def collate(collation, output="table", layout="horizontal", segmentation=True, near_match=False, astar=False, detect_transpositions=False, debug_scores=False, properties_filter=None):
if not astar:
algorithm = EditGraphAligner(collation, near_match=near_match, detect_transpositions=detect_transpositions, debug_scores=debug_scores, properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation, near_match=near_match, debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph, collation)
# join parallel segments
if segmentation:
join(graph)
# check which output format is requested: graph or table
if output == "svg":
return display_variant_graph_as_SVG(graph)
if output=="graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_HTML(table)
if output == "html2":
return visualizeTableVerticallyWithColors(table, collation)
if output == "table":
return table
else:
raise Exception("Unknown output type: "+output)
def test_superbase_generation_multiple_short_witnesses(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph)
def test_superbase_generation_multiple_short_witnesses(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph)
def test_superbase(self):
collation = Collation()
collation.add_plain_witness("A", "X a b c d e f X g h i Y Z j k")
collation.add_plain_witness("B", "a b c Y d e f Y Z g h i X j k")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph, collation)
superbase = aligner.new_superbase
self.assertSuperbaseEquals("X a b c Y d e f X Y Z g h i Y Z X j k", superbase)
def test_superbase(self):
collation = Collation()
collation.add_plain_witness("A", "X a b c d e f X g h i Y Z j k")
collation.add_plain_witness("B", "a b c Y d e f Y Z g h i X j k")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph, collation)
superbase = aligner.new_superbase
self.assertSuperbaseEquals("X a b c Y d e f X Y Z g h i Y Z X j k", superbase)
def test_superbase_generation_multiple_short_witnesses(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph, collation)
superbase = aligner.new_superbase
self.assertSuperbaseEquals("a b c", superbase)
def test_superbase_generation_multiple_short_witnesses(self):
collation = Collation()
collation.add_plain_witness("A", "a")
collation.add_plain_witness("B", "b")
collation.add_plain_witness("C", "c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph, collation)
superbase = aligner.new_superbase
self.assertSuperbaseEquals("a b c", superbase)
def collate(collation, output="table", layout="horizontal", segmentation=True, near_match=False, astar=False,
detect_transpositions=False, debug_scores=False, properties_filter=None, indent=False):
# collation may be collation or json; if it's the latter, use it to build a real collation
if isinstance(collation, dict):
json_collation = Collation()
for witness in collation["witnesses"]:
json_collation.add_witness(witness)
collation = json_collation
# assume collation is collation (by now); no error trapping
if not astar:
algorithm = EditGraphAligner(collation, near_match=False, detect_transpositions=detect_transpositions,
debug_scores=debug_scores, properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation, near_match=False, debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph)
ranking = VariantGraphRanking.of(graph)
if near_match:
# Segmentation not supported for near matching; raise exception if necessary
# There is already a graph ('graph', without near-match edges) and ranking ('ranking')
if segmentation:
raise SegmentationError('segmentation must be set to False for near matching')
ranking = perform_near_match(graph, ranking)
# join parallel segments
if segmentation:
join(graph)
ranking = VariantGraphRanking.of(graph)
# check which output format is requested: graph or table
if output == "svg" or output == "svg_simple":
return display_variant_graph_as_svg(graph, output)
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout, ranking)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_html(table)
if output == "html2":
return visualize_table_vertically_with_colors(table, collation)
if output == "table":
return table
if output == "xml":
return export_alignment_table_as_xml(table)
if output == "tei":
return export_alignment_table_as_tei(table, indent)
if output == "csv" or output == "tsv":
return display_alignment_table_as_csv(table, output)
else:
raise Exception("Unknown output type: " + output)
def testOmission2GlobalScore(self):
collation = Collation()
collation.add_plain_witness("A", "a a b c")
collation.add_plain_witness("B", "a b c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph)
table = aligner.table
self.assertRow([0, -1, -2, -3, -4], table[0])
self.assertRow([-1, 0, -1, -2, -3], table[1])
