mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
75f3234404
## 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.
69 lines
2.0 KiB
Python
69 lines
2.0 KiB
Python
# coding: utf-8
|
||
from __future__ import unicode_literals
|
||
|
||
import pytest
|
||
|
||
|
||
@pytest.mark.parametrize('text', [
|
||
"aujourd'hui", "Aujourd'hui", "prud'hommes", "prud’hommal"])
|
||
def test_fr_tokenizer_infix_exceptions(fr_tokenizer, text):
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 1
|
||
|
||
|
||
@pytest.mark.parametrize('text,lemma', [
|
||
("janv.", "janvier"),
|
||
("juill.", "juillet"),
|
||
("Dr.", "docteur"),
|
||
("av.", "avant"),
|
||
("sept.", "septembre")])
|
||
def test_fr_tokenizer_handles_abbr(fr_tokenizer, text, lemma):
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 1
|
||
assert tokens[0].lemma_ == lemma
|
||
|
||
|
||
def test_fr_tokenizer_handles_exc_in_text(fr_tokenizer):
|
||
text = "Je suis allé au mois de janv. aux prud’hommes."
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 10
|
||
assert tokens[6].text == "janv."
|
||
assert tokens[6].lemma_ == "janvier"
|
||
assert tokens[8].text == "prud’hommes"
|
||
|
||
|
||
def test_fr_tokenizer_handles_exc_in_text_2(fr_tokenizer):
|
||
text = "Cette après-midi, je suis allé dans un restaurant italo-mexicain."
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 11
|
||
assert tokens[1].text == "après-midi"
|
||
assert tokens[9].text == "italo-mexicain"
|
||
|
||
|
||
def test_fr_tokenizer_handles_title(fr_tokenizer):
|
||
text = "N'est-ce pas génial?"
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 6
|
||
assert tokens[0].text == "N'"
|
||
assert tokens[0].lemma_ == "ne"
|
||
assert tokens[1].text == "est"
|
||
assert tokens[1].lemma_ == "être"
|
||
assert tokens[2].text == "-ce"
|
||
assert tokens[2].lemma_ == "ce"
|
||
|
||
|
||
def test_fr_tokenizer_handles_title_2(fr_tokenizer):
|
||
text = "Est-ce pas génial?"
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 6
|
||
assert tokens[0].text == "Est"
|
||
assert tokens[0].lemma_ == "être"
|
||
|
||
|
||
def test_fr_tokenizer_handles_title_2(fr_tokenizer):
|
||
text = "Qu'est-ce que tu fais?"
|
||
tokens = fr_tokenizer(text)
|
||
assert len(tokens) == 7
|
||
assert tokens[0].text == "Qu'"
|
||
assert tokens[0].lemma_ == "que"
|