2018-07-18 17:43:16 +00:00
|
|
|
import pytest
|
2020-10-05 20:50:14 +00:00
|
|
|
|
|
|
|
from spacy import registry
|
2018-07-24 21:38:44 +00:00
|
|
|
from spacy.tokens import Span
|
|
|
|
from spacy.language import Language
|
|
|
|
from spacy.pipeline import EntityRuler
|
2019-08-06 22:40:53 +00:00
|
|
|
from spacy.errors import MatchPatternError
|
2018-07-18 17:43:16 +00:00
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
|
|
|
def nlp():
|
|
|
|
return Language()
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture
|
2020-10-05 20:50:14 +00:00
|
|
|
@registry.misc("entity_ruler_patterns")
|
2018-07-18 17:43:16 +00:00
|
|
|
def patterns():
|
|
|
|
return [
|
|
|
|
{"label": "HELLO", "pattern": "hello world"},
|
|
|
|
{"label": "BYE", "pattern": [{"LOWER": "bye"}, {"LOWER": "bye"}]},
|
|
|
|
{"label": "HELLO", "pattern": [{"ORTH": "HELLO"}]},
|
2018-11-27 00:09:36 +00:00
|
|
|
{"label": "COMPLEX", "pattern": [{"ORTH": "foo", "OP": "*"}]},
|
2019-06-16 11:29:04 +00:00
|
|
|
{"label": "TECH_ORG", "pattern": "Apple", "id": "a1"},
|
2020-01-16 01:01:31 +00:00
|
|
|
{"label": "TECH_ORG", "pattern": "Microsoft", "id": "a2"},
|
2018-07-18 17:43:16 +00:00
|
|
|
]
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
@Language.component("add_ent")
|
|
|
|
def add_ent_component(doc):
|
|
|
|
doc.ents = [Span(doc, 0, 3, label="ORG")]
|
|
|
|
return doc
|
2018-07-18 17:43:16 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_entity_ruler_init(nlp, patterns):
|
|
|
|
ruler = EntityRuler(nlp, patterns=patterns)
|
|
|
|
assert len(ruler) == len(patterns)
|
2019-06-16 11:29:04 +00:00
|
|
|
assert len(ruler.labels) == 4
|
2018-11-27 00:09:36 +00:00
|
|
|
assert "HELLO" in ruler
|
|
|
|
assert "BYE" in ruler
|
2020-07-22 11:42:59 +00:00
|
|
|
ruler = nlp.add_pipe("entity_ruler")
|
|
|
|
ruler.add_patterns(patterns)
|
2018-07-18 17:43:16 +00:00
|
|
|
doc = nlp("hello world bye bye")
|
|
|
|
assert len(doc.ents) == 2
|
2018-11-27 00:09:36 +00:00
|
|
|
assert doc.ents[0].label_ == "HELLO"
|
|
|
|
assert doc.ents[1].label_ == "BYE"
|
2018-07-18 17:43:16 +00:00
|
|
|
|
|
|
|
|
2020-10-05 20:50:14 +00:00
|
|
|
def test_entity_ruler_init_patterns(nlp, patterns):
|
|
|
|
# initialize with patterns
|
|
|
|
ruler = nlp.add_pipe("entity_ruler")
|
|
|
|
assert len(ruler.labels) == 0
|
|
|
|
ruler.initialize(lambda: [], patterns=patterns)
|
|
|
|
assert len(ruler.labels) == 4
|
|
|
|
doc = nlp("hello world bye bye")
|
|
|
|
assert doc.ents[0].label_ == "HELLO"
|
|
|
|
assert doc.ents[1].label_ == "BYE"
|
|
|
|
nlp.remove_pipe("entity_ruler")
|
|
|
|
# initialize with patterns from misc registry
|
|
|
|
nlp.config["initialize"]["components"]["entity_ruler"] = {
|
|
|
|
"patterns": {"@misc": "entity_ruler_patterns"}
|
|
|
|
}
|
|
|
|
ruler = nlp.add_pipe("entity_ruler")
|
|
|
|
assert len(ruler.labels) == 0
|
|
|
|
nlp.initialize()
|
|
|
|
assert len(ruler.labels) == 4
|
|
|
|
doc = nlp("hello world bye bye")
|
|
|
|
assert doc.ents[0].label_ == "HELLO"
|
|
|
|
assert doc.ents[1].label_ == "BYE"
|
|
|
|
|
|
|
|
|
2020-10-08 07:51:31 +00:00
|
|
|
def test_entity_ruler_init_clear(nlp, patterns):
|
|
|
|
"""Test that initialization clears patterns."""
