2020-05-14 13:58:06 +03:00
|
|
|
# coding: utf-8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
|
|
def test_noun_chunks_is_parsed_de(de_tokenizer):
|
2020-05-21 15:14:01 +03:00
|
|
|
"""Test that noun_chunks raises Value Error for 'de' language if Doc is not parsed.
|
2020-05-14 13:58:06 +03:00
|
|
|
To check this test, we're constructing a Doc
|
2020-05-21 15:14:01 +03:00
|
|
|
with a new Vocab here and forcing is_parsed to 'False'
|
2020-05-14 13:58:06 +03:00
|
|
|
to make sure the noun chunks don't run.
|
|
|
|
"""
|
|
|
|
doc = de_tokenizer("Er lag auf seinem")
|
|
|
|
doc.is_parsed = False
|
|
|
|
with pytest.raises(ValueError):
|
|
|
|
list(doc.noun_chunks)
|