mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-01 00:17:44 +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.
120 lines
4.2 KiB
Python
120 lines
4.2 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import pytest
|
|
from spacy.vocab import Vocab
|
|
from spacy.strings import StringStore
|
|
|
|
from ..util import make_tempdir
|
|
|
|
|
|
test_strings = [([], []), (['rats', 'are', 'cute'], ['i', 'like', 'rats'])]
|
|
test_strings_attrs = [(['rats', 'are', 'cute'], 'Hello')]
|
|
|
|
|
|
@pytest.mark.xfail
|
|
@pytest.mark.parametrize('text', ['rat'])
|
|
def test_serialize_vocab(en_vocab, text):
|
|
text_hash = en_vocab.strings.add(text)
|
|
vocab_bytes = en_vocab.to_bytes()
|
|
new_vocab = Vocab().from_bytes(vocab_bytes)
|
|
assert new_vocab.strings(text_hash) == text
|
|
|
|
|
|
@pytest.mark.parametrize('strings1,strings2', test_strings)
|
|
def test_serialize_vocab_roundtrip_bytes(strings1, strings2):
|
|
vocab1 = Vocab(strings=strings1)
|
|
vocab2 = Vocab(strings=strings2)
|
|
vocab1_b = vocab1.to_bytes()
|
|
vocab2_b = vocab2.to_bytes()
|
|
if strings1 == strings2:
|
|
assert vocab1_b == vocab2_b
|
|
else:
|
|
assert vocab1_b != vocab2_b
|
|
vocab1 = vocab1.from_bytes(vocab1_b)
|
|
assert vocab1.to_bytes() == vocab1_b
|
|
new_vocab1 = Vocab().from_bytes(vocab1_b)
|
|
assert new_vocab1.to_bytes() == vocab1_b
|
|
assert len(new_vocab1) == len(strings1)
|
|
assert sorted([lex.text for lex in new_vocab1]) == sorted(strings1)
|
|
|
|
|
|
@pytest.mark.parametrize('strings1,strings2', test_strings)
|
|
def test_serialize_vocab_roundtrip_disk(strings1,strings2):
|
|
vocab1 = Vocab(strings=strings1)
|
|
vocab2 = Vocab(strings=strings2)
|
|
with make_tempdir() as d:
|
|
file_path1 = d / 'vocab1'
|
|
file_path2 = d / 'vocab2'
|
|
vocab1.to_disk(file_path1)
|
|
vocab2.to_disk(file_path2)
|
|
vocab1_d = Vocab().from_disk(file_path1)
|
|
vocab2_d = Vocab().from_disk(file_path2)
|
|
assert list(vocab1_d) == list(vocab1)
|
|
assert list(vocab2_d) == list(vocab2)
|
|
if strings1 == strings2:
|
|
assert list(vocab1_d) == list(vocab2_d)
|
|
else:
|
|
assert list(vocab1_d) != list(vocab2_d)
|
|
|
|
|
|
@pytest.mark.parametrize('strings,lex_attr', test_strings_attrs)
|
|
def test_serialize_vocab_lex_attrs_bytes(strings, lex_attr):
|
|
vocab1 = Vocab(strings=strings)
|
|
vocab2 = Vocab()
|
|
vocab1[strings[0]].norm_ = lex_attr
|
|
assert vocab1[strings[0]].norm_ == lex_attr
|
|
assert vocab2[strings[0]].norm_ != lex_attr
|
|
vocab2 = vocab2.from_bytes(vocab1.to_bytes())
|
|
assert vocab2[strings[0]].norm_ == lex_attr
|
|
|
|
|
|
@pytest.mark.parametrize('strings,lex_attr', test_strings_attrs)
|
|
def test_serialize_vocab_lex_attrs_disk(strings, lex_attr):
|
|
vocab1 = Vocab(strings=strings)
|
|
vocab2 = Vocab()
|
|
vocab1[strings[0]].norm_ = lex_attr
|
|
assert vocab1[strings[0]].norm_ == lex_attr
|
|
assert vocab2[strings[0]].norm_ != lex_attr
|
|
with make_tempdir() as d:
|
|
file_path = d / 'vocab'
|
|
vocab1.to_disk(file_path)
|
|
vocab2 = vocab2.from_disk(file_path)
|
|
assert vocab2[strings[0]].norm_ == lex_attr
|
|
|
|
|
|
@pytest.mark.parametrize('strings1,strings2', test_strings)
|
|
def test_serialize_stringstore_roundtrip_bytes(strings1, strings2):
|
|
sstore1 = StringStore(strings=strings1)
|
|
sstore2 = StringStore(strings=strings2)
|
|
sstore1_b = sstore1.to_bytes()
|
|
sstore2_b = sstore2.to_bytes()
|
|
if strings1 == strings2:
|
|
assert sstore1_b == sstore2_b
|
|
else:
|
|
assert sstore1_b != sstore2_b
|
|
sstore1 = sstore1.from_bytes(sstore1_b)
|
|
assert sstore1.to_bytes() == sstore1_b
|
|
new_sstore1 = StringStore().from_bytes(sstore1_b)
|
|
assert new_sstore1.to_bytes() == sstore1_b
|
|
assert list(new_sstore1) == strings1
|
|
|
|
|
|
@pytest.mark.parametrize('strings1,strings2', test_strings)
|
|
def test_serialize_stringstore_roundtrip_disk(strings1, strings2):
|
|
sstore1 = StringStore(strings=strings1)
|
|
sstore2 = StringStore(strings=strings2)
|
|
with make_tempdir() as d:
|
|
file_path1 = d / 'strings1'
|
|
file_path2 = d / 'strings2'
|
|
sstore1.to_disk(file_path1)
|
|
sstore2.to_disk(file_path2)
|
|
sstore1_d = StringStore().from_disk(file_path1)
|
|
sstore2_d = StringStore().from_disk(file_path2)
|
|
assert list(sstore1_d) == list(sstore1)
|
|
assert list(sstore2_d) == list(sstore2)
|
|
if strings1 == strings2:
|
|
assert list(sstore1_d) == list(sstore2_d)
|
|
else:
|
|
assert list(sstore1_d) != list(sstore2_d)
|