def test_matcher_pipe_with_context(nlp: Language) -> None:
"""It returns a stream of Doc objects as tuples with context."""
doc_stream = (
(nlp.make_doc("test doc 1: Corvold"), "Jund"),
(nlp.make_doc("test doc 2: Prosh"), "Jund"),
)
matcher = FuzzyMatcher(nlp.vocab)
output = matcher.pipe(doc_stream, as_tuples=True)
assert list(output) == list(doc_stream)
def test_matcher_pipe(nlp: Language) -> None:
"""It returns a stream of Doc objects."""
doc_stream = (
nlp.make_doc("test doc 1: Corvold"),
nlp.make_doc("test doc 2: Prosh"),
)
matcher = FuzzyMatcher(nlp.vocab)
output = matcher.pipe(doc_stream)
assert list(output) == list(doc_stream)
def test_matcher_pipe_with_matches(nlp: Language) -> None:
"""It returns a stream of Doc objects and matches as tuples."""
doc_stream = (
nlp.make_doc("test doc 1: Corvold"),
nlp.make_doc("test doc 2: Prosh"),
)
matcher = FuzzyMatcher(nlp.vocab)
matcher.add("DRAGON", [nlp.make_doc("Korvold"), nlp.make_doc("Prossh")])
output = matcher.pipe(doc_stream, return_matches=True)
matches = [entry[1] for entry in output]
assert matches == [[("DRAGON", 4, 5, 86)], [("DRAGON", 4, 5, 91)]]
def test_add_with_more_patterns_than_explicit_kwargs_warns(
matcher: FuzzyMatcher, nlp: Language) -> None:
"""It will warn when more patterns are added than explicit kwargs."""
with pytest.warns(KwargsWarning):
matcher.add(
"TEST",
[nlp.make_doc("Test1"),
nlp.make_doc("Test2")],
[{
"ignore_case": False
}],
)
def test_matcher_pipe_with_matches_and_context(nlp: Language) -> None:
"""It returns a stream of Doc objects and matches and context as tuples."""
doc_stream = (
(nlp.make_doc("test doc 1: Corvold"), "Jund"),
(nlp.make_doc("test doc 2: Prosh"), "Jund"),
)
matcher = FuzzyMatcher(nlp.vocab)
matcher.add("DRAGON", [nlp.make_doc("Korvold"), nlp.make_doc("Prossh")])
output = matcher.pipe(doc_stream, return_matches=True, as_tuples=True)
matches = [(entry[0][1], entry[1]) for entry in output]
assert matches == [
([("DRAGON", 4, 5, 86)], "Jund"),
([("DRAGON", 4, 5, 91)], "Jund"),
]
def matcher(nlp: Language, ) -> FuzzyMatcher:
"""Fuzzy matcher with patterns added."""
animals = ["Heifer", "chicken"]
sounds = ["mooo"]
names = ["Steven"]
matcher = FuzzyMatcher(nlp.vocab)
matcher.add(
"ANIMAL",
[nlp.make_doc(animal) for animal in animals],
kwargs=[{
"ignore_case": False
}, {}],
)
matcher.add("SOUND", [nlp.make_doc(sound) for sound in sounds])
matcher.add("NAME", [nlp.make_doc(name) for name in names],
on_match=add_name_ent)
return matcher
def test_remove_label_raises_error_if_label_not_in_matcher(
matcher: FuzzyMatcher, ) -> None:
"""It raises a ValueError if trying to remove a label not present."""
with pytest.raises(ValueError):
matcher.remove("TEST")
def test_remove_label(matcher: FuzzyMatcher, nlp: Language) -> None:
"""It removes a label from the matcher."""
matcher.add("TEST", [nlp.make_doc("test")])
assert "TEST" in matcher
matcher.remove("TEST")
assert "TEST" not in matcher
def test_add_where_kwargs_are_not_dicts_raises_error(matcher: FuzzyMatcher,
nlp: Language) -> None:
"""Trying to add non Dict objects as kwargs raises a TypeError."""
with pytest.raises(TypeError):
matcher.add("TEST", [nlp.make_doc("Test1")], ["ignore_case"])
def test_add_without_doc_objects_raises_error(matcher: FuzzyMatcher, ) -> None:
"""Trying to add non Doc objects as patterns raises a TypeError."""
with pytest.raises(TypeError):
matcher.add("TEST", ["Test1"])