def test_gdata(self):
"""DndTokenizer should work as expected on real data"""
exp = \
['(', '(', 'xyz', ':', '0.28124',',', '(', 'def', ':', '0.24498',\
',', 'mno', ':', '0.03627', ')', ':', '0.17710', ')', ':', '0.04870', \
',', 'abc', ':', '0.05925', ',', '(', 'ghi', ':', '0.06914', ',', \
'jkl', ':', '0.13776', ')', ':', '0.09853', ')', ';']
#split it up for debugging on an item-by-item basis
obs = list(DndTokenizer(sample))
self.assertEqual(len(obs), len(exp))
for i, j in zip(obs, exp):
self.assertEqual(i, j)
#try it all in one go
self.assertEqual(list(DndTokenizer(sample)), exp)
def test_minimal(self):
"""DndTokenizer should work as expected a minimal tree without names"""
exp = ['(', ')', ';']
obs = list(DndTokenizer(minimal))
self.assertEqual(obs, exp)
def test_missing_tip_name(self):
"""DndTokenizer should work as expected on trees with a missing name"""
exp = ['(', '(', 'a', ',', 'b', ')', ',', '(', 'c', ',', ')', ')', ';']
obs = list(DndTokenizer(missing_tip_name))
self.assertEqual(obs, exp)
def test_nonames(self):
"""DndTokenizer should work as expected on trees with no names"""
exp = ['(', '(', ',', ')', ',', '(', ',', ')', ')', ';']
obs = list(DndTokenizer(no_names))
self.assertEqual(obs, exp)