explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Try to reduce memory usage of test_matcher

Browse Source
This commit is contained in:
Matthew Honnibal 2018-02-23 15:34:37 +01:00
parent 24563f4026
commit 7b575a119e
1 changed files with 15 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
spacy/tests/test_matcher.py
View File

@ -3,12 +3,17 @@ from __future__ import unicode_literals
from ..matcher import Matcher, PhraseMatcher from ..matcher import Matcher, PhraseMatcher
from .util import get_doc from .util import get_doc
from ..util import get_lang_class
from ..tokens import Doc from ..tokens import Doc
import pytest import pytest
@pytest.fixture(scope="session")
def en_vocab():
return get_lang_class('en').Defaults.create_vocab()
@pytest.fixture
@pytest.fixture(scope="session")
def matcher(en_vocab): def matcher(en_vocab):
rules = { rules = {
'JS': [[{'ORTH': 'JavaScript'}]], 'JS': [[{'ORTH': 'JavaScript'}]],
@ -76,7 +81,15 @@ def test_matcher_no_match(matcher):
assert matcher(doc) == [] assert matcher(doc) == []
def test_matcher_compile(matcher): def test_matcher_compile(en_vocab):
rules = {
'JS': [[{'ORTH': 'JavaScript'}]],
'GoogleNow': [[{'ORTH': 'Google'}, {'ORTH': 'Now'}]],
'Java': [[{'LOWER': 'java'}]]
}
matcher = Matcher(en_vocab)
for key, patterns in rules.items():
matcher.add(key, None, *patterns)
assert len(matcher) == 3 assert len(matcher) == 3