mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
358cbb21e3
* candidate generator as separate part of EL config * update comment * ent instead of str as input for candidate generation * Span instead of str: correct type indication * fix types * unit test to create new candidate generator * fix replace_pipe argument passing * move error message, general cleanup * add vocab back to KB constructor * provide KB as callable from Vocab arg * rename to kb_loader, fix KB serialization as part of the EL pipe * fix typo * reformatting * cleanup * fix comment * fix wrongly duplicated code from merge conflict * rename dump to to_disk * from_disk instead of load_bulk * update test after recent removal of set_morphology in tagger * remove old doc
252 lines
7.9 KiB
Python
252 lines
7.9 KiB
Python
import pytest
|
|
from spacy.language import Language
|
|
|
|
|
|
@pytest.fixture
|
|
def nlp():
|
|
return Language()
|
|
|
|
|
|
@Language.component("new_pipe")
|
|
def new_pipe(doc):
|
|
return doc
|
|
|
|
|
|
@Language.component("other_pipe")
|
|
def other_pipe(doc):
|
|
return doc
|
|
|
|
|
|
def test_add_pipe_no_name(nlp):
|
|
nlp.add_pipe("new_pipe")
|
|
assert "new_pipe" in nlp.pipe_names
|
|
|
|
|
|
def test_add_pipe_duplicate_name(nlp):
|
|
nlp.add_pipe("new_pipe", name="duplicate_name")
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("new_pipe", name="duplicate_name")
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["parser"])
|
|
def test_add_pipe_first(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name, first=True)
|
|
assert nlp.pipeline[0][0] == name
|
|
|
|
|
|
@pytest.mark.parametrize("name1,name2", [("parser", "lambda_pipe")])
|
|
def test_add_pipe_last(nlp, name1, name2):
|
|
Language.component("new_pipe2", func=lambda doc: doc)
|
|
nlp.add_pipe("new_pipe2", name=name2)
|
|
nlp.add_pipe("new_pipe", name=name1, last=True)
|
|
assert nlp.pipeline[0][0] != name1
|
|
assert nlp.pipeline[-1][0] == name1
|
|
|
|
|
|
def test_cant_add_pipe_first_and_last(nlp):
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("new_pipe", first=True, last=True)
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_get_pipe(nlp, name):
|
|
with pytest.raises(KeyError):
|
|
nlp.get_pipe(name)
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.get_pipe(name) == new_pipe
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"name,replacement,invalid_replacement",
|
|
[("my_component", "other_pipe", lambda doc: doc)],
|
|
)
|
|
def test_replace_pipe(nlp, name, replacement, invalid_replacement):
|
|
with pytest.raises(ValueError):
|
|
nlp.replace_pipe(name, new_pipe)
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
with pytest.raises(ValueError):
|
|
nlp.replace_pipe(name, invalid_replacement)
|
|
nlp.replace_pipe(name, replacement)
|
|
assert nlp.get_pipe(name) == nlp.create_pipe(replacement)
|
|
|
|
|
|
def test_replace_last_pipe(nlp):
|
|
nlp.add_pipe("sentencizer")
|
|
nlp.add_pipe("ner")
|
|
assert nlp.pipe_names == ["sentencizer", "ner"]
|
|
nlp.replace_pipe("ner", "ner")
|
|
assert nlp.pipe_names == ["sentencizer", "ner"]
|
|
|
|
|
|
def test_replace_pipe_config(nlp):
|
|
nlp.add_pipe("entity_linker")
|
|
nlp.add_pipe("sentencizer")
|
|
assert nlp.get_pipe("entity_linker").cfg["incl_prior"] == True
|
|
nlp.replace_pipe("entity_linker", "entity_linker", config={"incl_prior": False})
|
|
assert nlp.get_pipe("entity_linker").cfg["incl_prior"] == False
|
|
|
|
|
|
@pytest.mark.parametrize("old_name,new_name", [("old_pipe", "new_pipe")])
|
|
def test_rename_pipe(nlp, old_name, new_name):
|
|
with pytest.raises(ValueError):
|
|
nlp.rename_pipe(old_name, new_name)
|
|
nlp.add_pipe("new_pipe", name=old_name)
|
|
nlp.rename_pipe(old_name, new_name)
|
|
assert nlp.pipeline[0][0] == new_name
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_remove_pipe(nlp, name):
|
|
with pytest.raises(ValueError):
|
|
nlp.remove_pipe(name)
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert len(nlp.pipeline) == 1
|
|
removed_name, removed_component = nlp.remove_pipe(name)
|
|
assert not len(nlp.pipeline)
|
|
assert removed_name == name
|
|
assert removed_component == new_pipe
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_disable_pipes_method(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
