spaCy/spacy/tests/serialize/test_serialize_tokenizer.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* Remove unicode declarations

* Remove Python 3.5 and 2.7 from CI

* Don't require pathlib

* Replace compat helpers

* Remove OrderedDict

* Use f-strings

* Set Cython compiler language level

* Fix typo

* Re-add OrderedDict for Table

* Update setup.cfg

* Revert CONTRIBUTING.md

* Revert lookups.md

* Revert top-level.md

* Small adjustments and docs [ci skip]
2019-12-22 01:53:56 +01:00

42 lines
1.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import pytest
from spacy.util import get_lang_class
from spacy.tokenizer import Tokenizer
from ..util import make_tempdir, assert_packed_msg_equal
def load_tokenizer(b):
tok = get_lang_class("en").Defaults.create_tokenizer()
tok.from_bytes(b)
return tok
def test_serialize_custom_tokenizer(en_vocab, en_tokenizer):
"""Test that custom tokenizer with not all functions defined can be
serialized and deserialized correctly (see #2494)."""
tokenizer = Tokenizer(en_vocab, suffix_search=en_tokenizer.suffix_search)
tokenizer_bytes = tokenizer.to_bytes()
Tokenizer(en_vocab).from_bytes(tokenizer_bytes)
@pytest.mark.skip(reason="Currently unreliable across platforms")
@pytest.mark.parametrize("text", ["I💜you", "theyre", "“hello”"])
def test_serialize_tokenizer_roundtrip_bytes(en_tokenizer, text):
tokenizer = en_tokenizer
new_tokenizer = load_tokenizer(tokenizer.to_bytes())
assert_packed_msg_equal(new_tokenizer.to_bytes(), tokenizer.to_bytes())
assert new_tokenizer.to_bytes() == tokenizer.to_bytes()
doc1 = tokenizer(text)
doc2 = new_tokenizer(text)
assert [token.text for token in doc1] == [token.text for token in doc2]
@pytest.mark.skip(reason="Currently unreliable across platforms")
def test_serialize_tokenizer_roundtrip_disk(en_tokenizer):
tokenizer = en_tokenizer
with make_tempdir() as d:
file_path = d / "tokenizer"
tokenizer.to_disk(file_path)
tokenizer_d = en_tokenizer.from_disk(file_path)
assert tokenizer.to_bytes() == tokenizer_d.to_bytes()