mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
|
# coding: utf-8
|
||
|
|
"""Test that tokens are created correctly for whitespace."""
|
||
|
|
|
||
|
|
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
import pytest
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem ipsum"])
|
||
|
|
def test_tokenizer_splits_single_space(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert len(tokens) == 2
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem ipsum"])
|
||
|
|
def test_tokenizer_splits_double_space(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert len(tokens) == 3
|
||
|
|
assert tokens[1].text == " "
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem ipsum "])
|
||
|
|
def test_tokenizer_handles_double_trainling_ws(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert repr(tokens.text_with_ws) == repr(text)
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem\nipsum"])
|
||
|
|
def test_tokenizer_splits_newline(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert len(tokens) == 3
|
||
|
|
assert tokens[1].text == "\n"
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem \nipsum"])
|
||
|
|
def test_tokenizer_splits_newline_space(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert len(tokens) == 3
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem \nipsum"])
|
||
|
|
def test_tokenizer_splits_newline_double_space(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert len(tokens) == 3
|
||
|
|
|
||
|
|
|
||
|
|
@pytest.mark.parametrize('text', ["lorem \n ipsum"])
|
||
|
|
def test_tokenizer_splits_newline_space_wrap(tokenizer, text):
|
||
|
|
tokens = tokenizer(text)
|
||
|
|
assert len(tokens) == 3
|