2018-05-15 01:27:19 +03:00
|
|
|
# coding: utf-8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
2018-07-25 00:38:44 +03:00
|
|
|
@pytest.mark.parametrize('text', ["ق.م", "إلخ", "ص.ب", "ت."])
|
2018-05-15 01:27:19 +03:00
|
|
|
def test_ar_tokenizer_handles_abbr(ar_tokenizer, text):
|
|
|
|
tokens = ar_tokenizer(text)
|
|
|
|
assert len(tokens) == 1
|
|
|
|
|
|
|
|
|
|
|
|
def test_ar_tokenizer_handles_exc_in_text(ar_tokenizer):
|
2018-07-25 00:38:44 +03:00
|
|
|
text = "تعود الكتابة الهيروغليفية إلى سنة 3200 ق.م"
|
2018-05-15 01:27:19 +03:00
|
|
|
tokens = ar_tokenizer(text)
|
|
|
|
assert len(tokens) == 7
|
|
|
|
assert tokens[6].text == "ق.م"
|
|
|
|
assert tokens[6].lemma_ == "قبل الميلاد"
|
|
|
|
|
|
|
|
|
|
|
|
def test_ar_tokenizer_handles_exc_in_text(ar_tokenizer):
|
2018-07-25 00:38:44 +03:00
|
|
|
text = "يبلغ طول مضيق طارق 14كم "
|
2018-05-15 01:27:19 +03:00
|
|
|
tokens = ar_tokenizer(text)
|
|
|
|
assert len(tokens) == 6
|