mirror of
https://github.com/lancedb/lancedb.git
synced 2026-09-04 12:38:38 +00:00
Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| b64284d8ca | |||
| 8347375362 |
@@ -276,38 +276,14 @@ jobs:
|
||||
# unreadable outside their own branch anyway, since GitHub scopes
|
||||
# caches to the creating ref.
|
||||
save-if: ${{ github.ref == 'refs/heads/main' }}
|
||||
- name: Downgrade dependencies
|
||||
# These packages have newer requirements for MSRV
|
||||
run: |
|
||||
cargo update -p aws-sdk-bedrockruntime --precise 1.77.0
|
||||
cargo update -p aws-sdk-dynamodb --precise 1.68.0
|
||||
cargo update -p aws-config --precise 1.6.0
|
||||
cargo update -p aws-sdk-kms --precise 1.63.0
|
||||
cargo update -p aws-sdk-s3 --precise 1.79.0
|
||||
cargo update -p aws-sdk-sso --precise 1.62.0
|
||||
cargo update -p aws-sdk-ssooidc --precise 1.63.0
|
||||
cargo update -p aws-sdk-sts --precise 1.63.0
|
||||
# aws-runtime/sigv4/credential-types/types and the aws-smithy-*
|
||||
# crates bumped their MSRV to 1.91.1 in late 2026; pin to the last
|
||||
# 1.91.0-compatible versions. The order matters — each downgrade
|
||||
# only succeeds once everything that still pins it at a higher
|
||||
# version has itself been downgraded.
|
||||
cargo update -p aws-runtime --precise 1.5.12
|
||||
cargo update -p aws-types --precise 1.3.9
|
||||
cargo update -p aws-sigv4 --precise 1.3.5
|
||||
cargo update -p aws-credential-types --precise 1.2.8
|
||||
cargo update -p aws-smithy-checksums --precise 0.63.9
|
||||
cargo update -p aws-smithy-runtime --precise 1.9.3
|
||||
cargo update -p aws-smithy-http --precise 0.62.4
|
||||
cargo update -p aws-smithy-eventstream --precise 0.60.12
|
||||
cargo update -p aws-smithy-http-client --precise 1.1.3
|
||||
cargo update -p aws-smithy-observability --precise 0.1.4
|
||||
cargo update -p aws-smithy-query --precise 0.60.8
|
||||
cargo update -p aws-smithy-runtime-api --precise 1.9.1
|
||||
cargo update -p aws-smithy-async --precise 1.2.6
|
||||
cargo update -p aws-smithy-types --precise 1.3.5
|
||||
cargo update -p aws-smithy-xml --precise 0.60.11
|
||||
cargo update -p home --precise 0.5.9
|
||||
- name: Downgrade dependencies that exceed our MSRV
|
||||
# Re-resolve the lockfile against `rust-version` instead of hand-pinning
|
||||
# every crate that raises its MSRV. Hand-pinning drifts: the pins keep
|
||||
# ratcheting further back than needed and eventually contradict a real
|
||||
# requirement elsewhere in the graph.
|
||||
env:
|
||||
CARGO_RESOLVER_INCOMPATIBLE_RUST_VERSIONS: fallback
|
||||
run: cargo update
|
||||
- name: cargo +${{ matrix.msrv }} check
|
||||
env:
|
||||
RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
|
||||
|
||||
Generated
+258
-234
File diff suppressed because it is too large
Load Diff
+14
-14
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
|
||||
rust-version = "1.91.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { "version" = "=11.0.0-beta.1", default-features = false, "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=11.0.0-beta.1", default-features = false, "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=11.0.0-beta.1", default-features = false, "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=11.0.0-beta.1", "tag" = "v11.0.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "58.0.0", optional = false }
|
||||
|
||||
@@ -17,25 +17,6 @@ The general flow of using the API is:
|
||||
pip install lancedb
|
||||
```
|
||||
|
||||
The core package does not require PyLance. When you need access to the underlying
|
||||
Lance dataset or GPU-accelerated indexing, add the `pylance` extra to the
|
||||
distribution you already installed.
