mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
0d94737857
* make disable_pipes deprecated in favour of the new toggle_pipes * rewrite disable_pipes statements * update documentation * remove bin/wiki_entity_linking folder * one more fix * remove deprecated link to documentation * few more doc fixes * add note about name change to the docs * restore original disable_pipes * small fixes * fix typo * fix error number to W096 * rename to select_pipes * also make changes to the documentation Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
201 lines
6.1 KiB
Python
201 lines
6.1 KiB
Python
import pytest
|
|
from spacy.language import Language
|
|
|
|
|
|
@pytest.fixture
|
|
def nlp():
|
|
return Language()
|
|
|
|
|
|
def new_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):
|
|
nlp.add_pipe(lambda doc: doc, 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,not_callable", [("my_component", lambda doc: doc, {})]
|
|
)
|
|
def test_replace_pipe(nlp, name, replacement, not_callable):
|
|
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, not_callable)
|
|
nlp.replace_pipe(name, replacement)
|
|
assert nlp.get_pipe(name) != new_pipe
|
|
assert nlp.get_pipe(name) == replacement
|
|
|
|
|
|
@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):
|
|
for i in range(n_pipes):
|
|
nlp.add_pipe(lambda doc: doc, name=f"pipe_{i}")
|
|
assert len(nlp.pipe_names) == n_pipes
|
|
|
|
|
|
@pytest.mark.parametrize("component", ["ner", {"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():
|
|
pipe = nlp.create_pipe(name)
|
|
for label in labels:
|
|
pipe.add_label(label)
|
|
assert len(pipe.labels) == len(labels)
|
|
nlp.add_pipe(pipe)
|
|
assert len(nlp.pipe_labels) == len(input_labels)
|
|
for name, labels in nlp.pipe_labels.items():
|
|
assert sorted(input_labels[name]) == sorted(labels)
|