spaCy/spacy/tests/regression/test_issue4529.py

14 lines
317 B
Python

# coding: utf8
from __future__ import unicode_literals
import pytest
from spacy.gold import GoldParse
@pytest.mark.parametrize(
"text,words", [("A'B C", ["A", "'", "B", "C"]), ("A-B", ["A-B"])]
)
def test_gold_misaligned(en_tokenizer, text, words):
doc = en_tokenizer(text)
GoldParse(doc, words=words)