mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +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.
49 lines
1.3 KiB
Python
49 lines
1.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem ipsum"])
|
|
def test_tokenizer_splits_single_space(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == 2
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem ipsum"])
|
|
def test_tokenizer_splits_double_space(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == 3
|
|
assert tokens[1].text == " "
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem ipsum "])
|
|
def test_tokenizer_handles_double_trainling_ws(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert repr(tokens.text_with_ws) == repr(text)
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem\nipsum"])
|
|
def test_tokenizer_splits_newline(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == 3
|
|
assert tokens[1].text == "\n"
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem \nipsum"])
|
|
def test_tokenizer_splits_newline_space(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == 3
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem \nipsum"])
|
|
def test_tokenizer_splits_newline_double_space(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == 3
|
|
|
|
|
|
@pytest.mark.parametrize('text', ["lorem \n ipsum"])
|
|
def test_tokenizer_splits_newline_space_wrap(tokenizer, text):
|
|
tokens = tokenizer(text)
|
|
assert len(tokens) == 3
|