def setUp(self):
if self.universal:
self.trees = trees_ud
else:
self.trees = trees_sd
kwargs = dict(version=self.version, download_if_missing=True)
if self.backend is not None:
kwargs['backend'] = self.backend
self.sd = StanfordDependencies.get_instance(**kwargs)
def setUp(self):
if self.universal:
self.trees = trees_ud
else:
self.trees = trees_sd
kwargs = dict(version=self.version, download_if_missing=True)
if self.backend is not None:
kwargs['backend'] = self.backend
self.sd = StanfordDependencies.get_instance(**kwargs)
def test_convert_doc_no_jpype(self):
c = NegBioPtb2DepConverter()
c._backend = 'subprocess'
c._sd = StanfordDependencies.get_instance(backend=c._backend)
text = 'No pneumothorax.'
tree = '(S1 (S (S (NP (DT No) (NN pneumothorax))) (. .)))'
d = text_to_bioc([text], type='d/p/s')
s = d.passages[0].sentences[0]
s.infons['parse tree'] = tree
d = c.__call__(d)
s = d.passages[0].sentences[0]
assert 'lemma' not in s.annotations[1].infons
def __init__(self, document_as_string):
""" Construct a document from a string representation.
The Format must follow the CoNLL format, see
http://conll.cemantix.org/2012/data.html.
Args:
document_as_string (str): A representation of a document in
the CoNLL format.
"""
logging.info("Create CONLL_doc")
identifier = " ".join(document_as_string.split("\n")[0].split(" ")[2:])
self.document_table = CoNLLDocument.__string_to_table(
document_as_string)
in_sentence_ids = [int(i) for i in self.__extract_from_column(2)]
indexing_start = in_sentence_ids[0]
if indexing_start != 0:
logger.warning("Detected " + str(indexing_start) +
"-based indexing for tokens in sentences in input,"
"transformed to 0-based indexing.")
in_sentence_ids = [i - indexing_start for i in in_sentence_ids]
sentence_spans = CoNLLDocument.__extract_sentence_spans(
in_sentence_ids)
temp_tokens = self.__extract_from_column(3)
temp_pos = self.__extract_from_column(4)
temp_ner = self.__extract_ner()
temp_speakers = self.__extract_from_column(9)
coref = CoNLLDocument.__get_span_to_id(self.__extract_from_column(-1))
parses = [
CoNLLDocument.get_parse(span, self.__extract_from_column(5),
temp_pos, temp_tokens)
for span in sentence_spans
]
sd = StanfordDependencies.get_instance()
# print(identifier)
dep_trees = sd.convert_trees(
[parse.replace("NOPARSE", "S") for parse in parses])
sentences = []
for i, span in enumerate(sentence_spans):
sentences.append((temp_tokens[span.begin:span.end + 1],
temp_pos[span.begin:span.end + 1],
temp_ner[span.begin:span.end + 1],
temp_speakers[span.begin:span.end + 1],
parses[i], dep_trees[i]))
print("WEDFWEFW")
super(CoNLLDocument, self).__init__(identifier, sentences, coref)
def test_jpype_backend_creation(self):
sd = StanfordDependencies.get_instance(backend='jpype',
version='3.5.2',
download_if_missing=True)
assert isinstance(sd, JPypeBackend), \
"Fell back to another backend due to a JPype error"
def test_subprocess_backend_creation(self):
sd = StanfordDependencies.get_instance(backend='subprocess',
version='3.4.1',
download_if_missing=True)
assert isinstance(sd, SubprocessBackend)
def setUp(self):
kwargs = dict(version=self.version, download_if_missing=True)
if self.backend is not None:
kwargs['backend'] = self.backend
self.sd = StanfordDependencies.get_instance(**kwargs)
def test_jpype_backend_creation():
sd = StanfordDependencies.get_instance(backend='jpype',
version='3.4.1',
download_if_missing=True)
assert isinstance(sd, JPypeBackend), \
"Fell back to another backend due to a JPype error"
def test_subprocess_backend_creation():
sd = StanfordDependencies.get_instance(backend='subprocess',
version='3.4.1',
download_if_missing=True)
assert isinstance(sd, SubprocessBackend)
def setUp(self):
kwargs = dict(version=self.version, download_if_missing=True)
if self.backend is not None:
kwargs['backend'] = self.backend
self.sd = StanfordDependencies.get_instance(**kwargs)