|
||||
|
||||
For the standard distribution:
|
||||
|
||||
```shell
|
||||
pip install "lancedb[pylance]"
|
||||
```
|
||||
|
||||
For the pre-Haswell compatibility distribution:
|
||||
|
||||
```shell
|
||||
pip install "lancedb-compat[pylance]"
|
||||
```
|
||||
|
||||
Use only the extra matching your installed distribution. Do not install both
|
||||
distributions because they share the `lancedb` namespace.
|
||||
|
||||
The following methods describe the synchronous API client. There
|
||||
is also an [asynchronous API client](#connections-asynchronous).
|
||||
|
||||
|
||||
+1
-1
@@ -28,7 +28,7 @@
|
||||
<properties>
|
||||
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
|
||||
<arrow.version>15.0.0</arrow.version>
|
||||
<lance-core.version>10.1.0-beta.1</lance-core.version>
|
||||
<lance-core.version>11.0.0-beta.1</lance-core.version>
|
||||
<spotless.skip>false</spotless.skip>
|
||||
<spotless.version>2.30.0</spotless.version>
|
||||
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
|
||||
|
||||
@@ -8,25 +8,6 @@ A Python library for [LanceDB](https://github.com/lancedb/lancedb).
|
||||
pip install lancedb
|
||||
```
|
||||
|
||||
The core package does not require PyLance. When you need access to the underlying
|
||||
Lance dataset or GPU-accelerated indexing, add the `pylance` extra to the
|
||||
distribution you already installed.
|
||||
|
||||
For the standard distribution:
|
||||
|
||||
```bash
|
||||
pip install "lancedb[pylance]"
|
||||
```
|
||||
|
||||
For the pre-Haswell compatibility distribution:
|
||||
|
||||
```bash
|
||||
pip install "lancedb-compat[pylance]"
|
||||
```
|
||||
|
||||
Use only the extra matching your installed distribution. Do not install both
|
||||
distributions because they share the `lancedb` namespace.
|
||||
|
||||
### Pre-Haswell x86_64 hosts: `lancedb-compat`
|
||||
|
||||
The default `lancedb` wheel targets `x86-64-haswell` (AVX2 + FMA + F16C) for full performance on modern hardware. Pre-Haswell hosts — Intel Sandy Bridge / Ivy Bridge / Westmere; AMD Bulldozer / Piledriver / Steamroller — don't have AVX2 and crash with `Illegal instruction` at `import lancedb`.
|
||||
|
||||
@@ -707,9 +707,6 @@ class LanceDBConnection(DBConnection):
|
||||
self._namespace_client_properties = namespace_client_properties
|
||||
if _inner is not None:
|
||||
self._conn = _inner
|
||||
# Native-derived wrappers resolve this in their async reconstruction
|
||||
# path so construction never synchronously re-enters LOOP.
|
||||
self._read_consistency_interval = read_consistency_interval
|
||||
self._cached_namespace_client = None
|
||||
return
|
||||
|
||||
@@ -759,14 +756,11 @@ class LanceDBConnection(DBConnection):
|
||||
# storage_options. Also, this class really shouldn't be holding any state
|
||||
# beyond _conn.
|
||||
self._conn = AsyncConnection(LOOP.run(do_connect()))
