def test_suffix_binary_search_tobeornottobe_contains_tobeornottobe(self):
text = "tobeornottobe$"
suffix_array = [13, 11, 2, 12, 3, 6, 10, 1, 4, 7, 5, 9, 0, 8]
substring = "tobeornottobe$"
expected = 0
computed = suffix_binary_search(text, suffix_array, substring)
self.assertEquals(computed, expected)
def test_suffix_binary_search_abracadabra_doesnt_contain_abrax(self):
text = "abracadabra$"
suffix_array = [11, 10, 7, 0, 3, 5, 8, 1, 4, 6, 9, 2]
substring = "abrax"
expected = -1
computed = suffix_binary_search(text, suffix_array, substring)
self.assertEquals(computed, expected)
def search_dataset(search_type):
print "Searching dataset..."
sorted_keys = sorted(dataset_dict.keys())
for key in sorted_keys:
total_time = 0
dataset = dataset_dict[key]
for substring in dataset:
i = time.time()
if search_type == "lcp":
answer = lcp_search(text, suffix_array, substring, llcp, rlcp)
else:
answer = suffix_binary_search(text, suffix_array, substring)
f = time.time()
assert substring == text[answer: answer + len(substring)]
total_time += f - i
print " key: %2d | total time: %f | average time: %f" %\
(key, total_time, total_time / LIST_SIZE)
print "Done."