Files
lancedb/python/python/lancedb/job.py
T
Xuanwo b0dae5eb0b feat: return typed refresh job results (#4013)
## Problem

`refresh_column_async` returned a unit-result job even though durable
refresh jobs carry a canonical terminal result. Python callers could not
obtain row counts or source and published versions through the public
`Job` API, and local and remote refresh jobs exposed different result
semantics.

## Behavior

`refresh_column_async` now returns `Job[RefreshColumnResult]` for local
and remote tables. The general typed-job bridge binds each endpoint to
its public result model while preserving unit-result jobs and existing
status, wait, cancel, and timeout behavior. A local no-op refresh
reports no published version.

The Node.js API continues to resolve `wait()` as `void`; its binding
erases the Rust result type internally to preserve the existing public
contract.

## Ownership and integration boundary

LanceDB owns the language-neutral `Job<T>` contract and language-binding
decode. Sophon owns production and durable persistence of terminal
payloads. Sophon #7348 and #7378 now publish the canonical refresh
result for Function-backed and expression-backed refresh jobs,
respectively. The remote client fixture matches the merged server
schema; live deployment and end-to-end demo acceptance remain separate
rollout checks.
2026-08-25 00:01:32 +08:00

131 lines
4.2 KiB
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
"""Handles to operations a server may run asynchronously."""
import asyncio
from datetime import timedelta
from typing import Any, Callable, Generic, Optional, TypeVar, cast
from lancedb.background_loop import LOOP
from . import _lancedb
T = TypeVar("T")
class AsyncJob(Generic[T]):
"""A handle to an operation that may still be running.
The operation may already be complete when the handle is created. ``T``
is the endpoint's terminal result type; unit-result jobs resolve to
``None``.
"""
def __init__(
self,
inner: Optional[Any],
result_decoder: Optional[Callable[[Any], T]] = None,
):
self._inner = inner
self._result_decoder = result_decoder
@property
def id(self) -> Optional[str]:
"""Identifies the operation on the server that is running it.
Returned for correlating with server logs or the jobs API. Operations
that run in this process have no server id and return `None`. The value
is opaque: parsing it or storing it to resume the job later is not
supported.
"""
return self._inner.id if self._inner is not None else None
async def status(self) -> str:
"""The operation's current lifecycle state: "running", "finished",
"failed", or "cancelled".
A point snapshot; unlike `wait` it does not block or raise on a
terminal failure state. States a newer server reports that this
client version does not know pass through as-is.
"""
if self._inner is None:
return "finished"
return await self._inner.status()
async def wait(self, timeout: Optional[timedelta] = None) -> T:
"""Wait until the operation reaches a terminal state.
Returns the endpoint's typed result, or ``None`` for a unit-result
job.
Raises `JobFailedError` if the operation failed, `JobCancelledError`
if it was cancelled, and `TimeoutError` if `timeout` elapses first.
"""
if self._inner is None:
return cast(T, None)
if timeout is None:
result = await self._inner.wait()
else:
result = await asyncio.wait_for(self._inner.wait(), timeout.total_seconds())
if self._result_decoder is not None:
return self._result_decoder(result)
return cast(T, result)
async def cancel(self):
"""Request cancellation. Cancelling a finished operation is a no-op."""
if self._inner is None:
return
await self._inner.cancel()
class Job(Generic[T]):
"""Synchronous counterpart of `AsyncJob` with the same result type."""
def __init__(self, inner: Optional[AsyncJob[T]]):
self._inner = inner
@property
def id(self) -> Optional[str]:
"""Identifies the operation on the server that is running it.
See :attr:`AsyncJob.id`.
"""
return self._inner.id if self._inner is not None else None
def status(self) -> str:
"""The operation's current lifecycle state: "running", "finished",
"failed", or "cancelled".
See :meth:`AsyncJob.status`.
"""
if self._inner is None:
return "finished"
return LOOP.run(self._inner.status())
def wait(self, timeout: Optional[timedelta] = None) -> T:
"""Block until the operation reaches a terminal state.
Returns the endpoint's typed result, or ``None`` for a unit-result
job.
Raises `JobFailedError` if the operation failed, `JobCancelledError`
if it was cancelled, and `TimeoutError` if `timeout` elapses first.
"""
if self._inner is None:
return cast(T, None)
return LOOP.run(self._inner.wait(timeout))
def cancel(self):
"""Request cancellation. Cancelling a finished operation is a no-op."""
if self._inner is None:
return
LOOP.run(self._inner.cancel())
def _typed_job(
inner: "_lancedb.Job", result_decoder: Callable[[str], T]
) -> AsyncJob[T]:
"""Bind an internal JSON-producing job to its public result model."""
return AsyncJob(inner, result_decoder)