self.assertRow([-2, -1, -2, -1, -2], table[2])
self.assertRow([-3, -2, -3, -2, -1], table[3])
def testOmission2GlobalScore(self):
collation = Collation()
collation.add_plain_witness("A", "a a b c")
collation.add_plain_witness("B", "a b c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph, collation)
table = aligner.table
self.assertRow([0, -1, -2, -3, -4], table[0])
self.assertRow([-1, 0, -1, -2, -3], table[1])
self.assertRow([-2, -1, -2, -1, -2], table[2])
self.assertRow([-3, -2, -3, -2, -1], table[3])
def collate(collation,
output="table",
layout="horizontal",
segmentation=True,
near_match=False,
astar=False,
debug_scores=False):
algorithm = EditGraphAligner(collation,
near_match=near_match,
astar=astar,
debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph, collation)
# join parallel segments
if segmentation:
join(graph)
# check which output format is requested: graph or table
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout)
if collation.pretokenized and not segmentation:
token_list = [[tk.token_data for tk in witness.tokens()]
for witness in collation.witnesses]
# only with segmentation=False
# there could be a different comportment of get_tokenized_table if semgentation=True
table = get_tokenized_at(table,
token_list,
segmentation=segmentation,
layout=layout)
# for display purpose, table and html output will return only token 't' (string) and not the full token_data (dict)
if output == "table" or output == "html":
for row in table.rows:
row.cells = [cell["t"] for cell in row.cells]
if output == "json":
return export_alignment_table_as_json(table, layout=layout)
if output == "html":
return display_alignment_table_as_HTML(table)
if output == "table":
return table
else:
raise Exception("Unknown output type: " + output)
def collate(collation,
output="table",
layout="horizontal",
segmentation=True,
near_match=False,
astar=False,
detect_transpositions=False,
debug_scores=False,
properties_filter=None):
if not astar:
algorithm = EditGraphAligner(
collation,
near_match=near_match,
detect_transpositions=detect_transpositions,
debug_scores=debug_scores,
properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation,
near_match=near_match,
debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph, collation)
# join parallel segments
if segmentation:
join(graph)
# check which output format is requested: graph or table
if output == "svg":
return display_variant_graph_as_SVG(graph)
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_HTML(table)
if output == "html2":
return visualizeTableVerticallyWithColors(table, collation)
if output == "table":
return table
else:
raise Exception("Unknown output type: " + output)
def testOmission(self):
collation = Collation()
collation.add_plain_witness("A", "a b c")
collation.add_plain_witness("B", "b c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph, collation)
table = aligner.table
# self.debug_table(aligner, table)
self.assertEqual(0, table[0][0].g)
self.assertEqual(-1, table[0][1].g)
self.assertEqual(-2, table[0][2].g)
self.assertEqual(-3, table[0][3].g)
self.assertEqual(-1, table[1][0].g)
self.assertEqual(-2, table[1][1].g)
self.assertEqual(-1, table[1][2].g)
self.assertEqual(-2, table[1][3].g)
self.assertEqual(-2, table[2][0].g)
self.assertEqual(-3, table[2][1].g)
self.assertEqual(-2, table[2][2].g)
self.assertEqual(-1, table[2][3].g)
def testOmission(self):
collation = Collation()
collation.add_plain_witness("A", "a b c")
collation.add_plain_witness("B", "b c")
aligner = EditGraphAligner(collation)
graph = VariantGraph()
aligner.collate(graph)
table = aligner.table
# self.debug_table(aligner, table)
self.assertEqual(0, table[0][0].g)
self.assertEqual(-1, table[0][1].g)
self.assertEqual(-2, table[0][2].g)
self.assertEqual(-3, table[0][3].g)
self.assertEqual(-1, table[1][0].g)
self.assertEqual(-2, table[1][1].g)
self.assertEqual(-1, table[1][2].g)
self.assertEqual(-2, table[1][3].g)
self.assertEqual(-2, table[2][0].g)
self.assertEqual(-3, table[2][1].g)
self.assertEqual(-2, table[2][2].g)
self.assertEqual(-1, table[2][3].g)
def collate(collation, output="table", layout="horizontal", segmentation=True, near_match=False, astar=False, debug_scores=False):
scorer = Scorer(collation, near_match)
algorithm = EditGraphAligner(collation, scorer, astar=astar, debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph, collation)
# join parallel segments
if segmentation:
join(graph)
# check which output format is requested: graph or table
if output == "svg":
return display_variant_graph_as_SVG(graph)
if output=="graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_HTML(table)
if output == "table":
return table
else:
