def test_dc_replacements(self):
'''make sure we can read in various scenarios in dc_replacements
using a test version of the replacement rules, and ensure any
invalid format of rule is not included.
'''
curr_dc = DataClean(replacements=self.tst_replacements)
print('-------------------------')
for k, v in curr_dc.replacements.items():
print('%s=%s' % (k, v))
print('--------------------------------------------------------')
print('testing for %s, to be replaced with %s' % (k, v))
test_string = 'recording_7.wav %s Wow that is awesome' % k
print('...test string >>%s' % test_string)
#set contents prior to processing,typically users would not do this
#would set contents at instance. doing this just for testing
curr_dc.contents = test_string
curr_dc.process_contents(show_results=False)
print('...processed as>>%s' % curr_dc.contents.decode())
self.assertEqual(
-1,
curr_dc.contents.decode().find(k),
'...seems the original token is still in the string')
self.assertGreater(0,
curr_dc.contents.decode().find(k),
'...seems like the new token was not applied')
def test_dc_process_contents_clean_find_n_replace_symbols(self):
'''ensure that we can replace at the multiple locations of symbols'''
curr_replacements = self.dc.replacements
for k, v in curr_replacements.items():
if k == 'SYMBOL_AS_SPACE':
ignore_sym = ['[', ']', ',']
for each in v:
if each not in ignore_sym:
print(
'--------------------------------------------------------'
)
print(
'testing for symbol "%s", to be removed (i.e. replaced with '
'' % each)
test_string = 'recording_7.wav %s Wow %s%s%s that is awesome %s' % (
each, each, each, each, each)
print('...test string >>%s' % test_string)
tst_dc = DataClean(contents=test_string)
tst_dc.process_contents(show_results=False)
print('...processed as>>%s' % tst_dc.contents.decode())
self.assertEqual(
-1,
tst_dc.contents.decode().find(k),
'...seems the original token is still in the string'
)
self.assertGreater(
0,
tst_dc.contents.decode().find(k),
'...seems like the new token was not applied')
def test_dc_process_contents_clean_find_n_replace_end_of_string(self):
'''ensure that we can replace at the end of the string'''
curr_replacements = self.dc.replacements
for k,v in curr_replacements.items():
if k != 'SYMBOL_AS_SPACE':
print('--------------------------------------------------------')
print('testing for %s, to be replaced with %s' % (k,v))
test_string = 'recording_7.wav Wow that is awesome %s' % k
print('...test string >>%s' % test_string)
tst_dc = DataClean(contents=test_string)
tst_dc.process_contents(show_results=False)
print('...processed as>>%s' % tst_dc.contents.decode())
self.assertEqual(-1,tst_dc.contents.decode().find(k),'...seems the original token is still in the string')
self.assertGreater(0, tst_dc.contents.decode().find(k),'...seems like the new token was not applied')
def test_dc_datasource_data_to_castable(self):
'''process everything and build a castable from results'''
curr_dc = DataClean(conn=self.conn,
contents_as_path=self.full_filename)
response = curr_dc.process_contents(show_results=False)
curr_dc.create_castable(response['results'],
'cool_cas',
replace=True,
promote=True)