spaCy/spacy/tests/lang/da/test_text.py
Ines Montani 75f3234404
💫 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.
2018-07-24 23:38:44 +02:00

32 lines
1.2 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.lang.da.lex_attrs import like_num
def test_da_tokenizer_handles_long_text(da_tokenizer):
text = """Der var så dejligt ude på landet. Det var sommer, kornet stod gult, havren grøn,
høet var rejst i stakke nede i de grønne enge, og der gik storken på sine lange,
røde ben og snakkede ægyptisk, for det sprog havde han lært af sin moder.
Rundt om ager og eng var der store skove, og midt i skovene dybe søer; jo, der var rigtignok dejligt derude på landet!"""
tokens = da_tokenizer(text)
assert len(tokens) == 84
@pytest.mark.parametrize('text,match', [
('10', True), ('1', True), ('10.000', True), ('10.00', True),
('999,0', True), ('en', True), ('treoghalvfemsindstyvende', True), ('hundrede', True),
('hund', False), (',', False), ('1/2', True)])
def test_lex_attrs_like_number(da_tokenizer, text, match):
tokens = da_tokenizer(text)
assert len(tokens) == 1
assert tokens[0].like_num == match
@pytest.mark.parametrize('word', ['elleve', 'første'])
def test_da_lex_attrs_capitals(word):
assert like_num(word)
assert like_num(word.upper())