|
||||
# Keep property access synchronous so debugger introspection cannot wait on
|
||||
# the background loop while that thread is suspended at a breakpoint.
|
||||
self._read_consistency_interval = read_consistency_interval
|
||||
self._cached_namespace_client: Optional[LanceNamespace] = None
|
||||
|
||||
@property
|
||||
def read_consistency_interval(self) -> Optional[timedelta]:
|
||||
return self._read_consistency_interval
|
||||
return LOOP.run(self._conn.get_read_consistency_interval())
|
||||
|
||||
@property
|
||||
def session(self) -> Optional[Session]:
|
||||
@@ -777,16 +771,8 @@ class LanceDBConnection(DBConnection):
|
||||
return self._conn.uri
|
||||
|
||||
@classmethod
|
||||
def from_inner(
|
||||
cls,
|
||||
inner: LanceDbConnection,
|
||||
read_consistency_interval: Optional[timedelta],
|
||||
):
|
||||
return cls(
|
||||
None,
|
||||
read_consistency_interval=read_consistency_interval,
|
||||
_inner=inner,
|
||||
)
|
||||
def from_inner(cls, inner: LanceDbConnection):
|
||||
return cls(None, _inner=inner)
|
||||
|
||||
def __repr__(self) -> str:
|
||||
return f"{self.__class__.__name__}(uri={self._conn.uri!r})"
|
||||
|
||||
@@ -226,7 +226,7 @@ class PermutationBuilder:
|
||||
|
||||
async def do_execute():
|
||||
inner_tbl = await self._async.execute()
|
||||
return await LanceTable.from_inner(inner_tbl)
|
||||
return LanceTable.from_inner(inner_tbl)
|
||||
|
||||
return LOOP.run(do_execute())
|
||||
|
||||
|
||||
@@ -117,14 +117,6 @@ _MODEL_BACKED_TOKENIZER_ERRORS = (
|
||||
"Failed to initialize default tokenizer",
|
||||
)
|
||||
|
||||
_PYLANCE_INSTALL_ERROR = (
|
||||
"The lance library is required to use this function. Install the PyLance "
|
||||
"extra for the distribution already installed: "
|
||||
'`pip install "lancedb[pylance]"` for `lancedb`, or '
|
||||
'`pip install "lancedb-compat[pylance]"` for `lancedb-compat`. '
|
||||
"Do not install both distributions because they share the `lancedb` namespace."
|
||||
)
|
||||
|
||||
|
||||
def _add_unique_note(exception: BaseException, note: str) -> None:
|
||||
existing_notes = getattr(exception, "__notes__", ()) or ()
|
||||
@@ -2190,15 +2182,11 @@ class LanceTable(Table):
|
||||
return self.name
|
||||
|
||||
@classmethod
|
||||
async def from_inner(cls, tbl: LanceDBTable):
|
||||
from .db import AsyncConnection, LanceDBConnection
|
||||
def from_inner(cls, tbl: LanceDBTable):
|
||||
from .db import LanceDBConnection
|
||||
|
||||
async_tbl = AsyncTable(tbl)
|
||||
inner_conn = tbl.database()
|
||||
read_consistency_interval = await AsyncConnection(
|
||||
inner_conn
|
||||
).get_read_consistency_interval()
|
||||
conn = LanceDBConnection.from_inner(inner_conn, read_consistency_interval)
|
||||
conn = LanceDBConnection.from_inner(tbl.database())
|
||||
return cls(
|
||||
conn,
|
||||
async_tbl.name,
|
||||
@@ -2257,7 +2245,10 @@ class LanceTable(Table):
|
||||
try:
|
||||
import lance
|
||||
except ImportError:
|
||||
raise ImportError(_PYLANCE_INSTALL_ERROR)
|
||||
raise ImportError(
|
||||
"The lance library is required to use this function. "
|
||||
"Please install with `pip install pylance`."
|
||||
)
|
||||
|
||||
branch = self.current_branch()
|
||||
version = None if branch is not None else self.version
|
||||
@@ -4762,7 +4753,10 @@ class AsyncTable:
|
||||
try:
|
||||
import lance
|
||||
except ImportError:
|
||||
raise ImportError(_PYLANCE_INSTALL_ERROR)
|
||||
raise ImportError(
|
||||
"The lance library is required to use this function. "
|
||||
"Please install with `pip install pylance`."
|
||||
)
