2017-01-11 12:56:32 +00:00
|
|
|
import pytest
|
2018-07-24 21:38:44 +00:00
|
|
|
from spacy.util import get_lang_class
|
2017-01-11 12:56:32 +00:00
|
|
|
|
2017-11-21 19:23:59 +00:00
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
def pytest_addoption(parser):
|
|
|
|
|
parser.addoption("--slow", action="store_true", help="include slow tests")
|
2018-07-13 08:55:14 +00:00
|
|
|
|
2017-11-21 19:23:59 +00:00
|
|
|
|
2019-02-14 12:27:13 +00:00
|
|
|
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.
|
2019-12-25 16:59:52 +00:00
|
|
|
return item.config.getoption(f"--{opt}", False)
|
2019-02-14 12:27:13 +00:00
|
|
|
|
|
|
|
|
for opt in ["slow"]:
|
|
|
|
|
if opt in item.keywords and not getopt(opt):
|
2019-12-25 16:59:52 +00:00
|
|
|
pytest.skip(f"need --{opt} option to run")
|
2019-02-14 12:27:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# Fixtures for language tokenizers (languages sorted alphabetically)
|
|
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="module")
|
2017-06-05 00:26:13 +00:00
|
|
|
def tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("xx")().tokenizer
|
2017-01-11 12:56:32 +00:00
|
|
|
|
|
|
|
|
|
2020-12-22 15:50:34 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def am_tokenizer():
|
2021-01-14 09:49:30 +00:00
|
|
|
return get_lang_class("am")().tokenizer
|
2017-01-11 12:56:32 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def ar_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ar")().tokenizer
|
2015-06-07 15:53:14 +00:00
|
|
|
|
2016-09-26 09:57:54 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def bn_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("bn")().tokenizer
|
2017-01-11 12:56:32 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def ca_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ca")().tokenizer
|
2017-05-08 22:02:21 +00:00
|
|
|
|
2017-01-11 20:29:59 +00:00
|
|
|
|
2020-08-21 15:06:33 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def cs_tokenizer():
|
2020-09-04 12:05:55 +00:00
|
|
|
return get_lang_class("cs")().tokenizer
|
2020-08-21 15:06:33 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def da_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("da")().tokenizer
|
2017-04-06 16:48:45 +00:00
|
|
|
|
2017-01-11 20:29:59 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2017-01-11 12:56:32 +00:00
|
|
|
def de_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("de")().tokenizer
|
2017-01-11 12:56:32 +00:00
|
|
|
|
|
|
|
|
|
2020-09-21 18:43:54 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def de_vocab():
|
|
|
|
|
return get_lang_class("de")().vocab
|
2017-01-11 12:56:32 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def el_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("el")().tokenizer
|
2017-01-11 12:56:32 +00:00
|
|
|
|
2017-01-12 15:49:19 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def en_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("en")().tokenizer
|
2017-02-04 11:47:29 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def en_vocab():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("en")().vocab
|
2018-05-12 13:20:04 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def en_parser(en_vocab):
|
|
|
|
|
nlp = get_lang_class("en")(en_vocab)
|
|
|
|
|
return nlp.create_pipe("parser")
|
2017-02-04 11:47:29 +00:00
|
|
|
|
2017-10-14 11:11:18 +00:00
|
|
|
|
2019-02-04 21:39:25 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def es_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("es")().tokenizer
|
2019-02-04 21:39:25 +00:00
|
|
|
|
|
|
|
|
|
2020-03-04 06:58:56 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def eu_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("eu")().tokenizer
|
2020-03-04 06:58:56 +00:00
|
|
|
|
|
|
|
|
|
2020-05-14 10:58:06 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def fa_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("fa")().tokenizer
|
2020-05-14 10:58:06 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def fi_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("fi")().tokenizer
|
2017-02-04 14:21:34 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def fr_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("fr")().tokenizer
|
2017-03-05 01:11:26 +00:00
|
|
|
|
2017-10-31 14:50:13 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2017-09-11 09:31:41 +00:00
|
|
|
def ga_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ga")().tokenizer
|
2017-09-11 09:31:41 +00:00
|
|
|
|
2017-04-06 16:48:45 +00:00
|
|
|
|