|
|
|
|
ruler = nlp.add_pipe("entity_ruler")
|
|
|
|
ruler.add_patterns(patterns)
|
|
|
|
assert len(ruler.labels) == 4
|
|
|
|
ruler.initialize(lambda: [])
|
|
|
|
assert len(ruler.labels) == 0
|
|
|
|
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def test_entity_ruler_existing(nlp, patterns):
|
|
|
|
ruler = nlp.add_pipe("entity_ruler")
|
|
|
|
ruler.add_patterns(patterns)
|
|
|
|
nlp.add_pipe("add_ent", before="entity_ruler")
|
2018-07-18 17:43:16 +00:00
|
|
|
doc = nlp("OH HELLO WORLD bye bye")
|
|
|
|
assert len(doc.ents) == 2
|
2018-11-27 00:09:36 +00:00
|
|
|
assert doc.ents[0].label_ == "ORG"
|
|
|
|
assert doc.ents[1].label_ == "BYE"
|
2018-07-18 17:43:16 +00:00
|
|
|
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def test_entity_ruler_existing_overwrite(nlp, patterns):
|
|
|
|
ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
|
|
|
|
ruler.add_patterns(patterns)
|
|
|
|
nlp.add_pipe("add_ent", before="entity_ruler")
|
2018-07-18 17:43:16 +00:00
|
|
|
doc = nlp("OH HELLO WORLD bye bye")
|
|
|
|
assert len(doc.ents) == 2
|
2018-11-27 00:09:36 +00:00
|
|
|
assert doc.ents[0].label_ == "HELLO"
|
|
|
|
assert doc.ents[0].text == "HELLO"
|
|
|
|
assert doc.ents[1].label_ == "BYE"
|
2018-07-18 17:43:16 +00:00
|
|
|
|
|
|
|
|
2020-07-22 11:42:59 +00:00
|
|
|
def test_entity_ruler_existing_complex(nlp, patterns):
|
|
|
|
ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
|
|
|
|
ruler.add_patterns(patterns)
|
|
|
|
nlp.add_pipe("add_ent", before="entity_ruler")
|
2018-07-18 17:43:16 +00:00
|
|
|
doc = nlp("foo foo bye bye")
|
|
|
|
assert len(doc.ents) == 2
|
2018-11-27 00:09:36 +00:00
|
|
|
assert doc.ents[0].label_ == "COMPLEX"
|
|
|
|
assert doc.ents[1].label_ == "BYE"
|
2018-07-18 17:43:16 +00:00
|
|
|
assert len(doc.ents[0]) == 2
|
|
|
|
assert len(doc.ents[1]) == 2
|
|
|
|
|
|
|
|
|
2019-06-16 11:29:04 +00:00
|
|
|
def test_entity_ruler_entity_id(nlp, patterns):
|
2020-07-22 11:42:59 +00:00
|
|
|
ruler = nlp.add_pipe("entity_ruler", config={"overwrite_ents": True})
|
|
|
|
ruler.add_patterns(patterns)
|
2019-06-16 11:29:04 +00:00
|
|
|
doc = nlp("Apple is a technology company")
|
|
|
|
assert len(doc.ents) == 1
|
|
|
|
assert doc.ents[0].label_ == "TECH_ORG"
|
|
|
|
assert doc.ents[0].ent_id_ == "a1"
|
|
|
|
|
|
|
|
|
|
|
|
def test_entity_ruler_cfg_ent_id_sep(nlp, patterns):
|
2020-07-22 11:42:59 +00:00
|
|
|
config = {"overwrite_ents": True, "ent_id_sep": "**"}
|
|
|
|
ruler = nlp.add_pipe("entity_ruler", config=config)
|
|
|
|
ruler.add_patterns(patterns)
|
2019-06-16 11:29:04 +00:00
|
|
|
assert "TECH_ORG**a1" in ruler.phrase_patterns
|
|
|
|
doc = nlp("Apple is a technology company")
|
|
|
|
assert len(doc.ents) == 1
|
|
|
|
assert doc.ents[0].label_ == "TECH_ORG"
|
|
|
|
assert doc.ents[0].ent_id_ == "a1"
|
|
|
|
|
|
|
|
|
2018-07-18 17:43:16 +00:00
|
|
|
def test_entity_ruler_serialize_bytes(nlp, patterns):
|
|
|
|
ruler = EntityRuler(nlp, patterns=patterns)
|
|
|
|
assert len(ruler) == len(patterns)
|
2019-06-16 11:29:04 +00:00
|
|
|
assert len(ruler.labels) == 4
|
2018-07-18 17:43:16 +00:00
|
|
|
ruler_bytes = ruler.to_bytes()
|
|
|
|
new_ruler = EntityRuler(nlp)
|
|
|
|
assert len(new_ruler) == 0
|
|
|
|
assert len(new_ruler.labels) == 0
|
|
|
|
new_ruler = new_ruler.from_bytes(ruler_bytes)
|
2019-07-09 18:09:17 +00:00
|
|
|
assert len(new_ruler) == len(patterns)
