mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +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.
41 lines
1.8 KiB
Python
41 lines
1.8 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.lang.en import English
|
|
from spacy.tokenizer import Tokenizer
|
|
from spacy.util import compile_prefix_regex, compile_suffix_regex
|
|
from spacy.util import compile_infix_regex
|
|
|
|
|
|
@pytest.fixture
|
|
def custom_en_tokenizer(en_vocab):
|
|
prefix_re = compile_prefix_regex(English.Defaults.prefixes)
|
|
suffix_re = compile_suffix_regex(English.Defaults.suffixes)
|
|
custom_infixes = ['\.\.\.+',
|
|
'(?<=[0-9])-(?=[0-9])',
|
|
# '(?<=[0-9]+),(?=[0-9]+)',
|
|
'[0-9]+(,[0-9]+)+',
|
|
'[\[\]!&:,()\*—–\/-]']
|
|
infix_re = compile_infix_regex(custom_infixes)
|
|
return Tokenizer(en_vocab,
|
|
English.Defaults.tokenizer_exceptions,
|
|
prefix_re.search,
|
|
suffix_re.search,
|
|
infix_re.finditer,
|
|
token_match=None)
|
|
|
|
|
|
def test_en_customized_tokenizer_handles_infixes(custom_en_tokenizer):
|
|
sentence = "The 8 and 10-county definitions are not used for the greater Southern California Megaregion."
|
|
context = [word.text for word in custom_en_tokenizer(sentence)]
|
|
assert context == ['The', '8', 'and', '10', '-', 'county', 'definitions',
|
|
'are', 'not', 'used', 'for', 'the', 'greater',
|
|
'Southern', 'California', 'Megaregion', '.']
|
|
# the trailing '-' may cause Assertion Error
|
|
sentence = "The 8- and 10-county definitions are not used for the greater Southern California Megaregion."
|
|
context = [word.text for word in custom_en_tokenizer(sentence)]
|
|
assert context == ['The', '8', '-', 'and', '10', '-', 'county',
|
|
'definitions', 'are', 'not', 'used', 'for', 'the',
|
|
'greater', 'Southern', 'California', 'Megaregion', '.']
|