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 create_from_dict(cls, data, limit=None):
if "witnesses" not in data:
raise UnsupportedError("Json input not valid")
witnesses = data["witnesses"]
collation = Collation()
for witness in witnesses[:limit]:
# generate collation object from json_data
collation.add_witness(witness)
# determine if data is pretokenized
if 'tokens' in witness:
collation.pretokenized = True
return collation
def get_tokenized_at(table,
token_list,
segmentation=False,
layout="horizontal"):
tokenized_at = AlignmentTable(Collation(), layout=layout)
for witness_row, witness_tokens in zip(table.rows, token_list):
new_row = Row(witness_row.header)
tokenized_at.rows.append(new_row)
counter = 0
for cell in witness_row.cells:
if cell == "-":
# TODO: should probably be null or None instead, but that would break the rendering at the moment (line 41)
new_row.cells.append({"t": "-"})
# if segmentation=False
else:
new_row.cells.append(witness_tokens[counter])
counter += 1
# else if segmentation=True
##token_list must be a list of Token instead of list of dict (update lines 34, 64)
##line 41 will not be happy in case of table/html output
#string = witness_tokens[counter].token_string
#token_counter = 1
#while string != cell :
# if counter+token_counter-1 < len(witness_tokens)-1:
# #add token_string of the next token until it is equivalent to the string in the cell
# #if we are not at the last token
# string += ' '+witness_tokens[counter+token_counter].token_string
# token_counter += 1
##there is one list level too many in the output
#new_row.cells.append([tk.token_data for tk in witness_tokens[counter:counter+token_counter]])
#counter += token_counter.
return tokenized_at
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, 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, 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)