def _createannotationobjects(annotations):
"""
Create instances of the Annotation class for each of the "T" annotations.
Input is assumed to only be "T" annotations.
:param annotations: (dict) dictionary of "T" annotations.
:return: (OrderedDict) an ordered dictionary of Annotations objects.
Length of this dictionary should be equal to the input dictionary.
"""
targets = OrderedDict()
for key, t in annotations.items():
splitted = t.split("\t")
t = splitted[0]
repr = u" ".join(splitted[1:])
split = t.split()
label = split[0]
spans = [[int(span.split()[0]), int(span.split()[1])]
for span in u" ".join(split[1:]).split(";")]
targets[key] = Annotation(key, repr, spans, [label])
return targets
def _createannotationobjects(annotations):
"""
Create instances of the Annotation class for each of the "T" annotations.
Input is assumed to only be "T" annotations.
:param annotations: (dict) dictionary of "T" annotations.
:return: (OrderedDict) an ordered dictionary of Annotations objects.
Length of this dictionary should be equal to the input dictionary.
"""
targets = OrderedDict()
for key, t in annotations.items():
splitted = t.split("\t")
t = splitted[0]
repr = u" ".join(splitted[1:])
split = t.split()
label = split[0]
# print("t",t)
# print("key",key)
try:
#ann formate by brat
spans = [[int(span.split()[0]),
int(span.split()[1])]
for span in u" ".join(split[1:]).split(";")]
except:
#patch ann formate by BioNLP
split.append(splitted[1])
split.append(splitted[2])
spans = [[int(span.split()[0]),
int(span.split()[1])]
for span in u" ".join(split[1:]).split(";")]
targets[key] = Annotation(key, repr, spans, [label])
targets[key].type = 'T'
return targets
def importxml(filename):
"""
Imports an XML file formatted with the format created by this program. Used for persistency and to operate on
RepoModels in memory.
:param filename: (string) the path to the file to be imported.
:return: A tuple containing a dictionary of annotations and a list of dictionaries representing the context.
"""
anndict = OrderedDict()
sentobjects = []
with codecs.open(filename, 'r', encoding='utf-8') as f:
data = f.read()
doc = etree.fromstring(data)
sentences, annotations = doc.getchildren()
for s in sentences.getchildren():
repr = " ".join([w.text for w in s.getchildren()])
sentobjects.append(
Sentence(key=s.get('id').split(".")[1],
line=repr,
start=int(s.get("start"))))
for annotation in annotations.getchildren():
id = unicode(annotation.get('id')[3:])
repr = unicode(annotation.get('repr'))
spans = [[int(y) for y in x.split("|")]
for x in annotation.get('spans').split(",")]
ann = Annotation(id, repr, spans)
for span in ann.spans:
for s in sentobjects:
start, end = span
ann.words.extend(s.getwordsinspan(start, end))
anndict[id] = ann
for annotation in annotations.getchildren():
id = unicode(annotation.get('id')[3:])
ann = anndict[id]
for x, y in {
unicode(x): unicode(y)
for x, y in annotation.attrib.items()
if x not in ["id", "repr", "spans", "words"]
}.items():
if x.startswith("link."):
ann.links[x[5:]].extend(
[anndict[key[3:]] for key in y.split()])
else:
ann.labels[x].append(y)
return anndict, sentobjects