def write_sentence_documents(sentences: List[str],
labels: List[str],
path: Path,
labeled=True):
typesystem = TypeSystem()
cas = Cas(typesystem=typesystem)
SentenceType = typesystem.create_type(
"de.tudarmstadt.ukp.dkpro.core.api.segmentation.type.Sentence")
SentimentType = typesystem.create_type("webanno.custom.Sentiment")
typesystem.add_feature(type_=SentimentType,
name="value",
rangeTypeName="uima.cas.String")
cas.sofa_string = " ".join(sentences)
begin = 0
for sentence, label in zip(sentences, labels):
end = begin + len(sentence)
cas_sentence = SentenceType(begin=begin, end=end)
sentiment_annotation = SentimentType(begin=begin, end=end, value=label)
begin = end + 1
cas.add_annotation(cas_sentence)
if labeled:
cas.add_annotation(sentiment_annotation)
cas.to_xmi(path, pretty_print=True)
for sentence in cas.select(SENTENCE_TYPE):
print(cas.get_covered_text(sentence))
def build_typesystem() -> TypeSystem:
typesystem = TypeSystem()
SentenceType = typesystem.create_type(SENTENCE_TYPE)
PredictedType = typesystem.create_type(PREDICTED_TYPE)
typesystem.add_feature(PredictedType, PREDICTED_FEATURE, "uima.cas.String")
typesystem.add_feature(PredictedType, IS_PREDICTION, "uima.cas.Boolean")
return typesystem
def test_that_merging_types_with_different_incompatible_supertypes_throws():
ts1 = TypeSystem()
ts1.create_type("test.Sub",
description="Example type.",
supertypeName="uima.cas.EmptyIntegerList")
ts2 = TypeSystem()
ts2.create_type("test.Sub",
description="Example type.",
supertypeName="uima.cas.NonEmptyStringList")
with pytest.raises(ValueError, match=r".*incompatible super types.*"):
merge_typesystems(ts1, ts2)
def test_type_can_create_instance_with_inherited_fields():
typesystem = TypeSystem()
parent_type = typesystem.create_type(name="test.ParentType")
typesystem.add_feature(type_=parent_type, name="parentFeature", rangeTypeName="String")
child_type = typesystem.create_type(name="test.ChildType", supertypeName=parent_type.name)
typesystem.add_feature(type_=child_type, name="childFeature", rangeTypeName="Integer")
annotation = child_type(parentFeature="parent", childFeature="child")
assert annotation.parentFeature == "parent"
assert annotation.childFeature == "child"
def test_type_can_be_created():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
assert test_type.name == "test.Type"
assert test_type.supertypeName == "uima.tcas.Annotation"
def test_type_inherits_from_annotation_base():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type", supertypeName="uima.cas.AnnotationBase")
annotation = test_type(sofa=42)
assert annotation.sofa == 42
def test_type_inherits_from_annotation():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
annotation = test_type(begin=0, end=42, sofa=1337)
assert annotation.begin == 0
assert annotation.end == 42
assert annotation.sofa == 1337
def test_type_can_create_instances():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
typesystem.add_feature(type_=test_type, name="testFeature", rangeTypeName="String", description="A test feature")
annotation = test_type(begin=0, end=42, testFeature="testValue")
assert annotation.begin == 0
assert annotation.end == 42
assert annotation.testFeature == "testValue"
def test_feature_adding_throws_if_already_existing():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
typesystem.add_feature(type_=test_type, name="testFeature", rangeTypeName="String", description="A test feature")
with pytest.raises(ValueError):
typesystem.add_feature(
type_=test_type, name="testFeature", rangeTypeName="String", description="A test feature"
)
def test_feature_can_be_added():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
typesystem.add_feature(type_=test_type, name="testFeature", rangeTypeName="String", description="A test feature")
actual_type = typesystem.get_type("test.Type")
actual_feature = actual_type.get_feature("testFeature")
assert actual_feature.name == "testFeature"
assert actual_feature.rangeTypeName == "String"
assert actual_feature.description == "A test feature"
def test_feature_adding_throws_if_redefined_differently():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
typesystem.add_feature(type_=test_type,
name="testFeature",
rangeTypeName="String",
description="A test feature")
with pytest.raises(ValueError):
typesystem.add_feature(type_=test_type,
name="testFeature",
rangeTypeName="Boolean",
description="A test feature")
def test_feature_adding_warns_if_redefined_identically():
typesystem = TypeSystem()
test_type = typesystem.create_type(name="test.Type")
typesystem.add_feature(type_=test_type,
name="testFeature",
rangeTypeName="String",
description="A test feature")
with pytest.warns(UserWarning):
typesystem.add_feature(type_=test_type,
name="testFeature",
rangeTypeName="String",
description="A test feature")
def test_that_merging_incompatible_typesystem_throws(
name, rangeTypeName, elementType, multipleReferencesAllowed):
with open(typesystem_merge_base_path(), "r") as f:
base = load_typesystem(f.read())
ts = TypeSystem()
t = ts.create_type("test.ArraysAndListsWithElementTypes",
supertypeName="uima.cas.TOP")
ts.add_feature(
type_=t,
name=name,
rangeTypeName=rangeTypeName,
elementType=elementType,
multipleReferencesAllowed=multipleReferencesAllowed,
)
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning)
with pytest.raises(ValueError, match=r".*\[{0}\].*".format(name)):
merge_typesystems(base, ts)
def test_that_merging_compatible_typesystem_works(name, rangeTypeName,
elementType,
multipleReferencesAllowed):
with open(typesystem_merge_base_path(), "r") as f:
base = load_typesystem(f.read())
ts = TypeSystem()
t = ts.create_type("test.ArraysAndListsWithElementTypes",
supertypeName="uima.cas.TOP")
ts.add_feature(
type_=t,
name=name,
rangeTypeName=rangeTypeName,
elementType=elementType,
multipleReferencesAllowed=multipleReferencesAllowed,
)
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning)
result = merge_typesystems(base, ts)
assert result.contains_type("test.ArraysAndListsWithElementTypes")
def test_that_merging_types_with_different_compatible_supertypes_works():
ts1 = TypeSystem()
ts1.create_type("test.Sub",
description="Example type.",
supertypeName="uima.tcas.Annotation")
ts2 = TypeSystem()
ts2.create_type("test.Super",
description="Example type.",
supertypeName="uima.tcas.Annotation")
ts2.create_type("test.Sub",
description="Example type.",
supertypeName="test.Super")
result = merge_typesystems(ts1, ts2)
sub = result.get_type("test.Sub")
assert sub.supertypeName == "test.Super"
# Also check the other order
result = merge_typesystems(ts2, ts1)
sub = result.get_type("test.Sub")
assert sub.supertypeName == "test.Super"
def test_is_primitive_when_parent_is_primitive():
typesystem = TypeSystem()
typesystem.create_type("test.string", "uima.cas.String")
assert typesystem.is_primitive("test.string")