def test_token_dict_to_pb(json_dict):
token_dict = json_dict['sentences'][0]['tokens'][0]
token = AnnotatedToken.dict_to_pb(token_dict)
assert token.after == u' '
assert token.before == u''
assert token.beginChar == 0
assert token.endChar == 7
assert token.originalText == u'Belgian'
assert token.word == u'Belgian'
def test_json_to_pb(self, json_dict):
token_dict = json_dict['sentences'][0]['tokens'][0]
token = AnnotatedToken.json_to_pb(token_dict)
assert token.after == u' '
assert token.before == u''
assert token.beginChar == 0
assert token.endChar == 7
assert token.originalText == u'Belgian'
assert token.word == u'Belgian'
def test_parse_pb(self, document_pb):
token_pb = document_pb.sentence[1].token[3]
token = AnnotatedToken.from_pb(token_pb)
assert token.after == u' '
assert token.before == u' '
assert token.character_span == (117, 122)
assert token.originalText == u'first'
assert token.word == u'first'
assert token.lemma == u'first'
assert token.ner == u'ORDINAL'
assert token.pos == u'JJ'
def test_parse_pb(self, document_pb):
token_pb = document_pb.sentence[1].token[3]
token = AnnotatedToken.from_pb(token_pb)
assert token.after == u' '
assert token.before == u' '
assert token.character_span == (117, 122)
assert token.originalText == u'first'
assert token.word == u'first'
assert token.lemma == u'first'
assert token.ner == u'ORDINAL'
assert token.pos == u'JJ'
