spaCy/spacy/tests/regression/test_issue3972.py
Sofie Van Landeghem c417c380e3 Matcher ID fixes (#4179)
* allow phrasematcher to link one match to multiple original patterns

* small fix for defining ent_id in the matcher (anti-ghost prevention)

* cleanup

* formatting
2019-08-22 17:17:07 +02:00

24 lines
734 B
Python

# coding: utf8
from __future__ import unicode_literals
import pytest
from spacy.matcher import PhraseMatcher
from spacy.tokens import Doc
def test_issue3972(en_vocab):
"""Test that the PhraseMatcher returns duplicates for duplicate match IDs.
"""
matcher = PhraseMatcher(en_vocab)
matcher.add("A", None, Doc(en_vocab, words=["New", "York"]))
matcher.add("B", None, Doc(en_vocab, words=["New", "York"]))
doc = Doc(en_vocab, words=["I", "live", "in", "New", "York"])
matches = matcher(doc)
assert len(matches) == 2
# We should have a match for each of the two rules
found_ids = [en_vocab.strings[ent_id] for (ent_id, _, _) in matches]
assert "A" in found_ids
assert "B" in found_ids