|
||||
|
||||
# lance.dataset() can't open a branch directly, so open the base table
|
||||
# and check out the branch ref (a None branch resolves to main).
|
||||
|
||||
@@ -77,23 +77,6 @@ def test_sync_repr_does_not_use_background_loop(tmp_path, monkeypatch):
|
||||
assert repr(table) == f"LanceTable(name='test', _conn={db!r})"
|
||||
|
||||
|
||||
def test_read_consistency_interval_does_not_use_background_loop(tmp_path, monkeypatch):
|
||||
from lancedb.background_loop import LOOP
|
||||
from lancedb.db import LanceDBConnection
|
||||
|
||||
consistency_interval = timedelta(seconds=5)
|
||||
db = lancedb.connect(tmp_path, read_consistency_interval=consistency_interval)
|
||||
db_from_inner = LanceDBConnection.from_inner(db._inner, consistency_interval)
|
||||
|
||||
def fail_run(*args, **kwargs):
|
||||
raise AssertionError("properties should not use the Python background loop")
|
||||
|
||||
monkeypatch.setattr(LOOP, "run", fail_run)
|
||||
|
||||
assert db.read_consistency_interval == consistency_interval
|
||||
assert db_from_inner.read_consistency_interval == consistency_interval
|
||||
|
||||
|
||||
def test_ingest_pd(tmp_path):
|
||||
db = lancedb.connect(tmp_path)
|
||||
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
import subprocess
|
||||
import sys
|
||||
|
||||
|
||||
def test_import_lancedb_without_pylance():
|
||||
script = """
|
||||
import sys
|
||||
|
||||
|
||||
class BlockLanceImports:
|
||||
def find_spec(self, fullname, path=None, target=None):
|
||||
if fullname == "lance" or fullname.startswith("lance."):
|
||||
raise ModuleNotFoundError(f"blocked optional dependency: {fullname}")
|
||||
return None
|
||||
|
||||
|
||||
sys.meta_path.insert(0, BlockLanceImports())
|
||||
import lancedb
|
||||
"""
|
||||
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-c", script],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
|
||||
assert result.returncode == 0, result.stderr
|
||||
@@ -6,7 +6,6 @@ import math
|
||||
import pytest
|
||||
|
||||
from lancedb import DBConnection, Table, connect
|
||||
from lancedb.background_loop import LOOP
|
||||
from lancedb.permutation import Permutation, Permutations, permutation_builder
|
||||
|
||||
|
||||
@@ -32,25 +31,6 @@ def test_split_random_ratios(mem_db):
|
||||
assert 65 <= split_1_count <= 75 # ~70% ± tolerance
|
||||
|
||||
|
||||
def test_execute_does_not_reenter_background_loop(tmp_path, monkeypatch):
|
||||
import threading
|
||||
|
||||
db = connect(tmp_path)
|
||||
tbl = db.create_table("test_table", pa.table({"x": range(10)}))
|
||||
original_run = LOOP.run
|
||||
|
||||
def fail_on_reentry(future):
|
||||
assert threading.current_thread() is not LOOP.thread
|
||||
return original_run(future)
|
||||
|
||||
monkeypatch.setattr(LOOP, "run", fail_on_reentry)
|
||||
|
||||
permutation_tbl = permutation_builder(tbl).execute()
|
||||
|
||||
assert permutation_tbl.count_rows() == 10
|
||||
assert permutation_tbl._conn.read_consistency_interval is None
|
||||
|
||||
|
||||
def test_split_random_counts(mem_db):
|
||||
"""Test random splitting with absolute counts."""
