1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
|
# ====================================================================
# Copyright (c) 2007-2013 Open Source Applications Foundation.
#
# Permission is hereby granted, free of charge, to any person obtaining a
# copy of this software and associated documentation files (the "Software"),
# to deal in the Software without restriction, including without limitation
# the rights to use, copy, modify, merge, publish, distribute, sublicense,
# and/or sell copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included
# in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
# DEALINGS IN THE SOFTWARE.
# ====================================================================
#
# This is a python translation of ICU's LocaleDataTest.java
import sys, os
from unittest import TestCase, main
from icu import *
NOT_FOUND_ERR = 'The requested resource cannot be found, error code: 2'
def print_output(string):
pass
class ExemplarGroup:
def __init__(_self, s, scriptCodes):
_self.set = s
_self.scs = scriptCodes
def __hash__(_self):
hash = 0
for i in range(len(_self.scs) if len(_self.scs) < 4 else 4):
hash = (hash << 8) + _self.scs[i]
return hash
def __eq__(_self, other):
return (_self.set == other.set) and (_self.scs == other.scs)
class TestLocaleData(TestCase):
def setUp(self):
self.availableLocales = Locale.getAvailableLocales()
def testPapersize(self):
for locale in self.availableLocales.keys():
papersize = LocaleData(locale).getPaperSize()
#language = Locale(locale).getLanguage()
country = Locale(locale).getCountry()
if (['BZ','CA','CL','CO','CR','GT','MX','NI','PA','PH','PR','SV','US','VE'].count(country) > 0):
self.assertTrue(papersize == (279, 216))
elif country:
self.assertTrue(papersize == (297, 210))
def testMeasurementSystem(self):
for locale in self.availableLocales.keys():
measurementSystem = LocaleData(locale).getMeasurementSystem()
#language = Locale(locale).getLanguage()
country = Locale(locale).getCountry()
# 0 means SI, 1 means US
if (['LR', 'MM', 'US'].count(country) > 0):
self.assertTrue(measurementSystem == 1)
elif country:
self.assertTrue(measurementSystem == 0)
def testExemplarSet(self):
testedExemplars = set()
equalCount = 0
for locale in self.availableLocales:
scriptCodes = Script.getCode(locale)
exemplarSets = []
for k in range(2):
# it seems USET_CASE_INSENSITIVE = 2
option = 0 if k == 0 else 2
# standard = 0, auxiliary = 1, index = 2, count = 3
exemplarSet = LocaleData(locale).getExemplarSet(option, 0)
exemplarSets.append(exemplarSet)
exGrp = ExemplarGroup(exemplarSet, scriptCodes)
if (not exGrp in testedExemplars):
testedExemplars.add(exGrp)
sets = []
for j in range(len(scriptCodes)):
sets.append(UnicodeSet('[:' + Script(scriptCodes[j]).getShortName() + ':]'))
existsInScript = False
iter = UnicodeSetIterator(exemplarSet)
while (not existsInScript and iter.nextRange()):
if (iter.getCodepoint != iter.isString()):
for j in range(len(sets)):
if sets[j].contains(iter.getCodepoint(), iter.getCodepointEnd()):
existsInScript = True
break
else:
for j in range(len(sets)):
if sets[j].contains(iter.getString):
existsInScript = True
break
if existsInScript == False:
print_output("ExemplarSet containment failed for locale : "+ locale)
print_output(locale + " exemplar " + repr(unicode(exemplarSets[0])))
print_output(locale + " exemplar(case-folded) " + repr(unicode(exemplarSets[1])))
self.assertTrue(locale + " case-folded is a superset", exemplarSets[1].containsAll(exemplarSets[0]))
if (exemplarSets[1] == exemplarSets[0]):
++equalCount
self.assertTrue("case-folded is sometimes a strict superset, and sometimes equal",\
equalCount > 0 and equalCount < len(self.availableLocales))
def testExemplarSet2(self):
testedExemplars = set()
equalCount = 0
for locale in self.availableLocales:
ld = LocaleData(locale)
scriptCodes = Script.getCode(locale)
exemplarSets = []
for k in range(2): # for casing option in (normal, uncased)
# it seems USET_CASE_INSENSITIVE = 2
option = 0 if k == 0 else 2
for h in range(2):
esType = 0 if h == 0 else 1
# standard = 0, auxiliary = 1, index = 2, count = 3
exemplarSet = LocaleData(locale).getExemplarSet(option, esType)
exemplarSets.append(exemplarSet)
exGrp = ExemplarGroup(exemplarSet, scriptCodes)
if (not exGrp in testedExemplars):
testedExemplars.add(exGrp)
sets = []
for j in range(len(scriptCodes)):
sets.append(UnicodeSet('[:' + Script(scriptCodes[j]).getShortName() + ':]'))
existsInScript = False
iter = UnicodeSetIterator(exemplarSet)
while (not existsInScript and iter.nextRange()):
if (iter.getCodepoint != iter.isString()):
for j in range(len(sets)):
if sets[j].contains(iter.getCodepoint(), iter.getCodepointEnd()):
existsInScript = True
break
else:
for j in range(len(sets)):
if sets[j].contains(iter.getString):
existsInScript = True
break
if existsInScript == False and h == 0:
print_output("ExemplarSet containment failed for locale,option,type : " \
+ locale + "," + str(option) + "," + str(esType))
print_output(locale + " exemplar(ES_STANDARD)" + repr(unicode(exemplarSets[0])))
print_output(locale + " exemplar(ES_AUXILIARY)" + repr(unicode(exemplarSets[1])))
print_output(locale + " exemplar(case-folded,ES_STANDARD)" + repr(unicode(exemplarSets[2])))
print_output(locale + " exemplar(case-folded,ES_AUXILIARY)" + repr(unicode(exemplarSets[3])))
self.assertTrue(locale + " case-folded is a superset", exemplarSets[2].containsAll(exemplarSets[0]))
self.assertTrue(locale + " case-folder is a superset", exemplarSets[3].containsAll(exemplarSets[1]))
if (exemplarSets[2] == exemplarSets[0]):
++equalCount
if (exemplarSets[3] == exemplarSets[1]):
++equalCount
self.assertTrue("case-folded is sometimes a strict superset, and sometimes equal",\
equalCount > 0 and equalCount < len(self.availableLocales) * 2)
def testCoverage(self):
ld = LocaleData(Locale().getName())
t = ld.getNoSubstitute()
ld.setNoSubstitute(t)
self.assertEqual(t, ld.getNoSubstitute())
for i in range(4):
print_output(repr(ld.getDelimiter(i)))
def testLocaleDisplayPattern(self):
ld = LocaleData(Locale().getName())
print_output("Default locale LocaleDisplayPattern:" + ld.getLocaleDisplayPattern());
print_output("Default locale LocaleSeparator:" + ld.getLocaleSeparator());
for locale in self.availableLocales:
ld = LocaleData(locale)
try:
print_output(locale + " LocaleDisplayPattern:" + repr(ld.getLocaleDisplayPattern()))
getLocaleDisplayPattern = True
except ICUError, e: # resource not found
getLocaleDisplayPattern = str(e) == NOT_FOUND_ERR
except:
getLocaleDisplayPattern = False
self.assertTrue(getLocaleDisplayPattern)
try:
print_output(locale + " LocaleSeparator:" + repr(ld.getLocaleSeparator()))
getLocaleSeparator = True
except ICUError, e: # resource not found
getLocaleSeparator = str(e) == NOT_FOUND_ERR
except:
getLocaleSeparator = False
self.assertTrue(getLocaleSeparator)
if __name__ == "__main__":
main()
|
