mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
47 lines
1.1 KiB
Python
47 lines
1.1 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def open_puncts():
|
|
return ['(', '[', '{', '*']
|
|
|
|
|
|
def test_open(open_puncts, en_tokenizer):
|
|
word_str = 'Hello'
|
|
for p in open_puncts:
|
|
string = p + word_str
|
|
tokens = en_tokenizer(string)
|
|
assert len(tokens) == 2
|
|
assert tokens[0].orth_ == p
|
|
assert tokens[1].orth_ == word_str
|
|
|
|
|
|
def test_two_different_open(open_puncts, en_tokenizer):
|
|
word_str = 'Hello'
|
|
for p in open_puncts:
|
|
string = p + "`" + word_str
|
|
tokens = en_tokenizer(string)
|
|
assert len(tokens) == 3
|
|
assert tokens[0].orth_ == p
|
|
assert tokens[1].orth_ == "`"
|
|
assert tokens[2].orth_ == word_str
|
|
|
|
|
|
def test_three_same_open(open_puncts, en_tokenizer):
|
|
word_str = 'Hello'
|
|
for p in open_puncts:
|
|
string = p + p + p + word_str
|
|
tokens = en_tokenizer(string)
|
|
assert len(tokens) == 4
|
|
assert tokens[0].orth_ == p
|
|
assert tokens[3].orth_ == word_str
|
|
|
|
|
|
def test_open_appostrophe(en_tokenizer):
|
|
string = "'The"
|
|
tokens = en_tokenizer(string)
|
|
assert len(tokens) == 2
|
|
assert tokens[0].orth_ == "'"
|