Skip to content

fix: keep offset2id updated when deleting in sqlite #471

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JoanFM merged 5 commits into from
Aug 4, 2022
Merged

fix: keep offset2id updated when deleting in sqlite #471

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
59da7ca
fix: keep offset2id updated when deleting in sqlite
JohannesMessner Aug 3, 2022
89ab4ed
fix: remove unnecessary line in test
JohannesMessner Aug 3, 2022
639da09
test: apply test to all storage backends
JohannesMessner Aug 4, 2022
08a6b43
fix: sqlite consistency when deleting
JohannesMessner Aug 4, 2022
328715d
fix: update offset2id without updating too much
JohannesMessner Aug 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions docarray/array/storage/sqlite/getsetdel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@ class GetSetDelMixin(BaseGetSetDelMixin):

def _del_doc_by_id(self, _id: str):
self._sql(f'DELETE FROM {self._table_name} WHERE doc_id=?', (_id,))
self._save_offset2ids()
self._commit()

def _set_doc_by_id(self, _id: str, value: 'Document'):
Expand Down Expand Up @@ -47,6 +48,7 @@ def _del_docs_by_ids(self, ids: str) -> Iterable['Document']:
f"DELETE FROM {self._table_name} WHERE doc_id in ({','.join(['?'] * len(ids))})",
ids,
)
self._save_offset2ids()
self._commit()

def _load_offset2ids(self):
Expand All @@ -64,3 +66,11 @@ def _save_offset2ids(self):
(offset, doc_id),
)
self._commit()

def _del_docs(self, ids):
super()._del_docs(ids)
self._save_offset2ids()

def _del_doc_by_offset(self, offset: int):
super()._del_doc_by_offset(offset)
self._save_offset2ids()
56 changes: 56 additions & 0 deletions tests/unit/array/test_sequence.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,3 +103,59 @@ def test_context_manager_from_disk(storage, config, start_storage, tmpdir, tmpfi

del da
del da2


@pytest.mark.parametrize(
'storage, config',
[
('memory', None),
('weaviate', {'n_dim': 3, 'distance': 'l2-squared'}),
('annlite', {'n_dim': 3, 'metric': 'Euclidean'}),
('qdrant', {'n_dim': 3, 'distance': 'euclidean'}),
('elasticsearch', {'n_dim': 3, 'distance': 'l2_norm'}),
('sqlite', dict()),
],
)
@pytest.mark.parametrize(
'index', [1, '1', slice(1, 2), [1], [False, True, False, False, False]]
)
def test_del_and_append(index, storage, config):
da = DocumentArray(storage=storage, config=config)

with da:
da.extend([Document(id=str(i)) for i in range(5)])
with da:
del da[index]
da.append(Document(id='new'))

assert da[:, 'id'] == ['0', '2', '3', '4', 'new']


@pytest.mark.parametrize(
'index', [1, '1', slice(1, 2), [1], [False, True, False, False, False]]
)
@pytest.mark.parametrize(
'storage, config',
[
('memory', None),
('weaviate', {'n_dim': 3, 'distance': 'l2-squared'}),
('annlite', {'n_dim': 3, 'metric': 'Euclidean'}),
('qdrant', {'n_dim': 3, 'distance': 'euclidean'}),
('elasticsearch', {'n_dim': 3, 'distance': 'l2_norm'}),
('sqlite', dict()),
],
)
def test_set_and_append(index, storage, config):
da = DocumentArray(storage=storage, config=config)

with da:
da.extend([Document(id=str(i)) for i in range(5)])
with da:
da[index] = (
Document(id='new')
if isinstance(index, int) or isinstance(index, str)
else [Document(id='new')]
)
da.append(Document(id='new_new'))

assert da[:, 'id'] == ['0', 'new', '2', '3', '4', 'new_new']