raise Exception("Unknown output type: "+output)
def collate(collation,
output="table",
layout="horizontal",
segmentation=True,
near_match=False,
astar=False,
detect_transpositions=False,
debug_scores=False,
properties_filter=None,
svg_output=None,
indent=False,
scheduler=Scheduler()):
# collation may be collation or json; if it's the latter, use it to build a real collation
if isinstance(collation, dict):
json_collation = Collation()
for witness in collation["witnesses"]:
json_collation.add_witness(witness)
collation = json_collation
# assume collation is collation (by now); no error trapping
if not astar:
algorithm = EditGraphAligner(
collation,
near_match=False,
detect_transpositions=detect_transpositions,
debug_scores=debug_scores,
properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation,
near_match=False,
debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph, collation)
ranking = VariantGraphRanking.of(graph)
if near_match:
# Segmentation not supported for near matching; raise exception if necessary
if segmentation:
raise SegmentationError(
'segmentation must be set to False for near matching')
highestRank = ranking.byVertex[graph.end]
witnessCount = len(collation.witnesses)
# do-while loop to avoid looping through ranking while modifying it
rank = highestRank - 1
condition = True
while condition:
rank = process_rank(scheduler, rank, collation, ranking,
witnessCount)
rank -= 1
condition = rank > 0
# # Verify that nodes have been moved
# print("\nLabels at each rank at end of processing: ")
# for rank in ranking.byRank:
# print("\nRank: " + str(rank))
# print([node.label for node in ranking.byRank[rank]])
# join parallel segments
if segmentation:
join(graph)
ranking = VariantGraphRanking.of(graph)
# check which output format is requested: graph or table
if output == "svg" or output == "svg_simple":
return display_variant_graph_as_SVG(graph, svg_output, output)
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout, ranking)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_HTML(table)
if output == "html2":
return visualizeTableVerticallyWithColors(table, collation)
if output == "table":
return table
if output == "xml":
return export_alignment_table_as_xml(table)
if output == "tei":
return export_alignment_table_as_tei(table, indent)
else:
raise Exception("Unknown output type: " + output)
def collate(collation, output="table", layout="horizontal", segmentation=True, near_match=False, astar=False,
detect_transpositions=False, debug_scores=False, properties_filter=None, svg_output=None, indent=False, scheduler=Scheduler()):
# collation may be collation or json; if it's the latter, use it to build a real collation
if isinstance(collation, dict):
json_collation = Collation()
for witness in collation["witnesses"]:
json_collation.add_witness(witness)
collation = json_collation
# assume collation is collation (by now); no error trapping
if not astar:
algorithm = EditGraphAligner(collation, near_match=False, detect_transpositions=detect_transpositions, debug_scores=debug_scores, properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation, near_match=False, debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph, collation)
ranking = VariantGraphRanking.of(graph)
if near_match:
# Segmentation not supported for near matching; raise exception if necessary
if segmentation:
raise SegmentationError('segmentation must be set to False for near matching')
highestRank = ranking.byVertex[graph.end]
witnessCount = len(collation.witnesses)
# do-while loop to avoid looping through ranking while modifying it
rank = highestRank - 1
condition = True
while condition:
rank = process_rank(scheduler, rank, collation, ranking, witnessCount)
rank -= 1
condition = rank > 0
# # Verify that nodes have been moved
# print("\nLabels at each rank at end of processing: ")
# for rank in ranking.byRank:
# print("\nRank: " + str(rank))
# print([node.label for node in ranking.byRank[rank]])
# join parallel segments
if segmentation:
join(graph)
ranking = VariantGraphRanking.of(graph)
# check which output format is requested: graph or table
if output == "svg" or output == "svg_simple":
return display_variant_graph_as_SVG(graph, svg_output, output)
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout, ranking)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_HTML(table)
if output == "html2":
return visualizeTableVerticallyWithColors(table, collation)
if output == "table":
return table
if output == "xml":
return export_alignment_table_as_xml(table)
if output == "tei":
return export_alignment_table_as_tei(table, indent)
else:
raise Exception("Unknown output type: " + output)
def collate(collation,
output="table",
