def main():
with open(F, 'r') as f:
b64 = f.read()
enc = tools.fromB64(b64)
# print(tools.toHex(enc))
print(['# of bytes >=0x80: ', sum([(x >> 7) for x in enc])])
bestScore = 0
bestDist = 2**30
for l in range(2, 40):
print('L = ', l)
bl = tools.transpose(enc, l)
# for blx in bl:print(tools.toHex(blx))
distances = [
hamming.compute(enc[i * l:(i + 1) * l],
enc[(i + 1) * l:(i + 2) * l])
for i in range(len(enc) // l - 2)
]
avgDist = sum(distances) / (len(distances) * l)
print(['dist', l, distances[0] / l, avgDist])
if bestDist > avgDist:
bestDist = avgDist
bestDistL = l
# print([tools.toHex(x) for x in bl])
dec = decrypt(enc, bl)
if (dec[0] > bestScore):
bestScore = dec[0]
bestDec = dec[1]
bestLen = l
bestKey = dec[2]
print('*' * 72)
print(['best[dist=%.3f, keylen=%i]' % (bestDist, bestDistL)])
print([
'best[score,len,key,dec]', bestScore, bestLen,
bytes(bestKey), bestDec
])
return 0
def test_disallow_second_strand_longer(self):
with self.assertRaises(ValueError):
hamming.compute('ATA', 'AGTG')
def test_empty_strands(self):
self.assertEqual(0, hamming.compute('', ''))
def test_large_compute_in_off_by_one_strand(self):
self.assertEqual(9, hamming.compute('GGACGGATTCTG', 'AGGACGGATTCT'))
def test_same_nucleotides_in_different_positions(self):
self.assertEqual(2, hamming.compute('TAG', 'GAT'))
def test_small_compute_in_long_strands(self):
self.assertEqual(2, hamming.compute('ACCAGGG', 'ACTATGG'))
def test_small_compute_in_small_strands(self):
self.assertEqual(1, hamming.compute('AT', 'CT'))
def test_complete_compute_in_single_nucleotide_strands(self):
self.assertEqual(1, hamming.compute('A', 'G'))
def test_non_unique_character_in_second_strand(self):
self.assertEqual(1, hamming.compute('AGG', 'AGA'))
def test_small_compute_in_long_strands(self):
self.assertEqual(2, hamming.compute('ACCAGGG', 'ACTATGG'))
def test_small_compute(self):
self.assertEqual(1, hamming.compute('GGACG', 'GGTCG'))
def test_small_compute_in_small_strands(self):
self.assertEqual(1, hamming.compute('AT', 'CT'))
def test_complete_compute_in_small_strands(self):
self.assertEqual(2, hamming.compute('AG', 'CT'))
def test_complete_compute_in_single_nucleotide_strands(self):
self.assertEqual(1, hamming.compute('A', 'G'))
def test_long_identical_strands(self):
self.assertEqual(0, hamming.compute('GGACTGA', 'GGACTGA'))
def test_identical_strands(self):
self.assertEqual(0, hamming.compute('A', 'A'))
def test_long_identical_strands(self):
self.assertEqual(0, hamming.compute('GGACTGA', 'GGACTGA'))
def test_same_nucleotides_in_different_positions(self):
self.assertEqual(2, hamming.compute('TAG', 'GAT'))
def test_complete_compute_in_small_strands(self):
self.assertEqual(2, hamming.compute('AG', 'CT'))
def test_large_compute(self):
self.assertEqual(4, hamming.compute('GATACA', 'GCATAA'))
def test_small_compute(self):
self.assertEqual(1, hamming.compute('GGACG', 'GGTCG'))
def test_large_compute_in_off_by_one_strand(self):
self.assertEqual(9, hamming.compute('GGACGGATTCTG', 'AGGACGGATTCT'))
def test_non_unique_character_in_second_strand(self):
self.assertEqual(1, hamming.compute('AGG', 'AGA'))
def test_very_large_compute(self):
self.assertEqual(0, hamming.compute('CAT' * 5000, 'CAT' * 5000))
def test_large_compute(self):
self.assertEqual(4, hamming.compute('GATACA', 'GCATAA'))
def test_empty_strands(self):
self.assertEqual(0, hamming.compute('', ''))
def test_very_large_compute(self):
self.assertEqual(0, hamming.compute('CAT' * 5000, 'CAT' * 5000))
def test_disallow_first_strand_longer(self):
with self.assertRaises(ValueError):
hamming.compute('AATG', 'AAA')
def test_disallow_first_strand_longer(self):
with self.assertRaises(ValueError):
hamming.compute('AATG', 'AAA')
def test_disallow_second_strand_longer(self):
with self.assertRaises(ValueError):
hamming.compute('ATA', 'AGTG')
def test_identical_strands(self):
self.assertEqual(0, hamming.compute('A', 'A'))
def test_dna_strands(self):
self.assertEqual(
7, hamming.compute('GAGCCTACTAACGGGAT', 'CATCGTAATGACGGCCT'))