mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-01 08:27:44 +03:00
f94168a41e
* Fix scoring normalization (#7629) * fix scoring normalization * score weights by total sum instead of per component * cleanup * more cleanup * Use a context manager when reading model (fix #7036) (#8244) * Fix other open calls without context managers (#8245) * Don't add duplicate patterns all the time in EntityRuler (fix #8216) (#8246) * 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 * Exclude generated .cpp files from package (#8271) * Fix non-deterministic deduplication in Greek lemmatizer (#8421) * Fix setting empty entities in Example.from_dict (#8426) * Filter W036 for entity ruler, etc. (#8424) * Preserve paths.vectors/initialize.vectors setting in quickstart template * Various fixes for spans in Docs.from_docs (#8487) * Fix spans offsets if a doc ends in a single space and no space is inserted * Also include spans key in merged doc for empty spans lists * Fix duplicate spacy package CLI opts (#8551) Use `-c` for `--code` and not additionally for `--create-meta`, in line with the docs. * Raise an error for textcat with <2 labels (#8584) * Raise an error for textcat with <2 labels Raise an error if initializing a `textcat` component without at least two labels. * Add similar note to docs * Update positive_label description in API docs * Add Macedonian models to website (#8637) * Fix Azerbaijani init, extend lang init tests (#8656) * Extend langs in initialize tests * Fix az init * Fix ru/uk lemmatizer mp with spawn (#8657) Use an instance variable instead a class variable for the morphological analzyer so that multiprocessing with spawn is possible. * Use 0-vector for OOV lexemes (#8639) * Set version to v3.0.7 Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: Paul O'Leary McCann <polm@dampfkraft.com>
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
|