layout="horizontal",
segmentation=True,
near_match=False,
astar=False,
detect_transpositions=False,
debug_scores=False,
properties_filter=None,
indent=False):
# collation may be collation or json; if it's the latter, use it to build a real collation
if isinstance(collation, dict):
json_collation = Collation()
for witness in collation["witnesses"]:
json_collation.add_witness(witness)
collation = json_collation
# assume collation is collation (by now); no error trapping
if not astar:
algorithm = EditGraphAligner(
collation,
near_match=False,
detect_transpositions=detect_transpositions,
debug_scores=debug_scores,
properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation,
near_match=False,
debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph)
ranking = VariantGraphRanking.of(graph)
if near_match:
# Segmentation not supported for near matching; raise exception if necessary
# There is already a graph ('graph', without near-match edges) and ranking ('ranking')
if segmentation:
raise SegmentationError(
'segmentation must be set to False for near matching')
ranking = perform_near_match(graph, ranking)
# join parallel segments
if segmentation:
join(graph)
ranking = VariantGraphRanking.of(graph)
# check which output format is requested: graph or table
if output == "svg" or output == "svg_simple":
return display_variant_graph_as_svg(graph, output)
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout)
if collation.pretokenized and not segmentation:
token_list = [[tk.token_data for tk in witness.tokens()]
for witness in collation.witnesses]
# only with segmentation=False
# there could be a different comportment of get_tokenized_table if semgentation=True
table = get_tokenized_at(table,
token_list,
segmentation=segmentation,
layout=layout)
# for display purpose, table and html output will return only token 't' (string) and not the full token_data (dict)
if output == "table" or output == "html":
for row in table.rows:
row.cells = [cell["t"] for cell in row.cells]
if output == "json":
return export_alignment_table_as_json(table, layout=layout)
if output == "html":
return display_alignment_table_as_html(table)
if output == "html2":
return visualize_table_vertically_with_colors(table, collation)
if output == "table":
return table
if output == "xml":
return export_alignment_table_as_xml(table)
if output == "tei":
return export_alignment_table_as_tei(table, indent)
if output == "csv" or output == "tsv":
return display_alignment_table_as_csv(table, output)
else:
raise Exception("Unknown output type: " + output)
def collate(collation,
output="table",
layout="horizontal",
segmentation=True,
near_match=False,
astar=False,
detect_transpositions=False,
debug_scores=False,
properties_filter=None,
indent=False):
# collation may be collation or json; if it's the latter, use it to build a real collation
if isinstance(collation, dict):
json_collation = Collation()
for witness in collation["witnesses"]:
json_collation.add_witness(witness)
collation = json_collation
# assume collation is collation (by now); no error trapping
if not astar:
algorithm = EditGraphAligner(
collation,
near_match=False,
detect_transpositions=detect_transpositions,
debug_scores=debug_scores,
properties_filter=properties_filter)
else:
algorithm = ExperimentalAstarAligner(collation,
near_match=False,
debug_scores=debug_scores)
# build graph
graph = VariantGraph()
algorithm.collate(graph)
ranking = VariantGraphRanking.of(graph)
if near_match:
# Segmentation not supported for near matching; raise exception if necessary
# There is already a graph ('graph', without near-match edges) and ranking ('ranking')
if segmentation:
raise SegmentationError(
'segmentation must be set to False for near matching')
ranking = perform_near_match(graph, ranking)
# join parallel segments
if segmentation:
join(graph)
ranking = VariantGraphRanking.of(graph)
# check which output format is requested: graph or table
if output == "svg" or output == "svg_simple":
return display_variant_graph_as_svg(graph, output)
if output == "graph":
return graph
# create alignment table
table = AlignmentTable(collation, graph, layout, ranking)
if output == "json":
return export_alignment_table_as_json(table)
if output == "html":
return display_alignment_table_as_html(table)
if output == "html2":
return visualize_table_vertically_with_colors(table, collation)
if output == "table":
return table
if output == "xml":
return export_alignment_table_as_xml(table)
if output == "tei":
return export_alignment_table_as_tei(table, indent)
if output == "csv" or output == "tsv":
return display_alignment_table_as_csv(table, output)
else:
raise Exception("Unknown output type: " + output)