2020-04-27 09:07:37 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def gu_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("gu")().tokenizer
|
2020-04-27 09:07:37 +00:00
|
|
|
|
2020-05-21 12:14:01 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2017-03-24 15:27:44 +00:00
|
|
|
def he_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("he")().tokenizer
|
2017-03-24 15:27:44 +00:00
|
|
|
|
2017-10-14 11:11:18 +00:00
|
|
|
|
2020-10-07 08:23:32 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def hi_tokenizer():
|
2020-10-15 07:29:15 +00:00
|
|
|
return get_lang_class("hi")().tokenizer
|
2020-10-07 08:23:32 +00:00
|
|
|
|
|
|
|
|
|
2019-09-08 11:40:45 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def hr_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("hr")().tokenizer
|
2019-09-08 11:40:45 +00:00
|
|
|
|
|
|
|
|
|
2019-02-14 12:27:13 +00:00
|
|
|
@pytest.fixture
|
|
|
|
|
def hu_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("hu")().tokenizer
|
2019-02-14 12:27:13 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def id_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("id")().tokenizer
|
2017-05-08 22:02:21 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def it_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("it")().tokenizer
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2017-03-24 15:27:44 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2017-10-14 11:11:39 +00:00
|
|
|
def ja_tokenizer():
|
2020-06-11 08:23:50 +00:00
|
|
|
pytest.importorskip("sudachipy")
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ja")().tokenizer
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2017-10-14 11:11:39 +00:00
|
|
|
|
2019-07-09 20:23:16 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def ko_tokenizer():
|
|
|
|
|
pytest.importorskip("natto")
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ko")().tokenizer
|
2019-07-09 20:23:16 +00:00
|
|
|
|
2019-10-18 09:27:38 +00:00
|
|
|
|
2019-10-14 10:27:50 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def lb_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("lb")().tokenizer
|
2019-10-18 09:27:38 +00:00
|
|
|
|
|
|
|
|
|
2019-07-08 08:25:22 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def lt_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("lt")().tokenizer
|
2020-10-15 13:55:01 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def mk_tokenizer():
|
2020-11-25 09:33:49 +00:00
|
|
|
return get_lang_class("mk")().tokenizer
|
2019-07-08 08:25:22 +00:00
|
|
|
|
|
|
|
|
|
2020-04-27 07:45:08 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def ml_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ml")().tokenizer
|
2020-04-27 07:45:08 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def nb_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("nb")().tokenizer
|
2017-09-26 14:36:27 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2020-06-22 08:25:46 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def ne_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ne")().tokenizer
|
2020-06-22 08:25:46 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def nl_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("nl")().tokenizer
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2017-12-01 14:04:32 +00:00
|
|
|
|
2019-02-07 20:10:08 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def pl_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("pl")().tokenizer
|
2019-02-07 20:05:11 +00:00
|
|
|
|
2018-11-26 14:25:47 +00:00
|
|
|
|
2018-11-30 16:43:08 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def pt_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("pt")().tokenizer
|
💫 Port master changes over to develop (#2979)
* Create aryaprabhudesai.md (#2681)
* Update _install.jade (#2688)
Typo fix: "models" -> "model"
* Add FAC to spacy.explain (resolves #2706)
* Remove docstrings for deprecated arguments (see #2703)
* When calling getoption() in conftest.py, pass a default option (#2709)
* When calling getoption() in conftest.py, pass a default option
This is necessary to allow testing an installed spacy by running:
pytest --pyargs spacy
* Add contributor agreement
* update bengali token rules for hyphen and digits (#2731)
* Less norm computations in token similarity (#2730)
* Less norm computations in token similarity
* Contributor agreement
* Remove ')' for clarity (#2737)
Sorry, don't mean to be nitpicky, I just noticed this when going through the CLI and thought it was a quick fix. That said, if this was intention than please let me know.
