Python TokenIndex.create_token_index Examples

Example #1

File: test_suffix_based_scorer.py Project: ljo/collatex

 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

Example #2

File: test_suffix_based_scorer.py Project: mhbeals/collatex

 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

Example #3

File: test_suffix_based_scorer.py Project: ljo/collatex

 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

Example #4

File: test_suffix_based_scorer.py Project: mhbeals/collatex

 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

Example #5

File: test_suffix_based_scorer.py Project: ljo/collatex

 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

Example #6

File: test_suffix_based_scorer.py Project: mhbeals/collatex

 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