mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
b6e991440c
* Auto-format tests with black * Add flake8 config * Tidy up and remove unused imports * Fix redefinitions of test functions * Replace orths_and_spaces with words and spaces * Fix compatibility with pytest 4.0 * xfail test for now Test was previously overwritten by following test due to naming conflict, so failure wasn't reported * Unfail passing test * Only use fixture via arguments Fixes pytest 4.0 compatibility
55 lines
1.5 KiB
Python
55 lines
1.5 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
import re
|
|
from spacy.language import Language
|
|
from spacy.tokenizer import Tokenizer
|
|
|
|
from ..util import make_tempdir
|
|
|
|
|
|
@pytest.fixture
|
|
def meta_data():
|
|
return {
|
|
"name": "name-in-fixture",
|
|
"version": "version-in-fixture",
|
|
"description": "description-in-fixture",
|
|
"author": "author-in-fixture",
|
|
"email": "email-in-fixture",
|
|
"url": "url-in-fixture",
|
|
"license": "license-in-fixture",
|
|
"vectors": {"width": 0, "vectors": 0, "keys": 0, "name": None},
|
|
}
|
|
|
|
|
|
def test_serialize_language_meta_disk(meta_data):
|
|
language = Language(meta=meta_data)
|
|
with make_tempdir() as d:
|
|
language.to_disk(d)
|
|
new_language = Language().from_disk(d)
|
|
assert new_language.meta == language.meta
|
|
|
|
|
|
def test_serialize_with_custom_tokenizer():
|
|
"""Test that serialization with custom tokenizer works without token_match.
|
|
See: https://support.prodi.gy/t/how-to-save-a-custom-tokenizer/661/2
|
|
"""
|
|
prefix_re = re.compile(r"""1/|2/|:[0-9][0-9][A-K]:|:[0-9][0-9]:""")
|
|
suffix_re = re.compile(r"""""")
|
|
infix_re = re.compile(r"""[~]""")
|
|
|
|
def custom_tokenizer(nlp):
|
|
return Tokenizer(
|
|
nlp.vocab,
|
|
{},
|
|
prefix_search=prefix_re.search,
|
|
suffix_search=suffix_re.search,
|
|
infix_finditer=infix_re.finditer,
|
|
)
|
|
|
|
nlp = Language()
|
|
nlp.tokenizer = custom_tokenizer(nlp)
|
|
with make_tempdir() as d:
|
|
nlp.to_disk(d)
|