spaCy/spacy/tests/conftest.py
Adriane Boyd e962784531
Add Lemmatizer and simplify related components (#5848)
* Add Lemmatizer and simplify related components

* Add `Lemmatizer` pipe with `lookup` and `rule` modes using the
`Lookups` tables.
* Reduce `Tagger` to a simple tagger that sets `Token.tag` (no pos or lemma)
* Reduce `Morphology` to only keep track of morph tags (no tag map, lemmatizer,
or morph rules)
* Remove lemmatizer from `Vocab`
* Adjust many many tests

Differences:

* No default lookup lemmas
* No special treatment of TAG in `from_array` and similar required
* Easier to modify labels in a `Tagger`
* No extra strings added from morphology / tag map

* Fix test

* Initial fix for Lemmatizer config/serialization

* Adjust init test to be more generic

* Adjust init test to force empty Lookups

* Add simple cache to rule-based lemmatizer

* Convert language-specific lemmatizers

Convert language-specific lemmatizers to component lemmatizers. Remove
previous lemmatizer class.

* Fix French and Polish lemmatizers

* Remove outdated UPOS conversions

* Update Russian lemmatizer init in tests

* Add minimal init/run tests for custom lemmatizers

* Add option to overwrite existing lemmas

* Update mode setting, lookup loading, and caching

* Make `mode` an immutable property
* Only enforce strict `load_lookups` for known supported modes
* Move caching into individual `_lemmatize` methods

* Implement strict when lang is not found in lookups

* Fix tables/lookups in make_lemmatizer

* Reallow provided lookups and allow for stricter checks

* Add lookups asset to all Lemmatizer pipe tests

* Rename lookups in lemmatizer init test

* Clean up merge

* Refactor lookup table loading

* Add helper from `load_lemmatizer_lookups` that loads required and
optional lookups tables based on settings provided by a config.

Additional slight refactor of lookups:

* Add `Lookups.set_table` to set a table from a provided `Table`
* Reorder class definitions to be able to specify type as `Table`

* Move registry assets into test methods

* Refactor lookups tables config

Use class methods within `Lemmatizer` to provide the config for
particular modes and to load the lookups from a config.

* Add pipe and score to lemmatizer

* Simplify Tagger.score

* Add missing import

* Clean up imports and auto-format

* Remove unused kwarg

* Tidy up and auto-format

* Update docstrings for Lemmatizer

Update docstrings for Lemmatizer.

Additionally modify `is_base_form` API to take `Token` instead of
individual features.

