import unittest
import random
import scanner.logSetup as logSetup
from bitstring import Bits
import pyximport
print("Have Cython")
pyximport.install()
import deduplicator.cyHamDb as hamDb
def hamming(a, b):
tot = 0
x = (a ^ b)
while x > 0:
tot += x & 1
x >>= 1
return tot
def b2i(binaryStringIn):
if len(binaryStringIn) != 64:
print("ERROR: Passed string not 64 characters. String length = %s" % len(binaryStringIn))
print("ERROR: String value '%s'" % binaryStringIn)
raise ValueError("Input strings must be 64 chars long!")
val = Bits(bin=binaryStringIn)
return val.int
def b2u(binaryStringIn):
if len(binaryStringIn) != 64:
print("ERROR: Passed string not 64 characters. String length = %s" % len(binaryStringIn))
print("ERROR: String value '%s'" % binaryStringIn)
raise ValueError("Input strings must be 64 chars long!")
val = Bits(bin=binaryStringIn)
return val.uint
# Node ID numbers are derived from the list ordering.
# This will generate a single node with 64 children.
TEST_DATA_FLAT = [
"0000000000000000000000000000000000000000000000000000000000000000", # 0
"0000000000000000000000000000000000000000000000000000000000000001", # 1
"0000000000000000000000000000000000000000000000000000000000000011", # 2
"0000000000000000000000000000000000000000000000000000000000000111", # 3
"0000000000000000000000000000000000000000000000000000000000001111", # 4
"0000000000000000000000000000000000000000000000000000000000011111", # 5
"0000000000000000000000000000000000000000000000000000000000111111", # 6
"0000000000000000000000000000000000000000000000000000000001111111", # 7
"0000000000000000000000000000000000000000000000000000000011111111", # 8
"0000000000000000000000000000000000000000000000000000000111111111", # 9
"0000000000000000000000000000000000000000000000000000001111111111", # 10
"0000000000000000000000000000000000000000000000000000011111111111", # 11
"0000000000000000000000000000000000000000000000000000111111111111", # 12
"0000000000000000000000000000000000000000000000000001111111111111", # 13
"0000000000000000000000000000000000000000000000000011111111111111", # 14
"0000000000000000000000000000000000000000000000000111111111111111", # 15
"0000000000000000000000000000000000000000000000001111111111111111", # 16
"0000000000000000000000000000000000000000000000011111111111111111", # 17
"0000000000000000000000000000000000000000000000111111111111111111", # 18
"0000000000000000000000000000000000000000000001111111111111111111", # 19
"0000000000000000000000000000000000000000000011111111111111111111", # 20
"0000000000000000000000000000000000000000000111111111111111111111", # 21
"0000000000000000000000000000000000000000001111111111111111111111", # 22
"0000000000000000000000000000000000000000011111111111111111111111", # 23
"0000000000000000000000000000000000000000111111111111111111111111", # 24
"0000000000000000000000000000000000000001111111111111111111111111", # 25
"0000000000000000000000000000000000000011111111111111111111111111", # 26
"0000000000000000000000000000000000000111111111111111111111111111", # 27
"0000000000000000000000000000000000001111111111111111111111111111", # 28
"0000000000000000000000000000000000011111111111111111111111111111",
"0000000000000000000000000000000000111111111111111111111111111111",
"0000000000000000000000000000000001111111111111111111111111111111",
"0000000000000000000000000000000011111111111111111111111111111111",
"0000000000000000000000000000000111111111111111111111111111111111",
"0000000000000000000000000000001111111111111111111111111111111111",
"0000000000000000000000000000011111111111111111111111111111111111",
"0000000000000000000000000000111111111111111111111111111111111111",
"0000000000000000000000000001111111111111111111111111111111111111",
"0000000000000000000000000011111111111111111111111111111111111111",
"0000000000000000000000000111111111111111111111111111111111111111",
"0000000000000000000000001111111111111111111111111111111111111111",
"0000000000000000000000011111111111111111111111111111111111111111",
"0000000000000000000000111111111111111111111111111111111111111111",
"0000000000000000000001111111111111111111111111111111111111111111",
"0000000000000000000011111111111111111111111111111111111111111111",
"0000000000000000000111111111111111111111111111111111111111111111",
"0000000000000000001111111111111111111111111111111111111111111111",
"0000000000000000011111111111111111111111111111111111111111111111",
"0000000000000000111111111111111111111111111111111111111111111111",
"0000000000000001111111111111111111111111111111111111111111111111",
"0000000000000011111111111111111111111111111111111111111111111111",
"0000000000000111111111111111111111111111111111111111111111111111",
"0000000000001111111111111111111111111111111111111111111111111111",
"0000000000011111111111111111111111111111111111111111111111111111",
"0000000000111111111111111111111111111111111111111111111111111111",
"0000000001111111111111111111111111111111111111111111111111111111",
"0000000011111111111111111111111111111111111111111111111111111111",
"0000000111111111111111111111111111111111111111111111111111111111",
"0000001111111111111111111111111111111111111111111111111111111111",
"0000011111111111111111111111111111111111111111111111111111111111",
"0000111111111111111111111111111111111111111111111111111111111111",
"0001111111111111111111111111111111111111111111111111111111111111",
"0011111111111111111111111111111111111111111111111111111111111111",
"0111111111111111111111111111111111111111111111111111111111111111",
"1111111111111111111111111111111111111111111111111111111111111111",
]
