mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +03:00
c34420794a
* added support for nepali lang * added examples and test files * added spacy contributor agreement
19 lines
847 B
Python
19 lines
847 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
def test_ne_tokenizer_handlers_long_text(ne_tokenizer):
|
|
text = """मैले पाएको सर्टिफिकेटलाई म त बोक्रो सम्झन्छु र अभ्यास तब सुरु भयो, जब मैले कलेज पार गरेँ र जीवनको पढाइ सुरु गरेँ ।"""
|
|
tokens = ne_tokenizer(text)
|
|
assert len(tokens) == 24
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length",
|
|
[("समय जान कति पनि बेर लाग्दैन ।", 7), ("म ठूलो हुँदै थिएँ ।", 5)],
|
|
)
|
|
def test_ne_tokenizer_handles_cnts(ne_tokenizer, text, length):
|
|
tokens = ne_tokenizer(text)
|
|
assert len(tokens) == length |