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
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 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
with pytest.raises(ValueError):
nlp.to_bytes(meta=False)
with pytest.raises(ValueError):
Language().from_bytes(nlp.to_bytes(), meta=False)
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 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
with pytest.raises(ValueError):
nlp.to_bytes(meta=False)
with pytest.raises(ValueError):
Language().from_bytes(nlp.to_bytes(), meta=False)
def test_lemmatizer_reflects_lookups_changes():
"""Test for an issue that'd cause lookups available in a model loaded from
disk to not be reflected in the lemmatizer."""
nlp = Language()
assert Doc(nlp.vocab, words=["foo"])[0].lemma_ == "foo"
table = nlp.vocab.lookups.add_table("lemma_lookup")
table["foo"] = "bar"
assert Doc(nlp.vocab, words=["foo"])[0].lemma_ == "bar"
table = nlp.vocab.lookups.get_table("lemma_lookup")
table["hello"] = "world"
# The update to the table should be reflected in the lemmatizer
assert Doc(nlp.vocab, words=["hello"])[0].lemma_ == "world"
new_nlp = Language()
table = new_nlp.vocab.lookups.add_table("lemma_lookup")
table["hello"] = "hi"
assert Doc(new_nlp.vocab, words=["hello"])[0].lemma_ == "hi"
nlp_bytes = nlp.to_bytes()
new_nlp.from_bytes(nlp_bytes)
# Make sure we have the previously saved lookup table
assert len(new_nlp.vocab.lookups) == 1
assert len(new_nlp.vocab.lookups.get_table("lemma_lookup")) == 2
assert new_nlp.vocab.lookups.get_table("lemma_lookup")["hello"] == "world"
assert Doc(new_nlp.vocab, words=["foo"])[0].lemma_ == "bar"
assert Doc(new_nlp.vocab, words=["hello"])[0].lemma_ == "world"