# THis will generate a single, 64-node long branch, with no forks.
TEST_DATA_Narrow = [
"0000000000000000000000000000000000000000000000000000000000000000", # 0
"0000000000000000000000000000000000000000000000000000000000000001", # 1
"0000000000000000000000000000000000000000000000000000000000000010", # 2
"0000000000000000000000000000000000000000000000000000000000000100", # 3
"0000000000000000000000000000000000000000000000000000000000001000", # 4
"0000000000000000000000000000000000000000000000000000000000010000", # 5
"0000000000000000000000000000000000000000000000000000000000100000", # 6
"0000000000000000000000000000000000000000000000000000000001000000", # 7
"0000000000000000000000000000000000000000000000000000000010000000", # 8
"0000000000000000000000000000000000000000000000000000000100000000", # 9
"0000000000000000000000000000000000000000000000000000001000000000", # 10
"0000000000000000000000000000000000000000000000000000010000000000", # 11
"0000000000000000000000000000000000000000000000000000100000000000", # 12
"0000000000000000000000000000000000000000000000000001000000000000", # 13
"0000000000000000000000000000000000000000000000000010000000000000", # 14
"0000000000000000000000000000000000000000000000000100000000000000", # 15
"0000000000000000000000000000000000000000000000001000000000000000", # 16
"0000000000000000000000000000000000000000000000010000000000000000", # 17
"0000000000000000000000000000000000000000000000100000000000000000", # 18
"0000000000000000000000000000000000000000000001000000000000000000", # 19
"0000000000000000000000000000000000000000000010000000000000000000", # 20
"0000000000000000000000000000000000000000000100000000000000000000", # 21
"0000000000000000000000000000000000000000001000000000000000000000", # 22
"0000000000000000000000000000000000000000010000000000000000000000", # 23
"0000000000000000000000000000000000000000100000000000000000000000", # 24
"0000000000000000000000000000000000000001000000000000000000000000", # 25
"0000000000000000000000000000000000000010000000000000000000000000", # 26
"0000000000000000000000000000000000000100000000000000000000000000", # 27
"0000000000000000000000000000000000001000000000000000000000000000", # 28
"0000000000000000000000000000000000010000000000000000000000000000",
"0000000000000000000000000000000000100000000000000000000000000000",
"0000000000000000000000000000000001000000000000000000000000000000",
"0000000000000000000000000000000010000000000000000000000000000000",
"0000000000000000000000000000000100000000000000000000000000000000",
"0000000000000000000000000000001000000000000000000000000000000000",
"0000000000000000000000000000010000000000000000000000000000000000",
"0000000000000000000000000000100000000000000000000000000000000000",
"0000000000000000000000000001000000000000000000000000000000000000",
"0000000000000000000000000010000000000000000000000000000000000000",
"0000000000000000000000000100000000000000000000000000000000000000",
"0000000000000000000000001000000000000000000000000000000000000000",
"0000000000000000000000010000000000000000000000000000000000000000",
"0000000000000000000000100000000000000000000000000000000000000000",
"0000000000000000000001000000000000000000000000000000000000000000",
"0000000000000000000010000000000000000000000000000000000000000000",
"0000000000000000000100000000000000000000000000000000000000000000",
"0000000000000000001000000000000000000000000000000000000000000000",
"0000000000000000010000000000000000000000000000000000000000000000",
"0000000000000000100000000000000000000000000000000000000000000000",
"0000000000000001000000000000000000000000000000000000000000000000",
"0000000000000010000000000000000000000000000000000000000000000000",
"0000000000000100000000000000000000000000000000000000000000000000",
"0000000000001000000000000000000000000000000000000000000000000000",
"0000000000010000000000000000000000000000000000000000000000000000",
