def testSanitize2(self):
'''Test sanitize with argument set 2'''
data = [u'Äsbëst-Shop',
u'Süper Düper Plugin',
u'__RiemannΖ',
' ',
'\\_',
'Andre\'sSSuperPLUGIN',
'AndisSSuper_PluginSTOP !',
u'"Gauß"']
expected = ['Asbest-Shop',
'Super-Duper-Plugin',
'--RiemannZeta',
'----',
'\\-',
'Andre-sSSuperPLUGIN',
'AndisSSuper-PluginSTOP--',
'-Gau--']
for i, sample in enumerate(data):
result = TextFX.sanitize(sample, safechar='-',
replace_diacritics=True,
replace_umlauts=False,
replace_greek=True,
allowed_chars=r'\\')
self.assertEqual(result, expected[i])
def testSanitize1(self):
'''Test sanitize with argument set 1'''
data = [u'Äsbëst-Shop',
u'Süper Düper Plugin',
u'__RiemannΖ',
' ',
'\\_',
'Andre\'sSSuperPLUGIN',
'AndisSSuper_PluginSTOP !',
u'"Gauß"',
u'André']
expected = ['AesbestShop',
'SueperDueperPlugin',
'RiemannZeta',
'',
'',
'AndresSSuperPLUGIN',
'AndisSSuperPluginSTOP',
'Gauss',
'Andre']
for i, sample in enumerate(data):
result = TextFX.sanitize(sample, safechar='',
replace_diacritics=True,
replace_umlauts=True,
replace_greek=True,
allowed_chars='')
self.assertEqual(result, expected[i])
def testSanitizeWithDifferentEncoding(self):
'''Test sanitize with a different encoding than the default.'''
encoding = 'latin-1'
data = [u'Äsbëst-Shop'.decode("utf-8").encode(encoding),
u'Süper Düper Plugin'.encode(encoding),
' '.encode(encoding),
'\\_'.encode(encoding),
'Andre\'sSSuperPLUGIN'.encode(encoding),
'AndisSSuper_PluginSTOP !'.encode(encoding),
u'"Gauß"'.encode(encoding),
u'André'.encode(encoding)]
expected = ['AesbestShop',
'SueperDueperPlugin',
'',
'',
'AndresSSuperPLUGIN',
'AndisSSuperPluginSTOP',
'Gauss',
'Andre']
for i, sample in enumerate(data):
result = TextFX.sanitize(sample, safechar='',
replace_diacritics=True,
replace_umlauts=True,
replace_greek=True,
allowed_chars='', encoding=encoding)
self.assertEqual(result, expected[i])
def testSanitize(self):
'''Test sanitize with default arguments'''
data = ['Really',
'Super Duper Plugin',
'RSS Generator',
' ',
'_',
'AndreSSuperPLUGIN',
'AndisSSuper_PluginSTOP !']
expected = ['Really',
'Super_Duper_Plugin',
'RSS_Generator',
'____',
'_',
'AndreSSuperPLUGIN',
'AndisSSuper_PluginSTOP__']
for i, sample in enumerate(data):
result = TextFX.sanitize(sample)
self.assertEqual(result, expected[i])