mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +03:00
7d50804644
* Migrate regressions 1-1000 * Move serialize test to correct file * Remove tests that won't work in v3 * Migrate regressions 1000-1500 Removed regression test 1250 because v3 doesn't support the old LEX scheme anymore. * Add missing imports in serializer tests * Migrate tests 1500-2000 * Migrate regressions from 2000-2500 * Migrate regressions from 2501-3000 * Migrate regressions from 3000-3501 * Migrate regressions from 3501-4000 * Migrate regressions from 4001-4500 * Migrate regressions from 4501-5000 * Migrate regressions from 5001-5501 * Migrate regressions from 5501 to 7000 * Migrate regressions from 7001 to 8000 * Migrate remaining regression tests * Fixing missing imports * Update docs with new system [ci skip] * Update CONTRIBUTING.md - Fix formatting - Update wording * Remove lemmatizer tests in el lang * Move a few tests into the general tokenizer * Separate Doc and DocBin tests
136 lines
3.5 KiB
Python
136 lines
3.5 KiB
Python
import re
|
|
import pickle
|
|
|
|
import pytest
|
|
|
|
from spacy.language import Language
|
|
from spacy.lang.it import Italian
|
|
from spacy.lang.en import English
|
|
from spacy.tokenizer import Tokenizer
|
|
from spacy.training import Example
|
|
from spacy.util import load_config_from_str
|
|
|
|
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},
|
|
}
|
|
|
|
|
|
@pytest.mark.issue(2482)
|
|
def test_issue2482():
|
|
"""Test we can serialize and deserialize a blank NER or parser model."""
|
|
nlp = Italian()
|
|
nlp.add_pipe("ner")
|
|
b = nlp.to_bytes()
|
|
Italian().from_bytes(b)
|
|
|
|
|
|
CONFIG_ISSUE_6950 = """
|
|
[nlp]
|
|
lang = "en"
|
|
pipeline = ["tok2vec", "tagger"]
|
|
|
|
[components]
|
|
|
|
[components.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[components.tok2vec.model]
|
|
@architectures = "spacy.Tok2Vec.v1"
|
|
|
|
[components.tok2vec.model.embed]
|
|
@architectures = "spacy.MultiHashEmbed.v1"
|
|
width = ${components.tok2vec.model.encode:width}
|
|
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
|
rows = [5000,2500,2500,2500]
|
|
include_static_vectors = false
|
|
|
|
[components.tok2vec.model.encode]
|
|
@architectures = "spacy.MaxoutWindowEncoder.v1"
|
|
width = 96
|
|
depth = 4
|
|
window_size = 1
|
|
maxout_pieces = 3
|
|
|
|
[components.ner]
|
|
factory = "ner"
|
|
|
|
[components.tagger]
|
|
factory = "tagger"
|
|
|
|
[components.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
nO = null
|
|
|
|
[components.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode:width}
|
|
upstream = "*"
|
|
"""
|
|
|
|
|
|
@pytest.mark.issue(6950)
|
|
def test_issue6950():
|
|
"""Test that the nlp object with initialized tok2vec with listeners pickles
|
|
correctly (and doesn't have lambdas).
|
|
"""
|
|
nlp = English.from_config(load_config_from_str(CONFIG_ISSUE_6950))
|
|
nlp.initialize(lambda: [Example.from_dict(nlp.make_doc("hello"), {"tags": ["V"]})])
|
|
pickle.dumps(nlp)
|
|
nlp("hello")
|
|
pickle.dumps(nlp)
|
|
|
|
|
|
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)
|
|
|
|
|
|
def test_serialize_language_exclude(meta_data):
|
|
name = "name-in-fixture"
|
|
nlp = Language(meta=meta_data)
|
|
assert nlp.meta["name"] == name
|
|
new_nlp = Language().from_bytes(nlp.to_bytes())
|
|
assert new_nlp.meta["name"] == name
|
|
new_nlp = Language().from_bytes(nlp.to_bytes(), exclude=["meta"])
|
|
assert not new_nlp.meta["name"] == name
|
|
new_nlp = Language().from_bytes(nlp.to_bytes(exclude=["meta"]))
|
|
assert not new_nlp.meta["name"] == name
|