def test_leniency_type_not_in_typeystem_lenient(small_typesystem_xml):
typesystem = load_typesystem(small_typesystem_xml)
TokenType = typesystem.get_type("cassis.Token")
token = TokenType(begin=0, end=3, id="0", pos="NNP")
cas = Cas(lenient=True)
cas.add_annotation(token)
def test_leniency_type_not_in_typeystem_not_lenient(small_typesystem_xml):
typesystem = load_typesystem(small_typesystem_xml)
TokenType = typesystem.get_type("cassis.Token")
token = TokenType(begin=0, end=3, id="0", pos="NNP")
cas = Cas()
with pytest.raises(RuntimeError, match="Typesystem of CAS does not contain type"):
cas.add_annotation(token)
def test_annotations_are_ordered_correctly(tokens):
annotations = list(tokens)
random.shuffle(list(annotations))
cas = Cas()
for token in annotations:
cas.add_annotation(token)
actual_tokens = list(cas.select("cassis.Token"))
assert actual_tokens == tokens
def test_annotations_are_ordered_correctly(small_typesystem_xml, tokens):
typesystem = load_typesystem(small_typesystem_xml)
cas = Cas(typesystem)
annotations = list(tokens)
random.shuffle(list(annotations))
for token in annotations:
cas.add_annotation(token)
actual_tokens = list(cas.select("cassis.Token"))
assert actual_tokens == tokens
def test_select_covered_overlapping(small_typesystem_xml, tokens, sentences):
cas = Cas(typesystem=load_typesystem(small_typesystem_xml))
AnnotationType = cas.typesystem.create_type("test.Annotation")
SentenceType = cas.typesystem.get_type("cassis.Sentence")
sentence = SentenceType(begin=0, end=10)
annotations = [
AnnotationType(begin=0, end=5),
AnnotationType(begin=0, end=5)
]
cas.add_annotation(sentence)
cas.add_annotations(annotations)
actual_annotations = list(cas.select_covered("test.Annotation", sentence))
assert actual_annotations == annotations
def test_add_annotation_generates_ids(small_typesystem_xml, tokens):
typesystem = load_typesystem(small_typesystem_xml)
cas = Cas(typesystem)
TokenType = typesystem.get_type("cassis.Token")
tokens = [
TokenType(begin=0, end=3, id="0", pos="NNP"),
TokenType(begin=4, end=10, id="1", pos="VBD"),
TokenType(begin=11, end=14, id="2", pos="IN"),
TokenType(begin=15, end=18, id="3", pos="DT"),
TokenType(begin=19, end=24, id="4", pos="NN"),
TokenType(begin=25, end=26, id="5", pos="."),
]
for token in tokens:
cas.add_annotation(token)
actual_tokens = list(cas.select(TokenType.name))
assert all([token.xmiID is not None for token in actual_tokens])
def test_add_annotation_generates_ids(small_typesystem_xml, tokens):
cas = Cas()
typesystem = load_typesystem(small_typesystem_xml)
TokenType = typesystem.get_type('cassis.Token')
tokens = [
TokenType(sofa=1, begin=0, end=3, id='0', pos='NNP'),
TokenType(sofa=1, begin=4, end=10, id='1', pos='VBD'),
TokenType(sofa=1, begin=11, end=14, id='2', pos='IN'),
TokenType(sofa=1, begin=15, end=18, id='3', pos='DT'),
TokenType(sofa=1, begin=19, end=24, id='4', pos='NN'),
TokenType(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 all([token.xmiID != None for token in actual_tokens])
def test_add_annotation(small_typesystem_xml):
typesystem = load_typesystem(small_typesystem_xml)
TokenType = typesystem.get_type("cassis.Token")
cas = Cas(typesystem)
cas.sofa_string = "Joe waited for the train ."
tokens = [
TokenType(begin=0, end=3, id="0", pos="NNP"),
TokenType(begin=4, end=10, id="1", pos="VBD"),
TokenType(begin=11, end=14, id="2", pos="IN"),
TokenType(begin=15, end=18, id="3", pos="DT"),
TokenType(begin=19, end=24, id="4", pos="NN"),
TokenType(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 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
