def _parse_sofa(self, elem) -> Sofa:
attributes = dict(elem.attrib)
attributes["xmiID"] = int(attributes.pop("{http://www.omg.org/XMI}id"))
attributes["sofaNum"] = int(attributes["sofaNum"])
self._max_xmi_id = max(attributes["xmiID"], self._max_xmi_id)
self._max_sofa_num = max(attributes["sofaNum"], self._max_sofa_num)
return Sofa(**attributes)
def _parse_sofa(self, typesystem: TypeSystem, elem) -> Sofa:
attributes = dict(elem.attrib)
attributes["xmiID"] = int(attributes.pop("{http://www.omg.org/XMI}id"))
attributes["sofaNum"] = int(attributes["sofaNum"])
attributes["type"] = typesystem.get_type(TYPE_NAME_SOFA)
self._max_xmi_id = max(attributes["xmiID"], self._max_xmi_id)
self._max_sofa_num = max(attributes["sofaNum"], self._max_sofa_num)
return Sofa(**attributes)
def test_get_covered_text_sentences(sentences):
sofa = Sofa(sofaNum=1,
sofaString='Joe waited for the train . The train was late .')
cas = Cas(annotations=sentences, sofas=[sofa])
actual_text = [cas.get_covered_text(sentence) for sentence in sentences]
expected_text = ['Joe waited for the train .', 'The train was late .']
assert actual_text == expected_text
def test_get_covered_text_tokens(tokens):
sofa = Sofa(sofaNum=1,
sofaString='Joe waited for the train . The train was late .')
cas = Cas(annotations=tokens, sofas=[sofa])
actual_text = [cas.get_covered_text(token) for token in tokens]
expected_text = [
'Joe', 'waited', 'for', 'the', 'train', '.', 'The', 'train', 'was',
'late', '.'
]
assert actual_text == expected_text
def test_add_annotation(small_typesystem_xml):
sofa = Sofa(sofaNum=1, sofaString='Joe waited for the train .')
cas = Cas(sofas=[sofa])
typesystem = load_typesystem(small_typesystem_xml)
TokenType = typesystem.get_type('cassis.Token')
tokens = [
TokenType(xmiID=13, sofa=1, begin=0, end=3, id='0', pos='NNP'),
TokenType(xmiID=19, sofa=1, begin=4, end=10, id='1', pos='VBD'),
TokenType(xmiID=25, sofa=1, begin=11, end=14, id='2', pos='IN'),
TokenType(xmiID=31, sofa=1, begin=15, end=18, id='3', pos='DT'),
TokenType(xmiID=37, sofa=1, begin=19, end=24, id='4', pos='NN'),
TokenType(xmiID=43, sofa=1, begin=25, end=26, id='5', pos='.'),
]
for token in tokens:
cas.add_annotation(token)
actual_tokens = list(cas.select(TokenType.name))
assert actual_tokens == tokens
def _parse_sofa(self, elem) -> Sofa:
attributes = dict(elem.attrib)
attributes['xmiID'] = int(attributes.pop('{http://www.omg.org/XMI}id'))
attributes['sofaNum'] = int(attributes['sofaNum'])
return Sofa(**attributes)
def _parse_sofa(self, elem) -> Sofa:
attributes = dict(elem.attrib)
attributes["xmiID"] = int(attributes.pop("{http://www.omg.org/XMI}id"))
attributes["sofaNum"] = int(attributes["sofaNum"])
return Sofa(**attributes)