|
|
|
|
assert len(new_ruler.labels) == 4
|
|
|
|
assert len(new_ruler.patterns) == len(ruler.patterns)
|
|
|
|
for pattern in ruler.patterns:
|
|
|
|
assert pattern in new_ruler.patterns
|
2019-07-10 11:00:52 +00:00
|
|
|
assert sorted(new_ruler.labels) == sorted(ruler.labels)
|
2019-07-09 18:09:17 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_entity_ruler_serialize_phrase_matcher_attr_bytes(nlp, patterns):
|
|
|
|
ruler = EntityRuler(nlp, phrase_matcher_attr="LOWER", patterns=patterns)
|
2018-07-18 17:43:16 +00:00
|
|
|
assert len(ruler) == len(patterns)
|
2019-06-16 11:29:04 +00:00
|
|
|
assert len(ruler.labels) == 4
|
2019-07-09 18:09:17 +00:00
|
|
|
ruler_bytes = ruler.to_bytes()
|
|
|
|
new_ruler = EntityRuler(nlp)
|
|
|
|
assert len(new_ruler) == 0
|
|
|
|
assert len(new_ruler.labels) == 0
|
|
|
|
assert new_ruler.phrase_matcher_attr is None
|
|
|
|
new_ruler = new_ruler.from_bytes(ruler_bytes)
|
|
|
|
assert len(new_ruler) == len(patterns)
|
|
|
|
assert len(new_ruler.labels) == 4
|
|
|
|
assert new_ruler.phrase_matcher_attr == "LOWER"
|
2019-08-06 22:40:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_entity_ruler_validate(nlp):
|
|
|
|
ruler = EntityRuler(nlp)
|
|
|
|
validated_ruler = EntityRuler(nlp, validate=True)
|
|
|
|
|
|
|
|
valid_pattern = {"label": "HELLO", "pattern": [{"LOWER": "HELLO"}]}
|
|
|
|
invalid_pattern = {"label": "HELLO", "pattern": [{"ASDF": "HELLO"}]}
|
|
|
|
|
2019-08-21 12:00:37 +00:00
|
|
|
# invalid pattern raises error without validate
|
|
|
|
with pytest.raises(ValueError):
|
|
|
|
ruler.add_patterns([invalid_pattern])
|
2019-08-06 22:40:53 +00:00
|
|
|
|
|
|
|
# valid pattern is added without errors with validate
|
|
|
|
validated_ruler.add_patterns([valid_pattern])
|
|
|
|
|
|
|
|
# invalid pattern raises error with validate
|
|
|
|
with pytest.raises(MatchPatternError):
|
|
|
|
validated_ruler.add_patterns([invalid_pattern])
|
2020-01-16 01:01:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_entity_ruler_properties(nlp, patterns):
|
|
|
|
ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
|
2020-03-25 11:28:12 +00:00
|
|
|
assert sorted(ruler.labels) == sorted(["HELLO", "BYE", "COMPLEX", "TECH_ORG"])
|
2020-01-16 01:01:31 +00:00
|
|
|
assert sorted(ruler.ent_ids) == ["a1", "a2"]
|
2020-07-31 14:09:32 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_entity_ruler_overlapping_spans(nlp):
|
|
|
|
ruler = EntityRuler(nlp)
|
|
|
|
patterns = [
|
|
|
|
{"label": "FOOBAR", "pattern": "foo bar"},
|
|
|
|
{"label": "BARBAZ", "pattern": "bar baz"},
|
|
|
|
]
|
|
|
|
ruler.add_patterns(patterns)
|
|
|
|
doc = ruler(nlp.make_doc("foo bar baz"))
|
|
|
|
assert len(doc.ents) == 1
|
|
|
|
assert doc.ents[0].label_ == "FOOBAR"
|
2020-11-10 12:16:07 +00:00
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.parametrize("n_process", [1, 2])
|
|
|
|
def test_entity_ruler_multiprocessing(nlp, n_process):
|
|
|
|
texts = [
|
|
|
|
"I enjoy eating Pizza Hut pizza."
|
|
|
|
]
|
|
|
|
|
|
|
|
patterns = [
|
|
|
|
{"label": "FASTFOOD", "pattern": "Pizza Hut", "id": "1234"}
|
|
|
|
]
|
|
|
|
|
2020-11-25 09:33:49 +00:00
|
|
|
ruler = nlp.add_pipe("entity_ruler")
|
2020-11-10 12:16:07 +00:00
|
|
|
ruler.add_patterns(patterns)
|
|
|
|
|
|
|
|
for doc in nlp.pipe(texts, n_process=2):
|
|
|
|
for ent in doc.ents:
|
|
|
|
assert ent.ent_id_ == "1234"
|