def test_scan_collection_skip():
filenames = create_collections()
output_dir = tempfile.mkdtemp()
# remove one file
os.remove(filenames[0])
p = NegBioPipeline([('fake', FakePipe())])
p.scan(source=filenames, directory=output_dir, suffix='.xml')
assert not os.path.exists(os.path.join(output_dir, filenames[0]))
def test_scan_document_error():
class FakePipeError(Pipe):
def __call__(self, doc: bioc.BioCDocument, *args, **kwargs):
raise KeyError
filenames = create_collections()
output_dir = tempfile.mkdtemp()
p = NegBioPipeline([('fake_error', FakePipeError())])
p.scan(source=filenames, directory=output_dir, suffix='.xml')
for filename in filenames:
assert filecmp.cmp(filename, os.path.join(output_dir, os.path.basename(filename)))
def test_scan_collection():
filenames = create_collections()
output_dir = tempfile.mkdtemp()
os.rmdir(output_dir)
p = NegBioPipeline([('fake', FakePipe())])
p.scan(source=filenames, directory=output_dir, suffix='.xml')
for filename in filenames:
filename = os.path.join(output_dir, os.path.basename(filename))
with open(filename) as fp:
c = bioc.load(fp)
for doc in c.documents:
assert doc.infons['fake']
from negbio.pipeline2.dner_mm import MetaMapExtractor
from negbio.pipeline2.pipeline import NegBioPipeline
from pymetamap import MetaMap
def read_cuis(pathname):
cuis = set()
with open(pathname) as fp:
for line in fp:
line = line.strip()
if line:
cuis.add(line)
return cuis
if __name__ == '__main__':
argv = parse_args(__doc__)
mm = MetaMap.get_instance(argv['--metamap'])
if argv['--cuis'] is None:
cuis = None
else:
cuis = read_cuis(argv['--cuis'])
extractor = MetaMapExtractor(mm, cuis)
pipeline = NegBioPipeline(pipeline=[('MetaMapExtractor', extractor)])
pipeline.scan(source=argv['<file>'],
directory=argv['--output'],
suffix=argv['--suffix'],
overwrite=argv['--overwrite'])