explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-19 04:32:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add sentence map test

Browse Source
This commit is contained in:
Paul O'Leary McCann 2021-07-19 13:05:26 +09:00
parent 3ed0fae671
commit a151c62d13
1 changed files with 20 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
spacy/tests/pipeline/test_coref.py
View File

@ -6,7 +6,11 @@ from spacy.training import Example
from spacy.lang.en import English from spacy.lang.en import English
from spacy.tests.util import make_tempdir from spacy.tests.util import make_tempdir
from spacy.pipeline.coref import DEFAULT_CLUSTERS_PREFIX from spacy.pipeline.coref import DEFAULT_CLUSTERS_PREFIX
from spacy.ml.models.coref_util import select_non_crossing_spans, get_candidate_mentions from spacy.ml.models.coref_util import (
select_non_crossing_spans,
get_candidate_mentions,
get_sentence_map,
)
# fmt: off # fmt: off
TRAIN_DATA = [ TRAIN_DATA = [
@ -35,6 +39,13 @@ def nlp():
return English() return English()
@pytest.fixture
def snlp():
en = English()
en.add_pipe("sentencizer")
return en
def test_add_pipe(nlp): def test_add_pipe(nlp):
nlp.add_pipe("coref") nlp.add_pipe("coref")
assert nlp.pipe_names == ["coref"] assert nlp.pipe_names == ["coref"]
@ -158,17 +169,21 @@ def test_crossing_spans():
assert gold == guess assert gold == guess
def test_mention_generator(): def test_mention_generator(snlp):
# don't use the fixture because we want the sentencizer nlp = snlp
nlp = English()
doc = nlp("I like text.") # four tokens doc = nlp("I like text.") # four tokens
max_width = 20 max_width = 20
mentions = get_candidate_mentions(doc, max_width) mentions = get_candidate_mentions(doc, max_width)
assert len(mentions[0]) == 10 assert len(mentions[0]) == 10
# check multiple sentences # check multiple sentences
nlp.add_pipe("sentencizer")
doc = nlp("I like text. This is text.") # eight tokens, two sents doc = nlp("I like text. This is text.") # eight tokens, two sents
max_width = 20 max_width = 20
mentions = get_candidate_mentions(doc, max_width) mentions = get_candidate_mentions(doc, max_width)
assert len(mentions[0]) == 20 assert len(mentions[0]) == 20
def test_sentence_map(snlp):
doc = snlp("I like text. This is text.")
sm = get_sentence_map(doc)
assert sm == [0, 0, 0, 0, 1, 1, 1, 1]