* added contributor agreement for mbkupfer (#2738)
* Basic support for Telugu language (#2751)
* Lex _attrs for polish language (#2750)
* Signed spaCy contributor agreement
* Added polish version of english lex_attrs
* Introduces a bulk merge function, in order to solve issue #653 (#2696)
* Fix comment
* Introduce bulk merge to increase performance on many span merges
* Sign contributor agreement
* Implement pull request suggestions
* Describe converters more explicitly (see #2643)
* Add multi-threading note to Language.pipe (resolves #2582) [ci skip]
* Fix formatting
* Fix dependency scheme docs (closes #2705) [ci skip]
* Don't set stop word in example (closes #2657) [ci skip]
* Add words to portuguese language _num_words (#2759)
* Add words to portuguese language _num_words
* Add words to portuguese language _num_words
* Update Indonesian model (#2752)
* adding e-KTP in tokenizer exceptions list
* add exception token
* removing lines with containing space as it won't matter since we use .split() method in the end, added new tokens in exception
* add tokenizer exceptions list
* combining base_norms with norm_exceptions
* adding norm_exception
* fix double key in lemmatizer
* remove unused import on punctuation.py
* reformat stop_words to reduce number of lines, improve readibility
* updating tokenizer exception
* implement is_currency for lang/id
* adding orth_first_upper in tokenizer_exceptions
* update the norm_exception list
* remove bunch of abbreviations
* adding contributors file
* Fixed spaCy+Keras example (#2763)
* bug fixes in keras example
* created contributor agreement
* Adding French hyphenated first name (#2786)
* Fix typo (closes #2784)
* Fix typo (#2795) [ci skip]
Fixed typo on line 6 "regcognizer --> recognizer"
* Adding basic support for Sinhala language. (#2788)
* adding Sinhala language package, stop words, examples and lex_attrs.
* Adding contributor agreement
* Updating contributor agreement
* Also include lowercase norm exceptions
* Fix error (#2802)
* Fix error
ValueError: cannot resize an array that references or is referenced
by another array in this way. Use the resize function
* added spaCy Contributor Agreement
* Add charlax's contributor agreement (#2805)
* agreement of contributor, may I introduce a tiny pl languge contribution (#2799)
* Contributors agreement
* Contributors agreement
* Contributors agreement
* Add jupyter=True to displacy.render in documentation (#2806)
* Revert "Also include lowercase norm exceptions"
This reverts commit 70f4e8adf37cfcfab60be2b97d6deae949b30e9e.
* Remove deprecated encoding argument to msgpack
* Set up dependency tree pattern matching skeleton (#2732)
* Fix bug when too many entity types. Fixes #2800
* Fix Python 2 test failure
* Require older msgpack-numpy
* Restore encoding arg on msgpack-numpy
* Try to fix version pin for msgpack-numpy
* Update Portuguese Language (#2790)
* Add words to portuguese language _num_words
* Add words to portuguese language _num_words
* Portuguese - Add/remove stopwords, fix tokenizer, add currency symbols
* Extended punctuation and norm_exceptions in the Portuguese language
* Correct error in spacy universe docs concerning spacy-lookup (#2814)
* Update Keras Example for (Parikh et al, 2016) implementation (#2803)
* bug fixes in keras example
* created contributor agreement
* baseline for Parikh model
* initial version of parikh 2016 implemented
* tested asymmetric models
* fixed grevious error in normalization
* use standard SNLI test file
* begin to rework parikh example
* initial version of running example
* start to document the new version
* start to document the new version
* Update Decompositional Attention.ipynb
* fixed calls to similarity
* updated the README
* import sys package duh
* simplified indexing on mapping word to IDs
* stupid python indent error
* added code from https://github.com/tensorflow/tensorflow/issues/3388 for tf bug workaround
* Fix typo (closes #2815) [ci skip]
* Update regex version dependency
* Set version to 2.0.13.dev3
* Skip seemingly problematic test
* Remove problematic test
* Try previous version of regex
* Revert "Remove problematic test"
This reverts commit bdebbef45552d698d390aa430b527ee27830f11b.
* Unskip test
* Try older version of regex
* 💫 Update training examples and use minibatching (#2830)
<!--- Provide a general summary of your changes in the title. -->
## Description
Update the training examples in `/examples/training` to show usage of spaCy's `minibatch` and `compounding` helpers ([see here](https://spacy.io/usage/training#tips-batch-size) for details). The lack of batching in the examples has caused some confusion in the past, especially for beginners who would copy-paste the examples, update them with large training sets and experienced slow and unsatisfying results.
