def test_non_overlapping_blocks_overlap_case(self):
collation = Collation()
collation.add_plain_witness("W1", "in the in the bleach")
collation.add_plain_witness("W2", "in the in the bleach in the")
algorithm = Scorer(TokenIndex.create_token_index(collation))
blocks = algorithm._get_non_overlapping_repeating_blocks()
self.assertIn(Block(RangeSet("0-4, 6-10")),
blocks) # in the in the bleach
def test_blocks_splitting_token_case(self):
collation = Collation()
collation.add_plain_witness("W1", "a c b c")
collation.add_plain_witness("W2", "a c b")
algorithm = Scorer(collation)
blocks = algorithm._get_non_overlapping_repeating_blocks()
block1 = Block(RangeSet("0-2, 5-7")) # a c b
self.assertIn(block1, blocks)
def test_non_overlapping_blocks_black_cat(self):
collation = Collation()
collation.add_plain_witness("W1", "the black cat")
collation.add_plain_witness("W2", "the black cat")
algorithm = Scorer(collation)
blocks = algorithm._get_non_overlapping_repeating_blocks()
block1 = Block(RangeSet("0-2, 4-6"))
self.assertEqual([block1], blocks)
def test_block_witnesses_Hermans_case_two_witnesses(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")
algorithm = Scorer(collation)
block_witness = algorithm._get_block_witness(collation.witnesses[0])
self.assertEquals(["a b c d F g h i !", "q r s t"], block_witness.debug())
block_witness = algorithm._get_block_witness(collation.witnesses[1])
self.assertEquals(["a b c d F g h i !", "q r s t"], block_witness.debug())
def test_non_overlapping_blocks_Hermans(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")
algorithm = Scorer(TokenIndex.create_token_index(collation))
blocks = algorithm._get_non_overlapping_repeating_blocks()
self.assertIn(Block(RangeSet("0-8, 16-24")),
blocks) # a b c d F g h i !
self.assertIn(Block(RangeSet("11-14, 25-28")), blocks) # q r s t
def test_filter_potential_blocks(self):
collation = Collation()
collation.add_plain_witness("W1", "a a")
collation.add_plain_witness("w2", "a")
extsufarr = collation.to_extended_suffix_array()
potential_blocks = extsufarr.split_lcp_array_into_intervals()
algorithm = Scorer(collation)
algorithm.filter_potential_blocks(potential_blocks)
self.assertFalse(potential_blocks)
def test_non_overlapping_blocks_Hermans(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")
algorithm = Scorer(collation)
blocks = algorithm._get_non_overlapping_repeating_blocks()
self.assertIn(Block(RangeSet("0-8, 17-25")),
blocks) # a b c d F g h i !
self.assertIn(Block(RangeSet("11-14, 26-29")), blocks) # q r s t
def test_blocks_failing_transposition_use_case_old_algorithm(self):
collation = Collation()
collation.add_plain_witness("W1", "the cat and the dog")
collation.add_plain_witness("W2", "the dog and the cat")
algorithm = Scorer(collation)
blocks = algorithm._get_non_overlapping_repeating_blocks()
block1 = Block(RangeSet("0-1, 9-10"))
block2 = Block(RangeSet("3-4, 6-7"))
block3 = Block(RangeSet("2, 8"))
self.assertEqual([block1, block2, block3], blocks)
def __init__(self,
collation,
near_match=False,
astar=False,
debug_scores=False):
self.collation = collation
self.debug_scores = debug_scores
self.scorer = Scorer(collation, near_match)
print("INFO: Aligning using a* search algorithm. BETA quality.")
self.align_function = self._align_astar
def test_block_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")
algorithm = Scorer(collation)
block_witness1 = algorithm._get_block_witness(collation.witnesses[0])
self.assertEquals(["a b c d", "F", "g h i", "! q r s t"], block_witness1.debug())
block_witness2 = algorithm._get_block_witness(collation.witnesses[1])
self.assertEquals(["a b c d", "F", "g h i", "! q r s t"], block_witness2.debug())
block_witness3 = algorithm._get_block_witness(collation.witnesses[2])
self.assertEquals(["a b c d", "g h i", "! q r s t"], block_witness3.debug())
def test_blocks_Hermans_case_three_witnesses(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")
algorithm = Scorer(TokenIndex.create_token_index(collation))
blocks = algorithm._get_non_overlapping_repeating_blocks()
self.assertIn(Block(RangeSet("0-3, 16-19, 30-33")), blocks) # a b c d
self.assertIn(Block(RangeSet("5-7, 21-23, 35-37")), blocks) # g h i
self.assertIn(Block(RangeSet("10-14, 24-28, 38-42")),
blocks) # ! q r s t
self.assertIn(Block(RangeSet("4, 20")), blocks) # F
def test_blocks_Hermans_case_three_witnesses(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")
algorithm = Scorer(collation)
blocks = algorithm._get_non_overlapping_repeating_blocks()
self.assertIn(Block(RangeSet("0-3, 17-20, 32-35")), blocks) # a b c d
self.assertIn(Block(RangeSet("5-7, 22-24, 37-39")), blocks) # g h i
self.assertIn(Block(RangeSet("10-14, 25-29, 40-44")),
blocks) # ! q r s t
self.assertIn(Block(RangeSet("4, 21")), blocks) # F
def __init__(self,
collation,
near_match=False,
debug_scores=False,
detect_transpositions=False,
properties_filter=None):
self.collation = collation
self.debug_scores = debug_scores
self.detect_transpositions = detect_transpositions
self.token_index = TokenIndex(collation.witnesses)
self.scorer = Scorer(self.token_index,
near_match=near_match,
properties_filter=properties_filter)
self.align_function = self._align_table
