def test_get_random_substring_list(self):
text = "Welcome to where time stands still"
computed_list = get_random_substring_list(string=text,
list_size=3,
substring_size=6)
self.assertEquals(len(computed_list), 3)
self.assertEquals(len(computed_list[0]), 6)
self.assertEquals(len(computed_list[1]), 6)
self.assertEquals(len(computed_list[2]), 6)
self.assertTrue(computed_list[0] in text)
self.assertTrue(computed_list[1] in text)
self.assertTrue(computed_list[2] in text)
def test_get_random_substring_list(self):
text = "Welcome to where time stands still"
computed_list = get_random_substring_list(
string=text,
list_size=3,
substring_size=6
)
self.assertEquals(len(computed_list), 3)
self.assertEquals(len(computed_list[0]), 6)
self.assertEquals(len(computed_list[1]), 6)
self.assertEquals(len(computed_list[2]), 6)
self.assertTrue(computed_list[0] in text)
self.assertTrue(computed_list[1] in text)
self.assertTrue(computed_list[2] in text)
def load_dataset(fileprefix):
dataset_filename = "%s_dataset_dict.pck" % fileprefix
global dataset_dict
global text
print "Loading dataset..."
if exists(dataset_filename):
print " Reading dataset from %s..." % dataset_filename
dataset_dict = unpickle(dataset_filename)
else:
print " Computing dataset..."
dataset_dict = {}
for i in xrange(1, 11):
item_size = substring_size(i)
dataset_dict[i] = get_random_substring_list(\
text, LIST_SIZE, item_size)
print " Writing dataset to %s..." % dataset_filename
picklefy(dataset_filename, dataset_dict)
print " Done."
