mirror of https://github.com/explosion/spaCy.git
Add regression test for #4002
Test that the PhraseMatcher can match on overwritten NORM attributes.
This commit is contained in:
parent
0be6c7c06c
commit
a32b033b8c
|
@ -0,0 +1,28 @@
|
|||
# coding: utf8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import pytest
|
||||
from spacy.matcher import PhraseMatcher
|
||||
from spacy.tokens import Doc
|
||||
|
||||
|
||||
@pytest.mark.xfail
|
||||
def test_issue4002(en_vocab):
|
||||
"""Test that the PhraseMatcher can match on overwritten NORM attributes.
|
||||
"""
|
||||
matcher = PhraseMatcher(en_vocab, attr="NORM")
|
||||
pattern1 = Doc(en_vocab, words=["c", "d"])
|
||||
assert [t.norm_ for t in pattern1] == ["c", "d"]
|
||||
matcher.add("TEST", None, pattern1)
|
||||
doc = Doc(en_vocab, words=["a", "b", "c", "d"])
|
||||
assert [t.norm_ for t in doc] == ["a", "b", "c", "d"]
|
||||
matches = matcher(doc)
|
||||
assert len(matches) == 1
|
||||
matcher = PhraseMatcher(en_vocab, attr="NORM")
|
||||
pattern2 = Doc(en_vocab, words=["1", "2"])
|
||||
pattern2[0].norm_ = "c"
|
||||
pattern2[1].norm_ = "d"
|
||||
assert [t.norm_ for t in pattern2] == ["c", "d"]
|
||||
matcher.add("TEST", None, pattern2)
|
||||
matches = matcher(doc)
|
||||
assert len(matches) == 1
|
Loading…
Reference in New Issue