disabled = nlp.select_pipes(disable=name)
|
|
assert not nlp.has_pipe(name)
|
|
disabled.restore()
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_enable_pipes_method(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
disabled = nlp.select_pipes(enable=[])
|
|
assert not nlp.has_pipe(name)
|
|
disabled.restore()
|
|
|
|
|
|
@pytest.mark.parametrize("name", ["my_component"])
|
|
def test_disable_pipes_context(nlp, name):
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
with nlp.select_pipes(disable=name):
|
|
assert not nlp.has_pipe(name)
|
|
assert nlp.has_pipe(name)
|
|
|
|
|
|
def test_select_pipes_list_arg(nlp):
|
|
for name in ["c1", "c2", "c3"]:
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
with nlp.select_pipes(disable=["c1", "c2"]):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable="c3"):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable=["c1", "c2"], disable="c3"):
|
|
assert nlp.has_pipe("c1")
|
|
assert nlp.has_pipe("c2")
|
|
assert not nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable=[]):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert not nlp.has_pipe("c3")
|
|
with nlp.select_pipes(enable=["c1", "c2", "c3"], disable=[]):
|
|
assert nlp.has_pipe("c1")
|
|
assert nlp.has_pipe("c2")
|
|
assert nlp.has_pipe("c3")
|
|
with nlp.select_pipes(disable=["c1", "c2", "c3"], enable=[]):
|
|
assert not nlp.has_pipe("c1")
|
|
assert not nlp.has_pipe("c2")
|
|
assert not nlp.has_pipe("c3")
|
|
|
|
|
|
def test_select_pipes_errors(nlp):
|
|
for name in ["c1", "c2", "c3"]:
|
|
nlp.add_pipe("new_pipe", name=name)
|
|
assert nlp.has_pipe(name)
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes()
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes(enable=["c1", "c2"], disable=["c1"])
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes(enable=["c1", "c2"], disable=[])
|
|
|
|
with pytest.raises(ValueError):
|
|
nlp.select_pipes(enable=[], disable=["c3"])
|
|
|
|
|
|
@pytest.mark.parametrize("n_pipes", [100])
|
|
def test_add_lots_of_pipes(nlp, n_pipes):
|
|
Language.component("n_pipes", func=lambda doc: doc)
|
|
for i in range(n_pipes):
|
|
nlp.add_pipe("n_pipes", name=f"pipe_{i}")
|
|
assert len(nlp.pipe_names) == n_pipes
|
|
|
|
|
|
@pytest.mark.parametrize("component", [lambda doc: doc, {"hello": "world"}])
|
|
def test_raise_for_invalid_components(nlp, component):
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe(component)
|
|
|
|
|
|
@pytest.mark.parametrize("component", ["ner", "tagger", "parser", "textcat"])
|
|
def test_pipe_base_class_add_label(nlp, component):
|
|
label = "TEST"
|
|
pipe = nlp.create_pipe(component)
|
|
pipe.add_label(label)
|
|
if component == "tagger":
|
|
# Tagger always has the default coarse-grained label scheme
|
|
assert label in pipe.labels
|
|
else:
|
|
assert pipe.labels == (label,)
|
|
|
|
|
|
def test_pipe_labels(nlp):
|
|
input_labels = {
|
|
"ner": ["PERSON", "ORG", "GPE"],
|
|
"textcat": ["POSITIVE", "NEGATIVE"],
|
|
}
|
|
for name, labels in input_labels.items():
|
|
nlp.add_pipe(name)
|
|
pipe = nlp.get_pipe(name)
|
|
for label in labels:
|
|
pipe.add_label(label)
|
|
assert len(pipe.labels) == len(labels)
|
|
|
|
assert len(nlp.pipe_labels) == len(input_labels)
|
|
for name, labels in nlp.pipe_labels.items():
|
|
assert sorted(input_labels[name]) == sorted(labels)
|
|
|
|
|
|
def test_add_pipe_before_after():
|
|
"""Test that before/after works with strings and ints."""
|
|
nlp = Language()
|
|
nlp.add_pipe("ner")
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("textcat", before="parser")
|
|
nlp.add_pipe("textcat", before="ner")
|
|
assert nlp.pipe_names == ["textcat", "ner"]
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("parser", before=3)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("parser", after=3)
|
|
nlp.add_pipe("parser", after=0)
|
|
assert nlp.pipe_names == ["textcat", "parser", "ner"]
|
|
nlp.add_pipe("tagger", before=2)
|
|
assert nlp.pipe_names == ["textcat", "parser", "tagger", "ner"]
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", after=1, first=True)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", before="ner", after=2)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", before=True)
|
|
with pytest.raises(ValueError):
|
|
nlp.add_pipe("entity_ruler", first=False)
|