mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
cf65a80f36
* Move test * Allow default in Lookups.get_table * Start with blank tables in Lookups.from_bytes * Refactor lemmatizer to hold instance of Lookups * Get lookups table within the lemmatization methods to make sure it references the correct table (even if the table was replaced or modified, e.g. when loading a model from disk) * Deprecate other arguments on Lemmatizer.__init__ and expect Lookups for consistency * Remove old and unsupported Lemmatizer.load classmethod * Refactor language-specific lemmatizers to inherit as much as possible from base class and override only what they need * Update tests and docs * Fix more tests * Fix lemmatizer * Upgrade pytest to try and fix weird CI errors * Try pytest 4.6.5
41 lines
935 B
Python
41 lines
935 B
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.vocab import Vocab
|
|
from spacy.tokens import Doc
|
|
from spacy.lemmatizer import Lemmatizer
|
|
from spacy.lookups import Lookups
|
|
|
|
|
|
@pytest.fixture
|
|
def lemmatizer():
|
|
lookups = Lookups()
|
|
lookups.add_table("lemma_lookup", {"dogs": "dog", "boxen": "box", "mice": "mouse"})
|
|
return Lemmatizer(lookups)
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab(lemmatizer):
|
|
return Vocab(lemmatizer=lemmatizer)
|
|
|
|
|
|
def test_empty_doc(vocab):
|
|
doc = Doc(vocab)
|
|
assert len(doc) == 0
|
|
|
|
|
|
def test_single_word(vocab):
|
|
doc = Doc(vocab, words=["a"])
|
|
assert doc.text == "a "
|
|
doc = Doc(vocab, words=["a"], spaces=[False])
|
|
assert doc.text == "a"
|
|
|
|
|
|
def test_lookup_lemmatization(vocab):
|
|
doc = Doc(vocab, words=["dogs", "dogses"])
|
|
assert doc[0].text == "dogs"
|
|
assert doc[0].lemma_ == "dog"
|
|
assert doc[1].text == "dogses"
|
|
assert doc[1].lemma_ == "dogses"
|