fix: support __len__ on remote table (#2379)

This moves the __len__ method from LanceTable and RemoteTable to Table
so that child classes don't need to implement their own. In the process,
it fixes the implementation of RemoteTable's length method, which was
previously missing a return statement.

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **Refactor**
- Centralized the table length functionality in the base table class,
simplifying subclass behavior.
- Removed redundant or non-functional length methods from specific table
classes.

- **Tests**
- Added a new test to verify correct table length reporting for remote
tables.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->
This commit is contained in:
Wyatt Alt
2025-05-07 17:23:39 -07:00
committed by GitHub
parent c9ae1b1737
commit 9ee152eb42
3 changed files with 22 additions and 6 deletions

View File

@@ -47,9 +47,6 @@ class RemoteTable(Table):
def __repr__(self) -> str:
return f"RemoteTable({self.db_name}.{self.name})"
def __len__(self) -> int:
self.count_rows(None)
@property
def schema(self) -> pa.Schema:
"""The [Arrow Schema](https://arrow.apache.org/docs/python/api/datatypes.html#)

View File

@@ -620,6 +620,10 @@ class Table(ABC):
"""
raise NotImplementedError
def __len__(self) -> int:
"""The number of rows in this Table"""
return self.count_rows(None)
@property
@abstractmethod
def embedding_functions(self) -> Dict[str, EmbeddingFunctionConfig]:
@@ -1762,9 +1766,6 @@ class LanceTable(Table):
def count_rows(self, filter: Optional[str] = None) -> int:
return LOOP.run(self._table.count_rows(filter))
def __len__(self) -> int:
return self.count_rows()
def __repr__(self) -> str:
val = f"{self.__class__.__name__}(name={self.name!r}, version={self.version}"
if self._conn.read_consistency_interval is not None:

View File

@@ -149,6 +149,24 @@ async def test_async_checkout():
assert await table.count_rows() == 300
def test_table_len_sync():
def handler(request):
if request.path == "/v1/table/test/create/?mode=create":
request.send_response(200)
request.send_header("Content-Type", "application/json")
request.end_headers()
request.wfile.write(b"{}")
request.send_response(200)
request.send_header("Content-Type", "application/json")
request.end_headers()
request.wfile.write(json.dumps(1).encode())
with mock_lancedb_connection(handler) as db:
table = db.create_table("test", [{"id": 1}])
assert len(table) == 1
@pytest.mark.asyncio
async def test_http_error():
request_id_holder = {"request_id": None}