
"""Adapter for running test cases against multiple encodings."""
20
from copy import deepcopy
22
# prefix for micro (1/1000000)
25
# greek letter omega, not to be confused with
26
# the Ohm sign, u'\u2126'. Though they are probably identical
27
# cp437 can handle the first, but not the second
30
# smallest error possible, epsilon
31
# cp437 handles u03b5, but not u2208 the 'element of' operator
35
_erik = u'Erik B\xe5gfors'
37
# Swedish 'räksmörgås' means shrimp sandwich
38
_shrimp_sandwich = u'r\xe4ksm\xf6rg\xe5s'
40
# Arabic, probably only Unicode encodings can handle this one
41
_juju = u'\u062c\u0648\u062c\u0648'
43
# iso-8859-1 alternative for juju
44
_juju_alt = u'j\xfbj\xfa'
46
# Russian, 'Alexander' in russian
47
_alexander = u'\u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440'
48
# The word 'test' in Russian
49
_russian_test = u'\u0422\u0435\u0441\u0442'
52
# It is a kanji sequence for nihonjin, or Japanese in English.
54
# '\u4eba' being person, 'u\65e5' sun and '\u672c' origin. Ie,
55
# sun-origin-person, 'native from the land where the sun rises'. Note, I'm
56
# not a fluent speaker, so this is just my crude breakdown.
59
_nihonjin = u'\u65e5\u672c\u4eba'
62
# It's what is usually used for showing how fonts look, because it contains
63
# most accented characters, ie. in places where Englishman use 'Quick brown fox
64
# jumped over a lazy dog'. The literal translation of the Czech version would
65
# be something like 'Yellow horse groaned devilish codes'. Actually originally
66
# the last word used to be 'ódy' (odes). The 'k' was added as a pun when using
67
# the sentece to check whether one has properly set encoding.
68
_yellow_horse = (u'\u017dlu\u0165ou\u010dk\xfd k\u016f\u0148'
69
u' \xfap\u011bl \u010f\xe1belsk\xe9 k\xf3dy')
70
_yellow = u'\u017dlu\u0165ou\u010dk\xfd'
71
_someone = u'Some\u016f\u0148\u011b'
72
_something = u'\u0165ou\u010dk\xfd'
75
# Shalom -> 'hello' or 'peace', used as a common greeting
76
_shalom = u'\u05e9\u05dc\u05d5\u05dd'
79
encoding_scenarios = [
80
# Permutation 1 of utf-8
84
'message': _yellow_horse,
85
'filename': _shrimp_sandwich,
86
'directory': _nihonjin,
90
# Permutation 2 of utf-8
93
'committer': _alexander,
94
'message': u'Testing ' + _mu,
103
'message': u'Testing ' + _mu,
104
'filename': _juju_alt,
105
'directory': _shrimp_sandwich,
107
'encoding': 'iso-8859-1',
111
'committer': _someone,
112
'message': _yellow_horse,
114
'directory': _something,
116
'encoding': 'iso-8859-2',
120
'committer': _alexander,
121
'message': u'Testing ' + _mu,
122
'filename': _russian_test,
123
'directory': _russian_test + 'dir',
125
'encoding': 'cp1251',
127
# The iso-8859-1 tests run on a default windows cp437 installation
128
# and it takes a long time to run an extra permutation of the tests
129
# But just in case we want to add this back in:
130
# ('cp437', {'committer':_erik
131
# , 'message':u'Testing ' + _mu
132
# , 'filename':'file_' + _omega
133
# , 'directory':_epsilon + '_dir',
134
# 'encoding': 'cp437'}),