mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-30 23:47:31 +03:00
ad026dc5fd
* Don't add duplicate patterns (fix #8216) * Refactor EntityRuler init This simplifies the EntityRuler init code. This is helpful as prep for allowing the EntityRuler to reset itself. * Make EntityRuler.clear reset matchers Includes a new test for this. * Tidy PhraseMatcher instantiation Since the attr can be None safely now, the guard if is no longer required here. Also renamed the `_validate` attr. Maybe it's not needed? * Fix NER test * Add test to make sure patterns aren't increasing * Move test to regression tests
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
import pytest
|
|
|
|
from spacy import registry
|
|
from spacy.language import Language
|
|
from spacy.pipeline import EntityRuler
|
|
|
|
|
|
@pytest.fixture
|
|
def nlp():
|
|
return Language()
|
|
|
|
|
|
@pytest.fixture
|
|
@registry.misc("entity_ruler_patterns")
|
|
def patterns():
|
|
return [
|
|
{"label": "HELLO", "pattern": "hello world"},
|
|
{"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
|
|
{"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
|
|
{"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
|
|
{"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
|
|
{"label": "TECH_ORG", "pattern": "Microsoft", "id": "a2"},
|
|
]
|
|
|
|
|
|
def test_entity_ruler_fix8216(nlp, patterns):
|
|
"""Test that patterns don't get added excessively."""
|
|
ruler = nlp.add_pipe("entity_ruler", config={"validate": True})
|
|
ruler.add_patterns(patterns)
|
|
pattern_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
|
|
assert pattern_count > 0
|
|
ruler.add_patterns([])
|
|
after_count = sum(len(mm) for mm in ruler.matcher._patterns.values())
|
|
assert after_count == pattern_count
|