def create_passage_yields(p, constructions=None, reference=None, verbose=False):
"""
:returns dict: Construction ->
dict: set of terminal indices (excluding punctuation) ->
list of edges of the Construction whose yield (excluding remotes and punctuation) is that set
"""
yield_tags = OrderedDict()
for construction, edges in extract_edges(
p, constructions=constructions, reference=reference, verbose=verbose).items():
yield_tags[construction] = {}
for edge in edges:
yield_tags[construction].setdefault(get_yield(edge.child), []).append(edge.tag)
return yield_tags
def create_passage_yields(p, constructions=None, reference=None, verbose=False):
"""
:returns dict: Construction ->
dict: set of terminal indices (excluding punctuation) ->
list of edges of the Construction whose yield (excluding remotes and punctuation) is that set
"""
yield_tags = OrderedDict()
for construction, edges in extract_edges(
p, constructions=constructions, reference=reference, verbose=verbose).items():
yield_tags[construction] = {}
for edge in edges:
yield_tags[construction].setdefault(get_yield(edge.child), []).append(edge.tag)
return yield_tags
def main(args):
for passage in get_passages_with_progress_bar(args.passages):
extracted = constructions.extract_edges(
passage, constructions=args.constructions, verbose=args.verbose)
if any(extracted.values()):
with tqdm.external_write_mode():
if not args.verbose:
print("%s:" % passage.ID)
for construction, edges in extracted.items():
if edges:
print(" %s:" % construction.description)
for edge in edges:
print(" %s [%s %s]" %
(edge, edge.tag, edge.child))
print()
from ucca import constructions
from ucca.ioutil import read_files_and_dirs
if __name__ == "__main__":
argparser = ArgumentParser(
description="Extract linguistic constructions from UCCA corpus.")
argparser.add_argument("passages",
nargs="+",
help="the corpus, given as xml/pickle file names")
constructions.add_argument(argparser, False)
argparser.add_argument("-v",
"--verbose",
action="store_true",
help="print tagged text for each passage")
args = argparser.parse_args()
for passage in read_files_and_dirs(args.passages):
if args.verbose:
print("%s:" % passage.ID)
extracted = constructions.extract_edges(
passage, constructions=args.constructions, verbose=args.verbose)
if any(extracted.values()):
if not args.verbose:
print("%s:" % passage.ID)
for construction, edges in extracted.items():
if edges:
print(" %s:" % construction.description)
for edge in edges:
print(" %s [%s %s]" % (edge, edge.tag, edge.child))
print()
from argparse import ArgumentParser
from ucca import constructions
from ucca.ioutil import read_files_and_dirs
if __name__ == "__main__":
argparser = ArgumentParser(description="Extract linguistic constructions from UCCA corpus.")
argparser.add_argument("passages", nargs="+", help="the corpus, given as xml/pickle file names")
constructions.add_argument(argparser, False)
argparser.add_argument("-v", "--verbose", action="store_true", help="print tagged text for each passage")
args = argparser.parse_args()
for passage in read_files_and_dirs(args.passages):
if args.verbose:
print("%s:" % passage.ID)
extracted = constructions.extract_edges(passage, constructions=args.constructions, verbose=args.verbose)
if any(extracted.values()):
if not args.verbose:
print("%s:" % passage.ID)
for construction, edges in extracted.items():
if edges:
print(" %s:" % construction.description)
for edge in edges:
print(" %s [%s %s]" % (edge, edge.tag, edge.child))
print()
def extract_and_check(p, constructions=None, expected=None):
d = extract_edges(p, constructions=constructions)
if expected is not None:
hist = {c.name: len(e) for c, e in d.items()}
assert hist == expected, " != ".join(",".join(sorted(h))
for h in (hist, expected))