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_analysis_validate_attrs_remove_pipe():
"""Test that attributes are validated correctly on remove."""
@Language.component("pipe_analysis_c6", assigns=["token.tag"])
def c1(doc):
return doc
@Language.component("pipe_analysis_c7", requires=["token.pos"])
def c2(doc):
return doc
nlp = Language()
nlp.add_pipe("pipe_analysis_c6")
nlp.add_pipe("pipe_analysis_c7")
problems = nlp.analyze_pipes()["problems"]
assert problems["pipe_analysis_c7"] == ["token.pos"]
nlp.remove_pipe("pipe_analysis_c7")
problems = nlp.analyze_pipes()["problems"]
assert all(p == [] for p in problems.values())
def test_analysis_validate_attrs_remove_pipe():
"""Test that attributes are validated correctly on remove."""
spacy.language.ENABLE_PIPELINE_ANALYSIS = True
@component("c1", assigns=["token.tag"])
def c1(doc):
return doc
@component("c2", requires=["token.pos"])
def c2(doc):
return doc
nlp = Language()
nlp.add_pipe(c1)
with pytest.warns(UserWarning):
nlp.add_pipe(c2)
with pytest.warns(None) as record:
nlp.remove_pipe("c2")
assert not record.list
def test_pipe_methods_initialize():
"""Test that the [initialize] config reflects the components correctly."""
nlp = Language()
nlp.add_pipe("tagger")
assert "tagger" not in nlp.config["initialize"]["components"]
nlp.config["initialize"]["components"]["tagger"] = {"labels": ["hello"]}
assert nlp.config["initialize"]["components"]["tagger"] == {"labels": ["hello"]}
nlp.remove_pipe("tagger")
assert "tagger" not in nlp.config["initialize"]["components"]
nlp.add_pipe("tagger")
assert "tagger" not in nlp.config["initialize"]["components"]
nlp.config["initialize"]["components"]["tagger"] = {"labels": ["hello"]}
nlp.rename_pipe("tagger", "my_tagger")
assert "tagger" not in nlp.config["initialize"]["components"]
assert nlp.config["initialize"]["components"]["my_tagger"] == {"labels": ["hello"]}
nlp.config["initialize"]["components"]["test"] = {"foo": "bar"}
nlp.add_pipe("ner", name="test")
assert "test" in nlp.config["initialize"]["components"]
nlp.remove_pipe("test")
assert "test" not in nlp.config["initialize"]["components"]
def test_disable_enable_pipes():
name = "test_disable_enable_pipes"
results = {}
def make_component(name):
results[name] = ""
def component(doc):
nonlocal results
results[name] = doc.text
return doc
return component
c1 = Language.component(f"{name}1", func=make_component(f"{name}1"))
c2 = Language.component(f"{name}2", func=make_component(f"{name}2"))
nlp = Language()
nlp.add_pipe(f"{name}1")
nlp.add_pipe(f"{name}2")
assert results[f"{name}1"] == ""
assert results[f"{name}2"] == ""
assert nlp.pipeline == [(f"{name}1", c1), (f"{name}2", c2)]
assert nlp.pipe_names == [f"{name}1", f"{name}2"]
nlp.disable_pipe(f"{name}1")
assert nlp.disabled == [f"{name}1"]
assert nlp.component_names == [f"{name}1", f"{name}2"]
assert nlp.pipe_names == [f"{name}2"]
assert nlp.config["nlp"]["disabled"] == [f"{name}1"]
nlp("hello")
assert results[f"{name}1"] == "" # didn't run
assert results[f"{name}2"] == "hello" # ran
nlp.enable_pipe(f"{name}1")
assert nlp.disabled == []
assert nlp.pipe_names == [f"{name}1", f"{name}2"]
assert nlp.config["nlp"]["disabled"] == []
nlp("world")
assert results[f"{name}1"] == "world"
assert results[f"{name}2"] == "world"
nlp.disable_pipe(f"{name}2")
nlp.remove_pipe(f"{name}2")
assert nlp.components == [(f"{name}1", c1)]
assert nlp.pipeline == [(f"{name}1", c1)]
assert nlp.component_names == [f"{name}1"]
assert nlp.pipe_names == [f"{name}1"]
assert nlp.disabled == []
assert nlp.config["nlp"]["disabled"] == []
nlp.rename_pipe(f"{name}1", name)
assert nlp.components == [(name, c1)]
assert nlp.component_names == [name]
nlp("!")
assert results[f"{name}1"] == "!"
assert results[f"{name}2"] == "world"
with pytest.raises(ValueError):
nlp.disable_pipe(f"{name}2")
nlp.disable_pipe(name)
assert nlp.component_names == [name]
assert nlp.pipe_names == []
assert nlp.config["nlp"]["disabled"] == [name]
nlp("?")
assert results[f"{name}1"] == "!"
def remove_maskedlm_pipe(nlp: Language):
"""Remove maskedlm pipe from nlp"""
targets = [PIPES.bert_for_maskedlm, PIPES.bert_for_maskedlm_preprocessor]
for k in targets:
if k in nlp.pipe_names:
nlp.remove_pipe(k)
