mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +03:00
46 lines
1.3 KiB
Python
46 lines
1.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
def test_sa_tokenizer_handles_long_text(sa_tokenizer):
|
|
text = """नानाविधानि दिव्यानि नानावर्णाकृतीनि च।।"""
|
|
tokens = sa_tokenizer(text)
|
|
assert len(tokens) == 6
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,length",
|
|
[
|
|
("श्री भगवानुवाच पश्य मे पार्थ रूपाणि शतशोऽथ सहस्रशः।", 9,),
|
|
("गुणान् सर्वान् स्वभावो मूर्ध्नि वर्तते ।", 6),
|
|
],
|
|
)
|
|
def test_sa_tokenizer_handles_cnts(sa_tokenizer, text, length):
|
|
tokens = sa_tokenizer(text)
|
|
assert len(tokens) == length
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"text,match",
|
|
[
|
|
("10", True),
|
|
("1", True),
|
|
("10.000", True),
|
|
("1000", True),
|
|
("999,0", True),
|
|
("एकः ", True),
|
|
("दश", True),
|
|
("पञ्चदश", True),
|
|
("चत्वारिंशत् ", True),
|
|
("कूपे", False),
|
|
(",", False),
|
|
("1/2", True),
|
|
],
|
|
)
|
|
def test_lex_attrs_like_number(sa_tokenizer, text, match):
|
|
tokens = sa_tokenizer(text)
|
|
assert len(tokens) == 1
|
|
assert tokens[0].like_num == match
|