2019-02-08 19:50:01 +00:00
|
|
|
# coding: utf8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
from spacy.matcher import Matcher
|
|
|
|
|
from spacy.tokens import Token, Doc
|
|
|
|
|
|
|
|
|
|
|
2019-02-08 19:50:35 +00:00
|
|
|
@pytest.mark.xfail
|
2019-02-08 19:50:01 +00:00
|
|
|
def test_issue1971(en_vocab):
|
|
|
|
|
# Possibly related to #2675 and #2671?
|
|
|
|
|
matcher = Matcher(en_vocab)
|
|
|
|
|
pattern = [
|
|
|
|
|
{"ORTH": "Doe"},
|
|
|
|
|
{"ORTH": "!", "OP": "?"},
|
|
|
|
|
{"_": {"optional": True}, "OP": "?"},
|
|
|
|
|
{"ORTH": "!", "OP": "?"},
|
|
|
|
|
]
|
|
|
|
|
Token.set_extension("optional", default=False)
|
|
|
|
|
matcher.add("TEST", None, pattern)
|
|
|
|
|
doc = Doc(en_vocab, words=["Hello", "John", "Doe", "!"])
|
|
|
|
|
# We could also assert length 1 here, but this is more conclusive, because
|
|
|
|
|
# the real problem here is that it returns a duplicate match for a match_id
|
|
|
|
|
# that's not actually in the vocab!
|
|
|
|
|
assert all(match_id in en_vocab.strings for match_id, start, end in matcher(doc))
|