### Types of change
enhancements
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
* Visual C++ link updated (#2842) (closes #2841) [ci skip]
* New landing page
* Add contribution agreement
* Correcting lang/ru/examples.py (#2845)
* Correct some grammatical inaccuracies in lang\ru\examples.py; filled Contributor Agreement
* Correct some grammatical inaccuracies in lang\ru\examples.py
* Move contributor agreement to separate file
* Set version to 2.0.13.dev4
* Add Persian(Farsi) language support (#2797)
* Also include lowercase norm exceptions
* Remove in favour of https://github.com/explosion/spaCy/graphs/contributors
* Rule-based French Lemmatizer (#2818)
<!--- Provide a general summary of your changes in the title. -->
## Description
<!--- Use this section to describe your changes. If your changes required
testing, include information about the testing environment and the tests you
ran. If your test fixes a bug reported in an issue, don't forget to include the
issue number. If your PR is still a work in progress, that's totally fine – just
include a note to let us know. -->
Add a rule-based French Lemmatizer following the english one and the excellent PR for [greek language optimizations](https://github.com/explosion/spaCy/pull/2558) to adapt the Lemmatizer class.
### Types of change
<!-- What type of change does your PR cover? Is it a bug fix, an enhancement
or new feature, or a change to the documentation? -->
- Lemma dictionary used can be found [here](http://infolingu.univ-mlv.fr/DonneesLinguistiques/Dictionnaires/telechargement.html), I used the XML version.
- Add several files containing exhaustive list of words for each part of speech
- Add some lemma rules
- Add POS that are not checked in the standard Lemmatizer, i.e PRON, DET, ADV and AUX
- Modify the Lemmatizer class to check in lookup table as a last resort if POS not mentionned
- Modify the lemmatize function to check in lookup table as a last resort
- Init files are updated so the model can support all the functionalities mentioned above
- Add words to tokenizer_exceptions_list.py in respect to regex used in tokenizer_exceptions.py
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [X] I have submitted the spaCy Contributor Agreement.
- [X] I ran the tests, and all new and existing tests passed.
- [X] My changes don't require a change to the documentation, or if they do, I've added all required information.
* Set version to 2.0.13
* Fix formatting and consistency
* Update docs for new version [ci skip]
* Increment version [ci skip]
* Add info on wheels [ci skip]
* Adding "This is a sentence" example to Sinhala (#2846)
* Add wheels badge
* Update badge [ci skip]
* Update README.rst [ci skip]
* Update murmurhash pin
* Increment version to 2.0.14.dev0
* Update GPU docs for v2.0.14
* Add wheel to setup_requires
* Import prefer_gpu and require_gpu functions from Thinc
* Add tests for prefer_gpu() and require_gpu()
* Update requirements and setup.py
* Workaround bug in thinc require_gpu
* Set version to v2.0.14
* Update push-tag script
* Unhack prefer_gpu
* Require thinc 6.10.6
* Update prefer_gpu and require_gpu docs [ci skip]
* Fix specifiers for GPU
* Set version to 2.0.14.dev1
* Set version to 2.0.14
* Update Thinc version pin
* Increment version
* Fix msgpack-numpy version pin
* Increment version
* Update version to 2.0.16
* Update version [ci skip]
* Redundant ')' in the Stop words' example (#2856)
<!--- Provide a general summary of your changes in the title. -->
## Description
<!--- Use this section to describe your changes. If your changes required
testing, include information about the testing environment and the tests you
ran. If your test fixes a bug reported in an issue, don't forget to include the
issue number. If your PR is still a work in progress, that's totally fine – just
include a note to let us know. -->
### Types of change
<!-- What type of change does your PR cover? Is it a bug fix, an enhancement
or new feature, or a change to the documentation? -->
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [ ] I have submitted the spaCy Contributor Agreement.
- [ ] I ran the tests, and all new and existing tests passed.
- [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
* Documentation improvement regarding joblib and SO (#2867)
Some documentation improvements
## Description
1. Fixed the dead URL to joblib
2. Fixed Stack Overflow brand name (with space)
### Types of change
Documentation
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
* raise error when setting overlapping entities as doc.ents (#2880)
* Fix out-of-bounds access in NER training
The helper method state.B(1) gets the index of the first token of the
buffer, or -1 if no such token exists. Normally this is safe because we
pass this to functions like state.safe_get(), which returns an empty
token. Here we used it directly as an array index, which is not okay!
This error may have been the cause of out-of-bounds access errors during
training. Similar errors may still be around, so much be hunted down.
Hunting this one down took a long time...I printed out values across
training runs and diffed, looking for points of divergence between
runs, when no randomness should be allowed.
* Change PyThaiNLP Url (#2876)
* Fix missing comma
* Add example showing a fix-up rule for space entities
* Set version to 2.0.17.dev0
* Update regex version
* Revert "Update regex version"
This reverts commit 62358dd867d15bc6a475942dff34effba69dd70a.
