spaCy/spacy/tests/regression/test_issue3625.py

# 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(u"hi. how हुए. होटल, होटल")
    assert [token.text for token in doc] == ['hi', '.', 'how', 'हुए', '.', 'होटल', ',', 'होटल']
Add default encoding utf-8 for test file 2019-07-11 12:56:27 +03:00			`# coding: utf8`
Add test file for issue (#3625) and spacy contributor agreement 2019-07-11 12:23:14 +03:00			`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(u"hi. how हुए. होटल, होटल")`
			`assert [token.text for token in doc] == ['hi', '.', 'how', 'हुए', '.', 'होटल', ',', 'होटल']`