mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-18 12:08:35 +00:00
feat(python): add namespace/table exist support (#3460)
In the current LanceDB usage implementation, there is no way to check whether a table or namespace already exists. This PR introduces the namespace_exists and table_exists methods to determine the existence of tables and namespaces. useage like this: ``` # check table exists db.table_exists(table_id=['xxx']) # check namespace exists db.namespace_exists(namespace_id=['xxx']) ``` fixes: #3419 --------- Signed-off-by: farmer <farmerchillax@outlook.com> Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -178,6 +178,51 @@ class DBConnection(EnforceOverrides):
|
||||
"Namespace operations are not supported for this connection type"
|
||||
)
|
||||
|
||||
def namespace_exists(self, namespace_id: List[str]) -> bool:
|
||||
"""Check if a namespace exists.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
namespace_id: List[str]
|
||||
The namespace identifier to check.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
True if the namespace exists, False otherwise.
|
||||
|
||||
Raises
|
||||
------
|
||||
NotImplementedError
|
||||
If the connection type does not support namespace operations.
|
||||
"""
|
||||
raise NotImplementedError(
|
||||
"Namespace operations are not supported for this connection type"
|
||||
)
|
||||
|
||||
def table_exists(self, table_id: List[str]) -> bool:
|
||||
"""Check if a table exists.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
table_id: List[str]
|
||||
The table identifier to check (full path including namespace
|
||||
segments and table name).
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
True if the table exists, False otherwise.
|
||||
|
||||
Raises
|
||||
------
|
||||
NotImplementedError
|
||||
If the connection type does not support namespace operations.
|
||||
"""
|
||||
raise NotImplementedError(
|
||||
"Namespace operations are not supported for this connection type"
|
||||
)
|
||||
|
||||
def list_tables(
|
||||
self,
|
||||
namespace_path: Optional[List[str]] = None,
|
||||
|
||||
@@ -38,7 +38,11 @@ from lance_namespace_urllib3_client.models.query_table_request_vector import (
|
||||
QueryTableRequestVector,
|
||||
)
|
||||
from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
|
||||
from lance_namespace.errors import NamespaceNotEmptyError, TableNotFoundError
|
||||
from lance_namespace.errors import (
|
||||
NamespaceNotEmptyError,
|
||||
NamespaceNotFoundError,
|
||||
TableNotFoundError,
|
||||
)
|
||||
from lancedb._lancedb import (
|
||||
connect_namespace as _connect_namespace,
|
||||
connect_namespace_client as _connect_namespace_client,
|
||||
@@ -53,6 +57,8 @@ from lance_namespace import (
|
||||
DropNamespaceResponse,
|
||||
ListNamespacesResponse,
|
||||
ListTablesResponse,
|
||||
NamespaceExistsRequest,
|
||||
TableExistsRequest,
|
||||
)
|
||||
from lancedb.table import AsyncTable, LanceTable, Table
|
||||
from lancedb.util import validate_table_name
|
||||
@@ -780,6 +786,51 @@ class LanceNamespaceDBConnection(DBConnection):
|
||||
"""
|
||||
return LOOP.run(self._inner.describe_namespace(namespace_path))
|
||||
|
||||
@override
|
||||
def namespace_exists(self, namespace_id: List[str]) -> bool:
|
||||
"""
|
||||
Check if a namespace exists.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
namespace_id : List[str]
|
||||
The namespace identifier to check.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
True if the namespace exists, False otherwise.
|
||||
"""
|
||||
request = NamespaceExistsRequest(id=namespace_id)
|
||||
try:
|
||||
self._namespace_client.namespace_exists(request)
|
||||
return True
|
||||
except NamespaceNotFoundError:
|
||||
return False
|
||||
|
||||
@override
|
||||
def table_exists(self, table_id: List[str]) -> bool:
|
||||
"""
|
||||
Check if a table exists.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
table_id : List[str]
|
||||
The table identifier to check (full path including namespace
|
||||
segments and table name).
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
True if the table exists, False otherwise.
|
||||
"""
|
||||
request = TableExistsRequest(id=table_id)
|
||||
try:
|
||||
self._namespace_client.table_exists(request)
|
||||
return True
|
||||
except TableNotFoundError:
|
||||
return False
|
||||
|
||||
@override
|
||||
def list_tables(
|
||||
self,
|
||||
@@ -1233,6 +1284,49 @@ class AsyncLanceNamespaceDBConnection:
|
||||
"""
|
||||
return await self._inner.describe_namespace(namespace_path)
|
||||
|
||||
async def namespace_exists(self, namespace_id: List[str]) -> bool:
|
||||
"""
|
||||
Check if a namespace exists.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
namespace_id : List[str]
|
||||
The namespace identifier to check.
