mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
61ce126d4c
* initial LT lang support * Added more stopwords. Started setting up some basic test environment (not complete) * Initial morph rules for LT lang * Closes #1 Adds tokenizer exceptions for Lithuanian * Closes #5 Punctuation rules. Closes #6 Lexical Attributes * test: add native examples to basic tests * feat: add tag map for lt lang * fix: remove undefined tag attribute 'Definite' * feat: add lemmatizer for lt lang * refactor: add new instances to lt lang morph rules; use tags from tag map * refactor: add morph rules to lt lang defaults * refactor: only keep nouns, verbs, adverbs and adjectives in lt lang lemmatizer lookup * refactor: add capitalized words to lt lang lemmatizer * refactor: add more num words to lt lang lex attrs * refactor: update lt lang stop word set * refactor: add new instances to lt lang tokenizer exceptions * refactor: remove comments form lt lang init file * refactor: use function instead of lambda in lt lex lang getter * refactor: remove conversion to dict in lt init when dict is already provided * chore: rename lt 'test_basic' to 'test_text' * feat: add more lt text tests * feat: add lemmatizer tests * refactor: remove unused imports, add newline to end of file * chore: add contributor agreement * chore: change 'en' to 'lt' in lt example description * fix: add missing encoding info * style: add newline to end of file * refactor: use python2 compatible syntax * style: reformat code using black
204 lines
4.9 KiB
Python
204 lines
4.9 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
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("--%s" % opt, False)
|
|
|
|
for opt in ["slow"]:
|
|
if opt in item.keywords and not getopt(opt):
|
|
pytest.skip("need --%s option to run" % opt)
|
|
|
|
|
|
# Fixtures for language tokenizers (languages sorted alphabetically)
|
|
|
|
|
|
@pytest.fixture(scope="module")
|
|
def tokenizer():
|
|
return get_lang_class("xx").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ar_tokenizer():
|
|
return get_lang_class("ar").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def bn_tokenizer():
|
|
return get_lang_class("bn").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ca_tokenizer():
|
|
return get_lang_class("ca").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def da_tokenizer():
|
|
return get_lang_class("da").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def de_tokenizer():
|
|
return get_lang_class("de").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def el_tokenizer():
|
|
return get_lang_class("el").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def en_tokenizer():
|
|
return get_lang_class("en").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def en_vocab():
|
|
return get_lang_class("en").Defaults.create_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").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def fi_tokenizer():
|
|
return get_lang_class("fi").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def fr_tokenizer():
|
|
return get_lang_class("fr").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ga_tokenizer():
|
|
return get_lang_class("ga").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def he_tokenizer():
|
|
return get_lang_class("he").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture
|
|
def hu_tokenizer():
|
|
return get_lang_class("hu").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def id_tokenizer():
|
|
return get_lang_class("id").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def it_tokenizer():
|
|
return get_lang_class("it").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ja_tokenizer():
|
|
pytest.importorskip("MeCab")
|
|
return get_lang_class("ja").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def lt_tokenizer():
|
|
return get_lang_class("lt").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def lt_lemmatizer():
|
|
return get_lang_class("lt").Defaults.create_lemmatizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def nb_tokenizer():
|
|
return get_lang_class("nb").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def nl_tokenizer():
|
|
return get_lang_class("nl").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture
|
|
def nl_lemmatizer(scope="session"):
|
|
return get_lang_class("nl").Defaults.create_lemmatizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def pl_tokenizer():
|
|
return get_lang_class("pl").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def pt_tokenizer():
|
|
return get_lang_class("pt").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ro_tokenizer():
|
|
return get_lang_class("ro").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ru_tokenizer():
|
|
pytest.importorskip("pymorphy2")
|
|
return get_lang_class("ru").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def sv_tokenizer():
|
|
return get_lang_class("sv").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def th_tokenizer():
|
|
pytest.importorskip("pythainlp")
|
|
return get_lang_class("th").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def tr_tokenizer():
|
|
return get_lang_class("tr").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def tt_tokenizer():
|
|
return get_lang_class("tt").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def uk_tokenizer():
|
|
pytest.importorskip("pymorphy2")
|
|
pytest.importorskip("pymorphy2.lang")
|
|
return get_lang_class("uk").Defaults.create_tokenizer()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def ur_tokenizer():
|
|
return get_lang_class("ur").Defaults.create_tokenizer()
|