|
||||
tbl = mem_db.create_table(
|
||||
|
||||
@@ -6,7 +6,6 @@ import os
|
||||
import sys
|
||||
import threading
|
||||
import warnings
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from datetime import date, datetime, timedelta
|
||||
from time import sleep
|
||||
from typing import List
|
||||
@@ -1258,24 +1257,6 @@ def test_branch_to_lance_targets_branch(tmp_path):
|
||||
assert table.to_lance().count_rows() == 1
|
||||
|
||||
|
||||
def _assert_pylance_install_error(error: ImportError):
|
||||
message = str(error)
|
||||
assert 'pip install "lancedb[pylance]"' in message
|
||||
assert 'pip install "lancedb-compat[pylance]"' in message
|
||||
assert "distribution already installed" in message
|
||||
assert "Do not install both distributions" in message
|
||||
|
||||
|
||||
def test_to_lance_recommends_pylance_extra(tmp_db):
|
||||
table = tmp_db.create_table("t", [{"i": 1}])
|
||||
|
||||
with patch("builtins.__import__", side_effect=ImportError):
|
||||
with pytest.raises(ImportError) as exc_info:
|
||||
table.to_lance()
|
||||
|
||||
_assert_pylance_install_error(exc_info.value)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_to_lance(tmp_path):
|
||||
pytest.importorskip("lance")
|
||||
@@ -1287,18 +1268,6 @@ async def test_async_to_lance(tmp_path):
|
||||
assert dataset.count_rows() == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_to_lance_recommends_pylance_extra(tmp_path):
|
||||
db = await lancedb.connect_async(tmp_path)
|
||||
table = await db.create_table("t", [{"i": 1}])
|
||||
|
||||
with patch("builtins.__import__", side_effect=ImportError):
|
||||
with pytest.raises(ImportError) as exc_info:
|
||||
await table.to_lance()
|
||||
|
||||
_assert_pylance_install_error(exc_info.value)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_branch_to_lance_targets_branch(tmp_path):
|
||||
pytest.importorskip("lance")
|
||||
@@ -2155,27 +2124,6 @@ def test_delete(mem_db: DBConnection):
|
||||
assert table.to_arrow()["id"].to_pylist() == [1]
|
||||
|
||||
|
||||
def test_concurrent_deletes_are_thread_safe(mem_db: DBConnection):
|
||||
num_workers = 8
|
||||
table = mem_db.create_table(
|
||||
"my_table", data=[{"id": row_id} for row_id in range(num_workers)]
|
||||
)
|
||||
barrier = threading.Barrier(num_workers)
|
||||
|
||||
def delete(row_id: int):
|
||||
barrier.wait()
|
||||
return table.delete(f"id = {row_id}")
|
||||
|
||||
with ThreadPoolExecutor(max_workers=num_workers) as pool:
|
||||
results = list(pool.map(delete, range(num_workers)))
|
||||
|
||||
assert all(result.num_deleted_rows == 1 for result in results)
|
||||
assert sorted(result.version for result in results) == list(
|
||||
range(2, num_workers + 2)
|
||||
)
|
||||
assert table.count_rows() == 0
|
||||
|
||||
|
||||
def test_delete_expr(mem_db: DBConnection):
|
||||
table = mem_db.create_table(
|
||||
"my_table",
|
||||
|
||||
@@ -745,9 +745,6 @@ impl Table {
|
||||
|
||||
#[allow(private_interfaces)]
|
||||
pub fn delete(self_: PyRef<'_, Self>, condition: PredicateArg) -> PyResult<Bound<'_, PyAny>> {
|
||||
// Do not hold the Python borrow across the await. The cloned Rust table
|
||||
// handle is thread-safe and allows deletes on the same Python table to
|
||||
// run concurrently without PyO3 reporting "Already borrowed".
|
||||
let inner = self_.inner_ref()?.clone();
|
||||
future_into_py(self_.py(), async move {
|
||||
let result = match &condition {
|
||||
|
||||
@@ -49,8 +49,8 @@ lance-namespace = { workspace = true }
|
||||
lance-namespace-impls = { workspace = true }
|
||||
metrics = { workspace = true, optional = true }
|
||||
metrics-util = { workspace = true, optional = true }
|
||||
# Pin the transitive GooseFS SDK until the 0.1.6 compile break is fixed upstream.
|
||||
goosefs-sdk = { version = "=0.1.5", optional = true }
|
||||
# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency.