* Try setting older regex version, to align with conda
* Set version to 2.0.17
* Add spacy-js to universe [ci-skip]
* Add spacy-raspberry to universe (closes #2889)
* Add script to validate universe json [ci skip]
* Removed space in docs + added contributor indo (#2909)
* - removed unneeded space in documentation
* - added contributor info
* Allow input text of length up to max_length, inclusive (#2922)
* Include universe spec for spacy-wordnet component (#2919)
* feat: include universe spec for spacy-wordnet component
* chore: include spaCy contributor agreement
* Minor formatting changes [ci skip]
* Fix image [ci skip]
Twitter URL doesn't work on live site
* Check if the word is in one of the regular lists specific to each POS (#2886)
* 💫 Create random IDs for SVGs to prevent ID clashes (#2927)
Resolves #2924.
## Description
Fixes problem where multiple visualizations in Jupyter notebooks would have clashing arc IDs, resulting in weirdly positioned arc labels. Generating a random ID prefix so even identical parses won't receive the same IDs for consistency (even if effect of ID clash isn't noticable here.)
### Types of change
bug fix
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
* Fix typo [ci skip]
* fixes symbolic link on py3 and windows (#2949)
* fixes symbolic link on py3 and windows
during setup of spacy using command
python -m spacy link en_core_web_sm en
closes #2948
* Update spacy/compat.py
Co-Authored-By: cicorias <cicorias@users.noreply.github.com>
* Fix formatting
* Update universe [ci skip]
* Catalan Language Support (#2940)
* Catalan language Support
* Ddding Catalan to documentation
* Sort languages alphabetically [ci skip]
* Update tests for pytest 4.x (#2965)
<!--- Provide a general summary of your changes in the title. -->
## Description
- [x] Replace marks in params for pytest 4.0 compat ([see here](https://docs.pytest.org/en/latest/deprecations.html#marks-in-pytest-mark-parametrize))
- [x] Un-xfail passing tests (some fixes in a recent update resolved a bunch of issues, but tests were apparently never updated here)
### Types of change
<!-- What type of change does your PR cover? Is it a bug fix, an enhancement
or new feature, or a change to the documentation? -->
## Checklist
<!--- Before you submit the PR, go over this checklist and make sure you can
tick off all the boxes. [] -> [x] -->
- [x] I have submitted the spaCy Contributor Agreement.
- [x] I ran the tests, and all new and existing tests passed.
- [x] My changes don't require a change to the documentation, or if they do, I've added all required information.
* Fix regex pin to harmonize with conda (#2964)
* Update README.rst
* Fix bug where Vocab.prune_vector did not use 'batch_size' (#2977)
Fixes #2976
* Fix typo
* Fix typo
* Remove duplicate file
* Require thinc 7.0.0.dev2
Fixes bug in gpu_ops that would use cupy instead of numpy on CPU
* Add missing import
* Fix error IDs
* Fix tests
2018-11-29 15:30:29 +00:00
|
|
|
|
|
|
|
|
|
2019-02-08 12:28:09 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def ro_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ro")().tokenizer
|
2017-11-21 19:23:59 +00:00
|
|
|
|
2017-01-11 12:56:32 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def ru_tokenizer():
|
|
|
|
|
pytest.importorskip("pymorphy2")
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ru")().tokenizer
|
2018-06-19 08:17:53 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2019-09-27 15:57:59 +00:00
|
|
|
@pytest.fixture
|
|
|
|
|
def ru_lemmatizer():
|
|
|
|
|
pytest.importorskip("pymorphy2")
|
2020-08-07 13:27:13 +00:00
|
|
|
return get_lang_class("ru")().add_pipe("lemmatizer")
|
2019-09-27 15:57:59 +00:00
|
|
|
|
|
|
|
|
|
2020-08-25 08:56:29 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def sa_tokenizer():
|
2020-09-04 12:05:55 +00:00
|
|
|
return get_lang_class("sa")().tokenizer
|
2020-08-25 08:56:29 +00:00
|
|
|
|
|