* Update docstrings

* Remove tag map values from Tagger.add_label

* Update API docs

* Fix relative link in Lemmatizer API docs
2020-08-07 15:27:13 +02:00

282 lines
6.1 KiB
Python

import pytest
from spacy.util import get_lang_class
def pytest_addoption(parser):
parser.addoption("--slow", action="store_true", help="include slow tests")
def pytest_runtest_setup(item):
def getopt(opt):
# When using 'pytest --pyargs spacy' to test an installed copy of
# spacy, pytest skips running our pytest_addoption() hook. Later, when
# we call getoption(), pytest raises an error, because it doesn't
# recognize the option we're asking about. To avoid this, we need to
# pass a default value. We default to False, i.e., we act like all the
# options weren't given.
return item.config.getoption(f"--{opt}", False)
for opt in ["slow"]:
if opt in item.keywords and not getopt(opt):
pytest.skip(f"need --{opt} option to run")
# Fixtures for language tokenizers (languages sorted alphabetically)
@pytest.fixture(scope="module")
def tokenizer():
return get_lang_class("xx")().tokenizer
@pytest.fixture(scope="session")
def ar_tokenizer():
return get_lang_class("ar")().tokenizer
@pytest.fixture(scope="session")
def bn_tokenizer():
return get_lang_class("bn")().tokenizer
@pytest.fixture(scope="session")
def ca_tokenizer():
return get_lang_class("ca")().tokenizer
@pytest.fixture(scope="session")
def da_tokenizer():
return get_lang_class("da")().tokenizer
@pytest.fixture(scope="session")
def de_tokenizer():
return get_lang_class("de")().tokenizer
@pytest.fixture(scope="session")
def el_tokenizer():
return get_lang_class("el")().tokenizer
@pytest.fixture(scope="session")
def en_tokenizer():
return get_lang_class("en")().tokenizer
@pytest.fixture(scope="session")
def en_vocab():
return get_lang_class("en")().vocab
@pytest.fixture(scope="session")
def en_parser(en_vocab):
nlp = get_lang_class("en")(en_vocab)
return nlp.create_pipe("parser")
@pytest.fixture(scope="session")
def es_tokenizer():
return get_lang_class("es")().tokenizer
@pytest.fixture(scope="session")
def eu_tokenizer():
return get_lang_class("eu")().tokenizer
@pytest.fixture(scope="session")
def fa_tokenizer():
return get_lang_class("fa")().tokenizer
@pytest.fixture(scope="session")
def fi_tokenizer():
return get_lang_class("fi")().tokenizer
@pytest.fixture(scope="session")
def fr_tokenizer():
return get_lang_class("fr")().tokenizer
@pytest.fixture(scope="session")
def ga_tokenizer():
return get_lang_class("ga")().tokenizer
@pytest.fixture(scope="session")
def gu_tokenizer():
return get_lang_class("gu")().tokenizer
@pytest.fixture(scope="session")
def he_tokenizer():
return get_lang_class("he")().tokenizer
@pytest.fixture(scope="session")
def hr_tokenizer():
return get_lang_class("hr")().tokenizer
@pytest.fixture
def hu_tokenizer():
return get_lang_class("hu")().tokenizer
@pytest.fixture(scope="session")
def id_tokenizer():
return get_lang_class("id")().tokenizer
@pytest.fixture(scope="session")
def it_tokenizer():
return get_lang_class("it")().tokenizer
@pytest.fixture(scope="session")
def ja_tokenizer():
pytest.importorskip("sudachipy")
return get_lang_class("ja")().tokenizer
@pytest.fixture(scope="session")
def ko_tokenizer():
pytest.importorskip("natto")
return get_lang_class("ko")().tokenizer
@pytest.fixture(scope="session")
def lb_tokenizer():
return get_lang_class("lb")().tokenizer
@pytest.fixture(scope="session")
def lt_tokenizer():
return get_lang_class("lt")().tokenizer
@pytest.fixture(scope="session")
def ml_tokenizer():
return get_lang_class("ml")().tokenizer
@pytest.fixture(scope="session")
def nb_tokenizer():
return get_lang_class("nb")().tokenizer
@pytest.fixture(scope="session")
def ne_tokenizer():
return get_lang_class("ne")().tokenizer
@pytest.fixture(scope="session")
def nl_tokenizer():
return get_lang_class("nl")().tokenizer
@pytest.fixture(scope="session")
def pl_tokenizer():
return get_lang_class("pl")().tokenizer
@pytest.fixture(scope="session")
def pt_tokenizer():
return get_lang_class("pt")().tokenizer
@pytest.fixture(scope="session")
def ro_tokenizer():
return get_lang_class("ro")().tokenizer
@pytest.fixture(scope="session")
def ru_tokenizer():
pytest.importorskip("pymorphy2")
return get_lang_class("ru")().tokenizer
@pytest.fixture
def ru_lemmatizer():
pytest.importorskip("pymorphy2")
return get_lang_class("ru")().add_pipe("lemmatizer")
@pytest.fixture(scope="session")
def sr_tokenizer():
return get_lang_class("sr")().tokenizer
@pytest.fixture(scope="session")
def sv_tokenizer():
return get_lang_class("sv")().tokenizer
@pytest.fixture(scope="session")
def th_tokenizer():
pytest.importorskip("pythainlp")
return get_lang_class("th")().tokenizer
@pytest.fixture(scope="session")
def tr_tokenizer():
return get_lang_class("tr")().tokenizer
@pytest.fixture(scope="session")
def tt_tokenizer():
return get_lang_class("tt")().tokenizer
@pytest.fixture(scope="session")
def uk_tokenizer():
pytest.importorskip("pymorphy2")
pytest.importorskip("pymorphy2.lang")
return get_lang_class("uk")().tokenizer
@pytest.fixture(scope="session")
def ur_tokenizer():
return get_lang_class("ur")().tokenizer
@pytest.fixture(scope="session")
def yo_tokenizer():
return get_lang_class("yo")().tokenizer
@pytest.fixture(scope="session")
def zh_tokenizer_char():
nlp = get_lang_class("zh")()
return nlp.tokenizer
@pytest.fixture(scope="session")
def zh_tokenizer_jieba():
pytest.importorskip("jieba")
config = {
"@tokenizers": "spacy.zh.ChineseTokenizer",
"segmenter": "jieba",
}
nlp = get_lang_class("zh").from_config({"nlp": {"tokenizer": config}})
return nlp.tokenizer
@pytest.fixture(scope="session")
def zh_tokenizer_pkuseg():
pytest.importorskip("pkuseg")
config = {
"@tokenizers": "spacy.zh.ChineseTokenizer",
"segmenter": "pkuseg",
"pkuseg_model": "default",
}
nlp = get_lang_class("zh").from_config({"nlp": {"tokenizer": config}})
return nlp.tokenizer
@pytest.fixture(scope="session")
def hy_tokenizer():
return get_lang_class("hy")().tokenizer