mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 10:56:31 +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.
32 lines
1.3 KiB
Python
32 lines
1.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...util import get_doc
|
|
|
|
|
|
def test_de_parser_noun_chunks_standard_de(de_tokenizer):
|
|
text = "Eine Tasse steht auf dem Tisch."
|
|
heads = [1, 1, 0, -1, 1, -2, -4]
|
|
tags = ['ART', 'NN', 'VVFIN', 'APPR', 'ART', 'NN', '$.']
|
|
deps = ['nk', 'sb', 'ROOT', 'mo', 'nk', 'nk', 'punct']
|
|
tokens = de_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 2
|
|
assert chunks[0].text_with_ws == "Eine Tasse "
|
|
assert chunks[1].text_with_ws == "dem Tisch "
|
|
|
|
|
|
def test_de_extended_chunk(de_tokenizer):
|
|
text = "Die Sängerin singt mit einer Tasse Kaffee Arien."
|
|
heads = [1, 1, 0, -1, 1, -2, -1, -5, -6]
|
|
tags = ['ART', 'NN', 'VVFIN', 'APPR', 'ART', 'NN', 'NN', 'NN', '$.']
|
|
deps = ['nk', 'sb', 'ROOT', 'mo', 'nk', 'nk', 'nk', 'oa', 'punct']
|
|
tokens = de_tokenizer(text)
|
|
doc = get_doc(tokens.vocab, words=[t.text for t in tokens], tags=tags, deps=deps, heads=heads)
|
|
chunks = list(doc.noun_chunks)
|
|
assert len(chunks) == 3
|
|
assert chunks[0].text_with_ws == "Die Sängerin "
|
|
assert chunks[1].text_with_ws == "einer Tasse Kaffee "
|
|
assert chunks[2].text_with_ws == "Arien "
|