Add test for partial sentences in ent.sents.

This commit is contained in:
Raphael Mitsch 2023-03-13 11:24:24 +01:00
parent f27bce67fd
commit 8cfbe5a4d1
2 changed files with 18 additions and 3 deletions

View File

@ -7,6 +7,7 @@ from spacy.lang.en import English
from spacy.tokens import Doc, Span, Token
from spacy.vocab import Vocab
from spacy.util import filter_spans
from spacy.training import Example
from thinc.api import get_current_ops
from ..util import add_vecs_to_vocab
@ -700,3 +701,18 @@ def test_span_group_copy(doc):
assert len(doc.spans["test"]) == 3
# check that the copy spans were not modified and this is an isolated doc
assert len(doc_copy.spans["test"]) == 2
def test_for_partial_ent_sents():
"""Spans may be associated with multiple sentences. These .sents should always be complete, not partial, sentences,
which this tests for.
"""
nlp = English()
text = ["Mahler's", "Symphony", "No.", "8", "was", "beautiful."]
doc = Doc(nlp.vocab, words=text, sent_starts=[1, 0, 0, 1, 0, 0])
doc.set_ents([Span(doc, 1, 4, "WORK")])
# The specified entity is associated with both sentences in this doc, so we expect all sentences in the doc to be
# equal to the sentences referenced in ent.sents.
for doc_sent, ent_sent in zip(doc.sents, doc.ents[0].sents):
assert doc_sent == ent_sent

View File

@ -460,9 +460,8 @@ cdef class Span:
start = i
if start >= self.end:
break
if start < self.end:
yield Span(self.doc, start, self.end)
elif i == self.doc.length - 1:
yield Span(self.doc, start, i + 1)
@property
def ents(self):