1#@!#!123s

: / proc / 2 / root / usr / local / lib64 / python3.6 / site-packages / spacy / tests / regression /

Filename : test_issue3625.py

back

# 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