mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
27 lines
902 B
Python
27 lines
902 B
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from spacy.matcher import PhraseMatcher
|
||
|
|
from spacy.tokens import Doc
|
||
|
|
|
||
|
|
|
||
|
|
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
|