def repos2id_sequence(args):
log = logging.getLogger("repos2id_distance")
extractor = IdSequenceExtractor(args.split)
session_name = "repos2roles_and_ids-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
if not args.skip_docname:
mapper = Rower(lambda x: {"document": x[0][1], "identifiers": x[0][0]})
else:
mapper = Rower(lambda x: {"identifiers": x[0][0]})
start_point \
.link(UastRow2Document()) \
.link(UastDeserializer()) \
.link(Uast2BagFeatures(extractor)) \
.link(mapper) \
.link(CsvSaver(args.output)) \
.execute()
pipeline_graph(args, log, root)
def repos2roles_and_ids(args):
log = logging.getLogger("repos2roles_and_ids")
session_name = "repos2roles_and_ids-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
start_point \
.link(UastRow2Document()) \
.link(UastDeserializer()) \
.link(Uast2BagFeatures([RolesAndIdsExtractor(args.split)])) \
.link(Rower(lambda x: dict(identifier=x[0][0], role=x[1]))) \
.link(CsvSaver(args.output)) \
.execute()
pipeline_graph(args, log, root)
def repos2id_distance(args):
log = logging.getLogger("repos2roles_and_ids")
extractor = IdentifierDistance(args.split, args.type, args.max_distance)
session_name = "repos2roles_and_ids-%s" % uuid4()
root, start_point = create_uast_source(args, session_name)
start_point \
.link(UastRow2Document()) \
.link(UastDeserializer()) \
.link(Uast2BagFeatures(extractor)) \
.link(Rower(lambda x: {"identifier1": x[0][0][0],
"identifier2": x[0][0][1],
"distance": x[1]})) \
.link(CsvSaver(args.output)) \
.execute()
pipeline_graph(args, log, root)