spaCy/spacy/tests/serialize/test_serialize_tokenizer.py

64 lines
2.4 KiB
Python
Raw Normal View History

2017-06-03 14:26:34 +03:00
# coding: utf-8
from __future__ import unicode_literals
import pytest
import re
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
from spacy.util import get_lang_class
from spacy.tokenizer import Tokenizer
from ..util import make_tempdir, assert_packed_msg_equal
2017-06-03 14:26:34 +03:00
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 or empty
properties can be serialized and deserialized correctly (see #2494,
#4991)."""
tokenizer = Tokenizer(en_vocab, suffix_search=en_tokenizer.suffix_search)
tokenizer_bytes = tokenizer.to_bytes()
2018-11-30 19:43:08 +03:00
Tokenizer(en_vocab).from_bytes(tokenizer_bytes)
# test that empty/unset values are set correctly on deserialization
tokenizer = get_lang_class("en").Defaults.create_tokenizer()
tokenizer.token_match = re.compile("test").match
assert tokenizer.rules != {}
assert tokenizer.token_match is not None
assert tokenizer.url_match is not None
tokenizer.from_bytes(tokenizer_bytes)
assert tokenizer.rules == {}
assert tokenizer.token_match is None
assert tokenizer.url_match is None
2020-03-25 14:28:12 +03:00
tokenizer = Tokenizer(en_vocab, rules={"ABC.": [{"ORTH": "ABC"}, {"ORTH": "."}]})
tokenizer.rules = {}
tokenizer_bytes = tokenizer.to_bytes()
tokenizer_reloaded = Tokenizer(en_vocab).from_bytes(tokenizer_bytes)
assert tokenizer_reloaded.rules == {}
2018-07-06 13:40:28 +03:00
@pytest.mark.skip(reason="Currently unreliable across platforms")
@pytest.mark.parametrize("text", ["I💜you", "theyre", "“hello”"])
2017-06-03 14:26:34 +03:00
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())
2018-07-06 13:40:28 +03:00
assert new_tokenizer.to_bytes() == tokenizer.to_bytes()
doc1 = tokenizer(text)
2017-06-03 14:26:34 +03:00
doc2 = new_tokenizer(text)
assert [token.text for token in doc1] == [token.text for token in doc2]
2018-07-06 13:40:28 +03:00
@pytest.mark.skip(reason="Currently unreliable across platforms")
2017-06-03 14:26:34 +03:00
def test_serialize_tokenizer_roundtrip_disk(en_tokenizer):
tokenizer = en_tokenizer
with make_tempdir() as d:
file_path = d / "tokenizer"
2017-06-03 14:26:34 +03:00
tokenizer.to_disk(file_path)
tokenizer_d = en_tokenizer.from_disk(file_path)
assert tokenizer.to_bytes() == tokenizer_d.to_bytes()