def test_language_factories_scores():
name = "test_language_factories_scores"
func = lambda nlp, name: lambda doc: doc
weights1 = {"a1": 0.5, "a2": 0.5}
weights2 = {"b1": 0.2, "b2": 0.7, "b3": 0.1}
Language.factory(f"{name}1", default_score_weights=weights1, func=func)
Language.factory(f"{name}2", default_score_weights=weights2, func=func)
meta1 = Language.get_factory_meta(f"{name}1")
assert meta1.default_score_weights == weights1
meta2 = Language.get_factory_meta(f"{name}2")
assert meta2.default_score_weights == weights2
nlp = Language()
nlp._config["training"]["score_weights"] = {}
nlp.add_pipe(f"{name}1")
nlp.add_pipe(f"{name}2")
cfg = nlp.config["training"]
expected_weights = {"a1": 0.25, "a2": 0.25, "b1": 0.1, "b2": 0.35, "b3": 0.05}
assert cfg["score_weights"] == expected_weights
# Test with custom defaults
config = nlp.config.copy()
config["training"]["score_weights"]["a1"] = 0.0
config["training"]["score_weights"]["b3"] = 1.3
nlp = English.from_config(config)
score_weights = nlp.config["training"]["score_weights"]
expected = {"a1": 0.0, "a2": 0.12, "b1": 0.05, "b2": 0.17, "b3": 0.65}
assert score_weights == expected
# Test with null values
config = nlp.config.copy()
config["training"]["score_weights"]["a1"] = None
nlp = English.from_config(config)
score_weights = nlp.config["training"]["score_weights"]
expected = {"a1": None, "a2": 0.12, "b1": 0.05, "b2": 0.17, "b3": 0.66}
assert score_weights == expected
def test_pipe_factory_meta_config_cleanup():
"""Test that component-specific meta and config entries are represented
correctly and cleaned up when pipes are removed, replaced or renamed."""
nlp = Language()
nlp.add_pipe("ner", name="ner_component")
nlp.add_pipe("textcat")
assert nlp.get_factory_meta("ner")
assert nlp.get_pipe_meta("ner_component")
assert nlp.get_pipe_config("ner_component")
assert nlp.get_factory_meta("textcat")
assert nlp.get_pipe_meta("textcat")
assert nlp.get_pipe_config("textcat")
nlp.rename_pipe("textcat", "tc")
assert nlp.get_pipe_meta("tc")
assert nlp.get_pipe_config("tc")
with pytest.raises(ValueError):
nlp.remove_pipe("ner")
nlp.remove_pipe("ner_component")
assert "ner_component" not in nlp._pipe_meta
assert "ner_component" not in nlp._pipe_configs
with pytest.raises(ValueError):
nlp.replace_pipe("textcat", "parser")
nlp.replace_pipe("tc", "parser")
assert nlp.get_factory_meta("parser")
assert nlp.get_pipe_meta("tc").factory == "parser"
def test_pipe_function_component():
name = "test_component"
@Language.component(name)
def component(doc: Doc) -> Doc:
return doc
assert name in registry.factories
nlp = Language()
with pytest.raises(ValueError):
nlp.add_pipe(component)
nlp.add_pipe(name)
assert name in nlp.pipe_names
assert nlp.pipe_factories[name] == name
assert Language.get_factory_meta(name)
assert nlp.get_pipe_meta(name)
pipe = nlp.get_pipe(name)
assert pipe == component
pipe = nlp.create_pipe(name)
assert pipe == component
def test_pipe_class_component_init():
name1 = "test_class_component1"
name2 = "test_class_component2"
@Language.factory(name1)
class Component1:
def __init__(self, nlp: Language, name: str):
self.nlp = nlp
def __call__(self, doc: Doc) -> Doc:
return doc
class Component2:
def __init__(self, nlp: Language, name: str):
self.nlp = nlp
def __call__(self, doc: Doc) -> Doc:
return doc
@Language.factory(name2)
def factory(nlp: Language, name=name2):
return Component2(nlp, name)
nlp = Language()
for name, Component in [(name1, Component1), (name2, Component2)]:
assert name in registry.factories
with pytest.raises(ValueError):
nlp.add_pipe(Component(nlp, name))
nlp.add_pipe(name)
assert name in nlp.pipe_names
assert nlp.pipe_factories[name] == name
assert Language.get_factory_meta(name)
assert nlp.get_pipe_meta(name)
pipe = nlp.get_pipe(name)
assert isinstance(pipe, Component)
assert isinstance(pipe.nlp, Language)
pipe = nlp.create_pipe(name)
assert isinstance(pipe, Component)
assert isinstance(pipe.nlp, Language)
def test_add_meta_cat(self):
PipeTests.undertest.add_meta_cat(PipeTests.meta_cat, "cat_name")
self.assertEqual(PipeTests.meta_cat.name, Language.get_factory_meta(PipeTests.meta_cat.name).factory)
def test_add_linker(self):
PipeTests.undertest.add_linker(PipeTests.linker)
self.assertEqual(PipeTests.linker.name, Language.get_factory_meta(PipeTests.linker.name).factory)
def test_add_token_normalizer(self):
PipeTests.undertest.add_token_normalizer(PipeTests.config, spell_checker=PipeTests.spell_checker)
self.assertEqual("token_normalizer", Language.get_factory_meta("token_normalizer").factory)
def test_add_tagger(self):
PipeTests.undertest.add_tagger(tagger=tag_skip_and_punct, name="tag_skip_and_punct", additional_fields=["is_punct"])
self.assertEqual(tag_skip_and_punct.__name__, Language.get_factory_meta(tag_skip_and_punct.__name__).factory)
self.assertEqual(PipeTests.config, Language.get_factory_meta(tag_skip_and_punct.__name__).default_config["config"])