"0000000000100000000000000000000000000000000000000000000000000000",
"0000000001000000000000000000000000000000000000000000000000000000",
"0000000010000000000000000000000000000000000000000000000000000000",
"0000000100000000000000000000000000000000000000000000000000000000",
"0000001000000000000000000000000000000000000000000000000000000000",
"0000010000000000000000000000000000000000000000000000000000000000",
"0000100000000000000000000000000000000000000000000000000000000000",
"0001000000000000000000000000000000000000000000000000000000000000",
"0010000000000000000000000000000000000000000000000000000000000000",
"0100000000000000000000000000000000000000000000000000000000000000",
"1000000000000000000000000000000000000000000000000000000000000000",
]
class TestSequenceFunctions_FlatTree(unittest.TestCase):
def __init__(self, *args, **kwargs):
logSetup.initLogging()
super().__init__(*args, **kwargs)
def setUp(self):
self.tree = hamDb.BkHammingTree()
for x in range(4):
with self.tree.writer_context():
self.tree.dropTree()
self.buildTestTree()
def buildTestTree(self):
self.tree = hamDb.BkHammingTree()
for nodeId, node_hash in enumerate(TEST_DATA_FLAT):
print("Inserting node id: ", nodeId, "hash", node_hash, "value: ", b2i(node_hash))
node_hash = b2i(node_hash)
self.tree.unlocked_insert(node_hash, nodeId)
def test_1(self):
tgtHash = "0000000000000000000000000000000000000000000000000000000000000001"
tgtHash = b2i(tgtHash)
ret = self.tree.getWithinDistance(tgtHash, 0)
self.assertEqual(ret, set((1, )))
def test_2(self):
tgtHash = "0000000000000000000000000000000000000000001111111111111111111111"
tgtHash = b2i(tgtHash)
ret = self.tree.getWithinDistance(tgtHash, 0)
self.assertEqual(ret, set((22, )))
def test_3(self):
tgtHash = "1111111111111111111111111111111111111111111111111111111111111111"
tgtHash = b2i(tgtHash)
ret = self.tree.getWithinDistance(tgtHash, 0)
self.assertEqual(ret, set((64, )))
class TestSequenceFunctions_TallTree(unittest.TestCase):
def __init__(self, *args, **kwargs):
logSetup.initLogging()
super().__init__(*args, **kwargs)
def setUp(self):
self.tree = hamDb.BkHammingTree()
for x in range(4):
with self.tree.writer_context():
self.tree.dropTree()
self.buildTestTree()
def buildTestTree(self):
self.tree = hamDb.BkHammingTree()
for nodeId, node_hash in enumerate(TEST_DATA_Narrow):
print("Inserting node id: ", nodeId, "hash", node_hash, "value: ", b2i(node_hash))
node_hash = b2i(node_hash)
self.tree.insert(node_hash, nodeId)
def test_1(self):
tgtHash = "0000000000000000000000000000000000000000000000000000000000000001"
tgtHash = b2i(tgtHash)
ret = self.tree.getWithinDistance(tgtHash, 0)
self.assertEqual(ret, set((1, )))
def test_2(self):
tgtHash = "0000000000000000000000000000000000000000001000000000000000000000"
tgtHash = b2i(tgtHash)
ret = self.tree.getWithinDistance(tgtHash, 0)
self.assertEqual(ret, set((22, )))
def test_3(self):
tgtHash = "1000000000000000000000000000000000000000000000000000000000000000"
tgtHash = b2i(tgtHash)
ret = self.tree.getWithinDistance(tgtHash, 0)
self.assertEqual(ret, set((64, )))
class TestSignConversion(unittest.TestCase):
def __init__(self, *args, **kwargs):
logSetup.initLogging()
super().__init__(*args, **kwargs)
def test_signModification_1(self):
for val in TEST_DATA_Narrow:
tgtHash = b2i(val)
x = hamDb.explicitUnsignCast(tgtHash)
self.assertEqual(x, b2u(val))
x = hamDb.explicitSignCast(x)
self.assertEqual(x, tgtHash)
def test_signModification_2(self):
for val in TEST_DATA_FLAT:
tgtHash = b2i(val)
x = hamDb.explicitUnsignCast(tgtHash)
self.assertEqual(x, b2u(val))
x = hamDb.explicitSignCast(x)
self.assertEqual(x, tgtHash)
def test_signModification_3(self):
random.seed(500000)
for x in range(50000):
val = "".join([random.choice(("1", "0")) for z in range(64)])
tgtHash = b2i(val)
x = hamDb.explicitUnsignCast(tgtHash)
self.assertEqual(x, b2u(val))
x = hamDb.explicitSignCast(x)
self.assertEqual(x, tgtHash)