|
||||
goosefs-sdk = { version = "=0.1.9", optional = true }
|
||||
moka = { workspace = true }
|
||||
pin-project = { workspace = true }
|
||||
tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
|
||||
|
||||
@@ -17,7 +17,7 @@ use arrow_array::builder::LargeBinaryBuilder;
|
||||
use arrow_schema::{DataType, Field, Schema};
|
||||
use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
|
||||
use lance_arrow::FieldExt;
|
||||
use lance_encoding::version::LanceFileVersion;
|
||||
use lance_file::version::LanceFileVersion;
|
||||
use lance_io::object_store::ObjectStore;
|
||||
use object_store::path::Path;
|
||||
|
||||
|
||||
@@ -34,7 +34,7 @@ use crate::remote::{
|
||||
db::{OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION},
|
||||
};
|
||||
use lance::io::ObjectStoreParams;
|
||||
pub use lance_encoding::version::LanceFileVersion;
|
||||
pub use lance_file::version::LanceFileVersion;
|
||||
#[cfg(feature = "remote")]
|
||||
use lance_io::object_store::StorageOptions;
|
||||
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
|
||||
|
||||
@@ -12,7 +12,7 @@ use lance::dataset::refs::Ref;
|
||||
use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
|
||||
use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
|
||||
use lance_datafusion::utils::StreamingWriteSource;
|
||||
use lance_encoding::version::LanceFileVersion;
|
||||
use lance_file::version::LanceFileVersion;
|
||||
use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
|
||||
use lance_table::io::commit::commit_handler_from_url;
|
||||
use object_store::local::LocalFileSystem;
|
||||
|
||||
@@ -201,7 +201,7 @@ impl LanceNamespaceDatabase {
|
||||
&self,
|
||||
request: &DbCreateTableRequest,
|
||||
) -> Result<(
|
||||
Option<lance_encoding::version::LanceFileVersion>,
|
||||
Option<lance_file::version::LanceFileVersion>,
|
||||
Option<bool>,
|
||||
Option<bool>,
|
||||
)> {
|
||||
@@ -214,7 +214,7 @@ impl LanceNamespaceDatabase {
|
||||
|
||||
let storage_version_override = storage_options
|
||||
.and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
|
||||
.map(|s| s.parse::<lance_encoding::version::LanceFileVersion>())
|
||||
.map(|s| s.parse::<lance_file::version::LanceFileVersion>())
|
||||
.transpose()?;
|
||||
|
||||
let v2_manifest_override = storage_options
|
||||
|
||||
@@ -2939,7 +2939,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
|
||||
}
|
||||
|
||||
#[derive(Serialize, Clone, Debug)]
|
||||
pub(crate) struct MergeInsertRequest {
|
||||
pub struct MergeInsertRequest {
|
||||
on: String,
|
||||
when_matched_update_all: bool,
|
||||
when_matched_update_all_filt: Option<String>,
|
||||
|
||||
@@ -90,7 +90,7 @@ struct RemoteBlobState {
|
||||
|
||||
/// Seekable Cloud blob handle over HTTP Range.
|
||||
#[derive(Debug)]
|
||||
pub(crate) struct RemoteBlobFile {
|
||||
pub struct RemoteBlobFile {
|
||||
requester: Arc<dyn BlobRangeRequester>,
|
||||
state: Mutex<RemoteBlobState>,
|
||||
closed: AtomicBool,
|
||||
|
||||
@@ -33,7 +33,7 @@ use crate::table::{AddResult, MergeResult};
|
||||
/// same Arrow-IPC streaming body and error side-channel; only the target
|
||||
/// endpoint, query parameters, and parsed result type differ.
|
||||
#[derive(Debug, Clone)]
|
||||
pub(crate) enum WriteOp {
|
||||
pub enum WriteOp {
|
||||
/// `add`: stream to `/v1/table/{id}/insert/`, optionally overwriting.
|
||||
Insert { overwrite: bool },
|
||||
/// `merge_insert`: stream to `/v1/table/{id}/merge_insert/` with the merge
|
||||
@@ -49,7 +49,7 @@ pub(crate) enum WriteOp {
|
||||
/// The parsed server response for a completed write, discriminated by the
|
||||
/// operation that produced it.
|
||||
#[derive(Debug, Clone)]
|
||||
pub(crate) enum WriteResult {
|
||||
pub enum WriteResult {
|
||||
Add(AddResult),
|
||||
Merge(MergeResult),
|
||||
}
|
||||
|
||||
@@ -10,7 +10,7 @@ use arrow_array::{
|
||||
use arrow_schema::{DataType, Field, Fields, Schema};
|
||||
use futures::TryStreamExt;
|
||||
use lance::Dataset;
|
||||
use lance_encoding::version::LanceFileVersion;
|
||||
use lance_file::version::LanceFileVersion;
|
||||
use lancedb::{
|
||||
Connection, Error, Result, Table,
|
||||
blob::{BlobRangeRequest, blob},
|
||||
|
||||
Reference in New Issue
Block a user