spaCy/spacy/tests/lang/es/test_text.py

65 lines
1.7 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.lang.es.lex_attrs import like_num
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## 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. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
def test_es_tokenizer_handles_long_text(es_tokenizer):
text = """Cuando a José Mujica lo invitaron a dar una conferencia
en Oxford este verano, su cabeza hizo "crac". La "más antigua" universidad de habla
inglesa, esa que cobra decenas de miles de euros de matrícula a sus alumnos
y en cuyos salones han disertado desde Margaret Thatcher hasta Stephen Hawking,
reclamaba los servicios de este viejo de 81 años, formado en un colegio público
en Montevideo y que pregona las bondades de la vida austera."""
tokens = es_tokenizer(text)
assert len(tokens) == 90
@pytest.mark.parametrize(
"text,length",
[
("¿Por qué José Mujica?", 6),
("“¿Oh no?”", 6),
("""¡Sí! "Vámonos", contestó José Arcadio Buendía""", 11),
("Corrieron aprox. 10km.", 5),
("Y entonces por qué...", 5),
],
)
💫 Refactor test suite (#2568) ## Description Related issues: #2379 (should be fixed by separating model tests) * **total execution time down from > 300 seconds to under 60 seconds** 🎉 * removed all model-specific tests that could only really be run manually anyway – those will now live in a separate test suite in the [`spacy-models`](https://github.com/explosion/spacy-models) repository and are already integrated into our new model training infrastructure * changed all relative imports to absolute imports to prepare for moving the test suite from `/spacy/tests` to `/tests` (it'll now always test against the installed version) * merged old regression tests into collections, e.g. `test_issue1001-1500.py` (about 90% of the regression tests are very short anyways) * tidied up and rewrote existing tests wherever possible ### Todo - [ ] move tests to `/tests` and adjust CI commands accordingly - [x] move model test suite from internal repo to `spacy-models` - [x] ~~investigate why `pipeline/test_textcat.py` is flakey~~ - [x] review old regression tests (leftover files) and see if they can be merged, simplified or deleted - [ ] update documentation on how to run tests ### Types of change enhancement, tests ## 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. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information.
2018-07-25 00:38:44 +03:00
def test_es_tokenizer_handles_cnts(es_tokenizer, text, length):
tokens = es_tokenizer(text)
assert len(tokens) == length
@pytest.mark.parametrize(
"text,match",
[
("10", True),
("1", True),
("10.000", True),
("1000", True),
("999,0", True),
("uno", True),
("dos", True),
("billón", True),
("veintiséis", True),
("perro", False),
(",", False),
("1/2", True),
],
)
def test_lex_attrs_like_number(es_tokenizer, text, match):
tokens = es_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].like_num == match
@pytest.mark.parametrize("word", ["once"])
def test_es_lex_attrs_capitals(word):
assert like_num(word)
assert like_num(word.upper())