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
True if the namespace exists, False otherwise.
|
||||
"""
|
||||
request = NamespaceExistsRequest(id=namespace_id)
|
||||
try:
|
||||
self._namespace_client.namespace_exists(request)
|
||||
return True
|
||||
except NamespaceNotFoundError:
|
||||
return False
|
||||
|
||||
async def table_exists(self, table_id: List[str]) -> bool:
|
||||
"""
|
||||
Check if a table exists.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
table_id : List[str]
|
||||
The table identifier to check (full path including namespace
|
||||
segments and table name).
|
||||
|
||||
Returns
|
||||
-------
|
||||
bool
|
||||
True if the table exists, False otherwise.
|
||||
"""
|
||||
request = TableExistsRequest(id=table_id)
|
||||
try:
|
||||
self._namespace_client.table_exists(request)
|
||||
return True
|
||||
except TableNotFoundError:
|
||||
return False
|
||||
|
||||
async def list_tables(
|
||||
self,
|
||||
namespace_path: Optional[List[str]] = None,
|
||||
|
||||
@@ -18,6 +18,7 @@ Tests verify:
|
||||
"""
|
||||
|
||||
import copy
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
@@ -239,7 +240,7 @@ def create_tracking_namespace(
|
||||
|
||||
dir_props = {f"storage.{k}": v for k, v in storage_options_with_refresh.items()}
|
||||
|
||||
if bucket_name.startswith("/") or bucket_name.startswith("file://"):
|
||||
if os.path.isabs(bucket_name) or bucket_name.startswith("file://"):
|
||||
dir_props["root"] = f"{bucket_name}/namespace_root"
|
||||
else:
|
||||
dir_props["root"] = f"s3://{bucket_name}/namespace_root"
|
||||
@@ -767,3 +768,70 @@ def test_namespace_with_schema_only(s3_bucket: str, use_custom: bool):
|
||||
|
||||
# Verify data was added
|
||||
assert table.count_rows() == 2
|
||||
|
||||
|
||||
@pytest.mark.parametrize("use_custom", [False, True], ids=["DirectoryNS", "CustomNS"])
|
||||
def test_namespace_exists(use_custom: bool):
|
||||
"""
|
||||
Test namespace_exists returns True for existing and False for non-existent.
|
||||
"""
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
try:
|
||||
ns_client, _ = create_tracking_namespace(
|
||||
bucket_name=temp_dir,
|
||||
storage_options={},
|
||||
credential_expires_in_seconds=3600,
|
||||
use_custom=use_custom,
|
||||
)
|
||||
db = LanceNamespaceDBConnection(ns_client)
|
||||
|
||||
namespace_name = f"test_ns_{uuid.uuid4().hex[:8]}"
|
||||
db.create_namespace([namespace_name])
|
||||
|
||||
# Existing namespace should return True
|
||||
assert db.namespace_exists(namespace_id=[namespace_name]) is True
|
||||
|
||||
# Non-existent namespace should return False
|
||||
assert db.namespace_exists(namespace_id=["nonexistent_ns"]) is False
|
||||
finally:
|
||||
shutil.rmtree(temp_dir, ignore_errors=True)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("use_custom", [False, True], ids=["DirectoryNS", "CustomNS"])
|
||||
def test_table_exists(use_custom: bool):
|
||||
"""
|
||||
Test table_exists returns True for existing table and False for non-existent.
|
||||
"""
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
try:
|
||||
ns_client, _ = create_tracking_namespace(
|
||||
bucket_name=temp_dir,
|
||||
storage_options={},
|
||||
credential_expires_in_seconds=3600,
|
||||
use_custom=use_custom,
|
||||
)
|
||||
db = LanceNamespaceDBConnection(ns_client)
|
||||
|
||||
namespace_name = f"test_ns_{uuid.uuid4().hex[:8]}"
|
||||
db.create_namespace([namespace_name])
|
||||
|
||||
table_name = f"test_table_{uuid.uuid4().hex}"
|
||||
namespace_path = [namespace_name]
|
||||
schema = pa.schema(
|
||||
[
|
||||
pa.field("id", pa.int64()),
|
||||
pa.field("vector", pa.list_(pa.float32(), 2)),
|
||||
pa.field("text", pa.string()),
|
||||
]
|
||||
)
|
||||
|
||||
db.create_table(table_name, schema=schema, namespace_path=namespace_path)
|
||||
|
||||
# Existing table should return True
|
||||
table_id = namespace_path + [table_name]
|
||||
assert db.table_exists(table_id=table_id) is True
|
||||
|
||||
# Non-existent table should return False
|
||||
assert db.table_exists(table_id=namespace_path + ["nonexistent_table"]) is False
|
||||
finally:
|
||||
shutil.rmtree(temp_dir, ignore_errors=True)
|
||||
|
||||
Generated
+1168
-1066
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user