mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-12 18:26:30 +03:00
de5a9ecdf3
* remove duplicate unit test * unit test (currently failing) for issue 4267 * bugfix: ensure doc.ents preserves kb_id annotations * fix in setting doc.ents with empty label * rename * test for presetting an entity to a certain type * allow overwriting Outside + blocking presets * fix actions when previous label needs to be kept * fix default ent_iob in set entities * cleaner solution with U- action * remove debugging print statements * unit tests with explicit transitions and is_valid testing * remove U- from move_names explicitly * remove unit tests with pre-trained models that don't work * remove (working) unit tests with pre-trained models * clean up unit tests * move unit tests * small fixes * remove two TODO's from doc.ents comments
43 lines
1.0 KiB
Python
43 lines
1.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
import spacy
|
|
|
|
from spacy.lang.en import English
|
|
from spacy.pipeline import EntityRuler
|
|
from spacy.tokens import Span
|
|
|
|
|
|
def test_issue4267():
|
|
""" Test that running an entity_ruler after ner gives consistent results"""
|
|
nlp = English()
|
|
ner = nlp.create_pipe("ner")
|
|
ner.add_label("PEOPLE")
|
|
nlp.add_pipe(ner)
|
|
nlp.begin_training()
|
|
|
|
assert "ner" in nlp.pipe_names
|
|
|
|
# assert that we have correct IOB annotations
|
|
doc1 = nlp("hi")
|
|
assert doc1.is_nered
|
|
for token in doc1:
|
|
assert token.ent_iob == 2
|
|
|
|
# add entity ruler and run again
|
|
ruler = EntityRuler(nlp)
|
|
patterns = [{"label": "SOFTWARE", "pattern": "spacy"}]
|
|
|
|
ruler.add_patterns(patterns)
|
|
nlp.add_pipe(ruler)
|
|
assert "entity_ruler" in nlp.pipe_names
|
|
assert "ner" in nlp.pipe_names
|
|
|
|
# assert that we still have correct IOB annotations
|
|
doc2 = nlp("hi")
|
|
assert doc2.is_nered
|
|
for token in doc2:
|
|
assert token.ent_iob == 2
|