spaCy/spacy/tests/regression/test_issue3625.py
2019-09-29 17:32:12 +02:00

13 lines
417 B
Python

# coding: utf8
from __future__ import unicode_literals
from spacy.lang.hi import Hindi
def test_issue3625():
"""Test that default punctuation rules applies to hindi unicode characters"""
nlp = Hindi()
doc = nlp("hi. how हुए. होटल, होटल")
expected = ["hi", ".", "how", "हुए", ".", "होटल", ",", "होटल"]
assert [token.text for token in doc] == expected