|
|
|
|
2019-08-22 09:43:07 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def sr_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("sr")().tokenizer
|
2019-08-22 09:43:07 +00:00
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def sv_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("sv")().tokenizer
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2018-07-10 11:48:38 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def th_tokenizer():
|
|
|
|
|
pytest.importorskip("pythainlp")
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("th")().tokenizer
|
2017-03-24 15:27:44 +00:00
|
|
|
|
|
|
|
|
|
2020-12-22 15:50:34 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def ti_tokenizer():
|
2021-01-14 09:49:30 +00:00
|
|
|
return get_lang_class("ti")().tokenizer
|
2018-11-27 00:09:36 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def tr_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("tr")().tokenizer
|
2018-11-27 00:09:36 +00:00
|
|
|
|
2018-06-22 09:14:03 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2019-02-14 12:27:13 +00:00
|
|
|
def tt_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("tt")().tokenizer
|
2018-09-03 07:57:52 +00:00
|
|
|
|
2018-11-28 22:33:34 +00:00
|
|
|
|
2021-01-24 14:56:16 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def ky_tokenizer():
|
2021-01-27 10:29:02 +00:00
|
|
|
return get_lang_class("ky")().tokenizer
|
2021-01-24 14:56:16 +00:00
|
|
|
|
|
|
|
|
|
2019-02-14 12:27:13 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def uk_tokenizer():
|
|
|
|
|
pytest.importorskip("pymorphy2")
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("uk")().tokenizer
|
2018-09-03 07:57:52 +00:00
|
|
|
|
2019-02-14 12:27:13 +00:00
|
|
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def ur_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("ur")().tokenizer
|
2019-11-11 13:23:21 +00:00
|
|
|
|
2019-12-21 18:04:17 +00:00
|
|
|
|
2019-12-21 13:11:50 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def yo_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("yo")().tokenizer
|
2019-11-11 13:23:21 +00:00
|
|
|
|
2019-12-21 18:04:17 +00:00
|
|
|
|
2019-11-11 13:23:21 +00:00
|
|
|
@pytest.fixture(scope="session")
|
2020-04-18 15:01:53 +00:00
|
|
|
def zh_tokenizer_char():
|
2020-07-22 11:42:59 +00:00
|
|
|
nlp = get_lang_class("zh")()
|
|
|
|
|
return nlp.tokenizer
|
2020-04-18 15:01:53 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def zh_tokenizer_jieba():
|
2019-11-11 13:23:21 +00:00
|
|
|
pytest.importorskip("jieba")
|
2020-07-22 11:42:59 +00:00
|
|
|
config = {
|
2020-09-30 09:46:45 +00:00
|
|
|
"nlp": {
|
|
|
|
|
"tokenizer": {
|
|
|
|
|
"@tokenizers": "spacy.zh.ChineseTokenizer",
|
|
|
|
|
"segmenter": "jieba",
|
|
|
|
|
}
|
|
|
|
|
}
|
2020-07-22 11:42:59 +00:00
|
|
|
}
|
2020-09-30 09:46:45 +00:00
|
|
|
nlp = get_lang_class("zh").from_config(config)
|
2020-07-22 11:42:59 +00:00
|
|
|
return nlp.tokenizer
|
2020-04-03 11:02:18 +00:00
|
|
|
|
2020-04-18 15:01:53 +00:00
|
|
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def zh_tokenizer_pkuseg():
|
2020-10-05 12:21:53 +00:00
|
|
|
pytest.importorskip("spacy_pkuseg")
|
2020-07-22 11:42:59 +00:00
|
|
|
config = {
|
2020-09-29 19:10:22 +00:00
|
|
|
"nlp": {
|
|
|
|
|
"tokenizer": {
|
|
|
|
|
"@tokenizers": "spacy.zh.ChineseTokenizer",
|
|
|
|
|
"segmenter": "pkuseg",
|
|
|
|
|
}
|
|
|
|
|
},
|
2020-10-15 08:08:53 +00:00
|
|
|
"initialize": {"tokenizer": {"pkuseg_model": "web"}},
|
2020-07-22 11:42:59 +00:00
|
|
|
}
|
2020-09-29 19:10:22 +00:00
|
|
|
nlp = get_lang_class("zh").from_config(config)
|
|
|
|
|
nlp.initialize()
|
2020-07-22 11:42:59 +00:00
|
|
|
return nlp.tokenizer
|
2020-04-18 15:01:53 +00:00
|
|
|
|
|
|
|
|
|
2020-04-03 11:02:18 +00:00
|
|
|
@pytest.fixture(scope="session")
|
|
|
|
|
def hy_tokenizer():
|
2020-07-22 11:42:59 +00:00
|
|
|
return get_lang_class("hy")().tokenizer
|