def test_threading():
cache_dir = check_cache()
fe = EmailParser(cache_dir=cache_dir)
uuid = fe.transform(data_dir, file_pattern='.*\d')
filenames, res = fe.load(uuid)
cat = _EmailThreadingWrapper(cache_dir=cache_dir, parent_id=uuid)
tree = cat.thread()
cat.get_params()
tree_ref = [{
'id':
0,
'parent':
None,
'children': [{
'id': 1,
'children': [],
'parent': 0
}, {
'id':
2,
'parent':
0,
'children': [{
'id': 3,
'children': [],
'parent': 2
}, {
'id': 4,
'children': [],
'parent': 2
}],
}]
}]
assert [el.to_dict() for el in tree] == tree_ref
assert len(filenames) == sum([el.size for el in tree])
assert len(filenames) == 5
def test_search_filenames():
cache_dir = check_cache()
fe = EmailParser(cache_dir=cache_dir)
fe.transform(data_dir, file_pattern='.*\d')
filenames = fe._pars['filenames']
for low, high, step in [(0, 1, 1),
(0, 4, 1),
(3, 1, -1)]:
idx_slice = list(range(low, high, step))
filenames_slice = [filenames[idx] for idx in idx_slice]
idx0 = fe.search(filenames_slice)
assert_equal(idx0, idx_slice)
assert_equal(filenames_slice, fe[idx0])
with pytest.raises(KeyError):
fe.search(['DOES_NOT_EXIST.txt'])
fe.list_datasets()
def test_email_parser():
cache_dir = check_cache()
fe = EmailParser(cache_dir=cache_dir)
uuid = fe.transform(data_dir, file_pattern='.*\d')
filenames, res = fe.load(uuid)
assert_equal(filenames, fe._pars['filenames'])
assert len(filenames) == len(res)
assert len(filenames) == 5
for message in res:
assert isinstance(message, Message)
fe.delete()