def test_get_covered_text_sentences(sentences):
cas = Cas()
cas.sofa_string = "Joe waited for the train . The train was late ."
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_FeatureStructure_get_covered_text_tokens(tokens):
cas = Cas()
cas.sofa_string = "Joe waited for the train . The train was late ."
actual_text = [token.get_covered_text() for token in tokens]
expected_text = ["Joe", "waited", "for", "the", "train", ".", "The", "train", "was", "late", "."]
assert actual_text == expected_text
def test_get_view_finds_existing_view():
cas = Cas()
cas.create_view("testView")
cas.sofa_string = "Initial"
view = cas.get_view("testView")
view.sofa_string = "testView42"
sofa = view.get_sofa()
attr.validate(sofa)
assert sofa.sofaID == "testView"
assert cas.sofa_string == "Initial"
assert view.sofa_string == "testView42"
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_sofa_string_can_be_set_and_read():
cas = Cas()
cas.sofa_string = "I am a test sofa string!"
assert cas.sofa_string == "I am a test sofa string!"
