spaCy/spacy/tests/matcher/test_phrase_matcher.py

31 lines
915 B
Python
Raw Normal View History

💫 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 21:38:44 +00:00
# coding: utf-8
from __future__ import unicode_literals
import pytest
from spacy.matcher import PhraseMatcher
from spacy.tokens import Doc
def test_matcher_phrase_matcher(en_vocab):
doc = Doc(en_vocab, words=["Google", "Now"])
matcher = PhraseMatcher(en_vocab)
matcher.add('COMPANY', None, doc)
doc = Doc(en_vocab, words=["I", "like", "Google", "Now", "best"])
assert len(matcher(doc)) == 1
def test_phrase_matcher_length(en_vocab):
matcher = PhraseMatcher(en_vocab)
assert len(matcher) == 0
matcher.add('TEST', None, Doc(en_vocab, words=['test']))
assert len(matcher) == 1
matcher.add('TEST2', None, Doc(en_vocab, words=['test2']))
assert len(matcher) == 2
def test_phrase_matcher_contains(en_vocab):
matcher = PhraseMatcher(en_vocab)
matcher.add('TEST', None, Doc(en_vocab, words=['test']))
assert 'TEST' in matcher
assert 'TEST2' not in matcher