def ann_to_labels(ann_file: Union[str, Path],
document: Document,
label_index_name_prefix: str,
encoding: Optional[str],
create_indices: Optional[Iterable[str]] = None):
"""Reads all of the annotations in a brat annotations file into a document.
Parameters
----------
ann_file: str or Path
A BRAT .ann file to load annotations from.
document: Document
The document to add labels to.
label_index_name_prefix: str
A prefix to append to the brat annotation names.
encoding: optional str
The encoding to use when reading the ann file.
create_indices: optional iterable of str
These indices will be created no matter what, even if empty.
"""
labelers = {}
if create_indices is not None:
for index in create_indices:
labelers[index] = document.get_labeler(index)
ann_file = Path(ann_file)
with ann_file.open('r', encoding=encoding) as f:
for line in f.readlines():
splits = line.split('\t')
if len(splits) < 3 or not splits[0].startswith('T'):
continue
name, bounds = splits[1].split(' ', maxsplit=1)
name = label_index_name_prefix + name
bounds = bounds.split(';')
min_start = float('Inf')
max_end = 0
for pair in bounds:
start_index, end_index = pair.split(' ')
min_start = min(min_start, int(start_index))
max_end = max(max_end, int(end_index))
try:
labeler = labelers[name]
except KeyError:
labeler = document.get_labeler(name)
labelers[name] = labeler
labeler(min_start, max_end)
for labeler in labelers.values():
labeler.done()
def test_copy_document():
e = Event()
doc = Document(document_name='first', text='The quick brown fox jumped over the lazy dog.')
e.add_document(doc)
with doc.get_labeler('some_index') as label:
label(0, 3, word='The')
label(4, 9, word='quick')
label(10, 15, word='brown')
processor = CopyDocument('first', 'second')
processor.process(e, {})
second = e.documents['second']
assert second is not None
assert second.get_label_index('some_index') == [
GenericLabel(0, 3, word='The'),
GenericLabel(4, 9, word='quick'),
GenericLabel(10, 15, word='brown')
]
def process_document(self, document: Document,
params: Dict[str, Any]) -> Optional[Dict[str, Any]]:
if params['do_work']:
with self.started_stopwatch('fetch_time'):
text = document.text
a_count = text.count('a')
b_count = text.count('b')
with document.get_labeler(
'mtap.examples.letter_counts') as label_letter_count:
label_letter_count(start_index=0,
end_index=len(document.text),
letter='a',
count=a_count)
label_letter_count(start_index=0,
end_index=len(document.text),
letter='b',
count=b_count)
return {'answer': 42}