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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
|
#
# Tests the UnicodeSplitter
#
import os, sys
if __name__ == '__main__':
execfile(os.path.join(sys.path[0], 'framework.py'))
from Products.CMFPlone.tests import PloneTestCase
from Products.CMFPlone.tests import dummy
from Products.CMFPlone.UnicodeSplitter import Splitter
from Products.CMFPlone.UnicodeSplitter import CaseNormalizer
import locale
LATIN1 = ('de_DE.ISO8859-15', 'de_DE.ISO8859-15@euro')
def _setlocale(*names):
saved = locale.setlocale(locale.LC_ALL)
for name in names:
try:
locale.setlocale(locale.LC_ALL, name)
break
except locale.Error:
pass
else:
return None
return saved
class TestSplitter(PloneTestCase.PloneTestCase):
def afterSetUp(self):
self.splitter = Splitter()
self.process = self.splitter.process
self.processGlob = self.splitter.processGlob
def testProcessGerman(self):
# German letters
input = [u"\xc4ffin foo"]
output = [u"\xc4ffin", u"foo"]
output = [t.encode('utf-8') for t in output]
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
input = [t.encode('utf-8') for t in input]
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
def testProcessGreek(self):
# Greek letters
input = [u'\u039d\u03af\u03ba\u03bf\u03c2 \u03a4\u03b6\u03ac\u03bd\u03bf\u03c2 foo']
output = [u'\u039d\u03af\u03ba\u03bf\u03c2',
u'\u03a4\u03b6\u03ac\u03bd\u03bf\u03c2', u'foo']
output = [t.encode('utf-8') for t in output]
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
input = [t.encode('utf-8') for t in input]
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
def testProcessTurkish(self):
# Turkish letters
input = [u"\xdc\u011f\xfcr foo"]
output = [u"\xdc\u011f\xfcr", u"foo"]
output = [t.encode('utf-8') for t in output]
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
input = [t.encode('utf-8') for t in input]
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
def testProcessLatin1(self):
#
# Test passes because plone_lexicon pipeline elements
# are coded defensively.
#
input = ["\xc4ffin foo"]
output = ["\xc4ffin", "foo"]
# May still fail if none of the locales is available
saved = _setlocale(*LATIN1)
try:
self.assertEqual(self.process(input), output)
self.assertEqual(self.processGlob(input), output)
finally:
_setlocale(saved)
class TestCaseNormalizer(PloneTestCase.PloneTestCase):
def afterSetUp(self):
self.normalizer = CaseNormalizer()
self.process = self.normalizer.process
def testNormalizeGerman(self):
input = [u"\xc4ffin"]
output = [u"\xe4ffin"]
output = [t.encode('utf-8') for t in output]
self.assertEqual(self.process(input), output)
input = [t.encode('utf-8') for t in input]
self.assertEqual(self.process(input), output)
def testNormalizeLatin1(self):
#
# Test passes because plone_lexicon pipeline elements
# are coded defensively.
#
input = ["\xc4ffin"]
output = ["\xe4ffin"]
# May still fail if none of the locales is available
saved = _setlocale(*LATIN1)
try:
self.assertEqual(self.process(input), output)
finally:
_setlocale(saved)
class TestQuery(PloneTestCase.PloneTestCase):
def afterSetUp(self):
self.catalog = self.portal.portal_catalog
self.folder._setObject('doc1', dummy.Item('doc1'))
self.doc1 = self.folder.doc1
self.folder._setObject('doc2', dummy.Item('doc2'))
self.doc2 = self.folder.doc2
def testQueryByUmlaut(self):
self.doc1.SearchableText = '\303\204ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText='\303\204ffin')
self.assertEqual(len(brains), 1)
def testQueryByUmlautLower(self):
self.doc1.SearchableText = '\303\204ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText='\303\244ffin')
self.assertEqual(len(brains), 1)
def testQueryDifferentiatesUmlauts(self):
self.doc1.SearchableText = '\303\204ffin'
self.catalog.indexObject(self.doc1)
self.doc2.SearchableText = '\303\226ffin'
self.catalog.indexObject(self.doc2)
brains = self.catalog(SearchableText='\303\226ffin')
self.assertEqual(len(brains), 1)
def testQueryDifferentiatesUmlautsLower(self):
self.doc1.SearchableText = '\303\204ffin'
self.catalog.indexObject(self.doc1)
self.doc2.SearchableText = '\303\226ffin'
self.catalog.indexObject(self.doc2)
brains = self.catalog(SearchableText='\303\266ffin')
self.assertEqual(len(brains), 1)
def testQueryByLatin1(self):
#
# Test passes because plone_lexicon pipeline elements
# are coded defensively.
#
saved = _setlocale(*LATIN1)
try:
self.doc1.SearchableText = '\xc4ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText='\xc4ffin')
self.assertEqual(len(brains), 1)
finally:
_setlocale(saved)
def testQueryByLatin1Lower(self):
#
# Test passes because plone_lexicon pipeline elements
# are coded defensively.
#
saved = _setlocale(*LATIN1)
try:
self.doc1.SearchableText = '\xc4ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText='\xe4ffin')
self.assertEqual(len(brains), 1)
finally:
_setlocale(saved)
def testMixedModeQuery(self):
#
# Test passes because plone_lexicon pipeline elements
# are coded defensively.
#
saved = _setlocale(*LATIN1)
try:
# Index Latin-1
self.doc1.SearchableText = '\xc4ffin'
self.catalog.indexObject(self.doc1)
# Query by UTF-8
brains = self.catalog(SearchableText='\303\204ffin')
# We get no results, but at least we don't break
self.assertEqual(len(brains), 0)
finally:
_setlocale(saved)
def testQueryByUnicode(self):
self.doc1.SearchableText = '\303\204ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText=u'\xc4ffin')
self.assertEqual(len(brains), 1)
def testQueryByUnicodeLower(self):
self.doc1.SearchableText = '\303\204ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText=u'\xe4ffin')
self.assertEqual(len(brains), 1)
def testIndexUnicode(self):
self.doc1.SearchableText = u'\xc4ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText='\303\204ffin')
self.assertEqual(len(brains), 1)
def testIndexUnicodeLower(self):
self.doc1.SearchableText = u'\xc4ffin'
self.catalog.indexObject(self.doc1)
brains = self.catalog(SearchableText='\303\244ffin')
self.assertEqual(len(brains), 1)
def test_suite():
from unittest import TestSuite, makeSuite
suite = TestSuite()
suite.addTest(makeSuite(TestSplitter))
suite.addTest(makeSuite(TestCaseNormalizer))
suite.addTest(makeSuite(TestQuery))
return suite
if __name__ == '__main__':
framework()
|
