def brat_file(filename, encoding="utf-8"):
no_ext, ext = os.path.splitext(filename)
txt_file = no_ext + ".txt"
ann_file = no_ext + ".ann"
if not (os.path.exists(txt_file) and os.path.exists(ann_file)):
raise ValueError("missing either .ann or .txt file")
document = Document(os.path.basename(txt_file),
encoding=encoding,
mime_type="text/plain")
document.content = codecs.open(txt_file, "rU",
encoding).read().replace(u"\r", u"")
annotations = Annotation("NER")
for line in codecs.open(ann_file, "rU", encoding):
line = line.strip()
if line != u"" and line.startswith(u'T'):
parts = line.split(u"\t")
value, bounds = parts[1].split(" ", 1)
for bound in bounds.split(";"):
lb, ub = bound.split()
lb = int(lb)
ub = int(ub)
annotations.append(Tag(lb=lb, ub=ub, value=value))
annotations.sort()
document.add_annotation(annotations)
return document
def gate_data(data, name=None):
document = Document(name or "__DOCUMENT__", mime_type="text/plain")
textwithnodes = data.findall("TextWithNodes")[0]
annotation_sets = data.findall("AnnotationSet")
text_parts = [textwithnodes.text or u""]
nodes = {}
for node in list(textwithnodes):
nodes[int(node.attrib["id"])] = sum([len(part) for part in text_parts])
text_parts.append(node.tail or u"")
document.content = u"".join(text_parts)
annotations = []
for annotation_set in annotation_sets:
annotation_name = annotation_set.attrib["Name"]
sem_annotation = Annotation(annotation_name)
for annotation in annotation_set:
lb = nodes[int(annotation.attrib["StartNode"])]
ub = nodes[int(annotation.attrib["EndNode"])]
sem_annotation.append(Tag(lb, ub, annotation.attrib["Type"]))
document.add_annotation(sem_annotation)
return document