class DecisionTreeTest(TestCase):
def setUp(self):
# we need to create witnesses
# 1: a, b, c, d, e
# 2: a, e, c, d
# 3: a, d, b
a = Witness({'id': 'A', 'content': "a b c d e"})
b = Witness({'id': 'B', 'content': "a e c d"})
c = Witness({'id': 'C', 'content': "a d b"})
self.witnesses = [a, b, c]
self.tokenindex = TokenIndex(self.witnesses)
self.tokenindex.prepare()
def test_maximum_score(self):
# from the token index we need to calculate the maximum amount of matches
lcp_intervals = self.tokenindex.split_lcp_array_into_intervals()
possible_matches = calculate_maximum(lcp_intervals)
# print(possible_matches)
self.assertEquals(12, possible_matches)
def test_decision_tree(self):
tree = DecisionTree(self.witnesses)
root = tree.root
self.assertEquals((0, 0, 0), root.coordinates)
# we need three scores, (current score), (minimum global score, maximum global score)
self.assertEquals(0, root.current_score)
self.assertEquals(0, root.minimum_global_score)
self.assertEquals(12, root.maximum_global_score)
class DecisionTreeTest(TestCase):
def setUp(self):
# we need to create witnesses
# 1: a, b, c, d, e
# 2: a, e, c, d
# 3: a, d, b
a = Witness({'id':'A', 'content':"a b c d e"})
b = Witness({'id':'B', 'content':"a e c d"})
c = Witness({'id':'C', 'content':"a d b"})
self.witnesses = [a, b, c]
self.tokenindex = TokenIndex(self.witnesses)
self.tokenindex.prepare()
def test_maximum_score(self):
# from the token index we need to calculate the maximum amount of matches
lcp_intervals = self.tokenindex.split_lcp_array_into_intervals()
possible_matches = calculate_maximum(lcp_intervals)
# print(possible_matches)
self.assertEquals(12, possible_matches)
def test_decision_tree(self):
tree = DecisionTree(self.witnesses)
root = tree.root
self.assertEquals((0, 0, 0), root.coordinates)
# we need three scores, (current score), (minimum global score, maximum global score)
self.assertEquals(0, root.current_score)
self.assertEquals(0, root.minimum_global_score)
self.assertEquals(12, root.maximum_global_score)
def test_lcp_intervals_number_of_witnesses_Hermans_case(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d F g h i ! K ! q r s t")
collation.add_plain_witness("W2", "a b c d F g h i ! q r s t")
collation.add_plain_witness("W3", "a b c d E g h i ! q r s t")
token_index = TokenIndex(collation.witnesses)
token_index.prepare()
intervals = token_index.split_lcp_array_into_intervals()
potential_block = intervals[1] # ! q r s t
self.assertEqual(3, potential_block.number_of_witnesses)
class DecisionTree(object):
def __init__(self, witnesses):
self.witnesses = witnesses
self.tokenindex = TokenIndex(witnesses)
self.tokenindex.prepare()
self.lcp_intervals = self.tokenindex.split_lcp_array_into_intervals()
global_maximum_score = calculate_maximum(self.lcp_intervals)
self.root = DecisionNode(global_maximum_score)
pass
def test_lcp_intervals_number_of_witnesses_Hermans_case(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d F g h i ! K ! q r s t")
collation.add_plain_witness("W2", "a b c d F g h i ! q r s t")
collation.add_plain_witness("W3", "a b c d E g h i ! q r s t")
token_index = TokenIndex(collation.witnesses)
token_index.prepare()
intervals = token_index.split_lcp_array_into_intervals()
potential_block = intervals[1] # ! q r s t
self.assertEqual(3, potential_block.get_depth())
class DecisionTree(object):
def __init__(self, witnesses):
self.witnesses = witnesses
self.tokenindex = TokenIndex(witnesses)
self.tokenindex.prepare()
self.lcp_intervals = self.tokenindex.split_lcp_array_into_intervals()
global_maximum_score = calculate_maximum(self.lcp_intervals)
self.root = DecisionNode(global_maximum_score)
pass
def test_filter_potential_blocks(self):
collation = Collation()
collation.add_plain_witness("W1", "a a")
collation.add_plain_witness("w2", "a")
token_index = TokenIndex(collation.witnesses)
token_index.prepare()
intervals = token_index.split_lcp_array_into_intervals()
# expectations
# There is one interval with length 1, number of occurrences 3, number of witnesses: 2
a_interval = intervals[0] # a
self.assertEqual(2, a_interval.number_of_witnesses)
self.assertEqual(1, a_interval.length)
self.assertEqual(3, a_interval.number_of_occurrences)
def test_filter_potential_blocks(self):
collation = Collation()
collation.add_plain_witness("W1", "a a")
collation.add_plain_witness("w2", "a")
token_index = TokenIndex(collation.witnesses)
token_index.prepare()
blocks = token_index.split_lcp_array_into_intervals()
# expectations
# There is one interval with length 1, number of occurrences 3, number of witnesses: 2
a_block = blocks[0] # a
self.assertEqual(2, a_block.get_depth())
self.assertEqual(1, a_block.length)
self.assertEqual(3, len(a_block.get_all_instances()))
def testCaseDanielStoeklLCPIntervals(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d e")
collation.add_plain_witness("W2", "a e c d")
collation.add_plain_witness("W3", "a d b")
token_index = TokenIndex(collation.witnesses)
token_index.prepare()
blocks = token_index.split_lcp_array_into_intervals()
self.assertLCP_Interval(2, 1, 3, 3, blocks[0]) # a
self.assertLCP_Interval(5, 1, 2, 2, blocks[1]) # b
self.assertLCP_Interval(7, 2, 2, 2, blocks[2]) # c d
self.assertLCP_Interval(9, 1, 3, 3, blocks[3]) # d
self.assertLCP_Interval(12, 1, 2, 2, blocks[4]) # e
self.assertEquals(5, len(blocks))
def testCaseDanielStoeklLCPIntervals(self):
collation = Collation()
collation.add_plain_witness("W1", "a b c d e")
collation.add_plain_witness("W2", "a e c d")
collation.add_plain_witness("W3", "a d b")
token_index = TokenIndex(collation.witnesses)
token_index.prepare()
blocks = token_index.split_lcp_array_into_intervals()
self.assertLCP_Interval(2, 1, 3, 3, blocks[0]) # a
self.assertLCP_Interval(5, 1, 2, 2, blocks[1]) # b
self.assertLCP_Interval(7, 2, 2, 2, blocks[2]) # c d
self.assertLCP_Interval(9, 1, 3, 3, blocks[3]) # d
self.assertLCP_Interval(12, 1, 2, 2, blocks[4]) # e
self.assertEqual(5, len(blocks))
